CN109493077A - Activity recognition method and device, electronic equipment, storage medium - Google Patents
Activity recognition method and device, electronic equipment, storage medium Download PDFInfo
- Publication number
- CN109493077A CN109493077A CN201811333462.XA CN201811333462A CN109493077A CN 109493077 A CN109493077 A CN 109493077A CN 201811333462 A CN201811333462 A CN 201811333462A CN 109493077 A CN109493077 A CN 109493077A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- real
- newly
- time
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Computer Security & Cryptography (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure is directed to a kind of Activity recognition method and devices, electronic equipment, storage medium, are related to Internet technical field, this method comprises: according to multiple user informations and a plurality of medium information building cohort model in predetermined period；It obtains and Adds User information and newly-increased medium information in real time, and Add User information and the newly-increased medium information carries out real-time update to the cohort model by described, generate real-time cohort model；Target user's behavior is identified by the real-time cohort model.The disclosure can quickly identify user behavior, timely anticipating risk.
Description
Technical field
This disclosure relates to Internet technical field, in particular to a kind of Activity recognition method, Activity recognition device,
Electronic equipment and computer readable storage medium.
Background technique
With the development of internet technology and the extensive use of mobile payment, it is easy to produce black production batch to attack, cause
The financial risks such as loss of assets.
In the related technology, identify that user whether there is the risk of group's fraud by building cohort model mostly.Specifically
Ground can construct cohort model by graph model (Graph Model).Such as based on facility information, identity information, telecom information etc.
Medium information comes the side in structure figures, is associated with this to multiple accounts.When connected graph is excessive, it is believed that the use in figure
There are the risks that group is cheated at family.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure is designed to provide a kind of Activity recognition method and device, electronic equipment, storage medium, and then at least
Overcome the problems, such as to identify user behavior in time caused by the limitation and defect due to the relevant technologies to a certain extent.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to one aspect of the disclosure, a kind of Activity recognition method is provided, comprising: according to multiple use in predetermined period
Family information and a plurality of medium information construct cohort model；Add User information and newly-increased medium information are obtained in real time, and are led to
The information that Adds User described in crossing and the newly-increased medium information carry out real-time update to the cohort model, generate real-time group
Model；Target user's behavior is identified by the real-time cohort model.
In a kind of exemplary embodiment of the disclosure, according in predetermined period multiple user informations and a plurality of medium
Information architecture cohort model includes: to obtain in the predetermined period between the multiple user information and a plurality of medium information
Incidence relation；The group is constructed according to the incidence relation between the multiple user information and a plurality of medium information
Group model.
In a kind of exemplary embodiment of the disclosure, pass through information and the newly-increased medium information of Adding User
Real-time update is carried out to the cohort model, generating real-time cohort model includes: respectively to information and the institute of Adding User
It states newly-increased medium information and is associated calculating, obtain user media pair；According to the user media to obtaining increment relation pair, and
By the increment relation to the generation real-time cohort model.
In a kind of exemplary embodiment of the disclosure, respectively to information and the newly-increased medium letter of Adding User
Breath is associated calculating, obtains user media to including: to be associated each information that Adds User with All Media information, with
Determine the medium information for the information association that each Adds User；Each newly-increased medium information is associated with all user informations,
To determine each newly-increased associated user information of medium information；According to the medium information of each information association that Adds User and often
A associated user information of newly-increased medium information obtains the user media pair.
In a kind of exemplary embodiment of the disclosure, according to the user media to obtaining increment relation to including: to adopt
With Union-find Sets algorithm to the user media to analyzing, to obtain the increment relation pair.
In a kind of exemplary embodiment of the disclosure, passing through information and the newly-increased medium letter of Adding User
Before breath carries out real-time update to the cohort model, the method also includes: according to cleaning rule to the letter that Adds User
Add User information and the newly-increased medium that breath and the newly-increased medium information are filtered, and will meet the cleaning rule
Information is stored into caching.
