CN109670852A - User classification method, device, terminal and storage medium - Google Patents
User classification method, device, terminal and storage medium Download PDFInfo
- Publication number
- CN109670852A CN109670852A CN201811123393.XA CN201811123393A CN109670852A CN 109670852 A CN109670852 A CN 109670852A CN 201811123393 A CN201811123393 A CN 201811123393A CN 109670852 A CN109670852 A CN 109670852A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- preset
- abnormal
- model
- 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 55
- 230000002159 abnormal effect Effects 0.000 claims description 99
- 238000004891 communication Methods 0.000 claims description 53
- 238000010276 construction Methods 0.000 claims description 17
- 238000012216 screening Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/535—Tracking the activity of the user
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Signal Processing (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a kind of user classification method, device, terminal and storage mediums, which comprises obtains the user data in financial transaction data and the type of service of the financial business；The user tag that user draws a portrait in the multiple default dimensions of aspect is obtained according to the user data, and according to the type of service, obtains preset model corresponding with the type of service；The model label needed for selecting the preset model in the user tag；It is calculated the model label as the input of the corresponding preset model of the type of service, to obtain the result of user's classification.The present invention is by being arranged corresponding preset model for the financial business of each type of service, and the model label needed for finding preset model in multiple default dimensions in terms of user's portrait, it can be classified according to type of service to user, the diversified demand of application program business has been adapted to, the specific aim and accuracy of user's classification are improved.
Description
Technical Field
The present invention relates to the field of computers, and in particular, to a user classification method, a user classification device, a terminal, and a computer-readable storage medium.
Background
Currently, in order to increase income, financial enterprises usually develop some marketing activities, such as consuming a return package, etc., when the financial application is online. However, in practice, these marketing campaigns provide limited revenue to the business. In order to solve the problem of limited income brought by marketing activities, financial enterprises begin to distinguish all users so as to facilitate accurate marketing of further services. In the traditional user classification method, single-standard clustering is performed on users through user images, but the users obtained through classification in practical application cannot meet the requirement of diversification of financial application services, and the accuracy and pertinence of user classification are not high.
Disclosure of Invention
The invention mainly aims to provide a user classification method, a user classification device, a terminal and a computer readable storage medium, aiming at solving the problems that the traditional user classification method has single mode, cannot adapt to the requirement of diversified application program services and has low accuracy and pertinence of user classification.
In order to achieve the above object, the present invention provides a user classification method, comprising the steps of:
acquiring user data in financial service data and a service type of the financial service;
acquiring user tags on a plurality of preset dimensions according to the user data, and acquiring a preset model corresponding to the service type according to the service type;
selecting a model label required by the preset model from the user labels;
and calculating by taking the model label as the input of a preset model corresponding to the service type so as to obtain the user classification result.
Optionally, before the step of acquiring the user data in the financial service data and the service type of the financial service, the method further includes:
acquiring characteristic emphasis points corresponding to each service type of financial services;
calculating the association degree between each feature side gravity point and each preset dimension;
selecting a preset dimension with the association degree exceeding a preset threshold value from all preset dimensions as a model construction element corresponding to the service type by taking the service type as a unit;
and setting the weight corresponding to each model construction element according to the degree of association, so as to construct a preset model corresponding to each service type according to the model construction elements and the corresponding weights.
Optionally, the step of selecting a model tag required by the preset model from the user tags includes:
and selecting the model label from the user labels according to the model construction element of the preset model.
Optionally, the step of acquiring user data in the financial transaction data includes:
receiving a user classification request and financial service data sent by a financial service system; the financial business data comprises user data with identifiers to be classified;
and screening out user data with the identification to be classified from the financial service data according to the user classification request.
Optionally, the result of the user classification includes an abnormal user;
after the step of obtaining the result of the user classification, the method further includes:
when the user classification result is an abnormal user, extracting user data with an abnormal user tag from the user data of the user;
acquiring user data of other users associated with the abnormal user through the user data with the abnormal user tag;
and screening the abnormal users for the other users according to the user data of the associated other users.
Optionally, the result of the user classification further includes a normal user and a good-quality user;
after the step of obtaining the result of the user classification, the method further includes:
when the user classification result is an abnormal user, acquiring an exemption condition corresponding to the service type;
judging whether the service type of the user reaches the exemption condition or not according to the user data;
and when the service type of the user reaches the exemption condition, modifying the classification result of the user into a common user or a high-quality user.
Optionally, the user data includes at least one of device information, a network protocol IP address, and a communication number of a device used by the user when transacting financial services;
the step of obtaining user tags in a plurality of preset dimensions according to the user data comprises:
acquiring equipment information of equipment used by the user for transacting financial services from the user data;
generating a device fingerprint of the device according to a preset device fingerprint algorithm and the device information;
determining whether the device fingerprint is consistent with a historical device fingerprint of the device;
when the device fingerprint is inconsistent with a historical device fingerprint of the device, marking the user tag of the user on a device fingerprint dimension as abnormal;
when the device fingerprint is consistent with a historical device fingerprint of the device, marking the user tag of the user in a device fingerprint dimension as normal;
and/or, obtaining the IP address of the equipment used by the user when transacting the financial business from the user data;
judging whether the IP address of the equipment exists in a preset abnormal IP address library or not;
when the IP address of the equipment exists in a preset abnormal IP address library, marking the user label of the user on the dimension of the IP address as abnormal;
when the IP address of the equipment does not exist in a preset abnormal IP address library, marking the user label of the user on the dimension of the IP address as normal;
and/or, obtaining the communication number of the equipment used by the user when transacting the financial service from the user data;
judging whether the communication number of the equipment is an abnormal number or not;
when the communication number of the equipment is an abnormal number, marking the user label of the user on the communication number dimension as abnormal;
when the communication number of the device is not an abnormal number, the user tag of the user in the communication number dimension is marked as normal.
