CN110322343A - A kind of user's Life cycle credit prediction technique, device and computer equipment - Google Patents
A kind of user's Life cycle credit prediction technique, device and computer equipment Download PDFInfo
- Publication number
- CN110322343A CN110322343A CN201910588634.6A CN201910588634A CN110322343A CN 110322343 A CN110322343 A CN 110322343A CN 201910588634 A CN201910588634 A CN 201910588634A CN 110322343 A CN110322343 A CN 110322343A
- Authority
- CN
- China
- Prior art keywords
- time point
- user
- data
- material time
- credit
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of user's Life cycle credit prediction technique, device and computer equipments, belong to data analysis technique field.Method includes: the record data for obtaining user to be measured in client application, and record data includes the multiple behavioral datas to sort according to operating time dot sequency；It identifies the material time point in operating time point, and is directed to each current key time point, in record data, to extracting to obtain user characteristics in all behavioral datas between current key time point and previous material time point；The credit score of user characteristics and previous material time point is input in current key time point corresponding prediction model, user to be measured is obtained in the credit score at current key time point, the present invention can accurately and reliably evaluate the credit situation of user, to provide data supporting for policymaker.
Description
Technical field
The present invention relates to data analysis technique field more particularly to a kind of user's Life cycle credit prediction techniques, dress
It sets and computer equipment.
Background technique
In internet product field, subscriber lifecycle refer to user to product generate interest begin to use to stop make
With and no longer pay close attention to product overall process.
With the development of internet finance, more and more individuals seek the financial services such as debt-credit by internet.At present
It is typically all on the basis of carrying out credit evaluation to borrower, according to user's that the net for providing internet financial service, which borrows platform,
Credit situation provides credit extension loan to borrower.Therefore in personal credit's scene, the credit legal system of user is carried out very
It is important.
As the information that user submits is more and more, the credit situation of user how is accurately and reliably evaluated, with
Just the problem of providing data supporting for policymaker, being current urgent need to resolve.
Summary of the invention
In order to solve the problems, such as at least one mentioned in above-mentioned background technique, the present invention provides a kind of full Life Cycles of user
Phase credit prediction technique, device and computer equipment.
Specific technical solution provided in an embodiment of the present invention is as follows:
In a first aspect, providing a kind of user's Life cycle credit prediction technique, which comprises
Record data of the user to be measured in client application is obtained, the record data includes according to operation
Multiple behavioral datas of time dot sequency sequence；
It identifies the material time point in the operating time point, and is directed to each current key time point, in the behaviour
In data of noting down, to being mentioned in all behavioral datas between the current key time point and previous material time point
Obtain user characteristics；
The credit score of the user characteristics and the previous material time point is input to the current key time
In the corresponding prediction model of point, the user to be measured is obtained in the credit score at the current key time point.
Further, the record data for obtaining user to be measured in client application, comprising:
By bury a little to the client application, the user to be measured is obtained each of in the client application
Operation corresponding behavioral data and operating time point；
It sorts to behavioral data corresponding to each operation according to operating time dot sequency, obtains the operation note
Data.
Further, the material time point identified in the operating time point, comprising:
Identify whether the behavioral data in the record data is the corresponding behavioral data of key operation, if so,
The corresponding operating time point of the behavioral data is determined as material time point.
Further, the user characteristics include at least one of:
The operation duration of specified application page, the visitation frequency for specifying application page, accessed application page sum,
The fluctuation variance of the sum of the specified page element being clicked, user location.
Further, the corresponding prediction model of the material time point is trained in the following way obtains:
It obtains sample operations of the sample of users in the client application and records data, wherein the sample operations note
Record data include the multiple behavioral datas to sort according to operating time sequence, and the sample of users is marked with credit label；
For the material time point, in sample operations record data, to the material time point with it is previous
It extracts to obtain sample of users feature in all behavioral datas between material time point；
Preset nerve is trained using the credit score of the sample of users feature and the previous material time point
Network model obtains the corresponding prediction model of the material time point.