According to one aspect of the disclosure, a kind of Activity recognition device is provided, comprising: model construction module is used for basis
Multiple user informations and a plurality of medium information in predetermined period construct cohort model；Model modification module, for obtaining in real time
Take Add User information and newly-increased medium information, and by information and the newly-increased medium information of Adding User to institute
It states cohort model and carries out real-time update, generate real-time cohort model；Control module is identified, for passing through the real-time cohort model
User behavior is identified.
In a kind of exemplary embodiment of the disclosure, the model modification module includes: medium to computing module, is used for
Information is Added User and the newly-increased medium information is associated calculating to described respectively, obtains user media pair；Real-time mould
Type generation module, for according to the user media to obtaining increment relation pair, and through the increment relation described in generation
Real-time cohort model.
According to one aspect of the disclosure, a kind of electronic equipment is provided, comprising: processor；And memory, for storing
The executable instruction of the processor；Wherein, the processor is configured to above-mentioned to execute via the executable instruction is executed
Activity recognition method described in any one.
According to one aspect of the disclosure, a kind of computer readable storage medium is provided, computer program is stored thereon with,
The computer program realizes Activity recognition method described in above-mentioned any one when being executed by processor.
A kind of Activity recognition method for being there is provided in disclosure exemplary embodiment, Activity recognition device, electronic equipment and
In computer readable storage medium, on the one hand, only corresponding to predetermined period by Add User information and newly-increased medium information
Cohort model carry out real-time update, without consider failure user information and medium information, reduce update cohort model when
The information content needed, reduces the operating time, improves operating efficiency；On the other hand, since real-time group can be generated in time
Model, therefore target user's behavior can be identified by real-time cohort model in time, and then prevent and avoid in time risk.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 schematically shows a kind of Activity recognition method schematic diagram in disclosure exemplary embodiment；
Fig. 2 schematically shows cohort model frame diagram in disclosure exemplary embodiment；
Fig. 3 schematically shows the flow chart that disclosure exemplary embodiment generates real-time cohort model；
Fig. 4 schematically shows the flow chart that disclosure exemplary embodiment calculates real-time cohort model；
Fig. 5 schematically shows a kind of block diagram of Activity recognition device in disclosure exemplary embodiment；
Fig. 6 schematically shows the block diagram of a kind of electronic equipment in disclosure exemplary embodiment；
Fig. 7 schematically shows a kind of program product in disclosure exemplary embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiment of the present disclosure to provide.It will be appreciated, however, by one skilled in the art that can
It is omitted with technical solution of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that all aspects of this disclosure thicken.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Cohort model is built upon the relational model of certain time window T, it may be assumed that over time, new binding is closed
System is added in relational network, constructs new group by newly-increased and merging, and old binding relationship fails from relational network,
So that group fissions.In the related technology, it when updating cohort model by graph model, due to the newly-increased of relationship and loses
Effect is while and uninterruptedly occurring.Therefore real-time full dose update cohort model is very time-consuming on line, and efficiency is lower；In addition,
Full dose more new model will lead to Activity recognition not in time, cannot timely anticipating risk.
To solve the above-mentioned problems, a kind of Activity recognition method is proposed in the present exemplary embodiment, can be applied to pair
User behavior is identified, to determine whether user behavior is in each identification scene of fraud.Next, with reference to Fig. 1
It is shown, the Activity recognition method in the present exemplary embodiment is specifically described.
In step s 110, according to the multiple user informations and a plurality of medium information building group's mould in predetermined period
Type.
In the present exemplary embodiment, predetermined period refers to regular hour window, can be indicated with T, predetermined period
It such as can be 90 days, or other suitable numerical value.The quantity of user information can be multiple, user information include but
It is not limited to the account information of user, and each user can correspond to an account information, different account letters can also be corresponded to
Breath.The quantity of medium information may be it is a plurality of, medium information includes but is not limited to facility information used by a user, user
Identity information and telecom information used by a user etc..The effect of cohort model is for describing all users in predetermined period
Incidence relation between information and All Media information.If being stored with a certain user information on a certain medium information, it is determined that two
There is association between person, so as to obtain incidence relation between the two.It is possible to further according to description incidence relation
Cohort model judges user behavior with the presence or absence of group's risk of fraud.
