CN113554515A - Internet financial control method, system, device and medium - Google Patents
Internet financial control method, system, device and medium Download PDFInfo
- Publication number
- CN113554515A CN113554515A CN202110715133.7A CN202110715133A CN113554515A CN 113554515 A CN113554515 A CN 113554515A CN 202110715133 A CN202110715133 A CN 202110715133A CN 113554515 A CN113554515 A CN 113554515A
- Authority
- CN
- China
- Prior art keywords
- financial
- type
- user
- information
- preset
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012549 training Methods 0.000 claims abstract description 28
- 238000003062 neural network model Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 230000015654 memory Effects 0.000 claims description 28
- 238000012795 verification Methods 0.000 claims description 14
- 230000001419 dependent effect Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 2
- 230000006399 behavior Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000013210 evaluation model Methods 0.000 description 4
- 238000011835 investigation Methods 0.000 description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000329 smooth muscle myocyte Anatomy 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
Abstract
The invention relates to the technical field of Internet, and provides an Internet financial control method, system, equipment and storage medium. The method comprises the following steps: the method comprises the steps of obtaining financial related information of a first type user and financial related information of a second type user from a predetermined database, executing preprocessing operation on the financial related information, training based on the preprocessed financial related information and a neural network model to obtain a financial control recognition model, obtaining financial attribute information of the user to be recognized, inputting the financial attribute information into the financial control recognition model to obtain a recognition result, judging whether the type of the recognition result is a first type recognition result, obtaining operation trace information of the user to be recognized on a preset page according to a preset embedded point set when the type of the recognition result is judged to be the first type recognition result, inputting the operation trace information into a predetermined trace recognition model, obtaining a target recognition result and feeding the target recognition result back to a preset terminal. The invention can improve the accuracy of identifying financial fraud.
Description
Technical Field
The invention relates to the technical field of internet, in particular to an internet financial control method, system, equipment and storage medium.
Background
At present, the business scope of many financial companies relates to a plurality of financial business categories such as investment, financing and the like, and in order to effectively control financial risks, such companies perform anti-fraud identification on clients after handling corresponding financial businesses (for example, loan businesses and the like) for the clients. The financial anti-fraud automatic identification scheme appearing in the market at present usually identifies according to a single factor of personal data information of a user, and has the technical problem of low accuracy because sample data of fraud behaviors is lack and financial fraud behaviors are identified by only utilizing the single factor.
Disclosure of Invention
In view of the above, the present invention provides an internet financial control method, system, device and storage medium, which aims to solve the technical problem of low accuracy in controlling and identifying financial fraud in the prior art.
In order to achieve the above object, the present invention provides an internet financial control method, including:
acquiring financial related information of a first type of user and a second type of user from a predetermined database, performing preprocessing operation on the financial related information, and training based on the preprocessed financial related information and a neural network model to obtain a financial control recognition model;
acquiring financial attribute information of a user to be identified, inputting the financial attribute information into the financial control identification model to obtain an identification result, judging whether the type of the identification result is a first type identification result, and acquiring operation trace information of the user to be identified on a preset page according to a pre-configured buried point set when the type of the identification result is judged to be the first type identification result;
and inputting the operation trace information into a predetermined trace recognition model to obtain a target recognition result and feeding the target recognition result back to a preset terminal.
Preferably, after determining whether the type of the recognition result is the first recognition result, the method further includes:
and randomly selecting a preset number of users with the identification result type as a second type identification result at regular time, acquiring the operation trace information of the users with the second type identification result on a preset page according to a preset buried point set, converting the operation trace information into time sequence data, and inputting the time sequence data into a predetermined trace identification model.
Preferably, the specific construction process of the trace identification model comprises the following steps:
respectively acquiring historical operation trace information of a first type user and a second type user from the database;
calculating the distance value of any two pieces of historical operation trace information based on a preset algorithm;
judging whether the two pieces of historical operation trace information are similar operation traces or not according to the distance value;
if the two pieces of historical operation trace information are similar operation traces, combining the two pieces of historical operation trace information to serve as a clustering center point;
and if the two pieces of historical operation trace information are not similar operation traces, forming a clustering center point according to each piece of historical operation trace information of the two pieces of historical operation trace information respectively.
Preferably, the performing of the preprocessing operation on the financial-related information includes:
performing one or more of deviation data detection, missing value processing, and noise data smoothing on the financial-related information.
Preferably, the training of the financial control recognition model based on the preprocessed financial-related information and the neural network model comprises:
allocating preset labels to users corresponding to the preprocessed financial related information, taking the financial related information as variables, and taking the labels of the users corresponding to the financial related information as dependent variables to generate a sample set;
dividing the sample set into a training set and a verification set according to a preset proportion;
training a convolutional neural network model by using each variable and each dependent variable in the training set, verifying the convolutional neural network model by using the verification set every other preset period, and verifying the accuracy of the financial control identification model by using each variable and each dependent variable in the verification set;
and when the accuracy is greater than a first preset threshold value, obtaining the financial control recognition model.