In order to achieve the above object, the present invention further provides a user classifying device, including:
the acquisition module is used for acquiring user data in financial service data and a service type corresponding to the financial service;
the acquisition module is further used for acquiring user tags on a plurality of preset dimensions according to the user data and acquiring a preset model corresponding to the service type according to the service type;
the selection module is used for selecting the model label required by the preset model from the user label;
and the operation module is used for calculating the model label as the input of a preset model corresponding to the service type so as to obtain the user classification result.
In order to achieve the above object, the present invention further provides a terminal, including: a communication module, a memory, a processor and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the user classification method as described above.
To achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, implements the steps of the user classification method as described above.
According to the scheme, user data in financial service data and the service type of the financial service are obtained; acquiring user tags on a plurality of preset dimensions in the aspect of user portrait dimensions according to the user data, and acquiring a preset model corresponding to the service type according to the service type; selecting a model label required by the preset model from the user labels; and calculating by taking the model label as the input of a preset model corresponding to the service type so as to obtain the user classification result. Therefore, the corresponding preset model is configured for each service type of the financial service, the model labels required by the preset model in multiple preset dimensions in the aspect of user portrait are found, customized user classification of the financial services of different service types is realized according to the user labels in the multiple preset dimensions in the user portrait, the requirement of application program service diversification is met, and the pertinence and the accuracy of user classification are improved.
Drawings
Fig. 1 is a schematic structural diagram of a terminal according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a user classification method according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating a user classifying method according to a second embodiment of the present invention;
FIG. 4 is a flowchart illustrating a detailed process of step S10 in the third embodiment of the user classifying method according to the present invention;
FIG. 5 is a flowchart illustrating a user classifying method according to a fourth embodiment of the present invention;
FIG. 6 is a functional block diagram of a user classifying device according to 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
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a hardware structure of a terminal provided by the present invention. The terminal is used for user classification, and may be a server, a computer or an electronic device dedicated to user classification, and includes components such as a communication module 10, a memory 20, and a processor 30. In the terminal, the processor 30 is connected to the memory 20 and the communication module 10, respectively, and the memory 20 stores thereon a computer program which is executed by the processor 30 at the same time.
The communication module 10 may be connected to an external communication device through a network. The communication module 10 may receive a request from an external communication device, and may also send a request, an instruction, and information to the external communication device. The external communication device may be at least one of a device for transacting financial transactions, other terminals, and financial transaction system devices. The financial transaction system device may be a financial application backend server that receives user data. The financial transaction may include a loan transaction, a financial product purchase transaction, a trusted product purchase transaction, an insurance product purchase transaction, and so on.
The memory 20 may be used to store software programs as well as various data. The memory 20 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for at least one function (such as obtaining user tags of a user in a plurality of preset dimensions in terms of user representation), and the like; the storage data area may include a database, and the storage data area may store data or information created according to the use of the terminal, and the like. Further, the memory 20 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The processor 30, which is a control center of the terminal, connects various parts of the entire terminal using various interfaces and lines, and performs various functions of the terminal and processes data by operating or executing software programs and/or modules stored in the memory 20 and calling data stored in the memory 20, thereby performing overall monitoring of the terminal. Processor 30 may include one or more processing units; alternatively, the processor 30 may integrate an application processor, which primarily handles operating systems, user interfaces, applications, etc., and a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 30.
Although not shown in fig. 1, the terminal may further include a circuit control module for connecting to a power supply to ensure the normal operation of other components. The terminal may further include a display module for extracting data from the memory 20 and displaying the data as a front-end display interface of the terminal and user classification results of various types of financial transactions. Those skilled in the art will appreciate that the terminal structure shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
Based on the hardware structure, various embodiments of the method of the invention are provided.
Referring to fig. 2, in a first embodiment of the user classification method of the present invention, the method includes:
step S10, acquiring user data in financial service data and the service type of the financial service;
the terminal collects financial transaction data from an external communications device, which may be a device used by the user to transact one or more financial transactions, such as a mobile telephone. The financial transaction data may include transaction flow data, user credit data, user basic information data, user operation trajectory data, device information of a device used by the user when transacting financial transactions, and the like. After the user classification is started, the processor selects user data including user operation track data, equipment information of equipment used by the user when the user transacts financial services and user basic information data. Each piece of user data can be attached with a service type identifier, and when the user data is classified according to a certain service type or a plurality of service types, the user data can be screened, and the service type of financial services can be determined. Alternatively, a terminal transacting financial services or financial services system equipment may send a user classification request to the terminal, where the user classification request includes a service type of financial services to be subjected to user classification.
It should be noted that the user operation trajectory data may be obtained through a buried point set in the financial application, and further may be obtained by combining with an XPATH (Xml Path Language) in the use process of the financial application. The device information may include a MAC (Media Access Control) address of the device, a device serial number, an IMEI (International Mobile Equipment Identity), and personalized setting information of the device, such as font setting information. The user basic information data may include an application registration account name, a communication number of the device, an IP Address (Internet Protocol Address), user device location information, and the like.
Step S20, acquiring user labels on a plurality of preset dimensions according to the user data, and acquiring a preset model corresponding to the service type according to the service type;
the user tag may be an abnormality level of the user in the preset dimension, for example, may be abnormal or normal, or may also be medium abnormal, and high abnormal. The user tag may be represented by an alphanumeric and/or chinese-english character, etc.
The user tag obtaining method is related to a preset dimension of the user portrait, for example, when the user tag is in a user positioning information dimension, user equipment positioning information, such as GPS positioning information and base station positioning information, of a user operating a financial application can be obtained from user data. If the distance between the GPS positioning information and the base station positioning information exceeds a certain distance threshold, determining that a user tag on the user positioning information dimension is abnormal; otherwise, the user label on the user positioning information dimension is considered to be normal. Each service type corresponds to a preset model, and the service types correspond to the preset models one by one.
In addition, if a financial service of a new service type is introduced, a preset model of a similar service type can be obtained, and the preset model corresponding to the new service type is obtained by increasing and changing the preset model.
Step S30, selecting a model label required by the preset model from the user labels;
the preset model is pre-stored in the memory and may include a plurality of model building elements, each model building element being a preset dimension of the preset model required in user portrayal. In order to implement the operation of the model, on the basis of determining the preset model corresponding to the service type, a preset dimension (i.e., a model building element) required by the preset model may be determined according to the preset model, then a user tag corresponding to the preset dimension is obtained from the determined preset dimension, and finally the user tag is used as a model tag required by the preset model.
Step S40, calculating the model label as an input of a preset model corresponding to the service type to obtain a result of the user classification.
It can be understood that the preset model is similar to a black box, and after the preset model is built, data is input and the model is operated, so that a user classification result can be obtained. The results of the user classification may include abnormal users, normal users, and premium users.
In the embodiment, user data in financial service data and the service type of the financial service are acquired; acquiring user tags on a plurality of preset dimensions in the aspect of user portrait dimensions according to the user data, and acquiring a preset model corresponding to the service type according to the service type; selecting a model label required by the preset model from the user labels; and calculating by taking the model label as the input of a preset model corresponding to the service type so as to obtain the user classification result. Therefore, the corresponding preset model is configured for each service type of the financial service, the model labels required by the preset model in multiple preset dimensions in the aspect of user portrait are found, customized user classification of the financial services of different service types is realized according to the user labels in the multiple preset dimensions in the user portrait, the requirement of application program service diversification is met, and the pertinence and the accuracy of user classification are improved.
Furthermore, after the user classification result of the service type is obtained, oriented service pushing or service communication can be carried out for the high-quality user; for the abnormal user, returning the financial service transacted by the abnormal user or further auditing the abnormal user can be considered; and further screening whether the user is a good user and/or an abnormal user in financial services of other service types for the common user. Therefore, the classification result of the user is effectively utilized, and the accuracy of business marketing is indirectly improved.
Further, in other embodiments, when the user data includes at least one of device information, an IP address, and a communication number of a device used by the user to transact financial services, the step of obtaining user tags in a plurality of preset dimensions according to the user data in step S20 may correspondingly include the following steps:
acquiring equipment information of equipment used by the user for transacting financial services from the user data; generating a device fingerprint of the device according to a preset device fingerprint algorithm and the device information; determining whether the device fingerprint is consistent with a historical device fingerprint of the device; when the device fingerprint is inconsistent with a historical device fingerprint of the device, marking the user tag of the user on a device fingerprint dimension as abnormal; when the device fingerprint matches a historical device fingerprint for the device, marking the user tag of the user in a device fingerprint dimension as normal. The device fingerprint is a device feature or a unique device identifier which can be used for uniquely identifying the device, each device fingerprint corresponds to a unique device, some device information of the device is not changed, but other device information is changed, so that a newly generated device fingerprint is changed, at this time, the historical fingerprint is inconsistent with the newly generated device fingerprint, and the terminal considers that the user has an abnormality in the device fingerprint dimension.
Acquiring the IP address of equipment used by the user when transacting financial services from the user data; judging whether the IP address of the equipment exists in a preset abnormal IP address library or not; when the IP address of the equipment exists in a preset abnormal IP address library, marking the user label of the user on the dimension of the IP address as abnormal; and when the IP address of the equipment does not exist in a preset abnormal IP address library, marking the user label of the user on the IP address dimension as normal. It should be noted that the IP address is a 32-bit binary number, and can be divided into a plurality of IP address fields, and the IP address can be classified by the IP address fields. The classification of IP addresses includes normal operator IP addresses, proxy IP, server IP, and IP pools. The user label of the user on the IP address dimension is abnormal if the IP address is classified into other categories than the normal operator IP address. For example, foreign IP addresses need to be used through proxy IP, and the user tag is considered abnormal. The server IP may be, for example, a broiler IP, which is a jumper board when a hacker operates with other devices, and if the hacker needs to search back, the server IP can only be searched, and the hacker at a remote end cannot be found, and at this time, the user tag may also be considered as abnormal.
Acquiring a communication number of equipment used by the user for transacting financial services from the user data; judging whether the communication number of the equipment is an abnormal number or not; when the communication number of the equipment is an abnormal number, marking the user label of the user on the communication number dimension as abnormal; when the communication number of the device is not an abnormal number, the user tag of the user in the communication number dimension is marked as normal. When the terminal collects user data based on the user portrait technology, the terminal collects user basic information data, which may include basic information such as user name, occupation, age, home residence, identification number, and communication number. The user label of the communication number dimension can be determined by acquiring the communication number and distinguishing the type of the communication number. For example, it may be determined whether the communication number is a communication number that has not been authenticated by real name from a non-formal channel through a third party interface, and it may also be verified whether the communication number of the user is a virtual number (e.g., a small number opened by a virtual operator). And if the communication number and/or the virtual number are not subjected to real-name authentication from the informal channel, setting the user tag of the user as an exception in the communication number dimension.
The scheme provides how to acquire the user tags in all dimensions based on the user portrait technology, and provides technical dimensional reference for user classification.
Further, referring to fig. 3, a second embodiment of the user classifying method according to the present invention is provided based on the first embodiment of the user classifying method according to the present invention, in this embodiment, the step S10 further includes:
step S50, acquiring characteristic emphasis points corresponding to each service type of the financial service;
the feature emphasis is set according to different service types and can be determined according to the data direction of the service type bias during model development, for example, the emphasis of loan is mainly on credit analysis of users and/or the value of mortgage assets, and the insurance purchase is mainly on the real condition of an insured object or an insured person. After the emphasis points are determined, the feature emphasis points can be obtained by digitizing the emphasis points.
Step S60, calculating the association degree between each feature side gravity point and each preset dimension;
the method for calculating the association degree may be set according to actual needs, for example, the feature side weight point and each preset dimension may be subjected to cluster analysis, and a distance between the feature side weight point and each preset dimension after the cluster analysis is used as an influence factor of the association degree, for example, the association degree is equal to 1 divided by the distance. The closer the distance is, the stronger the relevance between the characteristic side gravity point and the preset dimension is, and the greater the relevance is; the longer the distance between the feature side gravity point and the preset dimension is, the weaker the relevance is, and the smaller the relevance is. It should be noted that the clustering algorithm used in the association degree calculation may be set by referring to the prior art, for example, the K-means algorithm, which is not described herein again.
Step S70, selecting the preset dimension with the relevance degree exceeding a preset threshold value from all preset dimensions as a model construction element corresponding to the service type by taking the service type as a unit;
the strength of the association degree is distinguished through a preset threshold, a preset dimension within a certain distance is emphasized on a certain characteristic side, the preset dimension can be considered as a model construction element of the service type, the preset dimension outside the certain distance is considered as weak association, and the preset dimension can be excluded from the model construction elements for constructing the preset model.
It can be understood that the preset threshold corresponding to each service type may be consistent, or may be set according to the user data amount included in the service type. In addition, since each service type corresponds to a different preset model, in order to obtain the preset model corresponding to each service type, multiple clustering analyses need to be performed on feature emphasis points and multiple preset dimensions.
And step S80, setting the weight corresponding to each model construction element according to the degree of association, so as to construct a preset model corresponding to each service type according to the model construction elements and the corresponding weights.
The value of the weight may be related to the occupancy of the degree of association in all degrees of association. The relevance is high, and the weight of the corresponding model construction element is also high; and if the association degree is low, the weight of the corresponding model building element is also low.
In this embodiment, the model building element and the corresponding weight are used for building the preset model, for example, the model building element of the preset model may be used as the dimension required by the preset model, then the user label corresponding to the required dimension is selected from the user labels with the plurality of preset dimensions as the model label, then the model label is replaced with a numerical value, for example, the normal value is 1, the abnormal value is 0.5, and the corresponding weight is multiplied to obtain a total score, and finally the total score is determined to belong to which class of user classification interval range, so that the user classification result can be finally obtained. The scheme provides how to obtain the preset model corresponding to each service type, and provides technical support for user classification. In addition, the selected model tags in the user tags are obtained according to model building elements of the preset model, and the terminal is helped to quickly select the required user tags from all the user tags.
Further, referring to fig. 4, a third embodiment of the user classifying method according to the present invention is proposed based on the first embodiment of the user classifying method according to the present invention, in this embodiment, the step S10 includes:
step S11, receiving a user classification request and financial service data sent by a financial service system; the financial business data comprises user data with identifiers to be classified;
the financial service system sends a user classification request to the terminal, and the terminal responds to the request to start user classification after receiving the user classification request. In addition, the financial service system can also send financial service data of all users to the terminal, wherein the financial service data comprises non-user data, user data with the identification to be classified and user data without the identification to be classified.
And step S12, according to the user classification request, screening out user data with to-be-classified identification from the financial service data.
It can be understood that, in the data processing process, only part of the financial business data of part of users is collected, and the user classification is not enough; when the financial service data of the user is collected and is enough for user classification, the user data in the financial service data of the user can be added with the identifier to be classified, so that the terminal screens the user data with the identifier to be classified from the financial service data through triggering of the user classification request. The scheme screens original financial service data, and ensures the accuracy of user data in user classification.
Further, referring to fig. 5, a fourth embodiment of the user classification method of the present invention is proposed based on the first embodiment of the user classification method of the present invention, in this embodiment, the result of the user classification includes an abnormal user; the step S40 is followed by:
step S90, when the user classification result is abnormal user, extracting user data with abnormal user label from the user data of the user;
if the user is an abnormal user, the user labels of certain parts of preset dimensions in the plurality of preset dimensions of the user portrait are abnormal, and the part of user data of which the user labels are abnormal can be extracted. For example, if the user tag of the Wi-Fi information dimension of the user is abnormal, extracting the Wi-Fi information of the equipment used by the user when transacting financial services; and if the user label of the user in the communication number dimension is abnormal, extracting the communication number when the user transacts the financial service.
Step S100, acquiring user data of other users associated with the abnormal user through the user data with the abnormal user tag;
if the user tags in the dimensions are abnormal, the user data in the process of actually obtaining the user tags are also abnormal, and other user lists with the same user data can be searched for the abnormal user data through the user tags. If the user data with the user tag being abnormal also exists in other users, the other users are considered to be associated with the abnormal user, and the user data of the other users can be obtained.
Step S110, screening the abnormal user for the other users according to the user data of the associated other users.
It can be understood that the abnormal user and other users associated with the abnormal user all have the same user data with the user label as abnormal, so that the risk of the other user is higher than that of the general user in the user portrait risk assessment, and the abnormal user can be screened preferentially for the potential abnormal user. The screening process of the abnormal user is consistent with the user classification process, and is not described herein. It should be further noted that the abnormal users and the user tags are only performed for a single service type, and the screening of the abnormal users for the associated other users is also only performed for the same service type. According to the scheme, the abnormal users are screened by other users associated with the abnormal users, so that the abnormal users are preferentially and quickly identified from the risk angle of user portrait, and the efficiency of user classification is indirectly improved.
Further, in other embodiments, the result of the user classification may also include a general user and a good user. The step S40 may further include:
when the user classification result is an abnormal user, acquiring an exemption condition corresponding to the service type; judging whether the service type of the user reaches the exemption condition or not according to the user data; and when the service type of the user reaches the exemption condition, modifying the classification result of the user into a common user or a high-quality user. And when the user does not meet the exemption condition in the service type, no operation can be performed.
In the following, the financial business is taken as an example of a loan application business, and the exemption condition corresponding to the loan application may be that the value corresponding to the mortgage item provided by the user exceeds the loan amount. After the user is determined to be an abnormal user, loan application data provided by the user can be obtained according to the user data of the user, and the value of mortgage articles provided by the user is evaluated; and then judging whether the value corresponding to the mortgage articles provided by the user exceeds the loan amount, if the value of the mortgage articles exceeds the loan amount, the user reaches an exemption condition in the service type, and the user in the service type can be classified and adjusted into a high-quality user or a common user. The specific adjustment is that the user is a common user or a high-quality user, the user can determine the price of the mortgage articles provided by the user exceeds the loan amount, the more the exceeding value is, the user is more likely to be the high-quality user, and the user classification can be further performed in a limited interval. Alternatively, the user's loan application may be directly approved when the value of the mortgage item exceeds the loan amount. According to the scheme, corresponding exemption conditions are provided for different business types, under the condition that risks are controllable, more chances of successfully handling the businesses are provided for users, and good benefits are brought to financial enterprises.
Referring to fig. 6, the present invention also provides a user classifying device, which may be a server, a computer or an electronic device dedicated to user classification, including:
the acquiring module 10 is configured to acquire user data in financial service data and a service type corresponding to the financial service;
the obtaining module 10 is further configured to obtain a plurality of user tags in a preset dimension according to the user data, and obtain a preset model corresponding to the service type according to the service type;
a selecting module 20, configured to select a model tag required by the preset model from the user tags;
and the operation module 30 is configured to calculate the model label as an input of a preset model corresponding to the service type, so as to obtain a result of the user classification.
Further, in another embodiment, the user classification device further comprises a calculation module and a construction module; wherein,
the acquisition module is also used for acquiring characteristic emphasis points corresponding to each service type of the financial service;
the calculation module is used for calculating the association degree between each feature side gravity point and each preset dimension;
the selection module is further configured to select, from the preset dimensions, a preset dimension, for which the association exceeds a preset threshold, as a model construction element corresponding to the service type, in units of service types;
the building module is used for setting the weight corresponding to each model building element according to the degree of association so as to build a preset model corresponding to each service type according to the model building elements and the corresponding weights.
Further, in yet another embodiment, the selection module includes:
and the selection unit is used for selecting the model label from the user labels according to the model construction element of the preset model.
Further, in yet another embodiment, the obtaining module includes:
the receiving unit is used for receiving the user classification request and the financial service data sent by the financial service system; the financial business data comprises user data with identifiers to be classified;
and the screening unit is used for screening the user data with the identification to be classified from the financial service data according to the user classification request.
Further, in yet another embodiment, the results of the user classification include abnormal users; the user classification device further comprises an extraction module and a screening module;
the extraction module is used for extracting user data with abnormal user tags from the user data of the users when the user classification result is abnormal users;
the acquisition module is further configured to acquire user data of other users associated with the abnormal user through the user data with the user tag being abnormal;
the screening module is further configured to screen the abnormal user for the other users according to the user data of the associated other users.
Further, in another embodiment, the result of the user classification further includes a normal user and a good user; the user classification device also comprises a judgment module and a modification module;
the obtaining module is further configured to obtain an exemption condition corresponding to the service type when the user classification result is an abnormal user;
the judging module is used for judging whether the service type of the user reaches the exemption condition or not according to the user data;
and the modification module is used for modifying the classification result of the user into a common user or a high-quality user when the service type of the user reaches the exemption condition.
Further, in yet another embodiment, the user data includes at least one of device information, a network protocol IP address, and a communication number of a device used when the user transacts financial transactions;
the acquisition module is also used for acquiring equipment information of equipment used by the user when the user transacts financial services from the user data; generating a device fingerprint of the device according to a preset device fingerprint algorithm and the device information; determining whether the device fingerprint is consistent with a historical device fingerprint of the device; when the device fingerprint is inconsistent with a historical device fingerprint of the device, marking the user tag of the user on a device fingerprint dimension as abnormal; when the device fingerprint is consistent with a historical device fingerprint of the device, marking the user tag of the user in a device fingerprint dimension as normal;
and/or, obtaining the IP address of the equipment used by the user when transacting the financial business from the user data; judging whether the IP address of the equipment exists in a preset abnormal IP address library or not; when the IP address of the equipment exists in a preset abnormal IP address library, marking the user label of the user on the dimension of the IP address as abnormal; when the IP address of the equipment does not exist in a preset abnormal IP address library, marking the user label of the user on the dimension of the IP address as normal;
and/or, obtaining the communication number of the equipment used by the user when transacting the financial service from the user data; judging whether the communication number of the equipment is an abnormal number or not; when the communication number of the equipment is an abnormal number, marking the user label of the user on the communication number dimension as abnormal; when the communication number of the device is not an abnormal number, the user tag of the user in the communication number dimension is marked as normal.
The invention also proposes a computer-readable storage medium on which a computer program is stored. The computer-readable storage medium may be the Memory 20 in the terminal of fig. 1, and may also be at least one of a ROM (Read-Only Memory)/RAM (Random Access Memory), a magnetic disk, and an optical disk, and the computer-readable storage medium includes instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, a financial evaluation device, or a network device) having a processor to execute the method according to the embodiments of the present invention.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or server 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 server. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or service that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
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.
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. A method for classifying a user, comprising the steps of:
acquiring user data in financial service data and a service type of the financial service;
acquiring user tags on a plurality of preset dimensions according to the user data, and acquiring a preset model corresponding to the service type according to the service type;
selecting a model label required by the preset model from the user labels;
and calculating by taking the model label as the input of a preset model corresponding to the service type so as to obtain the user classification result.
2. The method for classifying users according to claim 1, wherein the step of obtaining the user data in the financial transaction data and the transaction type of the financial transaction is preceded by the steps of:
acquiring characteristic emphasis points corresponding to each service type of financial services;
calculating the association degree between each feature side gravity point and each preset dimension;
selecting a preset dimension with the association degree exceeding a preset threshold value from all preset dimensions as a model construction element corresponding to the service type by taking the service type as a unit;
and setting the weight corresponding to each model construction element according to the degree of association, so as to construct a preset model corresponding to each service type according to the model construction elements and the corresponding weights.
3. The user classification method according to claim 2, wherein the step of selecting a model label required for the preset model from the user labels comprises:
and selecting the model label from the user labels according to the model construction element of the preset model.
4. The user classifying method according to claim 1, wherein the step of acquiring the user data in the financial transaction data comprises:
receiving a user classification request and financial service data sent by a financial service system; the financial business data comprises user data with identifiers to be classified;
and screening out user data with the identification to be classified from the financial service data according to the user classification request.
5. The user classification method according to claim 1, wherein the result of the user classification includes an abnormal user;
after the step of obtaining the result of the user classification, the method further includes:
when the user classification result is an abnormal user, extracting user data with an abnormal user tag from the user data of the user;
acquiring user data of other users associated with the abnormal user through the user data with the abnormal user tag;
and screening the abnormal users for the other users according to the user data of the associated other users.
6. The user classification method according to claim 5, wherein the result of the user classification further includes a general user and a good-quality user;
after the step of obtaining the result of the user classification, the method further includes:
when the user classification result is an abnormal user, acquiring an exemption condition corresponding to the service type;
judging whether the service type of the user reaches the exemption condition or not according to the user data;
and when the service type of the user reaches the exemption condition, modifying the classification result of the user into a common user or a high-quality user.
7. The user classifying method according to any one of claims 1 to 6, wherein the user data includes at least one of device information, a network protocol IP address, and a communication number of a device used when the user transacts a financial transaction;
the step of obtaining user tags in a plurality of preset dimensions according to the user data comprises:
acquiring equipment information of equipment used by the user for transacting financial services from the user data;
generating a device fingerprint of the device according to a preset device fingerprint algorithm and the device information;
determining whether the device fingerprint is consistent with a historical device fingerprint of the device;
when the device fingerprint is inconsistent with a historical device fingerprint of the device, marking the user tag of the user on a device fingerprint dimension as abnormal;
when the device fingerprint is consistent with a historical device fingerprint of the device, marking the user tag of the user in a device fingerprint dimension as normal;
and/or, obtaining the IP address of the equipment used by the user when transacting the financial business from the user data;
judging whether the IP address of the equipment exists in a preset abnormal IP address library or not;
when the IP address of the equipment exists in a preset abnormal IP address library, marking the user label of the user on the dimension of the IP address as abnormal;
when the IP address of the equipment does not exist in a preset abnormal IP address library, marking the user label of the user on the dimension of the IP address as normal;
and/or, obtaining the communication number of the equipment used by the user when transacting the financial service from the user data;
judging whether the communication number of the equipment is an abnormal number or not;
when the communication number of the equipment is an abnormal number, marking the user label of the user on the communication number dimension as abnormal;
when the communication number of the device is not an abnormal number, the user tag of the user in the communication number dimension is marked as normal.
8. A user classifying apparatus, comprising:
the acquisition module is used for acquiring user data in financial service data and a service type corresponding to the financial service;
the acquisition module is further used for acquiring user tags on a plurality of preset dimensions according to the user data and acquiring a preset model corresponding to the service type according to the service type;
the selection module is used for selecting the model label required by the preset model from the user label;
and the operation module is used for calculating the model label as the input of a preset model corresponding to the service type so as to obtain the user classification result.
9. A terminal, characterized in that the terminal comprises: a communication module, a memory, a processor and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the user classification method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the user classification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811123393.XA CN109670852A (en) | 2018-09-26 | 2018-09-26 | User classification method, device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811123393.XA CN109670852A (en) | 2018-09-26 | 2018-09-26 | User classification method, device, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109670852A true CN109670852A (en) | 2019-04-23 |
Family
ID=66141958
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811123393.XA Pending CN109670852A (en) | 2018-09-26 | 2018-09-26 | User classification method, device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109670852A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232150A (en) * | 2019-05-21 | 2019-09-13 | 平安科技（深圳）有限公司 | A kind of Users'Data Analysis method, apparatus, readable storage medium storing program for executing and terminal device |
| CN110322899A (en) * | 2019-06-18 | 2019-10-11 | 平安银行股份有限公司 | User's intelligent method for classifying, server and storage medium |
| CN110597984A (en) * | 2019-08-12 | 2019-12-20 | 大箴(杭州)科技有限公司 | Method and device for determining abnormal behavior user information, storage medium and terminal |
| CN110796483A (en) * | 2019-10-10 | 2020-02-14 | 深圳小智科技有限公司 | User positioning method and device |
| CN110956269A (en) * | 2019-10-12 | 2020-04-03 | 平安科技（深圳）有限公司 | Data model generation method, device, equipment and computer storage medium |
| CN111132144A (en) * | 2019-12-25 | 2020-05-08 | 中国联合网络通信集团有限公司 | Abnormal number identification method and equipment |
| CN111815375A (en) * | 2020-09-04 | 2020-10-23 | 北京悠易网际科技发展有限公司 | User portrayal method and device in advertisement putting |
| CN112232960A (en) * | 2020-10-21 | 2021-01-15 | 中国银行股份有限公司 | Transaction application system monitoring method and device |
| CN112347343A (en) * | 2020-09-25 | 2021-02-09 | 北京淇瑀信息科技有限公司 | Customized information pushing method and device and electronic equipment |
| CN113065947A (en) * | 2021-03-18 | 2021-07-02 | 平安普惠企业管理有限公司 | Data processing method, device, equipment and storage medium |
| CN113204603A (en) * | 2021-05-21 | 2021-08-03 | 中国光大银行股份有限公司 | Method and device for marking categories of financial data assets |
| CN113239083A (en) * | 2021-05-13 | 2021-08-10 | 北京沃东天骏信息技术有限公司 | Data analysis method and device |
| CN115860283A (en) * | 2023-02-28 | 2023-03-28 | 北京信立方科技发展股份有限公司 | Contribution degree prediction method and device based on portrait of knowledge worker |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106952162A (en) * | 2016-01-07 | 2017-07-14 | 平安科技（深圳）有限公司 | Money laundering risks rating calculation method and system |
| CN106980663A (en) * | 2017-03-21 | 2017-07-25 | 上海星红桉数据科技有限公司 | Based on magnanimity across the user's portrait method for shielding behavioral data |
| CN107194815A (en) * | 2016-11-15 | 2017-09-22 | 平安科技（深圳）有限公司 | Client segmentation method and system |
| CN107590673A (en) * | 2017-03-17 | 2018-01-16 | 南方科技大学 | user classification method and device |
| WO2018099275A1 (en) * | 2016-11-29 | 2018-06-07 | 阿里巴巴集团控股有限公司 | Method, apparatus, and system for generating business object attribute identifier |
-
2018
- 2018-09-26 CN CN201811123393.XA patent/CN109670852A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106952162A (en) * | 2016-01-07 | 2017-07-14 | 平安科技（深圳）有限公司 | Money laundering risks rating calculation method and system |
| CN107194815A (en) * | 2016-11-15 | 2017-09-22 | 平安科技（深圳）有限公司 | Client segmentation method and system |
| WO2018099275A1 (en) * | 2016-11-29 | 2018-06-07 | 阿里巴巴集团控股有限公司 | Method, apparatus, and system for generating business object attribute identifier |
| CN107590673A (en) * | 2017-03-17 | 2018-01-16 | 南方科技大学 | user classification method and device |
| CN106980663A (en) * | 2017-03-21 | 2017-07-25 | 上海星红桉数据科技有限公司 | Based on magnanimity across the user's portrait method for shielding behavioral data |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232150A (en) * | 2019-05-21 | 2019-09-13 | 平安科技（深圳）有限公司 | A kind of Users'Data Analysis method, apparatus, readable storage medium storing program for executing and terminal device |
| CN110232150B (en) * | 2019-05-21 | 2023-04-14 | 平安科技（深圳）有限公司 | User data analysis method and device, readable storage medium and terminal equipment |
| CN110322899A (en) * | 2019-06-18 | 2019-10-11 | 平安银行股份有限公司 | User's intelligent method for classifying, server and storage medium |
| CN110322899B (en) * | 2019-06-18 | 2023-09-22 | 平安银行股份有限公司 | User intelligent classification method, server and storage medium |
| CN110597984B (en) * | 2019-08-12 | 2022-05-20 | 大箴(杭州)科技有限公司 | Method and device for determining abnormal behavior user information, storage medium and terminal |
| CN110597984A (en) * | 2019-08-12 | 2019-12-20 | 大箴(杭州)科技有限公司 | Method and device for determining abnormal behavior user information, storage medium and terminal |
| CN110796483A (en) * | 2019-10-10 | 2020-02-14 | 深圳小智科技有限公司 | User positioning method and device |
| CN110956269A (en) * | 2019-10-12 | 2020-04-03 | 平安科技（深圳）有限公司 | Data model generation method, device, equipment and computer storage medium |
| CN110956269B (en) * | 2019-10-12 | 2024-05-10 | 平安科技（深圳）有限公司 | Method, device, equipment and computer storage medium for generating data model |
| CN111132144A (en) * | 2019-12-25 | 2020-05-08 | 中国联合网络通信集团有限公司 | Abnormal number identification method and equipment |
| CN111132144B (en) * | 2019-12-25 | 2022-09-13 | 中国联合网络通信集团有限公司 | Abnormal number identification method and equipment |
| CN111815375A (en) * | 2020-09-04 | 2020-10-23 | 北京悠易网际科技发展有限公司 | User portrayal method and device in advertisement putting |
| CN112347343A (en) * | 2020-09-25 | 2021-02-09 | 北京淇瑀信息科技有限公司 | Customized information pushing method and device and electronic equipment |
| CN112347343B (en) * | 2020-09-25 | 2024-05-28 | 北京淇瑀信息科技有限公司 | Custom information pushing method and device and electronic equipment |
| CN112232960B (en) * | 2020-10-21 | 2023-09-19 | 中国银行股份有限公司 | Transaction application system monitoring method and device |
| CN112232960A (en) * | 2020-10-21 | 2021-01-15 | 中国银行股份有限公司 | Transaction application system monitoring method and device |
| CN113065947A (en) * | 2021-03-18 | 2021-07-02 | 平安普惠企业管理有限公司 | Data processing method, device, equipment and storage medium |
| CN113239083A (en) * | 2021-05-13 | 2021-08-10 | 北京沃东天骏信息技术有限公司 | Data analysis method and device |
| CN113204603A (en) * | 2021-05-21 | 2021-08-03 | 中国光大银行股份有限公司 | Method and device for marking categories of financial data assets |
| CN113204603B (en) * | 2021-05-21 | 2024-02-02 | 中国光大银行股份有限公司 | Category labeling method and device for financial data assets |
| CN115860283A (en) * | 2023-02-28 | 2023-03-28 | 北京信立方科技发展股份有限公司 | Contribution degree prediction method and device based on portrait of knowledge worker |
| CN115860283B (en) * | 2023-02-28 | 2023-05-02 | 北京信立方科技发展股份有限公司 | Contribution degree prediction method and device based on knowledge worker portrait |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670852A (en) | User classification method, device, terminal and storage medium | |
| EP2748781B1 (en) | Multi-factor identity fingerprinting with user behavior | |
| CN106384273B (en) | Malicious bill-swiping detection system and method | |
| CN107730389A (en) | Electronic installation, insurance products recommend method and computer-readable recording medium | |
| CN109636582B (en) | Credit information management method, apparatus, device and storage medium | |
| CN109634996A (en) | Customer information table generating method, device, equipment and computer readable storage medium | |
| CN108287823B (en) | Message data processing method and device, computer equipment and storage medium | |
| US9246925B2 (en) | Method and system for third-party service platform login | |
| WO2022002246A1 (en) | Verification method and apparatus for electronic equipment insurance | |
| CN109670931B (en) | Loan user behavior detection method, loan user behavior detection device, loan user behavior detection equipment and loan user behavior detection storage medium | |
| CN114116802A (en) | Data processing method, device, equipment and storage medium of Flink computing framework | |
| CN109460653B (en) | Rule engine based verification method, verification device, storage medium and apparatus | |
| CN110197386B (en) | Media resource pushing method and device, storage medium and electronic device | |
| CN107992527B (en) | Data mark checking method, server and storage medium | |
| CN111476633A (en) | Product service recommendation platform, product service path recommendation method and medium | |
| CN109472721A (en) | A kind of estate resource management method and system | |
| US20030120614A1 (en) | Automated e-commerce authentication method and system | |
| CN107679871B (en) | List management method, device, system and computer readable storage medium | |
| CN110704498A (en) | Data extraction method, device, equipment and computer readable storage medium | |
| US20220084048A1 (en) | Server apparatus, method of controlling server apparatus, computer-readable medium, genuine product determining system, and method of controlling genuine product determining system | |
| CN108055661B (en) | Telephone number blacklist establishing method and device based on communication network | |
| CN112668886A (en) | Method, device and equipment for monitoring risks of rental business and readable storage medium | |
| CN110598211A (en) | Article identification method and device, storage medium and electronic device | |
| CN109413031B (en) | Anti-fraud model construction method, device, equipment and readable storage medium | |
| CN110705382A (en) | Electronic invoice management method, device, equipment and medium based on invoice categories |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190423 |