Second aspect, provides a kind of user's Life cycle credit prediction meanss, and described device includes:
Module is obtained, for obtaining record data of the user to be measured in client application, the operation note number
According to include according to operating time dot sequency sort multiple behavioral datas；
Identification module, for identification material time point in the operating time point out；
Extraction module, for being directed to each current key time point, in the record data, to the current pass
It extracts to obtain user characteristics in all behavioral datas between key time point and previous material time point；
Prediction module, it is described for the credit score of the user characteristics and the previous material time point to be input to
In current key time point corresponding prediction model, the user to be measured is obtained in the credit score at the current key time point.
Further, the acquisition module is specifically used for:
By bury a little to the client application, the user to be measured is obtained each of in the client application
Operation corresponding behavioral data and operating time point；
It sorts to behavioral data corresponding to each operation according to operating time dot sequency, obtains the operation note
Data.
Further, the identification module is specifically used for:
Identify whether the behavioral data in the record data is the corresponding behavioral data of key operation, if so,
The corresponding operating time point of the behavioral data is determined as material time point.
Further, the user characteristics include at least one of:
The operation duration of specified application page, the visitation frequency for specifying application page, accessed application page sum,
The fluctuation variance of the sum of the specified page element being clicked, user location.
Further, described device further includes training module, and the training module is specifically used for:
It obtains sample operations of the sample of users in the client application and records data, wherein the sample operations note
Record data include the multiple behavioral datas to sort according to operating time sequence, and the sample of users is marked with credit label；
For the material time point, in sample operations record data, to the material time point with it is previous
It extracts to obtain sample of users feature in all behavioral datas between material time point；
Preset nerve is trained using the credit score of the sample of users feature and the previous material time point
Network model obtains the corresponding prediction model of the material time point.
The third aspect provides a kind of computer equipment, comprising:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the method as described in first aspect is any.
Fourth aspect provides a kind of computer readable storage medium, is stored thereon with computer program, described program quilt
The method as described in first aspect is any is realized when processor executes.
The embodiment of the invention provides a kind of authentication method, apparatus, computer equipment and storage mediums, pass through acquisition
Record data of the user to be measured in client application, record data include sorting according to operating time dot sequency
Multiple behavioral datas identify the material time point in operating time point, and are directed to each current key time point, remember in operation
It records in data, is used being extracted in all behavioral datas between current key time point and previous material time point
Family feature, and that the credit score of user characteristics and previous material time point is input to current key time point is corresponding pre-
It surveys in model, obtains user to be measured in the credit score at current key time point.The present invention is default not for different material time points
Same credit prediction model, so that prediction is more targeted, and when each material time point is predicted, by means of previous
Material time point to all user behavior datas and previous material time point between the material time point credit predicted value,
Such loop iteration, so that the letter of the credit value predicted in each material time point all material time points before being all associated with
With predicted value, predicted in this way by realizing more accurately and reliably credit using the association between behavior before and after user, in turn
Data supporting can be provided for policymaker；In addition, technical solution scalability provided by the invention is strong, it can adapt to different scenes
Under credit evaluation demand.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is a kind of flow chart of user's Life cycle credit prediction technique provided in an embodiment of the present invention；
Fig. 2 is a kind of structural block diagram of user's Life cycle credit prediction meanss provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached in the embodiment of the present invention
Figure, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only this
Invention a part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
It should be noted that in the description of the present invention, term " first ", " second " etc. are used for description purposes only, without
It can be interpreted as indication or suggestion relative importance.In addition, in the description of the present invention, unless otherwise indicated, the meaning of " multiple "
It is two or more.
Embodiment one
The embodiment of the invention provides a kind of user's Life cycle credit prediction technique, this method can be by user Quan Sheng
Period credit prediction meanss are ordered to execute, which can realize by the way of software/hardware.It is applied to service in this way
Device is illustrated this method.As shown in Figure 1, this method may include:
Step 101, obtain record data of the user to be measured in client application, record data include according to
Multiple behavioral datas of operating time dot sequency sequence.
Wherein, client application may be mounted in any electronic equipment with processor and memory, for example, can be with
It is the electronic products such as portable computer, desktop computer, smart phone, tablet computer.In personal credit's scene, client is answered
With can be loan APP, user to be measured can be borrower.
Specifically, by bury a little to client application, each operation of the user to be measured in client application is obtained
Corresponding behavioral data and operating time point；Behavioral data corresponding to each operation is arranged according to operating time dot sequency
Sequence obtains record data.