Preferably, the step of generating the preconfigured set of buried points comprises:
randomly generating an initial embedded point set on a preset page;
judging whether the accuracy of the initial buried point set is greater than a second preset threshold value, and when the accuracy of the initial buried point set is greater than the second preset threshold value, taking the initial buried point set as the pre-configured buried point set;
when the accuracy of the initial buried point set is judged to be smaller than or equal to a second preset threshold value, generating a first buried point set and a second buried point set according to a preset cross probability and a cross method based on the adaptability value of the buried points;
and taking the first buried point set and the second buried point set as a new initial buried point set.
In order to achieve the above object, the present invention also provides an internet financial control system, including:
a first control module: the system comprises a database, a neural network model and a financial control recognition model, wherein the database is used for acquiring financial related information of a first type of user and a second type of user from a predetermined database, performing preprocessing operation on the financial related information, and training based on the preprocessed financial related information and the neural network model to obtain the financial control recognition model;
a judging module: the financial control recognition model is used for acquiring financial attribute information of a user to be recognized, inputting the financial attribute information into the financial control recognition model to obtain a recognition result, judging whether the type of the recognition result is a first type recognition result, and acquiring operation trace information of the user to be recognized on a preset page according to a pre-configured buried point set when the type of the recognition result is judged to be the first type recognition result;
a second control module: and the operation trace information is input into a predetermined trace recognition model to obtain a target recognition result and feed the target recognition result back to a preset terminal.
In order to achieve the above object, the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a program executable by the at least one processor, the program being executable by the at least one processor to enable the at least one processor to perform the steps of:
acquiring financial related information of a first type of user and a second type of user from a predetermined database, performing preprocessing operation on the financial related information, and training based on the preprocessed financial related information and a neural network model to obtain a financial control recognition model;
acquiring financial attribute information of a user to be identified, inputting the financial attribute information into the financial control identification model to obtain an identification result, judging whether the type of the identification result is a first type identification result, and acquiring operation trace information of the user to be identified on a preset page according to a pre-configured buried point set when the type of the identification result is judged to be the first type identification result;
and inputting the operation trace information into a predetermined trace recognition model to obtain a target recognition result and feeding the target recognition result back to a preset terminal.
Preferably, the specific construction process of the trace identification model comprises the following steps:
respectively acquiring historical operation trace information of a first type user and a second type user from the database;
calculating the distance value of any two pieces of historical operation trace information based on a preset algorithm;
judging whether the two pieces of historical operation trace information are similar operation traces or not according to the distance value;
if the two pieces of historical operation trace information are similar operation traces, combining the two pieces of historical operation trace information to serve as a clustering center point;
and if the two pieces of historical operation trace information are not similar operation traces, forming a clustering center point according to each piece of historical operation trace information of the two pieces of historical operation trace information respectively.
To achieve the above object, the present invention also provides a computer-readable storage medium storing an internet financial control program, which when executed by a processor, implements any of the steps of the internet financial control method as described above.
According to the internet financial control method, the system, the equipment and the storage medium, the financial related information of the user is identified by combining the supervised model, and the identification result of the supervised model is further identified, controlled and identified by using the unsupervised clustering model of the operation trace, so that the user suspected of financial fraud behaviors can be identified in practical application, and the accuracy of financial fraud identification is improved.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating a preferred embodiment of the Internet financial control method of the present invention;
FIG. 2 is a block diagram of an Internet financial control system according to a preferred embodiment of the present invention;
FIG. 3 is a diagram of an electronic device according to a preferred embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides an internet financial control method. Referring to fig. 1, a method flow diagram of an embodiment of the internet financial control method of the present invention is shown. The method may be performed by an electronic device, which may be implemented by software and/or hardware. The Internet financial control method comprises the following steps:
step S10: the method comprises the steps of obtaining financial relevant information of a first type user and a second type user from a predetermined database, executing preprocessing operation on the financial relevant information, and training based on the preprocessed financial relevant information and a neural network model to obtain a financial control recognition model.
In this embodiment, the financial-related information of the first type user and the second type user, such as insurance business database, banking business data, credit investigation database, etc., may be obtained from a plurality of third party databases or local databases, the first type user is a fraudulent user or a malicious user suspected of fraud, the second type user is a normal user without fraudulent behavior, and the financial-related information includes user profile information, such as age, gender, occupation, annual income, native place, outstanding loan information, credit card arrears information, value-viewing information (e.g., degree of pessimism/optimism to society), credit investigation information, financial fraud information, etc. And then, preprocessing the financial related information, and training according to the preprocessed financial related information and the neural network model to obtain a financial control recognition model. A supervised recognition model is constructed for preliminarily identifying whether a user to be recognized is suspected of fraud.