With reference to shown in Fig. 2, the specific steps for constructing cohort model include: Step 1: obtaining institute in the predetermined period
State the incidence relation between multiple user informations and a plurality of medium information.Specifically, it can obtain multiple in predetermined period
User information, also multiple medium informations in available predetermined period.In the present exemplary embodiment, using medium information as equipment
It is specifically described for information.For example, user information A, Yong Huxin in available 1st day to the 90th day predetermined period
Cease B and user information C, also the medium information 1 in available 1st day to the 90th day predetermined period, medium information 2 and
Medium information 3.It is possible to further determine medium information corresponding to each user information, to establish each user letter
Incidence relation between breath and All Media information.Specifically, user information can be stored when user uses facility information
Extremely in used facility information, and then the two can be associated according to the user information stored in facility information, such as
User information A is associated with medium information 1, and user information B is associated with medium information 3, and user information C is associated with medium information 2
Deng.
Step 2: constructing institute according to the incidence relation between the multiple user information and a plurality of medium information
State cohort model.After obtaining the incidence relation between multiple user informations and a plurality of medium information, it can be closed according to these associations
System specifically can be using Timer thread one using the corresponding cohort model of timed task stream timing off-line calculation predetermined period
It fixes time or the interior realization timed task of certain time interval is dispatched, to calculate cohort model.It should be noted that user information
Quantity it is more, the quantity of medium information is more, and the accuracy of the cohort model constructed according to user information and medium information is got over
It is high.
Next, in the step s 120, obtaining Add User information and newly-increased medium information in real time, and by described new
Increase user information and the newly-increased medium information and real-time update is carried out to the cohort model, generates real-time cohort model.
In the present exemplary embodiment, the information that Adds User refers to the newly added user information after predetermined period；Class
As, newly-increased medium information refers to the newly added medium information after predetermined period.For example, the user in predetermined period believes
Breath includes user information A, user information B and user information C, and medium information includes medium information 1, medium information 2 and is situated between
Matter information 3.User information after predetermined period includes user information A, user information B, user information C, user information D, uses
Family information E, medium information includes medium information 1, medium information 2, medium information 3 and medium information 4, it may be considered that user
Information D and user information E belongs to the information that Adds User, and medium information 4 belongs to newly-increased medium information.
After getting and Adding User information and newly-increased medium information, the group's mould that will can be established offline in step S110
Type is pushed on line as basic model, and carries out model modification based on basic model.In the present exemplary embodiment, do not consider
Relationship between the user information and medium information of failure only considers the relationship between newly-increased user information and medium information,
Carry out real-time update cohort model, so as to realize the cohort model in a T+ Δ t time window.Specifically, as Δ t=1
When, i.e., offline T+1 cohort model；When Δ t is close to second grade, that is, real-time cohort model.Therefore Δ t determines cohort model
Updating survey, while also determine in face of group attack response rate and money loss rate.
With reference to shown in Fig. 2, real-time stream can be used, user's real-time logs of acquisition are handled, it specifically can be by industry
Business system generate user's real-time logs carry out real-time collecting, transfer to stream process frame carry out data cleansing, statistics, storage and can
To be shown by visual means to statistical result.User's real-time logs include but is not limited to user's logon data, user
Browse data, user buys data etc..Real-time update model is constructed in the present exemplary embodiment by taking Lambda framework as an example,
Lambda framework is integrated off-line calculation and is calculated in real time, and immutableness, a series of framves such as read and write abruption and complicated sexual isolation are merged
Structure principle can integrate Hadoop, Kafka, Storm, all kinds of big data components such as Spark, Hbase.
With reference to shown in Fig. 3, the detailed process of real-time cohort model is constructed in step S120 the following steps are included: step
S310 Adds User information and the newly-increased medium information is associated calculating to described respectively, obtains user media pair.?