Here, point can a little be buried, without burying point (a little also referred to as burying entirely a little without burying) etc. using code by bury to client application
Implementation, wherein burying an implementation is the prior art, and details are not described herein again.
In the present embodiment, by bury a little to client application, page elements all in client application are carried out
It parses and monitors, when there is user's operation behavior (alternative events) generation, i.e., the user's operation behavior is acquired, reported,
Server is available to arrive the corresponding behavioral data of user's operation and operating time point, including user identity information, accession page
The information such as geographical location locating for the access time point of element, residence time and user, that is to say, that at what time to user
It has accessed which page, which information is specifically had accessed, in the stay time of each page, user in which geographical location to visitor
The application information such as access in family end are obtained.
Wherein, page elements include but is not limited to button control, table sum number control.User's operation includes user in visitor
Upper various interactive operations are applied at family end, for example, to the clicking operation of the button control on the enrollment page of client application,
User carries out uploading on the authentication page operation of identity card, carries out checking declaration form, etc. in client application.
After obtaining each operation corresponding behavioral data and operating time point of the user to be measured in client application,
Each behavioral data can be ranked up according to operating time dot sequency, obtain record data.
Illustratively, the corresponding behavioral data of each operation to user to be measured in client application, record are as follows: C=
[C1, C2, C3 ..., Cn], n are the numbers of behavioral data；To the corresponding operating time point of each operation, be recorded as T=[T1,
T2, T3 ..., Tn], it is then ranked up according to operating time point, available record data as shown in table 1 below:
Table 1: user operation records data
In the present embodiment, by obtaining record data of the user to be measured in client application, commented to be subsequent
The credit situation for estimating user in each material time point provides data supporting.
Step 102, it identifies the material time point in operating time point, and is directed to each current key time point, grasping
In data of noting down, to being extracted in all behavioral datas between current key time point and previous material time point
To user characteristics.
Specifically, it identifies the material time point in operating time point, may include:
Identify whether the behavioral data in record data is the corresponding behavioral data of key operation, if so, will go
It is determined as material time point for the corresponding operating time point of data.
Wherein, key operation can be preset according to practical application scene, for example, in credit scene, setting
Key operation behavior includes: that user carries out the down operation of client application, user fills in personal essential information, user submits body
The operation of part certificate information, user carry out the operation of authentication, user requests operation of application service, etc..
After the material time point that server identifies user to be measured, for each current key time point, remember from operation
All behavioral datas between current key time point and previous material time point are extracted in record data, and according to behavior number
According to dimension to behavioral data carry out quantification treatment, obtain corresponding user characteristics vector, wherein user characteristics vector include extremely
Few user characteristics.
Wherein, user characteristics include at least one of:
The operation duration of specified application page, the visitation frequency for specifying application page, accessed application page sum,
The fluctuation variance of the sum of the specified page element being clicked, user location.
It is understood that user characteristics can also include other, the present invention is not especially limited this.
Specifically, the operation duration that all keys in the specified application page of APP can be clicked according to user, counts
To the operation duration of specified application page；The operation of all keys in the specified application page of APP can be clicked according to user
The frequency, statistics obtain the visitation frequency of specified application page；It can be according to user to the browsing behavior number of the application page in APP
According to, count in APP be accessed application page sum, browsed how many a pages；APP can be operated every time according to user
When where geographical location information, statistical analysis arrive user location fluctuation variance.
It should be noted that the previous material time point in the present embodiment, closest to current before referring to current time
The material time point of material time point.If it does not exist when the previous material time point at current key time point, then remember in operation
It records in data, all behavioral datas before current key time point is extracted to obtain user characteristics.
Step 103, the credit score of user characteristics and previous material time point is input to current key time point pair
In the prediction model answered, user to be measured is obtained in the credit score at current key time point.
Wherein, the credit score of previous material time point is pre- based on the corresponding prediction model institute of previous material time point
The credit score measured.
Specifically, when the credit score of the user characteristics of user to be measured and previous material time point being input to current key
Between put in corresponding prediction model, according to the weight parameter in the prediction model, user characteristics to user to be measured and previous
The credit score of material time point is weighted, and obtains user to be measured in the credit score at current key time point, credit score is used
To indicate the credit rating of user to be measured, wherein credit score is bigger, and the credit risk for indicating user to be measured is lower, and credit score is got over
The small credit risk for indicating user to be measured is higher.