In one embodiment, the preprocessing operations include:
performing one or more of deviation data detection, missing value processing, and noise data smoothing on the financial-related information. Wherein missing value processing comprises: automatic filling of global constants, automatic filling of central metrics and automatic filling of same-group mean values. Deviation data detection includes: and (3) constructing a probability distribution evaluation model, detecting an outlier by applying the probability distribution evaluation model, and taking a value corresponding to the outlier as deviation data. The noise data smoothing processing includes: and fitting the noisy variable in the financial-related information into a straight line or a curve, and replacing the noisy variable in the financial-related information with the value on the straight line or the curve.
Training according to the preprocessed financial related information and a neural network model to obtain a financial control recognition model, specifically, distributing preset labels to users corresponding to the preprocessed financial related information, wherein the labels comprise fraudulent users and normal users, the financial related information is used as variables, and the labels of the users corresponding to the financial related information are used as dependent variables to generate a sample set;
dividing the sample set into a training set and a verification set according to a preset proportion (for example, 4: 1);
training a convolutional neural network model by using each variable and each dependent variable in the training set, verifying the convolutional neural network model by using the verification set every preset period, verifying the accuracy of the financial control identification model by using each variable and each dependent variable in the verification set, and obtaining the financial control identification model when the accuracy is greater than a first preset threshold (for example, 90%).
Step S20: acquiring financial attribute information of a user to be identified, inputting the financial attribute information into the financial control identification model to obtain an identification result, judging whether the type of the identification result is a first type identification result, and acquiring operation trace information of the user to be identified on a preset page according to a pre-configured buried point set when the type of the identification result is judged to be the first type identification result.
In this embodiment, when it is received that whether a user is suspected of having financial fraud or not is identified by a terminal, the financial attribute information of the user to be identified is obtained and input to the financial control identification model to obtain an identification result, and the financial control identification model is a binary model, that is, the identification result is a first type identification result (suspected financial fraud-related user) and a second type identification result (normal user).
Because the sample data of the fraudulent user in the database is relatively less, the accuracy of the trained financial control recognition model for recognizing whether the user is the fraudulent user is not high, and the operation trace of the fraudulent user is generally automatically controlled by a program and is different from the manual operation of a normal user on the page of the financial product, so that the scheme further judges whether the user is the fraudulent user according to the operation trace information of the user on the preset page. And judging whether the identification result is a suspected financial fraud user, and when the identification result is judged that the user to be identified is the suspected financial fraud user, acquiring the operation trace information of the user on a preset page according to a preset buried point set. The operation trace information of the user may refer to an operation trace when the user browses the page. The frequency of obtaining the operation trace information may be different for different operation objects, for example, the behavior of browsing a page may be obtained once in about 2 minutes, and when the operation relates to links such as consumption and payment, the behavior may be obtained once in 5 seconds or less.
It can be understood that the embedded point set may be a plurality of data embedded points pre-configured in the program code, each data embedded point works independently, in the practical application, the data embedded points may be set in the function points of the key operation flow corresponding to different services provided by the client according to the requirement, so as to record user operation information such as access time, operation object, execution action, operation description and the like of the user through the embedded points, the operation trace of the user on a preset page may be obtained through the operation information, and the preset page may be a plurality of pages corresponding to the application client, for example, a detail page, an order page, a payment page and the like of a financial product.
In one embodiment, after determining whether the type of the recognition result is the first recognition result, the method further includes:
and randomly selecting a preset number of users with the identification result type as a second type identification result at regular time, acquiring the operation trace information of the users with the second type identification result on a preset page according to a preset buried point set, converting the operation trace information into time sequence data, and inputting the time sequence data into a predetermined trace identification model.
Because the financial control identification model lacks sample data, the fraudulent user can be identified as the normal user by mistake, therefore, the users with the preset number of identification results as the normal users can be randomly selected, the operation trace information of the user is obtained and input into the trace identification model for verification, and the identification accuracy of the user to be identified can be further improved.
In one embodiment, the generating of the pre-configured set of buried points comprises:
randomly generating an initial embedded point set on a preset page;
judging whether the accuracy of the initial buried point set is greater than a second preset threshold value, and when the accuracy of the initial buried point set is greater than the second preset threshold value, taking the initial buried point set as the pre-configured buried point set;
when the accuracy of the initial buried point set is judged to be smaller than or equal to a second preset threshold value, generating a first buried point set and a second buried point set according to a preset cross probability and a cross method based on the adaptability value of the buried points;
and taking the first buried point set and the second buried point set as a new initial buried point set.