In this step, user media is to the one-to-one relationship referred between user information and medium information, such as user information B-
Medium information 3 etc..Information is Added User and the newly-increased medium information closes to described respectively described in step 310
Online is calculated, and user media pair is obtained including the following steps: the first step, by each information and All Media information of Adding User
It is associated, to determine the medium information for the information association that each Adds User.For example, user A makes on day 1 in the 90th day
The account of oneself, i.e. user information A have been logged in mobile phone 1；At the 92nd day, user B logged in the account of user B using mobile phone 1
Number, i.e. user information B, then for mobile phone 1, the information that Adds User is user information B.It is possible to further obtain user
The corresponding All Media information of information B.
Each newly-increased medium information is associated by second step with all user informations, to determine each newly-increased medium letter
Cease associated user information.For example, user A has used mobile phone 1 to log in the account of oneself, that is, is situated between on day 1 in the 90th day
Matter information is mobile phone 1；At the 92nd day, user A logged in the account of oneself using mobile phone 2, i.e. medium information is mobile phone 2, then right
For user A, increasing medium information newly is mobile phone 2.It is possible to further obtain all user informations for using mobile phone 2 to log in.
Third step, according to the medium information of each information association that Adds User and each newly-increased associated use of medium information
Family information obtains the user media pair.On the basis of the first step and second step, it may be determined that for all information that Add User
And the user media pair for all newly-increased medium informations.For example, user information A and medium information 1, medium information 2, medium
Information 3 is related, and user information B is related to medium information 1, medium information 3 etc..
It can also include: step S320 that real-time cohort model is constructed in step S120, according to the user media to obtaining
Increment relation pair, and by the increment relation to the generation real-time cohort model.On the basis of the user media pair of generation
On, it is believed that all user informations of a corresponding medium information are related, may thereby determine that these relevant user informations belong to
One group.Specifically, can be judged according to the address information etc. stored on medium on a medium with the presence or absence of multiple users
Information, and if it exists, then think that these user informations belong to a group.For example, all users for logging in a mobile phone are related, belong to
In a group.
Increment relation, can basis to the user media pair for referring to that the user media relative to predetermined period increases newly for
Newly-increased user media determines increment relation pair to quick.Specifically, computing engines can be used, by Union-find Sets algorithm to user
Medium is to calculating is associated, to obtain increment relation pair.Union-find Sets algorithm is a kind of data structure of tree-shaped, is usually being used
In indicated with forest.Collection is exactly the set for allowing each element to constitute a single element, that is, will be belonged in certain sequence same
Set where one group of element merges.In some set application problems for having N number of element, usually allowed when starting each
Element constitutes the set of a single element, then in certain sequence merges the set where belonging to same group of element, therebetween
An element is searched repeatedly in which set.Union-find Sets be made of an array pre [] and two functions, wherein
One function is find () function, and for finding leading period, second function is join () for merging route.Specifically
Calculating process can be realized by writing program, be not specifically described herein.Only by increment relation to updating real-time cohort model,
User media pair without considering no longer valid reduces the data volume needed when calculating for the relevant technologies,
Therefore real-time cohort model can be quickly obtained, computational efficiency is improved.
With reference to shown in Fig. 4, increment relation is being obtained to rear, increment relation can calculate input group in real time and draw
It holds up, constructs real-time cohort model.It is possible to further according to the different type of the real-time cohort model of calculating by real-time group's mould
At least one database is arrived in type storage.At least one described database include group-user/medium bank, group information library and
Non- group-user/medium bank.With continued reference to shown in Fig. 4, if only including group in cohort model in real time, stored to
Group information library；If including group and user, medium in real-time cohort model, and user belongs to a group, then is stored
To group-user/medium bank, and then will be stored in the user-media storage engine provided；If including in real-time cohort model
Group, user and medium, but user is not belonging to a group, then is stored to non-group-user/medium bank.Passing through will
Cohort model is sub-category in real time stores to different databases, and the reality in the database for meeting condition can be only called when calling
When cohort model, such as only call group-user/medium bank in real-time cohort model, operating efficiency can be improved, and can
Accuracy rate is operated to improve.Wherein, User-Media, Group, User-Media-Group respectively indicate different for storing
Database structure.
