CN113298642B - Order detection method and device, electronic equipment and storage medium - Google Patents

Order detection method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113298642B
CN113298642B CN202110580257.9A CN202110580257A CN113298642B CN 113298642 B CN113298642 B CN 113298642B CN 202110580257 A CN202110580257 A CN 202110580257A CN 113298642 B CN113298642 B CN 113298642B
Authority
CN
China
Prior art keywords
order
target
similarity
time
determining
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.)
Active
Application number
CN202110580257.9A
Other languages
Chinese (zh)
Other versions
CN113298642A (en
Inventor
文芷晴
刘慈文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Xiaotu Network Technology Co ltd
Original Assignee
Shanghai Xiaotu Network Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Xiaotu Network Technology Co ltd filed Critical Shanghai Xiaotu Network Technology Co ltd
Priority to CN202110580257.9A priority Critical patent/CN113298642B/en
Publication of CN113298642A publication Critical patent/CN113298642A/en
Application granted granted Critical
Publication of CN113298642B publication Critical patent/CN113298642B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/03Credit; Loans; Processing thereof
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0633Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635Processing of requisition or of purchase orders
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Technology Law (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides an order detection method, an order detection device, electronic equipment and a storage medium, and belongs to the technical field of Internet. The method comprises the steps of obtaining an order set in a preset time period, wherein the order set comprises a first order and at least one second order; determining, for any one of the second orders, a first similarity of the first order to the second order based on the corresponding first and second characteristic data; determining, for any one of the second orders, a time decay similarity of the first order and the second order based on a corresponding first order placing time of the first order, a corresponding second order placing time of the second order, and a first similarity of the first order and the second order; and determining the second order with the time attenuation similarity larger than a preset threshold value and the first order as a target order set. The accuracy of detecting group fraud is improved.

Description

Order detection method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of internet technologies, and in particular, to an order detection method, an order detection device, an electronic device, and a storage medium.
Background
With the rapid development of the internet, various traditional businesses are gradually turned to online, network consumption credit in internet finance is gradually becoming a popular loan way, and the generation of the network consumption credit brings a large amount of electronic transaction data, and simultaneously, the network consumption credit fraud amount is greatly increased.
Traditional methods of detecting consumer credit fraud are generally: based on historical order data (the historical order data comprises fraudulent application orders and normal application orders), a classification model is established by adopting a supervised learning algorithm, and a new order is analyzed by using the classification model to obtain the fraud probability of the new order so as to quantify fraud risks. That is, the fraud features of the individual that are repeated in consuming credit fraud are found from the historical data, and fraud applications are detected based on the fraud features of the individual.
However, with the continuous evolution and development of consumer credit fraud modes, more and more group fraud occurs, and the orders of group fraud are often accompanied by characteristics of intensive and frequent or application behavior in time and space, association relation exists on application user information, and the like, so that individual fraud characteristics are not obvious in group fraud, and the result of detecting group fraud application only according to individual characteristics is not accurate enough.
Disclosure of Invention
An object of the embodiments of the present application is to provide an order detection method, an order detection device, an electronic device, and a storage medium, so as to solve the problem that a result of detecting a group fraud application according to individual characteristics is not accurate enough. The specific technical scheme is as follows:
in a first aspect, there is provided a method of order detection, the method comprising:
acquiring an order set in a preset time period, wherein the order set comprises a first order and at least one second order, the first order is an order meeting preset conditions in the order set, the first order corresponds to first characteristic data, and the second order corresponds to second characteristic data;
for any one of the second orders, determining first similarity between the first order and the second order based on the corresponding first characteristic data and second characteristic data, and obtaining at least one first similarity;
for any one of the second orders, determining the time attenuation similarity of the first order and the second order based on the corresponding first order placing time of the first order, the second order placing time of the second order and the first similarity of the first order and the second order, and obtaining at least one time attenuation similarity;
And determining the second order with the time attenuation similarity larger than a preset threshold value and the first order as a target order set.
In one possible implementation, the target order set includes: a first target order and at least one second target order; the first target order is provided with a plurality of types of characteristic data corresponding to the first target order; the second target order is provided with a plurality of types of characteristic data corresponding to the second target order;
the method further comprises the steps of:
regarding any second target order, taking the second target order and the first target order as a target order combination, wherein the target order combination corresponds to a target group;
determining second similarity of the first target order and the second target order corresponding to any category based on the feature data corresponding to any category for the first target order and the second target order in any one of the target order combinations, and obtaining at least one second similarity of the first target order and the second target order;
based on at least one of the second similarities, a community type of a target community corresponding to the target order combination is determined.
In one possible embodiment, the categories include: a first category, a second category, and a third category; the determining, based on at least one of the second similarities, a community type of the target community corresponding to the target order combination, including:
Among the at least one second similarity, the second similarity is the largest as the target similarity;
if the target similarity is the second similarity corresponding to the first category, determining that the type of the target group is the first type;
if the target similarity is the second similarity corresponding to the second category, determining that the type of the target group is a second type;
and if the target similarity is the second similarity corresponding to the third category, determining that the type of the target group is the third type.
In one possible embodiment, the method further comprises:
determining the risk level of a first target order and a second target order in the target order combination based on preset dividing conditions;
based on the risk level, control of a first target order and a second target order in the target order combination is determined.