Wherein the cross probability PcThe calculation formula (2) includes:
probability of variation PmThe calculation formula (2) includes:
fmaxrepresents the maximum fitness value, f, of the buried point setavgRepresenting the average fitness value of each generation of buried point set, f' representing the greater fitness value of two buried points to be crossed, f the fitness value of a buried point to be mutated, Pc1＝0.9，Pc2＝0.6，Pm1＝0.1，Pm2＝0.001。
Step S30: and inputting the operation trace information into a predetermined trace recognition model to obtain a target recognition result and feeding the target recognition result back to a preset terminal.
In this embodiment, the trace recognition model is an unsupervised clustering model, and the operation trace information is input into a predetermined trace recognition model to obtain a target recognition result and feed back the target recognition result to the preset terminal, where the preset terminal may be a terminal corresponding to a relevant supervisor. The financial related information of the user is identified by combining the supervised model, and the identification result of the supervised model is further identified and verified by utilizing the unsupervised clustering model of the operation trace, so that the user suspected of financial fraud behaviors can be identified in practical application.
In one embodiment, the specific construction process of the trace recognition model comprises the following steps:
respectively acquiring historical operation trace information of a first type user and a second type user from the database;
calculating the distance value of any two pieces of historical operation trace information based on a preset algorithm;
judging whether the two pieces of historical operation trace information are similar operation traces or not according to the distance value;
if the two pieces of historical operation trace information are similar operation traces, combining the two pieces of historical operation trace information to serve as a clustering center point;
and if the two pieces of historical operation trace information are not similar operation traces, forming a clustering center point according to each piece of historical operation trace information of the two pieces of historical operation trace information respectively.
Generally, the operation trace of the fraudulent user is automatically controlled by a program, which is different from the operation trace of the normal user on the page of the financial product manually, so that the scheme further judges whether the user is the fraudulent user by clustering the historical operation trace information to obtain a plurality of cluster clusters. When the distance value of any two pieces of historical operation trace information is calculated, a discrete Fourier distance algorithm can be adopted.
Referring to fig. 2, a functional block diagram of the internet financial control system 100 according to the present invention is shown.
The internet financial control system 100 according to the present invention may be installed in an electronic device. According to the implemented functions, the internet financial control system 100 may include a first control module 110, a determination module 120, and a second control module 130. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the first control module 110 is configured to obtain financial related information of the first type user and the second type user from a predetermined database, perform a preprocessing operation on the financial related information, and train based on the preprocessed financial related information and a neural network model to obtain a financial control recognition model.
In this embodiment, the financial-related information of the first type user and the second type user, such as insurance business database, banking business data, credit investigation database, etc., may be obtained from a plurality of third party databases or local databases, the first type user is a fraudulent user or a malicious user suspected of fraud, the second type user is a normal user without fraudulent behavior, and the financial-related information includes user profile information, such as age, gender, occupation, annual income, native place, outstanding loan information, credit card arrears information, value-viewing information (e.g., degree of pessimism/optimism to society), credit investigation information, financial fraud information, etc. And then, preprocessing the financial related information, and training according to the preprocessed financial related information and the neural network model to obtain a financial control recognition model. A supervised recognition model is constructed for preliminarily identifying whether a user to be recognized is suspected of fraud.
In one embodiment, the preprocessing operations include:
performing one or more of deviation data detection, missing value processing, and noise data smoothing on the financial-related information. Wherein missing value processing comprises: automatic filling of global constants, automatic filling of central metrics and automatic filling of same-group mean values. Deviation data detection includes: and (3) constructing a probability distribution evaluation model, detecting an outlier by applying the probability distribution evaluation model, and taking a value corresponding to the outlier as deviation data. The noise data smoothing processing includes: and fitting the noisy variable in the financial-related information into a straight line or a curve, and replacing the noisy variable in the financial-related information with the value on the straight line or the curve.
Training according to the preprocessed financial related information and a neural network model to obtain a financial control recognition model, specifically, distributing preset labels to users corresponding to the preprocessed financial related information, wherein the labels comprise fraudulent users and normal users, the financial related information is used as variables, and the labels of the users corresponding to the financial related information are used as dependent variables to generate a sample set;
dividing the sample set into a training set and a verification set according to a preset proportion (for example, 4: 1);
training a convolutional neural network model by using each variable and each dependent variable in the training set, verifying the convolutional neural network model by using the verification set every preset period, verifying the accuracy of the financial control identification model by using each variable and each dependent variable in the verification set, and obtaining the financial control identification model when the accuracy is greater than a first preset threshold (for example, 90%).
The judging module 120 is configured to obtain financial attribute information of the user to be identified, input the financial control identification model to obtain an identification result, judge whether the type of the identification result is a first type identification result, and obtain, when the type of the identification result is judged to be the first type identification result, operation trace information of the user to be identified on a preset page according to a pre-configured buried point set.