With continued reference to shown in Fig. 4, user media pair is being calculated and by the information and described newly-increased of Adding User
It, can be according to cleaning rule pair in order to guarantee the accuracy calculated before medium information carries out real-time update to the cohort model
It is described to Add User information and the newly-increased medium information is filtered.Cleaning rule can be arranged according to actual needs,
Such as in order to filter out the data of not practical function, cleaning rule can be set to simultaneously including that user information and medium are believed
Breath.Specifically, after getting real-time logs stream, can will in real-time logs stream only comprising user information and only include medium
The data filtering of information falls, and only stores the newly-increased data simultaneously including user information and medium information to user-medium and deposit
Store up in engine, i.e., by meet cleaning rule Add User information and newly-increased medium information is stored to user-media storage engine
In, and then store into caching, with quick calling direct from caching, and generate user media pair.
In step s 130, target user's behavior is identified by the real-time cohort model.
It, can be by real-time cohort model to the mesh in group after updating real-time cohort model in the present exemplary embodiment
Mark user behavior is identified, to judge whether target user's behavior is group's fraud etc., so can determine whether to deposit
In risk.Target user refers to any one user in group, will can be used to indicate the target user of target user's behavior
The inputs building such as logon data real-time cohort model, to determine the classification of target user's behavior, to judge target user
Whether behavior is group's fraud.Due to only considered newly-increased user information and medium letter when generating real-time cohort model
Breath, and the user information and medium information of failure are not considered, full dose load data are avoided, reduces calculation amount, improves behaviour
Make efficiency, therefore the real-time cohort model that can timely update, target can be used by real-time cohort model in time on this basis
Family behavior is identified, effectively avoids the risk in target user's behavior, while can guarantee system stability.
Fig. 3 shows the general frame figure of cohort model, including timed task stream, real-time task stream, storage engines,
Computing engines and externally service.Timed task stream is used for based on user's portrait, medium portrait and group's portrait, using offline
Timed task constructs the T+1 update mechanism of model, i.e., by based on cohort model, obtains real-time cohort model.Real time data
Stream is obtained user's real-time logs, calculates user information and medium information relationship for being calculated in real time based on online.Storage engines refer to
Be to have built user media storage engines and groups of users storage engines for different demands.Computing engines are used for based on simultaneously
Look into set algorithm and group's incremental computations logic calculation increment relation pair.Externally service includes groups of users query service and management
Platform, such as real-time cohort model can be inquired and be managed by externally servicing.
Fig. 4 shows the overall flow figure in line computation real time group group model, specifically includes the following steps: step S401,
Newly-increased real-time logs circulation is changed to log form first.Step S402, by cleaning rule and Storm frame to real-time
Log stream is handled.Step S401 and step S402 is real time process, and step S403 will meet the storage of cleaning rule
In user-media storage engine.Newly-increased log stream is stored in buffer area by step S404.Step S405 calls buffer area
In newly-increased log stream, generate user media pair.Step S406 is stored to user-medium and is deposited to user media to being extended
Store up engine.Step S407, according to the user media after the extension in user-media storage engine to generation increment relation pair.Step
Rapid S408 obtains real-time cohort model according to the real-time computing engines of group, and store respectively to group information library, group-user/
Medium bank, non-group-user/medium bank.Step S4081 is specifically included to step S4083: where step S4081, it will be real-time
Cohort model its store to group information library；Step S4082 will be stored in real-time cohort model to group-user/medium bank；
Step S4083 will be stored in real-time cohort model to non-group-user/medium bank.It, can basis based on the step in Fig. 4
Newly-increased user media obtains real-time cohort model to generation increment relation pair, due to not considering the relationship pair of failure, because
This reduces calculation amount, improves operating efficiency, can be updated in time to the corresponding cohort model of predetermined period, quick
To real-time cohort model.
The disclosure additionally provides a kind of Activity recognition device.Refering to what is shown in Fig. 5, behavior identification device 500 may include:
Model construction module 501, for according to the multiple user informations and the building of a plurality of medium information in predetermined period
Cohort model；
Model modification module 502, for obtaining Add User information and newly-increased medium information in real time, and by described new
Increase user information and the newly-increased medium information and real-time update is carried out to the cohort model, generates real-time cohort model；
Control module 503 is identified, for identifying by the real-time cohort model to target user's behavior.