In one possible implementation manner, the determining the time attenuation similarity of the first order and the second order based on the corresponding first order placing time of the first order, the second order placing time of the second order, and the first similarity of the first order and the second order includes:
Determining a placement interval time of a first order and a second order based on the first placement time and the second placement time;
determining time attenuation coefficients of the first order and the second order based on the placement interval time by using a preset time attenuation formula,
wherein, the preset time attenuation formula comprises: t=e -kt Wherein T is a time attenuation coefficient, k is an attenuation factor, T is a time period, and e is a natural base number;
and taking the product of the first similarity and the time attenuation coefficient as the time attenuation similarity.
In one possible implementation manner, the determining the first similarity between the first order and the second order based on the corresponding first feature data and the second feature data includes:
determining cosine similarity between the first feature data and the second feature data based on the first feature data and the second feature data by using a cosine similarity formula, and taking the cosine similarity as the first similarity of the first order and the second order;
wherein the cosine similarity formula includes:
wherein x is i As a result of the first characteristic data, Is the mean value of the first characteristic data, y i For the second characteristic data->Is the mean of the second feature data.
In one possible embodiment, the method further comprises:
and converting the first characteristic data and the second characteristic data into numerical data, and scaling the first characteristic data and the second characteristic data to the same dimension.
In a second aspect, there is provided an order detection apparatus, the apparatus comprising:
the system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring an order set in a preset time period, the order set comprises a first order and at least one second order, the first order is an order meeting preset conditions in the order set, the first order corresponds to first characteristic data, and the second order corresponds to second characteristic data;
the first determining module is used for determining first similarity between the first order and the second order according to the corresponding first characteristic data and the second characteristic data aiming at any one of the second orders, and obtaining at least one first similarity;
the second determining module is configured to determine, for any one of the second orders, a time attenuation similarity between the first order and the second order based on a corresponding first order placing time of the first order, a corresponding second order placing time of the second order, and a first similarity between the first order and the second order, so as to obtain at least one time attenuation similarity;
And the third determining module is used for determining the second order with the time attenuation similarity larger than a preset threshold value and the first order as a target order set.
In one possible implementation, the target order set includes: a first target order and at least one second target order; the first target order is provided with a plurality of types of characteristic data corresponding to the first target order; the second target order is provided with a plurality of types of characteristic data corresponding to the second target order;
the apparatus further comprises:
a combination module, configured to, for any one of the second target orders, take the second target order and the first target order as a target order combination, where the target order combination corresponds to a target group;
a fourth determining module, configured to determine, for a first target order and a second target order in any one of the target order combinations, a second similarity of the first target order and the second target order corresponding to any one of the categories based on feature data corresponding to the one of the categories, and obtain at least one second similarity of the first target order and the second target order;
and a fifth determining module, configured to determine a community type of the target community corresponding to the target order combination based on at least one of the second similarities.
In one possible embodiment, the categories include: a first category, a second category, and a third category; the fifth determining module is specifically configured to:
among the at least one second similarity, the second similarity is the largest as the target similarity;
if the target similarity is the second similarity corresponding to the first category, determining that the type of the target group is the first type;
if the target similarity is the second similarity corresponding to the second category, determining that the type of the target group is a second type;
and if the target similarity is the second similarity corresponding to the third category, determining that the type of the target group is the third type.
In one possible embodiment, the apparatus further comprises:
a sixth determining module, configured to determine a risk level of the first target order and the second target order in the target order combination based on a preset dividing condition;
and a seventh determining module, configured to determine control over the first target order and the second target order in the target order combination based on the risk level.
In a possible implementation manner, the second determining module is specifically configured to:
Determining a placement interval time of a first order and a second order based on the first placement time and the second placement time;
determining time attenuation coefficients of the first order and the second order based on the placement interval time by using a preset time attenuation formula,
wherein, the preset time attenuation formula comprises: t=e -kt Wherein T is a time attenuation coefficient, k is an attenuation factor, T is a time period, and e is a natural base number;
and taking the product of the first similarity and the time attenuation coefficient as the time attenuation similarity.
In a possible implementation manner, the first determining module is specifically configured to:
determining cosine similarity between the first feature data and the second feature data based on the first feature data and the second feature data by using a cosine similarity formula, and taking the cosine similarity as the first similarity of the first order and the second order;
wherein the cosine similarity formula includes:
wherein x is i As a result of the first characteristic data,is the mean value of the first characteristic data, y i For the second characteristic data->Is the mean of the second feature data.
In one possible embodiment, the apparatus further comprises:
And the conversion module is used for converting the first characteristic data and the second characteristic data into numerical data and scaling the first characteristic data and the second characteristic data to the same dimension.
In a third aspect, an electronic device is provided, 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 for implementing the method steps of any of the first aspects when executing a program stored on a memory.
In a fourth aspect, a computer-readable storage medium is provided, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of the first aspects.
In a fifth aspect, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform any of the order detection methods described above.
The beneficial effects of the embodiment of the application are that:
the embodiment of the application provides an order detection method, an order detection device, electronic equipment and a storage medium.
That is, the present application is directed to the time-space concentration and the behavior similarity of the group fraud in the internet financial field, and by determining the time attenuation similarity, whether the order is the group fraud is analyzed from two aspects of the time dimension and the space dimension, compared with the present detection of the fraud application only according to the individual characteristics, the detection of the group fraud result by the present scheme is more accurate.