Wherein, the corresponding prediction model of material time point is trained in the following way obtains:
It obtains sample operations of the sample of users in client application and records data, wherein sample operations record data packet
The multiple behavioral datas to sort according to operating time sequence are included, sample of users is marked with credit label；
For material time point, in sample operations record data, to material time point and previous material time point it
Between all behavioral datas in extract to obtain sample of users feature；
It is trained preset neural network model using the credit score of sample of users feature and previous material time point,
Obtain the corresponding prediction model of material time point.
Wherein, it is Mask-RCNN network or U-net network that neural network model, which can use,.
Wherein, the acquisition process of above-mentioned sample operations record data is referred to record data in step 101
Acquisition process, the extraction process of sample of users feature are referred to the extraction process of user characteristics in step 102, no longer add herein
To repeat.
In the embodiment of the present invention, the present invention presets different credit prediction models for different material time points, so that in advance
Survey is more targeted, and when each material time point is predicted, by means of previous material time point to the material time
The credit predicted value of all user behavior datas and previous material time point between point, such loop iteration, so that every
The credit predicted value of all material time points, passes through utilization in this way before the credit value predicted when one material time point is all associated with
Association before and after user between behavior realizes more accurately and reliably credit prediction, and then data branch can be provided for policymaker
Support；In addition, technical solution scalability provided by the invention is strong, the credit evaluation demand under different scenes can adapt to.
Embodiment two
The embodiment of the invention provides a kind of user's Life cycle credit prediction meanss, as shown in Fig. 2, the device can be with
Include:
Module 21 is obtained, for obtaining record data of the user to be measured in client application, record data
Including the multiple behavioral datas to sort according to operating time dot sequency；
Identification module 22 goes out the material time point in operation time point for identification；
Extraction module 23, for being directed to each current key time point, in record data, to the current key time
It extracts to obtain user characteristics in all behavioral datas between point and previous material time point；
Prediction module 24, when for the credit score of user characteristics and previous material time point to be input to current key
Between put in corresponding prediction model, obtain user to be measured in the credit score at current key time point.
Further, module 21 is obtained to be specifically used for:
By bury a little to client application, obtain corresponding to each operation of the user to be measured in client application
Behavioral data and operating time point；
It sorts to behavioral data corresponding to each operation according to operating time dot sequency, obtains record data.
Further, identification module 22 is specifically used for:
Identify whether the behavioral data in record data is the corresponding behavioral data of key operation, if so, will go
It is determined as material time point for the corresponding operating time point of data.
Further, user characteristics include at least one of:
The operation duration of specified application page, the visitation frequency for specifying application page, accessed application page sum,
The fluctuation variance of the sum of the specified page element being clicked, user location.
Further, device further includes training module 25, and training module 25 is specifically used for:
It obtains sample operations of the sample of users in client application and records data, wherein sample operations record data packet
The multiple behavioral datas to sort according to operating time sequence are included, sample of users is marked with credit label；
For material time point, in sample operations record data, to material time point and previous material time point it
Between all behavioral datas in extract to obtain sample of users feature；
It is trained preset neural network model using the credit score of sample of users feature and previous material time point,
Obtain the corresponding prediction model of material time point.
User's Life cycle credit prediction meanss provided in an embodiment of the present invention, are used with provided by the embodiment of the present invention
Family Life cycle credit prediction technique belongs to same inventive concept, and the full life of user provided by the embodiment of the present invention can be performed
Period credit prediction technique has and executes the corresponding functional module of user's Life cycle credit prediction technique and beneficial effect.
The not technical detail of detailed description in the present embodiment, reference can be made to user's Life cycle credit provided in an embodiment of the present invention is pre-
Survey method, is not repeated here herein.
In addition, the embodiment of the present invention also provides a kind of computer equipment, which includes:
One or more processor；
Memory；
Program stored in memory, when being executed by one or more processor, program executes processor
The step of stating user's Life cycle credit prediction technique of embodiment.
Another embodiment of the present invention also provides a kind of computer readable storage medium, and computer-readable recording medium storage has
Program, when program is executed by processor, so that processor executes user's Life cycle credit prediction side of above-described embodiment
The step of method.