It should be noted that the detail of each module is in corresponding Activity recognition side in above-mentioned Activity recognition device
It is described in detail in method, therefore details are not described herein again.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Fig. 6.The electronics that Fig. 6 is shown
Equipment 600 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 6, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 610, at least one above-mentioned storage unit 620, the different system components of connection
The bus 630 of (including storage unit 620 and processing unit 610).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 610
Row, so that various according to the present invention described in the execution of the processing unit 610 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 610 can execute step as shown in fig. 1: in step S110
In, according to the multiple user informations and a plurality of medium information building cohort model in predetermined period；In the step s 120, in real time
Acquisition Adds User information and newly-increased medium information, and passes through Add User information and the newly-increased medium information pair
The cohort model carries out real-time update, generates real-time cohort model；In step s 130, pass through the real-time cohort model pair
Target user's behavior identifies.
Storage unit 620 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Storage unit 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 630 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 800 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 600 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 660 is communicated by bus 630 with other modules of electronic equipment 600.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 600, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 7, describing the program product for realizing the above method of embodiment according to the present invention
700, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (10)
1. a kind of Activity recognition method characterized by comprising
According to the multiple user informations and a plurality of medium information building cohort model in predetermined period；
Add User information and newly-increased medium information are obtained in real time, and pass through Add User information and newly-increased Jie
Matter information carries out real-time update to the cohort model, generates real-time cohort model；
Target user's behavior is identified by the real-time cohort model.
2. Activity recognition method according to claim 1, which is characterized in that according to multiple user informations in predetermined period
And a plurality of medium information building cohort model includes:
Obtain the incidence relation between the multiple user information and a plurality of medium information in the predetermined period；
The cohort model is constructed according to the incidence relation between the multiple user information and a plurality of medium information.
3. Activity recognition method according to claim 1, which is characterized in that pass through the information and described of Adding User
Newly-increased medium information carries out real-time update to the cohort model, and generating real-time cohort model includes:
Information is Added User and the newly-increased medium information is associated calculating to described respectively, obtains user media pair；
According to the user media to obtaining increment relation pair, and by the increment relation to generating real-time group's mould
Type.
4. Activity recognition method according to claim 3, which is characterized in that respectively to information and the institute of Adding User
It states newly-increased medium information and is associated calculating, obtain user media to including:
Each information that Adds User is associated with All Media information, to determine the medium for the information association that each Adds User
Information；
Each newly-increased medium information is associated with all user informations, to determine each newly-increased associated user of medium information
Information；
According to the medium information of each information association that Adds User and each the associated user information of medium information is increased newly to obtain
The user media pair.
5. Activity recognition method according to claim 3, which is characterized in that closed according to the user media to increment is obtained
System is to including:
Using Union-find Sets algorithm to the user media to analyzing, to obtain the increment relation pair.
6. Activity recognition method according to claim 1, which is characterized in that passing through Add User information and the institute
Before newly-increased medium information is stated to cohort model progress real-time update, the method also includes:
Information is Added User and the newly-increased medium information is filtered to described according to cleaning rule, and will be met described clear
Wash rule Add User information and newly-increased medium information is stored into caching.
7. a kind of Activity recognition device characterized by comprising
Model construction module, for according to the multiple user informations and a plurality of medium information building group's mould in predetermined period
Type；
Model modification module Adds User for obtaining Add User information and newly-increased medium information in real time, and by described
Information and the newly-increased medium information carry out real-time update to the cohort model, generate real-time cohort model；
Control module is identified, for identifying by the real-time cohort model to target user's behavior.
8. Activity recognition device according to claim 7, which is characterized in that the model modification module includes:
Medium is to computing module, by Adding User information and based on the newly-increased medium information is associated to described respectively
It calculates, obtains user media pair；
Real-time model generation module, for obtaining increment relation pair, and passing through the increment relation according to the user media
To the generation real-time cohort model.