Of course, not all of the above-described advantages need be achieved simultaneously in practicing any one of the products or methods of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 is a flowchart of an order detection method provided in an embodiment of the present application;
FIG. 2 is a flow chart of an order detection method according to another embodiment of the present application;
fig. 3 is a schematic structural diagram of an order detecting device according to an embodiment of the present application;
Fig. 4 is a schematic structural diagram of an order detecting device according to another embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As more and more group fraud is currently occurring, the orders of the group fraud are often accompanied by characteristics of intensive and frequent or application behaviors in time and space, association relation exists in application user information, and the like, the individual fraud characteristics in the group fraud are not obvious, so that the result of detecting the group fraud application only according to the individual characteristics is not accurate enough. For this reason, the embodiment of the application provides an order detection method, which can be applied to a credit consumption system.
The following will describe a detailed description of an order detection method provided in the embodiment of the present application with reference to specific embodiments, as shown in fig. 1, the specific steps are as follows:
S101, acquiring an order set in a preset time period, wherein the order set comprises a first order and at least one second order, the first order is an order meeting preset conditions in the order set, the first order corresponds to first characteristic data, and the second order corresponds to second characteristic data.
In this embodiment of the present application, the first order and the second order refer to orders for which the subject applies for a loan on a platform that provides a consumer credit service, the first feature data refers to feature data of the first order, and the second feature data refers to feature data of the second order.
Considering that the group fraud orders are often accompanied by time and space intensive and frequent, in detecting the group fraud orders, it is necessary to detect whether the group fraud orders exist or not based on the order sets within a period of time, and thus it is necessary to acquire the order sets within a preset period of time. The order set comprises a first order and at least one second order, wherein the first order is the latest order in the order set, and the second order is the order of the order set, the order placing time of which is before the order placing time of the first order.
S102, for any one of the second orders, determining first similarity between the first order and the second order based on the corresponding first feature data and the second feature data, and obtaining at least one first similarity.
In this embodiment of the present application, the first similarity refers to a similarity of the first order and the second order in a spatial dimension. The consumer credit system may determine, for any one of the second orders, a first similarity of the first order to the second order based on the corresponding first feature data and second feature data, resulting in at least one first similarity, wherein each of the second orders corresponds to one of the first similarities.
In one implementation manner of the embodiment of the present application, a cosine similarity formula may be used to determine, based on the first feature data and the second feature data, a cosine similarity between the first feature data and the second feature data, and the cosine similarity is used as a first similarity between the first order and the second order;
wherein the cosine similarity formula includes:
wherein x is i As a result of the first characteristic data,is the mean value of the first characteristic data, y i For the second characteristic data->Is the mean of the second feature data.
S103, for any one of the second orders, determining the time attenuation similarity of the first order and the second order based on the corresponding first order placing time of the first order, the second order placing time of the second order and the first similarity of the first order and the second order, and obtaining at least one time attenuation similarity.
In the embodiment of the present application, the time-decay similarity refers to the similarity of the first order and the second order in the space dimension and the time dimension. The consumer credit system may determine, for any one of the second orders, a time-decay similarity of the first order and the second order based on a corresponding first order time of the first order, a second order time of the second order, and a first similarity of the first order and the second order, to obtain at least one time-decay similarity, where each of the second orders corresponds to one of the time-decay similarities.
S104, determining the second order with the time attenuation similarity larger than a preset threshold value and the first order as a target order set.
In this embodiment of the present application, if the time-decay similarity is less than or equal to a preset threshold, it indicates that the first order and the second order are not fraudulent orders applied by the same fraudulent party, and if the time-decay similarity is greater than the preset threshold, it indicates that the first order and the second order are fraudulent orders applied by the same fraudulent party. The method comprises the steps of presetting a threshold in a consumption credit system, comparing each time attenuation similarity with the preset threshold, and determining a second order with the time attenuation similarity larger than the preset threshold and a first order as a target order set, wherein the target order set is a fraud order set.
In the embodiment of the application, aiming at the time-space concentration and behavior similarity of group fraud in the internet financial field, whether the order is a group fraud order is analyzed from two aspects of time dimension and space dimension by determining the time attenuation similarity, and compared with the current fraud application detection method only according to individual characteristics, the group fraud detection method is more accurate in result.
In yet another embodiment of the present application, the method may further comprise the steps of:
s201, regarding any one of the second target orders, the second target order and the first target order are used as a target order combination, and the target order combination corresponds to a target group.
In the embodiment of the application, the target order set includes: and regarding any second target order, taking the second target order and the first target order as a target order combination, wherein the target order combination corresponds to a target group, and the target order set comprises at least one target order combination. The first target order and the second target order in the target order combination are orders applied by the target group.
S202, determining second similarity of the first target order and the second target order corresponding to any category based on the feature data corresponding to any category for the first target order and the second target order in any one of the target order combinations, and obtaining at least one second similarity of the first target order and the second target order.
In the embodiment of the application, the first target order corresponds to a plurality of types of feature data; the second target order is provided with a plurality of types of feature data corresponding to the first target order, and the second similarity of the first target order and the second target order corresponding to each type is determined from the type dimension of the feature data. And determining the second similarity of the first target order and the second target order corresponding to any one of the target order combinations based on the characteristic data corresponding to the category, so as to obtain at least one second similarity of the first target order and the second target order.