In this embodiment, when it is received that whether a user is suspected of having financial fraud or not is identified by a terminal, the financial attribute information of the user to be identified is obtained and input to the financial control identification model to obtain an identification result, and the financial control identification model is a binary model, that is, the identification result is a first type identification result (suspected financial fraud-related user) and a second type identification result (normal user).
Because the sample data of the fraudulent user in the database is relatively less, the accuracy of the trained financial control recognition model for recognizing whether the user is the fraudulent user is not high, and the operation trace of the fraudulent user is generally automatically controlled by a program and is different from the manual operation of a normal user on the page of the financial product, so that the scheme further judges whether the user is the fraudulent user according to the operation trace information of the user on the preset page. And judging whether the identification result is a suspected financial fraud user, and when the identification result is judged that the user to be identified is the suspected financial fraud user, acquiring the operation trace information of the user on a preset page according to a preset buried point set. The operation trace information of the user may refer to an operation trace when the user browses the page. The frequency of obtaining the operation trace information may be different for different operation objects, for example, the behavior of browsing a page may be obtained once in about 2 minutes, and when the operation relates to links such as consumption and payment, the behavior may be obtained once in 5 seconds or less.
It can be understood that the embedded point set may be a plurality of data embedded points pre-configured in the program code, each data embedded point works independently, in the practical application, the data embedded points may be set in the function points of the key operation flow corresponding to different services provided by the client according to the requirement, so as to record user operation information such as access time, operation object, execution action, operation description and the like of the user through the embedded points, the operation trace of the user on a preset page may be obtained through the operation information, and the preset page may be a plurality of pages corresponding to the application client, for example, a detail page, an order page, a payment page and the like of a financial product.
In one embodiment, the determining module 120 is further configured to:
and randomly selecting a preset number of users with the identification result type as a second type identification result at regular time, acquiring the operation trace information of the users with the second type identification result on a preset page according to a preset buried point set, converting the operation trace information into time sequence data, and inputting the time sequence data into a predetermined trace identification model.
Because the financial control identification model lacks sample data, the fraudulent user can be identified as the normal user by mistake, therefore, the users with the preset number of identification results as the normal users can be randomly selected, the operation trace information of the user is obtained and input into the trace identification model for verification, and the identification accuracy of the user to be identified can be further improved.
In one embodiment, the generating of the pre-configured set of buried points comprises:
randomly generating an initial embedded point set on a preset page;
judging whether the accuracy of the initial buried point set is greater than a second preset threshold value, and when the accuracy of the initial buried point set is greater than the second preset threshold value, taking the initial buried point set as the pre-configured buried point set;
when the accuracy of the initial buried point set is judged to be smaller than or equal to a second preset threshold value, generating a first buried point set and a second buried point set according to a preset cross probability and a cross method based on the adaptability value of the buried points;
and taking the first buried point set and the second buried point set as a new initial buried point set.
Wherein the cross probability PcThe calculation formula (2) includes:
probability of variation PmThe calculation formula (2) includes:
fmaxrepresents the maximum fitness value, f, of the buried point setavgRepresenting the average fitness value of each generation of buried point set, f' representing the greater fitness value of two buried points to be crossed, f the fitness value of a buried point to be mutated, Pc1＝0.9，Pc2＝0.6，Pm1＝0.1，Pm2＝0.001。
And the second control module 130 is configured to transfer the operation trace information into a predetermined trace recognition model, obtain a target recognition result, and feed the target recognition result back to a preset terminal.
In this embodiment, the trace recognition model is an unsupervised clustering model, and the operation trace information is input into a predetermined trace recognition model to obtain a target recognition result and feed back the target recognition result to the preset terminal, where the preset terminal may be a terminal corresponding to a relevant supervisor. The financial related information of the user is identified by combining the supervised model, and the identification result of the supervised model is further identified and verified by utilizing the unsupervised clustering model of the operation trace, so that the user suspected of financial fraud behaviors can be identified in practical application.
In one embodiment, the specific construction process of the trace recognition model comprises the following steps:
respectively acquiring historical operation trace information of a first type user and a second type user from the database;
calculating the distance value of any two pieces of historical operation trace information based on a preset algorithm;
judging whether the two pieces of historical operation trace information are similar operation traces or not according to the distance value;
if the two pieces of historical operation trace information are similar operation traces, combining the two pieces of historical operation trace information to serve as a clustering center point;
and if the two pieces of historical operation trace information are not similar operation traces, forming a clustering center point according to each piece of historical operation trace information of the two pieces of historical operation trace information respectively.
Generally, the operation trace of the fraudulent user is automatically controlled by a program, which is different from the operation trace of the normal user on the page of the financial product manually, so that the scheme further judges whether the user is the fraudulent user by clustering the historical operation trace information to obtain a plurality of cluster clusters. When the distance value of any two pieces of historical operation trace information is calculated, a discrete Fourier distance algorithm can be adopted.