9. a kind of electronic equipment characterized by comprising
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to come described in perform claim requirement 1-6 any one via the execution executable instruction
Activity recognition method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Activity recognition method as claimed in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811333462.XA CN109493077A (en) | 2018-11-09 | 2018-11-09 | Activity recognition method and device, electronic equipment, storage medium |
| CA3060692A CA3060692A1 (en) | 2018-11-09 | 2019-10-29 | Behaviour recognition method and apparatus, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811333462.XA CN109493077A (en) | 2018-11-09 | 2018-11-09 | Activity recognition method and device, electronic equipment, storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109493077A true CN109493077A (en) | 2019-03-19 |
Family
ID=65694184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811333462.XA Pending CN109493077A (en) | 2018-11-09 | 2018-11-09 | Activity recognition method and device, electronic equipment, storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109493077A (en) |
| CA (1) | CA3060692A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991505A (en) * | 2019-11-22 | 2020-04-10 | 拉扎斯网络科技（上海）有限公司 | Abnormal object identification method and device and abnormal behavior identification method and device |
| CN112989135A (en) * | 2021-04-15 | 2021-06-18 | 杭州网易再顾科技有限公司 | Real-time risk group identification method, medium, device and computing equipment |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016793B (en) * | 2020-07-15 | 2024-04-26 | 北京淇瑀信息科技有限公司 | Resource allocation method and device based on target user group and electronic equipment |
-
2018
- 2018-11-09 CN CN201811333462.XA patent/CN109493077A/en active Pending
-
2019
- 2019-10-29 CA CA3060692A patent/CA3060692A1/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991505A (en) * | 2019-11-22 | 2020-04-10 | 拉扎斯网络科技（上海）有限公司 | Abnormal object identification method and device and abnormal behavior identification method and device |
| CN110991505B (en) * | 2019-11-22 | 2023-12-26 | 拉扎斯网络科技（上海）有限公司 | Abnormal object recognition method and device and abnormal behavior recognition method and device |
| CN112989135A (en) * | 2021-04-15 | 2021-06-18 | 杭州网易再顾科技有限公司 | Real-time risk group identification method, medium, device and computing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CA3060692A1 (en) | 2020-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3610402B1 (en) | Novel non-parametric statistical behavioral identification ecosystem for electricity fraud detection | |
| CN108322473A (en) | User behavior analysis method and apparatus | |
| WO2018226404A1 (en) | Machine reasoning based on knowledge graph | |
| WO2020168851A1 (en) | Behavior recognition | |
| CN110442737A (en) | The twin method and system of number based on chart database | |
| KR101732319B1 (en) | IRIS: Goal-oriented big data business analytics framework | |
| CN110795509A (en) | Method and device for constructing index blood relationship graph of data warehouse and electronic equipment | |
| CN109493077A (en) | Activity recognition method and device, electronic equipment, storage medium | |
| WO2022083093A1 (en) | Probability calculation method and apparatus in graph, computer device and storage medium | |
| CN109408561A (en) | Business Name matching process and device | |
| CN111427971B (en) | Business modeling method, device, system and medium for computer system | |
| CN111639253B (en) | Data weight judging method, device, equipment and storage medium | |
| CA3015566A1 (en) | Systems and methods for expediting rule-based data processing | |
| CN110363636A (en) | Risk of fraud recognition methods and device based on relational network | |
| CN114205690A (en) | Flow prediction method, flow prediction device, model training method, model training device, electronic equipment and storage medium | |
| CN110162537A (en) | Data query method and device, storage medium and electronic equipment | |
| CN113392150A (en) | Data table display method, device, equipment and medium based on service domain | |
| CN111930366A (en) | Rule engine implementation method and system based on JIT real-time compilation | |
| CN114462577A (en) | Federated learning system, method, computer equipment and storage medium | |
| CN110162518A (en) | Data grouping method, apparatus, electronic equipment and storage medium | |
| CN109376430A (en) | Assembled architecture execution management method therefor | |
| CN111126629A (en) | Model generation method, system, device and medium for identifying brushing behavior | |
| CN108768742B (en) | Network construction method and device, electronic equipment and storage medium | |
| CN115840738A (en) | Data migration method and device, electronic equipment and storage medium | |
| CN113011672B (en) | Logistics aging prediction method and device, electronic equipment and storage medium |
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 |