In one example, the first target order a corresponds to a first category of feature data a1 and a second category of feature data a2, and the second target order B corresponds to a first category of feature data B1 and a second category of feature data B2. Substituting a1 and B1 into a preset similarity formula aiming at the characteristic data of the first category, so that a second similarity of A and B corresponding to the first category can be obtained; and substituting a2 and B2 into a preset similarity formula aiming at the characteristic data of the second category, so that the other second similarity of A and B corresponding to the second category can be obtained.
S203, determining the group type of the target group corresponding to the target order combination based on at least one second similarity.
In the embodiment of the application, the second similarity is determined based on the category dimension of the feature data, so that the similarity of the first target order and the second target order in the target order combination under each category dimension can be determined based on the second similarity, and then the group type of the target group corresponding to the target order combination is determined.
In this embodiment of the present application, for the first target order and the second target order in any one of the target order combinations, based on the feature data corresponding to any one of the categories, the second similarity between the first target order and the second target order corresponding to the category is determined, and based on the second similarity, the similarity between the first target order and the second target order in each of the target order combinations in each of the category dimensions may be determined, so as to determine the group type of the target group corresponding to the target order combination, thereby facilitating the analysis of the target group.
In yet another embodiment of the present application, the step S203 may include the following steps:
and step one, taking the second similarity with the largest second similarity as the target similarity in at least one second similarity.
In the embodiment of the present application, the category of the feature data includes: a first category, a second category, and a third category. The first category, the second category and the third category respectively correspond to one second similarity, and among the three second similarities, the second similarity with the largest similarity is taken as the target similarity.
And step two, if the target similarity is the second similarity corresponding to the first category, determining the type of the target group as the first type.
In the embodiment of the present application, the feature data of the first category may be behavior feature data of the user, and the first type may be a software attack type (network attack type). The behavior characteristic data of the user refer to: user behavior characteristics derived from user buried point data, such as: "how many times the user clicks in the first 1 minute of the order", "how many times the user backs up in the first 1 minute of the order", etc.
If the target similarity is the second similarity corresponding to the first category, it is indicated that the behavior similarity of the user between the first target order and the second target order is very high, and at this time, the type of the target group can be generally determined to be a software attack type (network attack type), the software attack type (network attack type) order is usually operated by using codes or software simulators, and different account information is adopted to apply for loans multiple times and frequently, so as to generate a large number of orders, and therefore, the orders often show similar or even identical behavior data such as "login", "click", "rollback", "exit" before application.
Preferably, the time interval between the first target order and the second target order can be added as a basis for determining the type of the target group, and when the target similarity is the second similarity corresponding to the first category and the time interval between the first target order and the second target order is in millisecond level, the type of the target group is determined to be the software attack type (network attack type).
And step three, if the target similarity is a second similarity corresponding to the second category, determining the type of the target group as a second type.
In the embodiment of the present application, the second category of feature data may be basic feature data, and the second type may be intermediate type or professional type. Intermediate means: fraudsters virtually package customer personal property information in the form of intermediaries, offering customers the assistance of acquiring loans. Occupational refers to: fraud is conducted directly on the issuing institution in the form of professional fraudulent groups by multiple fraudsters, not only to generate orders for one institution, but also to generate orders at multiple different issuing institutions. Such as: professional group fraudsters apply for the cash on a certain platform, and most cash institutions cannot pay the same applicant for a plurality of times in a short period of time, so that after a cash institution successfully applies for the cash, other cash institutions apply for the cash, and the cash is associated with a plurality of cash institutions.
Basic feature data refers to: features that can be directly acquired by the front page, such as: number attribution information, work, education level and the like. If the target similarity is the second similarity corresponding to the second type, it is indicated that the basic feature similarity between the first target order and the second target order is high, and it is indicated that the user corresponding to the first target order and the second target order has association in real life, so that the type of the target group can be generally identified as the intermediary type or the professional type.
And step four, if the target similarity is the second similarity corresponding to the third category, determining that the type of the target group is the third type.
In the embodiment of the present application, the third category of feature data may be external institution-related feature data, and the third type may be professional type. The external institution-associated feature data refers to: external data provided by other third parties, including data such as liabilities and rewards.
If the target similarity is the second similarity corresponding to the third category, it indicates that the similarity of the correlation features of the external mechanism between the first target order and the second target order is high, which indicates that the target group may have made a case on a plurality of platforms, so that the type of the target group can be generally determined as professional.
In the embodiment of the application, the type of the target group can be determined by determining the category of the characteristic data corresponding to the maximum similarity in the second similarity, so that human analysis can be reduced, and the efficiency of analyzing the fraudulent group is improved.
In yet another embodiment of the present application, the method may further comprise the steps of:
step one, if the types of target communities corresponding to any two target order combinations are the same, determining that the target communities corresponding to the two target order combinations are the same target community.
In the embodiment of the present application, if the types of target communities corresponding to any two target order combinations are the same, it is determined that the target communities corresponding to the two target order combinations are the same target community. The type of the target group a corresponding to the target order combination a is a first type, the type of the target group B corresponding to the target order combination B is a first type, and it is determined that the target group a and the target group B are the same target group. All orders applied by the same target group can be determined through the scheme, so that the specific application condition of the target group can be conveniently analyzed.
In yet another embodiment of the present application, the method may further comprise the steps of:
And generating a target group report based on a first target order corresponding to the target group, a second target order corresponding to the target group and a second similarity of the first target order and the second target order for any target group.