Fig. 3 is a schematic diagram of an electronic device 1 according to a preferred embodiment of the invention.
The electronic device 1 includes but is not limited to: memory 11, processor 12, display 13, and network interface 14. The electronic device 1 is connected to a network through a network interface 14 to obtain raw data. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System for Mobile communications (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, or a communication network.
The memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 11 may be an internal storage unit of the electronic device 1, such as a hard disk or a memory of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like equipped with the electronic device 1. Of course, the memory 11 may also comprise both an internal memory unit and an external memory device of the electronic device 1. In this embodiment, the memory 11 is generally used for storing an operating system installed in the electronic device 1 and various application software, such as program codes of the internet financial control program 10. Further, the memory 11 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 12 is typically used for controlling the overall operation of the electronic device 1, such as performing data interaction or communication related control and processing. In this embodiment, the processor 12 is configured to run the program code stored in the memory 11 or process data, such as the program code of the internet financial control program 10.
The display 13 may be referred to as a display screen or display unit. In some embodiments, the display 13 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch screen, or the like. The display 13 is used for displaying information processed in the electronic device 1 and for displaying a visual work interface, e.g. displaying the results of data statistics.
The network interface 14 may optionally comprise a standard wired interface, a wireless interface (e.g. WI-FI interface), the network interface 14 typically being used for establishing a communication connection between the electronic device 1 and other electronic devices.
Fig. 3 shows only the electronic device 1 with components 11-14 and the internet financial control program 10, but it should be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead.
Optionally, the electronic device 1 may further comprise a user interface, the user interface may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further comprise a standard wired interface and a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch screen, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
The electronic device 1 may further include a Radio Frequency (RF) circuit, a sensor, an audio circuit, and the like, which are not described in detail herein.
In the above embodiment, the processor 12, when executing the internet financial control program 10 stored in the memory 11, may implement the following steps:
acquiring financial related information of a first type of user and a second type of user from a predetermined database, performing preprocessing operation on the financial related information, and training based on the preprocessed financial related information and a neural network model to obtain a financial control recognition model;
acquiring financial attribute information of a user to be identified, inputting the financial attribute information into the financial control identification model to obtain an identification result, judging whether the type of the identification result is a first type identification result, and acquiring operation trace information of the user to be identified on a preset page according to a pre-configured buried point set when the type of the identification result is judged to be the first type identification result;
and inputting the operation trace information into a predetermined trace recognition model to obtain a target recognition result and feeding the target recognition result back to a preset terminal.
The storage device may be the memory 11 of the electronic device 1, or may be another storage device communicatively connected to the electronic device 1.
For detailed description of the above steps, please refer to the above description of fig. 2 regarding a functional block diagram of an embodiment of the internet financial control system 100 and fig. 1 regarding a flowchart of an embodiment of the internet financial control method.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium may be non-volatile or volatile. The computer readable storage medium may be any one or any combination of hard disks, multimedia cards, SD cards, flash memory cards, SMCs, Read Only Memories (ROMs), Erasable Programmable Read Only Memories (EPROMs), portable compact disc read only memories (CD-ROMs), USB memories, etc. The computer-readable storage medium includes a storage data area storing data created according to use of a blockchain node and a storage program area storing an internet financial control program 10, and the internet financial control program 10 implements the following operations when executed by a processor:
acquiring financial related information of a first type of user and a second type of user from a predetermined database, performing preprocessing operation on the financial related information, and training based on the preprocessed financial related information and a neural network model to obtain a financial control recognition model;
acquiring financial attribute information of a user to be identified, inputting the financial attribute information into the financial control identification model to obtain an identification result, judging whether the type of the identification result is a first type identification result, and acquiring operation trace information of the user to be identified on a preset page according to a pre-configured buried point set when the type of the identification result is judged to be the first type identification result;
and inputting the operation trace information into a predetermined trace recognition model to obtain a target recognition result and feeding the target recognition result back to a preset terminal.
The embodiment of the computer readable storage medium of the present invention is substantially the same as the embodiment of the internet financial control method, and will not be described herein again.
It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention essentially or contributing to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above and includes several instructions for enabling a terminal device (such as a mobile phone, a computer, an electronic device, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. An internet financial control method, comprising:
acquiring financial related information of a first type of user and a second type of user from a predetermined database, performing preprocessing operation on the financial related information, and training based on the preprocessed financial related information and a neural network model to obtain a financial control recognition model;
acquiring financial attribute information of a user to be identified, inputting the financial attribute information into the financial control identification model to obtain an identification result, judging whether the type of the identification result is a first type identification result, and acquiring operation trace information of the user to be identified on a preset page according to a pre-configured buried point set when the type of the identification result is judged to be the first type identification result;
and inputting the operation trace information into a predetermined trace recognition model to obtain a target recognition result and feeding the target recognition result back to a preset terminal.