It should be understood by those skilled in the art that, the embodiment in the embodiment of the present invention can provide as method, system or meter
Calculation machine program product.Therefore, complete hardware embodiment, complete software embodiment can be used in the embodiment of the present invention or combine soft
The form of the embodiment of part and hardware aspect.Moreover, being can be used in the embodiment of the present invention in one or more wherein includes meter
Computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, the optical memory of calculation machine usable program code
Deng) on the form of computer program product implemented.
It is referring to the method for middle embodiment, equipment (system) according to embodiments of the present invention and to calculate in the embodiment of the present invention
The flowchart and/or the block diagram of machine program product describes.It should be understood that can be realized by computer program instructions flow chart and/or
The combination of the process and/or box in each flow and/or block and flowchart and/or the block diagram in block diagram.It can mention
For the processing of these computer program instructions to general purpose computer, special purpose computer, Embedded Processor or other programmable datas
The processor of equipment is to generate a machine, so that being executed by computer or the processor of other programmable data processing devices
Instruction generation refer to for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of fixed function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although the preferred embodiment in the embodiment of the present invention has been described, once a person skilled in the art knows
Basic creative concept, then additional changes and modifications may be made to these embodiments.So appended claims are intended to explain
Being includes preferred embodiment and all change and modification for falling into range in the embodiment of the present invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of user's Life cycle credit prediction technique, which is characterized in that the described method includes:
Record data of the user to be measured in client application is obtained, the record data includes according to the operating time
Multiple behavioral datas of dot sequency sequence；
It identifies the material time point in the operating time point, and is directed to each current key time point, remember in the operation
It records in data, to being extracted in all behavioral datas between the current key time point and previous material time point
To user characteristics；
The credit score of the user characteristics and the previous material time point is input to the current key time point pair
In the prediction model answered, the user to be measured is obtained in the credit score at the current key time point.
2. the method according to claim 1, wherein the operation for obtaining user to be measured in client application
Record data, comprising:
By bury a little to the client application, each operation of the user to be measured in the client application is obtained
Corresponding behavioral data and operating time point；
It sorts to behavioral data corresponding to each operation according to operating time dot sequency, obtains the operation note number
According to.
3. the method according to claim 1, wherein the material time identified in the operating time point
Point, comprising:
Identify whether the behavioral data in the record data is the corresponding behavioral data of key operation, if so, by institute
It states the corresponding operating time point of behavioral data and is determined as material time point.
4. the method according to claim 1, wherein the user characteristics include at least one of:
The operation duration of specified application page, the visitation frequency for specifying application page, the sum of accessed application page, by point
The fluctuation variance of the sum of the specified page element hit, user location.
5. the method according to claim 1, which is characterized in that the corresponding prediction of the material time point
Model is trained in the following way obtains:
It obtains sample operations of the sample of users in the client application and records data, wherein the sample operations record number
According to including according to multiple behavioral datas of operating time sequence sequence, the sample of users is marked with credit label；
For the material time point, in sample operations record data, to the material time point and previous key
It extracts to obtain sample of users feature in all behavioral datas between time point；
Preset neural network is trained using the credit score of the sample of users feature and the previous material time point
Model obtains the corresponding prediction model of the material time point.
6. a kind of user's Life cycle credit prediction meanss, which is characterized in that described device includes:
Module is obtained, for obtaining record data of the user to be measured in client application, the record data packet
Include the multiple behavioral datas to sort according to operating time dot sequency；
Identification module, for identification material time point in the operating time point out；
Extraction module, for being directed to each current key time point, in the record data, when to the current key
Between put and previous material time point between all behavioral datas in extract to obtain user characteristics；
Prediction module, it is described current for the credit score of the user characteristics and the previous material time point to be input to
In the corresponding prediction model of material time point, the user to be measured is obtained in the credit score at the current key time point.
7. device according to claim 6, which is characterized in that the acquisition module is specifically used for:
By bury a little to the client application, each operation of the user to be measured in the client application is obtained
Corresponding behavioral data and operating time point；
It sorts to behavioral data corresponding to each operation according to operating time dot sequency, obtains the operation note number
According to.
8. device according to claim 6, which is characterized in that the identification module is specifically used for:
Identify whether the behavioral data in the record data is the corresponding behavioral data of key operation, if so, by institute
It states the corresponding operating time point of behavioral data and is determined as material time point.
9. a kind of computer equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now method as claimed in any one of claims 1 to 5, wherein.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
Device realizes method as claimed in any one of claims 1 to 5, wherein when executing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910588634.6A CN110322343A (en) | 2019-07-02 | 2019-07-02 | A kind of user's Life cycle credit prediction technique, device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910588634.6A CN110322343A (en) | 2019-07-02 | 2019-07-02 | A kind of user's Life cycle credit prediction technique, device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110322343A true CN110322343A (en) | 2019-10-11 |
Family
ID=68122204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910588634.6A Pending CN110322343A (en) | 2019-07-02 | 2019-07-02 | A kind of user's Life cycle credit prediction technique, device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110322343A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021147220A1 (en) * | 2020-01-20 | 2021-07-29 | 平安科技（深圳）有限公司 | Page access duration acquisition method, device, medium, and electronic apparatus |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106097043A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技（深圳）有限公司 | The processing method of a kind of credit data and server |
| US20180232805A1 (en) * | 2016-06-12 | 2018-08-16 | Tencent Technology (Shenzhen) Company Limited | User credit rating method and apparatus, and storage medium |
| US20180308018A1 (en) * | 2017-04-20 | 2018-10-25 | Capital One Services, Llc | Machine learning artificial intelligence system for predicting hours of operation |
-
2019
- 2019-07-02 CN CN201910588634.6A patent/CN110322343A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106097043A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技（深圳）有限公司 | The processing method of a kind of credit data and server |
| US20180232805A1 (en) * | 2016-06-12 | 2018-08-16 | Tencent Technology (Shenzhen) Company Limited | User credit rating method and apparatus, and storage medium |
| US20180308018A1 (en) * | 2017-04-20 | 2018-10-25 | Capital One Services, Llc | Machine learning artificial intelligence system for predicting hours of operation |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021147220A1 (en) * | 2020-01-20 | 2021-07-29 | 平安科技（深圳）有限公司 | Page access duration acquisition method, device, medium, and electronic apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107818344B (en) | Method and system for classifying and predicting user behaviors | |
| CN109460514A (en) | Method and apparatus for pushed information | |
| CN106716382B (en) | The method and system of aggregation multiple utility program behavioural analysis for mobile device behavior | |
| CN105956161B (en) | A kind of information recommendation method and device | |
| CN108090162A (en) | Information-pushing method and device based on artificial intelligence | |
| CN103177090B (en) | A kind of topic detection method and device based on big data | |
| CN106372249B (en) | A kind of clicking rate predictor method, device and electronic equipment | |
| CN110992167A (en) | Bank client business intention identification method and device | |
| CN107292412A (en) | A kind of problem Forecasting Methodology and forecasting system | |
| CN107944481A (en) | Method and apparatus for generating information | |
| CN107423613A (en) | The method, apparatus and server of device-fingerprint are determined according to similarity | |
| CN107885873A (en) | Method and apparatus for output information | |
| CN106709318A (en) | Recognition method, device and calculation equipment for user equipment uniqueness | |
| CN108256537A (en) | A kind of user gender prediction method and system | |
| CN112100221B (en) | Information recommendation method and device, recommendation server and storage medium | |
| CN110097170A (en) | Information pushes object prediction model acquisition methods, terminal and storage medium | |
| CN107977678A (en) | Method and apparatus for output information | |
| CN109992569A (en) | Cluster log feature extracting method, device and storage medium | |
| CN112561565A (en) | User demand identification method based on behavior log | |
| CN111181757B (en) | Information security risk prediction method and device, computing equipment and storage medium | |
| CN109754290A (en) | A kind for the treatment of method and apparatus of game data | |
| CN113918806A (en) | Method for automatically recommending training courses and related equipment | |
| CN104580109B (en) | Generation clicks the method and device of identifying code | |
| CN110377821A (en) | Generate method, apparatus, computer equipment and the storage medium of interest tags | |
| CN110322343A (en) | A kind of user's Life cycle credit prediction technique, device and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191011 |
|
| RJ01 | Rejection of invention patent application after publication |