In an embodiment of the present application, the content of the report may include: target group basic information, similar order feature details, and the like: the basic information of the group comprises: the current number of associated users, the total quantity of orders of the associated users, the basic information of the group, and the risk level of the group; the similar order information mainly includes: similar orders, order similarity, order time attenuation similarity, subset feature similarity, and order interval time; similar order feature details: including all features of similar orders within the system and their results.
For any target group, a target group report may be generated based on a first target order corresponding to the target group, a second target order corresponding to the target group, and a second similarity of the first target order and the second target order. By the method, the target group report is generated, and the wind control personnel can conveniently analyze the target group.
In yet another embodiment of the present application, the method may further comprise the steps of:
step one, determining risk levels of a first target order and a second target order in the target order combination based on preset dividing conditions.
In this embodiment of the present application, the preset dividing condition may be the number of people of the target group corresponding to the target order combination or the similarity of the first target order and the second target order in the target order combination. Based on the preset dividing conditions, the risk level of the first target order and the second target order in the target order combination can be determined.
The risk level is high when the number of the target group persons exceeds 5 persons; and if the number of people of the target group A corresponding to the target order combination A is 6, determining that the risk levels of the first target order and the second target order in the target order combination A are high.
And step two, determining control over a first target order and a second target order in the target order combination based on the risk level.
In embodiments of the present application, control of the first target order and the second target order in the target order combination may be determined based on the risk level. For example, when the risk level of order B is high, it may be classified as an abnormal order and its information pushed to the winders.
In the embodiment of the application, the risk level of the target order can be divided, the target order is controlled according to the risk level, and the problem that the target order is not processed timely due to untimely operation of personnel, so that the paying loss is caused is avoided.
In yet another embodiment of the present application, the step S103 may include the following steps:
step one, determining the order placing interval time of a first order and a second order based on the first order placing time and the second order placing time.
In the embodiment of the application, the order placing interval time of the first order and the second order can be determined based on the first order placing time and the second order placing time.
Step two, determining the time attenuation coefficients of the first order and the second order based on the time interval by using a preset time attenuation formula,
wherein, the preset time attenuation formula comprises: t=e -kt Wherein T is a time attenuation coefficient, k is an attenuation factor, T is a time period, and e is a natural base number.
In the embodiment of the application, the attenuation factor k needs to be determined in advance according to the order sample of the historical group fraud, and the determining process is as follows: taking the maximum time interval of the front order and the rear order from the historical group fraud order sample, and assuming that the maximum time interval is 10 days, t=10 can be set, wherein T is given by a pneumatic decision maker through a threshold value required to be taken, and the meaning of t=0.9 is as follows: within 30 days, the similarity corresponding to the two orders is attenuated by 10%, and T and T are substituted into the formula, so that the attenuation factor k can be obtained.
After obtaining the value of the attenuation factor k, when determining the time attenuation coefficients of the first order and the second order, only the time T between the first order and the second order is substituted into the formula t=e -kt Then the time attenuation coefficient T can be obtained, and the obtained time attenuation coefficient is [0,1 ]]In this case, the attenuation degree is larger as the attenuation degree is closer to 0, and the attenuation degree is smaller as the attenuation degree is closer to 1.
And thirdly, taking the product of the first similarity and the time attenuation coefficient as the time attenuation similarity.
In the embodiment of the application, after the time attenuation coefficient is obtained, the product of the first similarity and the time attenuation coefficient can be calculated, and the product is used as the time attenuation similarity of the first order and the second order.
In the embodiment of the application, a preset time attenuation formula is utilized to determine time attenuation coefficients of the first order and the second order based on the ordering interval time of the first order and the second order; and taking the product of the first similarity and the time attenuation coefficient as the time attenuation similarity. According to the method and the system for analyzing the group fraud orders, the time attenuation similarity of the first order and the second order can be determined, and whether the orders are group fraud orders or not can be analyzed from two aspects of time dimension and space dimension through the time attenuation similarity, so that analysis results are more accurate.
In yet another embodiment of the present application, the method may further comprise the steps of:
step one, converting the first characteristic data and the second characteristic data into numerical data, and scaling the first characteristic data and the second characteristic data to the same dimension.
In the embodiment of the application, advanced data processing and conversion are required before analysis is performed by using the first feature data and the second feature data, so that the first feature data and the second feature data are converted into numerical data of the same dimension. The specific process is as follows: firstly, data which cannot be directly subjected to mathematical computation is processed into data which can be subjected to mathematical computation, such as type data of 'men', 'women', and the like, and is converted into numerical data of '1', '0', and the like; and then, carrying out data scaling and unified dimension on the data.
In one implementation of the embodiment of the present application, the numerical data corresponding to the first feature data and the second feature data may be substituted into the conversion formula, all the data may be scaled to [ -1,1],
the conversion formula is specifically as follows:wherein x is * For the converted data, x is the data before conversion, mean is the average, max is the maximum, and min is the minimum. According to the scheme, the first characteristic data and the second characteristic data can be converted into numerical data with the same dimension, and subsequent analysis is facilitated.
In the embodiment of the application, aiming at the time-space concentration and behavior similarity of group fraud in the internet financial field, whether the order is a group fraud order is analyzed from two aspects of time dimension and space dimension by determining the time attenuation similarity, and compared with the current fraud application detection method only according to individual characteristics, the group fraud detection method is more accurate in result.