2. The internet financial control method of claim 1, wherein after determining whether the type of the recognition result is the first recognition result, the method further comprises:
and randomly selecting a preset number of users with the identification result type as a second type identification result at regular time, acquiring the operation trace information of the users with the second type identification result on a preset page according to a preset buried point set, converting the operation trace information into time sequence data, and inputting the time sequence data into a predetermined trace identification model.
3. The internet financial control method of claim 1 or 2 wherein the trace-recognition model is constructed by a specific process comprising:
respectively acquiring historical operation trace information of a first type user and a second type user from the database;
calculating the distance value of any two pieces of historical operation trace information based on a preset algorithm;
judging whether the two pieces of historical operation trace information are similar operation traces or not according to the distance value;
if the two pieces of historical operation trace information are similar operation traces, combining the two pieces of historical operation trace information to serve as a clustering center point;
and if the two pieces of historical operation trace information are not similar operation traces, forming a clustering center point according to each piece of historical operation trace information of the two pieces of historical operation trace information respectively.
4. The internet financial control method of claim 1 wherein said performing a preprocessing operation on the financial-related information comprises:
performing one or more of deviation data detection, missing value processing, and noise data smoothing on the financial-related information.
5. The internet financial control method of claim 4 wherein said training a financial control recognition model based on the preprocessed financial-related information and neural network model comprises:
allocating preset labels to users corresponding to the preprocessed financial related information, taking the financial related information as variables, and taking the labels of the users corresponding to the financial related information as dependent variables to generate a sample set;
dividing the sample set into a training set and a verification set according to a preset proportion;
training a convolutional neural network model by using each variable and each dependent variable in the training set, verifying the convolutional neural network model by using the verification set every other preset period, and verifying the accuracy of the financial control identification model by using each variable and each dependent variable in the verification set;
and when the accuracy is greater than a first preset threshold value, obtaining the financial control recognition model.
6. The internet financial control method of claim 1 wherein the step of generating the preconfigured set of buried points comprises:
randomly generating an initial embedded point set on a preset page;
judging whether the accuracy of the initial buried point set is greater than a second preset threshold value, and when the accuracy of the initial buried point set is greater than the second preset threshold value, taking the initial buried point set as the pre-configured buried point set;
when the accuracy of the initial buried point set is judged to be smaller than or equal to a second preset threshold value, generating a first buried point set and a second buried point set according to a preset cross probability and a cross method based on the adaptability value of the buried points;
and taking the first buried point set and the second buried point set as a new initial buried point set.
7. An internet financial control system, the system comprising:
a first control module: the system comprises a database, a neural network model and a financial control recognition model, wherein the database is used for acquiring financial related information of a first type of user and a second type of user from a predetermined database, performing preprocessing operation on the financial related information, and training based on the preprocessed financial related information and the neural network model to obtain the financial control recognition model;
a judging module: the financial control recognition model is used for acquiring financial attribute information of a user to be recognized, inputting the financial attribute information into the financial control recognition model to obtain a recognition result, judging whether the type of the recognition result is a first type recognition result, and acquiring operation trace information of the user to be recognized on a preset page according to a pre-configured buried point set when the type of the recognition result is judged to be the first type recognition result;
a second control module: and the operation trace information is input into a predetermined trace recognition model to obtain a target recognition result and feed the target recognition result back to a preset terminal.
8. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a program executable by the at least one processor, the program being executable by the at least one processor to cause the at least one processor to perform the steps of:
acquiring financial related information of a first type of user and a second type of user from a predetermined database, performing preprocessing operation on the financial related information, and training based on the preprocessed financial related information and a neural network model to obtain a financial control recognition model;
acquiring financial attribute information of a user to be identified, inputting the financial attribute information into the financial control identification model to obtain an identification result, judging whether the type of the identification result is a first type identification result, and acquiring operation trace information of the user to be identified on a preset page according to a pre-configured buried point set when the type of the identification result is judged to be the first type identification result;
and inputting the operation trace information into a predetermined trace recognition model to obtain a target recognition result and feeding the target recognition result back to a preset terminal.
9. The electronic device of claim 8, wherein the trace-recognition model is constructed in a specific process comprising:
respectively acquiring historical operation trace information of a first type user and a second type user from the database;
calculating the distance value of any two pieces of historical operation trace information based on a preset algorithm;
judging whether the two pieces of historical operation trace information are similar operation traces or not according to the distance value;
if the two pieces of historical operation trace information are similar operation traces, combining the two pieces of historical operation trace information to serve as a clustering center point;
and if the two pieces of historical operation trace information are not similar operation traces, forming a clustering center point according to each piece of historical operation trace information of the two pieces of historical operation trace information respectively.
10. A computer-readable storage medium storing an internet financial control program which, when executed by a processor, implements the steps of the internet financial control method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110715133.7A CN113554515A (en) | 2021-06-26 | 2021-06-26 | Internet financial control method, system, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110715133.7A CN113554515A (en) | 2021-06-26 | 2021-06-26 | Internet financial control method, system, device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113554515A true CN113554515A (en) | 2021-10-26 |
Family
ID=78130956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110715133.7A Pending CN113554515A (en) | 2021-06-26 | 2021-06-26 | Internet financial control method, system, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113554515A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109284371A (en) * | 2018-09-03 | 2019-01-29 | 平安证券股份有限公司 | Anti- fraud method, electronic device and computer readable storage medium |
| CN109636061A (en) * | 2018-12-25 | 2019-04-16 | 深圳市南山区人民医院 | Training method, device, equipment and the storage medium of medical insurance Fraud Prediction network |
| WO2019153604A1 (en) * | 2018-02-06 | 2019-08-15 | 平安科技（深圳）有限公司 | Device and method for creating human/machine identification model, and computer readable storage medium |
| CN111666351A (en) * | 2020-05-29 | 2020-09-15 | 北京睿知图远科技有限公司 | Fuzzy clustering system based on user behavior data |
| CN112069485A (en) * | 2020-06-12 | 2020-12-11 | 完美世界(北京)软件科技发展有限公司 | Safety processing method, device and equipment based on user behaviors |
| CN112511632A (en) * | 2020-12-03 | 2021-03-16 | 中国平安财产保险股份有限公司 | Object pushing method, device and equipment based on multi-source data and storage medium |
-
2021
- 2021-06-26 CN CN202110715133.7A patent/CN113554515A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019153604A1 (en) * | 2018-02-06 | 2019-08-15 | 平安科技（深圳）有限公司 | Device and method for creating human/machine identification model, and computer readable storage medium |
| CN109284371A (en) * | 2018-09-03 | 2019-01-29 | 平安证券股份有限公司 | Anti- fraud method, electronic device and computer readable storage medium |
| CN109636061A (en) * | 2018-12-25 | 2019-04-16 | 深圳市南山区人民医院 | Training method, device, equipment and the storage medium of medical insurance Fraud Prediction network |
| CN111666351A (en) * | 2020-05-29 | 2020-09-15 | 北京睿知图远科技有限公司 | Fuzzy clustering system based on user behavior data |
| CN112069485A (en) * | 2020-06-12 | 2020-12-11 | 完美世界(北京)软件科技发展有限公司 | Safety processing method, device and equipment based on user behaviors |
| CN112511632A (en) * | 2020-12-03 | 2021-03-16 | 中国平安财产保险股份有限公司 | Object pushing method, device and equipment based on multi-source data and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876133B (en) | Risk assessment processing method, device, server and medium based on business information | |
| CN109858737B (en) | Grading model adjustment method and device based on model deployment and computer equipment | |
| WO2019061994A1 (en) | Electronic device, insurance product recommendation method and system, and computer readable storage medium | |
| CN108876636B (en) | Intelligent air control method, system, computer equipment and storage medium for claim settlement | |
| CN109815803B (en) | Face examination risk control method and device, computer equipment and storage medium | |
| CN107688987A (en) | Electronic installation, insurance recommendation method and computer-readable recording medium | |
| CN110766275A (en) | Data verification method and device, computer equipment and storage medium | |
| CN111814472B (en) | Text recognition method, device, equipment and storage medium | |
| CN107818491A (en) | Electronic installation, Products Show method and storage medium based on user's Internet data | |
| CN111260189B (en) | Risk control method, risk control device, computer system and readable storage medium | |
| CN111582932A (en) | Inter-scene information pushing method and device, computer equipment and storage medium | |
| CN112507212A (en) | Intelligent return visit method and device, electronic equipment and readable storage medium | |
| CN112258238A (en) | User life value cycle detection method and device and computer equipment | |
| CN112511632B (en) | Object pushing method, device and equipment based on multi-source data and storage medium | |
| CN114880566A (en) | User behavior analysis method, device, equipment and medium based on graph neural network | |
| CN111541703B (en) | Terminal equipment authentication method and device, computer equipment and storage medium | |
| CN110598090B (en) | Interest tag generation method and device, computer equipment and storage medium | |
| CN112487021A (en) | Correlation analysis method, device and equipment for business data | |
| CN112634017A (en) | Remote card opening activation method and device, electronic equipment and computer storage medium | |
| CN117133006A (en) | Document verification method and device, computer equipment and storage medium | |
| CN113554515A (en) | Internet financial control method, system, device and medium | |
| CN111277465A (en) | Abnormal data message detection method and device and electronic equipment | |
| US11947643B2 (en) | Fraud detection system, fraud detection method, and program | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN113850500A (en) | Logistics risk early warning method and device based on DE-BP neural network 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 |