Based on the same technical concept, the embodiment of the application further provides an order detection device, as shown in fig. 3, including:
the acquiring module 301 is configured to acquire an order set in a preset time period, where the order set includes a first order and at least one second order, the first order is an order meeting a preset condition in the order set, the first order corresponds to first feature data, and the second order corresponds to second feature data;
a first determining module 302, configured to determine, for any one of the second orders, a first similarity between the first order and the second order based on the corresponding first feature data and the second feature data, so as to obtain at least one first similarity;
a second determining module 303, configured to determine, for any one of the second orders, a time attenuation similarity between the first order and the second order based on a corresponding first order placing time of the first order, a corresponding second order placing time of the second order, and a first similarity between the first order and the second order, so as to obtain at least one time attenuation similarity;
A third determining module 304, configured to determine, as a target order set, a second order with a time attenuation similarity greater than a preset threshold, and the first order.
In one possible implementation, the target order set includes: a first target order and at least one second target order; the first target order is provided with a plurality of types of characteristic data corresponding to the first target order; the second target order is provided with a plurality of types of characteristic data corresponding to the second target order;
as shown in fig. 4, the apparatus further includes:
a combination module 401, configured to, for any one of the second target orders, take the second target order and the first target order as a target order combination, where the target order combination corresponds to a target group;
a fourth determining module 402, configured to determine, for a first target order and a second target order in any one of the target order combinations, a second similarity of the first target order and the second target order corresponding to any one of the categories based on feature data corresponding to the one of the categories, and obtain at least one second similarity of the first target order and the second target order;
a fifth determining module 403, configured to determine a community type of the target community corresponding to the target order combination based on at least one of the second similarities.
In one possible embodiment, the categories include: a first category, a second category, and a third category; the fifth determining module is specifically configured to:
among the at least one second similarity, the second similarity is the largest as the target similarity;
if the target similarity is the second similarity corresponding to the first category, determining that the type of the target group is the first type;
if the target similarity is the second similarity corresponding to the second category, determining that the type of the target group is a second type;
and if the target similarity is the second similarity corresponding to the third category, determining that the type of the target group is the third type.
In one possible embodiment, the apparatus further comprises:
a sixth determining module, configured to determine a risk level of the first target order and the second target order in the target order combination based on a preset dividing condition;
and a seventh determining module, configured to determine control over the first target order and the second target order in the target order combination based on the risk level.
In a possible implementation manner, the second determining module is specifically configured to:
Determining a placement interval time of a first order and a second order based on the first placement time and the second placement time;
determining time attenuation coefficients of the first order and the second order based on the placement interval time by using a preset time attenuation formula,
wherein, the preset time attenuation formula comprises: t=e -kt Wherein T is a time attenuation coefficient, k is an attenuation factor, T is a time period, and e is a natural base number;
and taking the product of the first similarity and the time attenuation coefficient as the time attenuation similarity.
In a possible implementation manner, the first determining module is specifically configured to:
determining cosine similarity between the first feature data and the second feature data based on the first feature data and the second feature data by using a cosine similarity formula, and taking the cosine similarity as the first similarity of the first order and the second order;
wherein the cosine similarity formula includes:
wherein x is i As a result of the first characteristic data,is the mean value of the first characteristic data, y i For the second characteristic data->Is the mean of the second feature data.
In one possible embodiment, the apparatus further comprises:
And the conversion module is used for converting the first characteristic data and the second characteristic data into numerical data and scaling the first characteristic data and the second characteristic data to the same dimension.
The entity detection device provided in this embodiment may be a device as shown in fig. 3, and may perform all steps of the entity detection method shown in fig. 1-2, so as to achieve the technical effects of the entity detection method shown in fig. 1-2, and the detailed description will be omitted herein for brevity.
Based on the same technical concept, the embodiment of the present invention further provides an electronic device, as shown in fig. 5, including a processor 501, a communication interface 502, a memory 503, and a communication bus 504, where the processor 501, the communication interface 502, and the memory 503 complete communication with each other through the communication bus 504,
a memory 503 for storing a computer program;
the processor 501 is configured to execute the program stored in the memory 503, and implement the following steps:
acquiring an order set in a preset time period, wherein the order set comprises a first order and at least one second order, the first order is an order meeting preset conditions in the order set, the first order corresponds to first characteristic data, and the second order corresponds to second characteristic data;
For any one of the second orders, determining first similarity between the first order and the second order based on the corresponding first characteristic data and second characteristic data, and obtaining at least one first similarity;
for any one of the second orders, determining the time attenuation similarity of the first order and the second order based on the corresponding first order placing time of the first order, the second order placing time of the second order and the first similarity of the first order and the second order, and obtaining at least one time attenuation similarity;
and determining the second order with the time attenuation similarity larger than a preset threshold value and the first order as a target order set.
The communication bus mentioned above for the electronic devices may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the electronic device and other devices.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-Programmable gate arrays (FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
The entity detection device provided in this embodiment may be a device as shown in fig. 3, and may perform all steps of the entity detection method shown in fig. 1-2, so as to achieve the technical effects of the entity detection method shown in fig. 1-2, and the detailed description will be omitted herein for brevity.
In yet another embodiment of the present invention, a computer readable storage medium is provided, in which a computer program is stored, which when executed by a processor, implements the steps of any of the order detection methods described above.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the order detection methods of the above embodiments.
In the above embodiments, it may be implemented in whole or in part 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, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
It should be noted that in this document, relational terms such as "first" and "second" and the like are 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. Moreover, 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is merely a specific embodiment of the application to enable one skilled in the art to understand or practice the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (9)

1. A method of order detection, the method comprising:
acquiring an order set in a preset time period, wherein the order set comprises a first order and at least one second order, the first order is an order meeting preset conditions in the order set, the first order corresponds to first characteristic data, and the second order corresponds to second characteristic data;
for any one of the second orders, determining first similarity between the first order and the second order based on the corresponding first characteristic data and second characteristic data, and obtaining at least one first similarity;
for any one of the second orders, determining the time attenuation similarity of the first order and the second order based on the corresponding first order placing time of the first order, the second order placing time of the second order and the first similarity of the first order and the second order, and obtaining at least one time attenuation similarity;
determining a second order with the time attenuation similarity larger than a preset threshold value and the first order as a target order set;
wherein the determining the time attenuation similarity of the first order and the second order based on the corresponding first order placing time of the first order, the second order placing time of the second order, and the first similarity of the first order and the second order comprises:
Determining a placement interval time of a first order and a second order based on the first placement time and the second placement time;
determining time attenuation coefficients of the first order and the second order based on the placement interval time by using a preset time attenuation formula,
wherein, the preset time attenuation formula comprises: t=e -kt Wherein T is a time attenuation coefficient, k is an attenuation factor, T is a time period, and e is a natural base number;
and taking the product of the first similarity and the time attenuation coefficient as the time attenuation similarity.
2. The method of claim 1, wherein the target order set comprises: a first target order and at least one second target order; the first target order is provided with a plurality of types of characteristic data corresponding to the first target order; the second target order is provided with a plurality of types of characteristic data corresponding to the second target order;
the method further comprises the steps of:
regarding any second target order, taking the second target order and the first target order as a target order combination, wherein the target order combination corresponds to a target group;
determining second similarity of the first target order and the second target order corresponding to any category based on the feature data corresponding to any category for the first target order and the second target order in any one of the target order combinations, and obtaining at least one second similarity of the first target order and the second target order;
Based on at least one of the second similarities, a community type of a target community corresponding to the target order combination is determined.
3. The method of claim 2, wherein the categories include: a first category, a second category, and a third category; the determining, based on at least one of the second similarities, a community type of the target community corresponding to the target order combination, including:
among the at least one second similarity, the second similarity is the largest as the target similarity;
if the target similarity is the second similarity corresponding to the first category, determining that the type of the target group is the first type;
if the target similarity is the second similarity corresponding to the second category, determining that the type of the target group is a second type;
and if the target similarity is the second similarity corresponding to the third category, determining that the type of the target group is the third type.
4. The method according to claim 2, wherein the method further comprises:
determining the risk level of a first target order and a second target order in the target order combination based on preset dividing conditions;
Based on the risk level, control of a first target order and a second target order in the target order combination is determined.
5. The method of claim 1, wherein the determining a first similarity of the first order and the second order based on the corresponding first and second characteristic data comprises:
determining cosine similarity between the first feature data and the second feature data based on the first feature data and the second feature data by using a cosine similarity formula, and taking the cosine similarity as the first similarity of the first order and the second order;
wherein the cosine similarity formula includes:
wherein x is i As a result of the first characteristic data,is the mean value of the first characteristic data, y i For the second characteristic data->Is the mean of the second feature data.
6. The method according to claim 1, wherein the method further comprises:
and converting the first characteristic data and the second characteristic data into numerical data, and scaling the first characteristic data and the second characteristic data to the same dimension.
7. An order detection device, the device comprising:
The system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring an order set in a preset time period, the order set comprises a first order and at least one second order, the first order is an order meeting preset conditions in the order set, the first order corresponds to first characteristic data, and the second order corresponds to second characteristic data;
the first determining module is used for determining first similarity between the first order and the second order according to the corresponding first characteristic data and the second characteristic data aiming at any one of the second orders, and obtaining at least one first similarity;
the second determining module is configured to determine, for any one of the second orders, a time attenuation similarity between the first order and the second order based on a corresponding first order placing time of the first order, a corresponding second order placing time of the second order, and a first similarity between the first order and the second order, so as to obtain at least one time attenuation similarity;
the third determining module is used for determining a second order with the time attenuation similarity larger than a preset threshold value and the first order as a target order set;
the second determining module is specifically configured to:
Determining a placement interval time of a first order and a second order based on the first placement time and the second placement time;
determining time attenuation coefficients of the first order and the second order based on the placement interval time by using a preset time attenuation formula,
wherein, the preset time attenuation formula comprises: t=e -kt Wherein T is a time attenuation coefficient, k is an attenuation factor, T is a time period, and e is a natural base number;
and taking the product of the first similarity and the time attenuation coefficient as the time attenuation similarity.
8. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
a processor for carrying out the method steps of any one of claims 1-6 when executing a program stored on a memory.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-6.
CN202110580257.9A 2021-05-26 2021-05-26 Order detection method and device, electronic equipment and storage medium Active CN113298642B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110580257.9A CN113298642B (en) 2021-05-26 2021-05-26 Order detection method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110580257.9A CN113298642B (en) 2021-05-26 2021-05-26 Order detection method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113298642A CN113298642A (en) 2021-08-24
CN113298642B true CN113298642B (en) 2024-02-23

Family

ID=77325234

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110580257.9A Active CN113298642B (en) 2021-05-26 2021-05-26 Order detection method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113298642B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113570348A (en) * 2021-09-26 2021-10-29 山东光辉人力资源科技有限公司 Resume screening method

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016145993A1 (en) * 2015-03-13 2016-09-22 阿里巴巴集团控股有限公司 Method and system for user device identification
CN106886915A (en) * 2017-01-17 2017-06-23 华南理工大学 A kind of ad click predictor method based on time decay sampling
CN107341716A (en) * 2017-07-11 2017-11-10 北京奇艺世纪科技有限公司 A kind of method, apparatus and electronic equipment of the identification of malice order
CN109710623A (en) * 2018-12-10 2019-05-03 杭州爱聚科技有限公司 A kind of intelligence order synchronous method
WO2019157335A1 (en) * 2018-02-08 2019-08-15 Arizona Board Of Regents On Behalf Of Arizona State University Systems and methods for detecting pathogenic social media accounts without content or network structure
US10693855B1 (en) * 2016-03-31 2020-06-23 EMC IP Holding Company LLC Fraud detection
CN111539734A (en) * 2020-04-20 2020-08-14 车主邦(北京)科技有限公司 User-oriented risk control method
CN111612594A (en) * 2020-06-03 2020-09-01 天天向上(北京)网络科技有限公司 Localized merchant retail system
CN112163932A (en) * 2020-09-30 2021-01-01 中国民航信息网络股份有限公司 Malicious seat occupying order identification method and device and electronic equipment
CN112308566A (en) * 2020-09-27 2021-02-02 中智关爱通(上海)科技股份有限公司 Enterprise fraud identification method

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016145993A1 (en) * 2015-03-13 2016-09-22 阿里巴巴集团控股有限公司 Method and system for user device identification
US10693855B1 (en) * 2016-03-31 2020-06-23 EMC IP Holding Company LLC Fraud detection
CN106886915A (en) * 2017-01-17 2017-06-23 华南理工大学 A kind of ad click predictor method based on time decay sampling
CN107341716A (en) * 2017-07-11 2017-11-10 北京奇艺世纪科技有限公司 A kind of method, apparatus and electronic equipment of the identification of malice order
WO2019157335A1 (en) * 2018-02-08 2019-08-15 Arizona Board Of Regents On Behalf Of Arizona State University Systems and methods for detecting pathogenic social media accounts without content or network structure
CN109710623A (en) * 2018-12-10 2019-05-03 杭州爱聚科技有限公司 A kind of intelligence order synchronous method
CN111539734A (en) * 2020-04-20 2020-08-14 车主邦(北京)科技有限公司 User-oriented risk control method
CN111612594A (en) * 2020-06-03 2020-09-01 天天向上(北京)网络科技有限公司 Localized merchant retail system
CN112308566A (en) * 2020-09-27 2021-02-02 中智关爱通(上海)科技股份有限公司 Enterprise fraud identification method
CN112163932A (en) * 2020-09-30 2021-01-01 中国民航信息网络股份有限公司 Malicious seat occupying order identification method and device and electronic equipment

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Research of Trust Management in Web Services Based on Feedback and Time Decay;Guoping Zhang;2009 International Symposium on Computer Network and Multimedia Technology;全文 *
一种P2P文件共享网络高精度自适应声誉机制;王淼;软件学报;第22卷(第10期);全文 *
订单分配模型及其在旧物回收系统中的应用;张鑫;中国优秀硕士学位论文全文数据库;全文 *

Also Published As

Publication number Publication date
CN113298642A (en) 2021-08-24

Similar Documents

Publication Publication Date Title
US10572885B1 (en) Training method, apparatus for loan fraud detection model and computer device
US20180308160A1 (en) Risk assessment method and system
CN111429258B (en) Method and device for monitoring loan fund flow direction
CN108197795B (en) Malicious group account identification method, device, terminal and storage medium
CN112581291B (en) Risk assessment change detection method, apparatus, device and storage medium
CN111179051A (en) Financial target customer determination method and device and electronic equipment
CN111695938A (en) Product pushing method and system
CN112988840A (en) Time series prediction method, device, equipment and storage medium
CN111951008A (en) Risk prediction method and device, electronic equipment and readable storage medium
CN113034046A (en) Data risk metering method and device, electronic equipment and storage medium
CN113298642B (en) Order detection method and device, electronic equipment and storage medium
CN107871213B (en) Transaction behavior evaluation method, device, server and storage medium
CN116151840B (en) User service data intelligent management system and method based on big data
CN116934341A (en) Transaction risk assessment method, device, electronic equipment and medium
CN117131401A (en) Object recognition method, device, electronic equipment and storage medium
CN114626863A (en) Detection method, device, equipment and storage medium for export tax cheating enterprise
CN115330490A (en) Product recommendation method and device, storage medium and equipment
CN114881783A (en) Abnormal card identification method and device, electronic equipment and storage medium
CN115170153A (en) Multi-dimensional attribute-based work order processing method and device and storage medium
CN114722954A (en) Content exception handling method and device for evaluation information
CN113793210A (en) Method for evaluating network loan credit, related device and computer storage medium
CN112651572A (en) Profit prediction method and apparatus
CN111583021A (en) Modeling method and device for calculating pledge rate
CN113450116A (en) Transaction risk analysis method and device, electronic equipment and storage medium
CN111429257A (en) Transaction monitoring method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant