CN109598110A - A kind of recognition methods of user identity and device - Google Patents
A kind of recognition methods of user identity and device Download PDFInfo
- Publication number
- CN109598110A CN109598110A CN201811505465.7A CN201811505465A CN109598110A CN 109598110 A CN109598110 A CN 109598110A CN 201811505465 A CN201811505465 A CN 201811505465A CN 109598110 A CN109598110 A CN 109598110A
- Authority
- CN
- China
- Prior art keywords
- user
- identity
- data
- behavior data
- historical behavior
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/45—Structures or tools for the administration of authentication
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the invention discloses a kind of recognition methods of user identity and devices, it is related to technical field of data processing, the method of the embodiment of the present invention includes: to acquire the historical behavior data of user, and the historical behavior data, which include at least, social model behavioral data, dialogue mode data and consumption mode data；The identity of user is generated according to the historical behavior data；It is whether legal according to the identification user identity.It realizes and the identity of user is generated according to the non-biometric of user and user identity legitimacy is identified using the identity, improve the performance of user identity identification.
Description
Technical field
The present embodiments relate to the recognition methods of technical field of data processing more particularly to a kind of user identity and dresses
It sets.
Background technique
It is also more next along with the various applications of mobile terminal as what the fast development of science and technology, mobile terminal used popularizes
It is more, greatly facilitate people's lives.In order to there is better usage experience, user can bind in application program, webpage
Personal information, bank card etc., therefore when some account information of user is stolen, personal and other users wealth can be jeopardized
Produce safety etc..Thus, it is ensured that user identity safety is most important on network.
Currently, can browse webpage after needing user to input log-on message in each website or application program, use
Application program etc..After existing log-on message is in addition to account number cipher, it is most of be all by the biological characteristic such as fingerprint of user,
Whether vocal print etc. is legal as the log-on message and determination user identity of user, however since biological characteristic can be forged, make
It obtains identification and still has security risk, the problem for causing identification performance poor.
Summary of the invention
In view of the above problems, the embodiment of the present invention provides a kind of recognition methods of user identity and device, main purpose exist
Identity legitimacy identification is carried out as identity in the non-biometric using user.
In order to solve the above technical problems, in a first aspect, the embodiment of the invention provides a kind of recognition methods of user identity,
This method comprises:
The historical behavior data of user are acquired, the historical behavior data, which include at least, social model behavioral data, right
Talk about mode data and consumption mode data；
The identity of user is generated according to the historical behavior data；
It is whether legal according to the identification user identity.
Optionally, after the historical behavior data of the acquisition user, the method also includes:
The historical behavior data are classified, the behavioral data under multiple groups different mode is obtained；
It is described according to the historical behavior data generate user identity include:
Behavioral data under each group mode is parsed respectively, and is calculated and the use using preset neural network model
The corresponding multiple identity subvectors in family, the identity subvector are used for identity of the identity user under each mode；
Identity vector corresponding with the user is synthesized according to the multiple identity subvector, and the identity vector is true
It is set to the identity of the user.
Optionally, described whether legal according to the identification user identity to include:
Obtain the current behavior data of user；
The current identity of user is calculated using the preset neural network model；
User's body is determined according to the matching degree between the current identity of the user and the identity of the user
Whether part is legal.
Optionally, the method also includes:
It is clustered according to the identity vector, obtains multiple user's set；
The mark of user's set is determined according to the identity of each user in user set.
Optionally, it is described according to the identification user identity it is whether legal after, the method also includes:
If the user identity is illegal, outputting alarm information and/or terminator operation.
Second aspect, the embodiment of the invention also provides a kind of identification device of user identity, which includes:
Acquisition unit, for acquiring the historical behavior data of user, the historical behavior data, which include at least, social mould
Formula behavioral data, dialogue mode data and consumption mode data；
Generation unit, for generating the identity of user according to the historical behavior data；
Recognition unit, for whether legal according to the identification user identity.
Optionally, described device further include: taxon,
The taxon obtains the behavior under multiple groups different mode for the historical behavior data to be classified
Data；
The generation unit includes:
First computing module for parsing respectively to the behavioral data under each group mode, and utilizes preset nerve net
Network model calculates multiple identity subvectors corresponding with the user, and the identity subvector is for identity user in each mode
Under identity；
Synthesis module, for synthesizing identity vector corresponding with the user according to the multiple identity subvector；
First determining module, for the identity vector to be determined as to the identity of the user.
Optionally,
The recognition unit includes:
Module is obtained, for obtaining the current behavior data of user；
Second computing module, for calculating the current identity of user using the preset neural network model；
Second determining module is according to the matching between the current identity of the user and the identity of the user
It spends and determines whether user identity is legal.
Optionally, described device further include:
Cluster cell obtains multiple user's set for being clustered according to the identity vector；
Determination unit, for determining user's set according to the identity of each user in user set
Mark.
Optionally, described device further include:
Output unit, if illegal for the user identity, outputting alarm information and/or terminator operation.
To achieve the goals above, according to a third aspect of the embodiments of the present invention, a kind of storage medium is provided, it is described to deposit
Storage media includes the program of storage, wherein equipment where controlling the storage medium in described program operation executes above-mentioned institute
The recognition methods for the user identity stated.
To achieve the goals above, according to a fourth aspect of the embodiments of the present invention, a kind of processor, the processing are provided
Device is for running program, wherein described program executes the recognition methods of user identity described above when running.
By above-mentioned technical proposal, the recognition methods of user identity provided in an embodiment of the present invention and device, for existing
When technology determines user identity by biological characteristic such as fingerprint, vocal print etc., since biological characteristic can be forged, so that identity is known
Not Reng Rancun security risk, the embodiment of the present invention is by the historical behavior data of acquisition user, and according to the history row of user
Identity corresponding to the user is generated for data, and whether legal using identity identification user identity, therefore compare
In the prior art, the embodiment of the present invention can generate identification information corresponding to the user by historical behavior data, due to user
Behavioral data can not forge, ensure that the uniqueness of identity, avoid biological characteristic etc. as identification information
When there is a problem of forge identification performance may be made poor, so as to improve user identity identification performance.
Above description is only the general introduction of technical solution of the embodiment of the present invention, in order to better understand the embodiment of the present invention
Technological means, and can be implemented in accordance with the contents of the specification, and in order to allow above and other mesh of the embodiment of the present invention
, feature and advantage can be more clearly understood, the special specific embodiment for lifting the embodiment of the present invention below.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
The limitation of embodiment.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows a kind of recognition methods flow chart of user identity provided in an embodiment of the present invention；
Fig. 2 shows the recognition methods flow charts of another user identity provided in an embodiment of the present invention；
Fig. 3 shows a kind of composition block diagram of the identification device of user identity provided in an embodiment of the present invention；
Fig. 4 shows the composition block diagram of the identification device of another user identity provided in an embodiment of the present invention；
Fig. 5 shows a kind of composition block diagram of the electronic equipment of the identification of user identity provided in an embodiment of the present invention.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
In order to promote the performance of user identity identification, the embodiment of the invention provides a kind of recognition methods of user identity,
As shown in Figure 1, this method comprises:
101, the historical behavior data of user are acquired.
Wherein, the historical behavior data, which include at least, social model behavioral data, dialogue mode data and consumption mould
Formula data.And the historical behavior data can be the data in the past in one month, or the number in six months in past
Can be user's trip data according to, social action data, as user in the previous year in airplane, train data, or
Person user browses type, the time data etc. of video in each website；Dialogue mode data can be user in each shopping
With the dialogue data of customer service, in chat conversations data in social network sites between other users etc. in website；Consumption mode number
According to can be consumption data of the user in each shopping website or market.Specifically the historical behavior data in this step can
Think by background acquisition, from third party obtain etc., the embodiment of the present invention is not specifically limited in this embodiment.
It should be noted that specific implementation of the embodiment of the present invention can be used in terminal device to user for configuration
The device that identity is identified, user can be configured whether open identity knowledge when application operation in each application program
Other function, and when user opens identity recognition function and application program in application program and runs, i.e. triggering collection user
Historical behavior data, and then determine user identity legitimacy.
102, the identity of user is generated according to the historical behavior data.
Wherein, the identity is used for state of the identity user under each mode, such as the identity of user is
High consumption user, frequently go on a journey user, hobby classical music user etc..And this step specific embodiment can be to advance with
Mass data trains the neural network model for generating identity, so that collected user's history behavioral data be inputted
The neural network model can obtain the identity of user, but not limited to this.
103, identify whether user identity is legal according to the identity.
Specifically, this step can be the behavioral data that acquisition user generates in real time in actual application, and generate
Real-time identity then detects the real time identity and identifies between the identity according to the generation of user's history behavioral data
Matching degree, if matching degree be more than preset matching degree threshold value if determine user identity it is legal, otherwise determine user identity it is illegal.
Further, it when determining that user identity is illegal, then issues warning information or terminates the operation of application program.
The recognition methods of user identity provided in an embodiment of the present invention, for the prior art by biological characteristic such as fingerprint,
When vocal print etc. determines user identity, since biological characteristic can be forged, so that identification still has security risk, this hair
Bright embodiment generates body corresponding to the user according to the historical behavior data of user by acquiring the historical behavior data of user
Part mark, and it is whether legal using identity identification user identity, therefore compared with the prior art, the embodiment of the present invention
Identification information corresponding to the user can be generated by historical behavior data, since the behavioral data of user can not be forged, thus
The uniqueness for ensuring identity exists when avoiding biological characteristic etc. as identification information and forges and may identity be known
The poor problem of other performance, so as to improve user identity identification performance.
Further, as the refinement and extension to embodiment illustrated in fig. 1, the embodiment of the invention also provides another kinds to use
The recognition methods of family identity, as shown in Figure 2.
201, the historical behavior data of user are acquired.
Wherein, the historical behavior data, which include at least, social model behavioral data, dialogue mode data and consumption mould
Formula data.And the concept explanation of the behavioral data and the specific embodiment of this step can refer to the step 101
In accordingly describe, details are not described herein.
It should be noted that specific implementation of the embodiment of the present invention can be used in terminal device to user for configuration
The device that identity is identified, user can be configured whether open identity knowledge when application operation in each application program
Other function, and when user opens identity recognition function and application program in application program and runs, i.e. triggering collection user
Historical behavior data, and then determine user identity legitimacy.
202, the historical behavior data are classified.
Further, the behavioral data under multiple groups different mode is obtained.For the embodiment of the present invention, can be incited somebody to action in step
The schema category that behavioral data includes is classified, such as include in above-mentioned steps social model data, dialogue mode data,
Historical behavior data classification can be in this step then social model class, dialogue mode class by consumption mode data and be disappeared
Take mode class.And specific mode classification can be to be classified using disaggregated model, classification function etc. to historical behavior data,
The embodiment of the present invention is not specifically limited in this embodiment.
203, the behavioral data under each group mode is parsed respectively, and utilizes the calculating of preset neural network model and institute
State the corresponding multiple identity subvectors of user.
Wherein, the identity subvector is used for identity of the identity user under each mode.User is being got each
After behavioral data under mode, behavioral data is parsed, available habit corresponding to the user, such as habit word,
Idiomatic expression, habit travel time, consumption level, consumption direction etc., the characterization related to user for then obtaining parsing
Input neural network model trained in advance, then obtain the identity vector for identifying the user identity under each mode.
204, corresponding with user identity vector is synthesized according to the multiple identity subvector, and by the identity to
Amount is determined as the identity of the user.
For the embodiment of the present invention, the embodiment of subvector synthesis identity vector can be closed for vector in the prior art
At mode, the embodiment of the present invention do not do this and excessively repeats.It should be noted that when collecting user under all mode
After historical behavior data, data are divided to obtain the behavioral data under multiple modes first, be then calculated again each
Corresponding sub- identity vector under a mode finally obtains identifying the unique identities vector of the user identity in synthesis, can be with
Ensure each mode data of user is used as reference factor, avoids and is generating when the behavioral data under some mode is less
When user identity vector, User Identity caused by cannot embodying generates the poor problem of accuracy, and then improves use
The accuracy of family identity confirmation, improves the accuracy of user identity identification.
205, the current behavior data of user are obtained.
For the embodiment of the present invention, when user opens identity recognition function, i.e., permission server side acquires user mutual
The behavioral data generated when surfing in networking, therefore the current behavior data of user can be collected in real time in this step.
It should be noted that usually utilizing the life of user in the prior art when user's login application program or website
The log-on message of object feature such as fingerprint, vocal print, facial information etc. or account number cipher as user, and when server authentication should
Confirmation user identity is legal when log-on message meets default log-on message, and no longer supervises in surfing process on user network later
Whether legal identity is surveyed, so that can be cheated during later if criminal usurps the log-on message of user
Deceive equal violation operations.And in embodiments of the present invention, the current behavior data of user's generation can be acquired, in real time in order to basis
The data identify user identity, the monitoring on user network in surfing process to user identity legitimacy are realized, so that user
Identification is more comprehensive, improves the performance of user identity identification.
206, the current identity of user is calculated using the preset neural network model.
For the embodiment of the present invention, the mode for calculating current identity can be with generation user identity mark in above-mentioned steps
The mode of knowledge is identical, i.e., parses first to current behavior data, and the data result after parsing is then input to preset mind
Through in network model, obtaining the identity vector of user, because collected current behavior data are only a mould under normal conditions
Data under formula, so obtained identity vector to be directly determined as to the current identity of user at this time, without holding
Row vector synthetic operation, to improve the effect of user identity identification while under the accuracy that can ensure identification
Rate.
207, it is determined and is used according to the matching degree between the current identity of the user and the identity of the user
Whether family identity is legal.
Specifically, matching degree threshold value can be set according to different application scenarios, it is 95% that matching degree threshold value, which is such as arranged, because
This determines that user identity closes when detecting the matching degree between current identity and the identity of user is more than 95%
Otherwise method confirms that user identity is illegal, but not limited to this.
In order to further enhance user identity identification performance, the method can also include: according to the identity vector into
Row cluster obtains multiple user's set；User's collection is determined according to the identity of each user in user set
The mark of conjunction.Specifically, when classifying to user, can classify under each mode to user respectively, it can also be with
User is classified simultaneously in a plurality of modes, by being clustered according to the vector of identity user identity, can be realized by
Similar users assemble and form user's set.Further, whole body included in each user's set can be counted
Part mark quantity, and a fairly large number of one or more marks are determined as the mark that the user gathers.For example, to a user
The corresponding identity of multiple users in set counts, and finally obtains the user and gathers the identity that interior user carries
Quantity are as follows: tourism 128, shopping 330, animation 14, is stayed up late 263 at sport 29, then at this time can will be a fairly large number of
Mark " do shopping, stay up late " is determined as the mark of user set.For the embodiment of the present invention, by by user according to identity
Classify, counted so that similar user will be liked, recommends related letter in order to integrated management user and to user
Breath.
In order to promote the safety in network environment, if the method can also include: that the user identity is illegal,
Outputting alarm information and/or terminator operation.Wherein, the warning information can be pictorial information, audio-frequency information, text letter
Breath etc., the embodiment of the present invention is not specifically limited in this embodiment.In embodiments of the present invention, if current behavioral data is chatting for user
Day data can then send a warning message to user and other side simultaneously, to remind the other side user identity that there are security risks, and
Exit the program login after outputting alarm information；And if the current behavior data of user are what user generated when surfing the web
It, then can directly terminator operation when data.
But it should be recognized that specific embodiment described in above-mentioned application scenarios is only exemplary, not this hair
Unique specific embodiment of bright embodiment, herein be only meet method described in the embodiment of the present invention optimal enforcement mode it
One.
Further, as the realization to method shown in above-mentioned Fig. 1, the embodiment of the invention also provides a kind of user identity
Identification device, for being realized to above-mentioned method shown in FIG. 1.The Installation practice is corresponding with preceding method embodiment,
To be easy to read, present apparatus embodiment no longer repeats the detail content in preceding method embodiment one by one, but it should bright
Really, the device in the present embodiment can correspond to the full content realized in preceding method embodiment.As shown in figure 3, the device packet
It includes: acquisition unit 31, generation unit 32, recognition unit 33, wherein
Acquisition unit 31 acquires the historical behavior data of user, and the historical behavior data, which include at least, social model
Behavioral data, dialogue mode data and consumption mode data.
Generation unit 32, the historical behavior data for being acquired according to the acquisition unit 31 generate the identity of user
Mark.
Whether recognition unit 33, the identity identification user identity for being generated according to the generation unit 32 close
Method.
Further, as the realization to method shown in above-mentioned Fig. 2, the embodiment of the invention also provides another user's bodies
The identification device of part, for being realized to above-mentioned method shown in Fig. 2.The Installation practice and preceding method embodiment pair
It answers, to be easy to read, present apparatus embodiment no longer repeats the detail content in preceding method embodiment one by one, but it should
Clear, the device in the present embodiment can correspond to the full content realized in preceding method embodiment.As shown in figure 4, the device
It include: acquisition unit 41, generation unit 42, recognition unit 43, wherein
Acquisition unit 41 acquires the historical behavior data of user, and the historical behavior data, which include at least, social model
Behavioral data, dialogue mode data and consumption mode data.
Generation unit 42, the historical behavior data for being acquired according to the acquisition unit 41 generate the identity of user
Mark.
Whether recognition unit 43, the identity identification user identity for being generated according to the generation unit 42 close
Method.
Further, described device further include:
Taxon 44 obtains the behavior number under multiple groups different mode for the historical behavior data to be classified
According to.
Computing unit 45 for parsing respectively to the behavioral data under each group mode, and utilizes preset neural network
Model calculates multiple identity subvectors corresponding with the user.
Synthesis unit 46, for synthesizing identity vector corresponding with the user according to the multiple identity subvector.
Determination unit 47, for the identity vector to be determined as to the identity of the user.
Further, described device further include: acquiring unit 48.
The acquiring unit 48, for obtaining the current behavior data of user.
The computing unit 45 is also used to calculate the current identity of user using the preset neural network model.
The determination unit 47, specifically for according to the current identity of the user and the identity of the user
Between matching degree determine whether user identity legal.
Further, described device further include:
Cluster cell 49 obtains multiple user's set for being clustered according to the identity vector.
The determination unit 47 is also used to determine the use according to the identity of each user in user set
The mark of family set.
Further, described device further include:
Output unit 410, if illegal for the user identity, outputting alarm information and/or terminator operation.
The identification device of another kind user identity provided in an embodiment of the present invention.Described device includes: acquisition unit, generates
Unit and recognition unit.When determining user identity by biological characteristic such as fingerprint, vocal print etc. for the prior art, due to biological special
Sign can be forged, so that identification still has security risk, the historical behavior that the embodiment of the present invention passes through acquisition user
Data, and identity corresponding to the user is generated according to the historical behavior data of user, and use using identity identification
Whether family identity is legal, therefore compared with the prior art, the embodiment of the present invention can be generated by historical behavior data and user
Corresponding identification information ensures that the uniqueness of identity since the behavioral data of user can not be forged, avoid by
There is a problem of forging when biological characteristic etc. is as identification information may make identification performance poor, so as to improve user
Identification performance.
The adjustment device for the volume introduced by the present embodiment is the user identity that can be executed in the embodiment of the present invention
Recognition methods device, so based on personal identification method described in the embodiment of the present invention, the affiliated technology people in this field
Member can understand the specific embodiment and its various change form of the identification device of the user identity of the present embodiment, so
How this realizes the identification device of the user identity recognition methods of the user identity in the embodiment of the present invention is no longer detailed
It introduces.As long as those skilled in the art implement device used by the recognition methods of user identity in the embodiment of the present invention,
Belong to the range to be protected of the application.
The embodiment of the invention provides a kind of electronic equipment, as shown in Figure 5, comprising: at least one processor
(processor)51；And at least one processor (memory) 52, the bus 53 being connect with the processor 51；Wherein,
The processor 51, memory 52 complete mutual communication by the bus 53；
The processor 51 is used to call the program instruction in the memory 52, to execute in above method embodiment
Step.
Include kernel in processor 51, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set one
It is a or more, improve user identity identification performance by adjusting kernel parameter.
Memory 52 may include the non-volatile memory in computer-readable medium, random access memory (RAM)
And/or the forms such as Nonvolatile memory, if read-only memory (ROM) or flash memory (flashRAM), memory include at least one
Storage chip.
The present embodiment provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium
Computer instruction is stored, the computer instruction makes the computer execute method provided by above-mentioned each method embodiment.
The embodiment of the invention also provides a kind of computer program products, when executing on data processing equipment, are suitable for
It executes the program of initialization there are as below methods step: acquiring the historical behavior data of user, the historical behavior data are at least wrapped
Contain social model behavioral data, dialogue mode data and consumption mode data；User is generated according to the historical behavior data
Identity；Identify whether user identity is legal according to the identity.
Further, after the historical behavior data of the acquisition user, the method also includes:
The historical behavior data are classified, the behavioral data under multiple groups different mode is obtained；
It is described according to the historical behavior data generate user identity include:
Behavioral data under each group mode is parsed respectively, and is calculated and the use using preset neural network model
The corresponding multiple identity subvectors in family, the identity subvector are used for identity of the identity user under each mode；
Identity vector corresponding with the user is synthesized according to the multiple identity subvector, and the identity vector is true
It is set to the identity of the user.
Further, described whether legal according to the identification user identity to include:
Obtain the current behavior data of user；
The current identity of user is calculated using the preset neural network model；
User's body is determined according to the matching degree between the current identity of the user and the identity of the user
Whether part is legal.
Further, the method also includes:
It is clustered according to the identity vector, obtains multiple user's set；
The mark of user's set is determined according to the identity of each user in user set.
Further, it is described according to the identification user identity it is whether legal after, the method also includes:
If the user identity is illegal, outputting alarm information and/or terminator operation.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
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.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flashRAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (10)
1. a kind of recognition methods of user identity, which is characterized in that the described method includes:
The historical behavior data of user are acquired, the historical behavior data, which include at least, social model behavioral data, dialogue mould
Formula data and consumption mode data；
The identity of user is generated according to the historical behavior data；
Identify whether user identity is legal according to the identity.
2. the method according to claim 1, wherein it is described acquisition user historical behavior data after, it is described
Method further include:
The historical behavior data are classified, the behavioral data under multiple groups different mode is obtained；
It is described according to the historical behavior data generate user identity include:
Behavioral data under each group mode is parsed respectively, and is calculated and the user couple using preset neural network model
The multiple identity subvectors answered, the identity subvector are used for identity of the identity user under each mode；
Identity vector corresponding with the user is synthesized according to the multiple identity subvector, and the identity vector is determined as
The identity of the user.
3. according to the method described in claim 2, it is characterized in that, described whether legal according to the identification user identity
Include:
Obtain the current behavior data of user；
The current identity of user is calculated using the preset neural network model；
Determine that user identity is according to the matching degree between the current identity of the user and the identity of the user
It is no legal.
4. according to the method in claim 2 or 3, which is characterized in that the method also includes:
It is clustered according to the identity vector, obtains multiple user's set；
The mark of user's set is determined according to the identity of each user in user set.
5. according to the method in any one of claims 1 to 3, which is characterized in that described according to the identification user
After whether identity is legal, the method also includes:
If the user identity is illegal, outputting alarm information and/or terminator operation.
6. a kind of identification device of user identity, which is characterized in that described device includes:
Acquisition unit, for acquiring the historical behavior data of user, the historical behavior data, which include at least, social model row
For data, dialogue mode data and consumption mode data；
Generation unit, for generating the identity of user according to the historical behavior data；
Recognition unit, for identifying whether user identity is legal according to the identity.
7. device according to claim 6, which is characterized in that described device further include: taxon,
The taxon obtains the behavioral data under multiple groups different mode for the historical behavior data to be classified；
The generation unit includes:
First computing module for parsing respectively to the behavioral data under each group mode, and utilizes preset neural network mould
Type calculates multiple identity subvectors corresponding with the user, and the identity subvector is for identity user under each mode
Identity；
Synthesis module, for synthesizing identity vector corresponding with the user according to the multiple identity subvector；
First determining module, for the identity vector to be determined as to the identity of the user.
8. device according to claim 7, which is characterized in that the recognition unit includes:
Module is obtained, for obtaining the current behavior data of user；
Second computing module, for calculating the current identity of user using the preset neural network model；
Second determining module is true according to the matching degree between the current identity of the user and the identity of the user
Whether legal determine user identity.
9. a kind of electronic equipment characterized by comprising
At least one processor；
And at least one processor, the bus being connected to the processor；Wherein,
The processor, memory complete mutual communication by the bus；
The processor is used to call the program instruction in the memory, any into claim 5 with perform claim requirement 1
The recognition methods of user identity described in.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Store up computer instruction, the computer instruction requires the computer perform claim 1 to described in any one of claim 5
The recognition methods of user identity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811505465.7A CN109598110A (en) | 2018-12-10 | 2018-12-10 | A kind of recognition methods of user identity and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811505465.7A CN109598110A (en) | 2018-12-10 | 2018-12-10 | A kind of recognition methods of user identity and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109598110A true CN109598110A (en) | 2019-04-09 |
Family
ID=65962207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811505465.7A Pending CN109598110A (en) | 2018-12-10 | 2018-12-10 | A kind of recognition methods of user identity and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598110A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860350A (en) * | 2020-07-23 | 2020-10-30 | 深圳小辣椒科技有限责任公司 | Anti-fraud device and method integrating face recognition and voice recognition |
| CN111861240A (en) * | 2020-07-27 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Suspicious user identification method, device, equipment and readable storage medium |
| CN111935162A (en) * | 2020-08-14 | 2020-11-13 | 山东云海国创云计算装备产业创新中心有限公司 | Cloud file access method and device and related components |
| CN115578075A (en) * | 2022-11-01 | 2023-01-06 | 广州商学院 | AI intelligent English auxiliary learning method, system, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130042327A1 (en) * | 2011-08-12 | 2013-02-14 | Palo Alto Research Center Incorporated | Guided implicit authentication |
| CN103812872A (en) * | 2014-02-28 | 2014-05-21 | 中国科学院信息工程研究所 | Network water army behavior detection method and system based on mixed Dirichlet process |
| CN107368718A (en) * | 2017-07-06 | 2017-11-21 | 同济大学 | A kind of user browsing behavior authentication method and system |
| CN108268762A (en) * | 2018-01-17 | 2018-07-10 | 同济大学 | The mobile social networking user identity of Behavior-based control modeling knows fake method |
-
2018
- 2018-12-10 CN CN201811505465.7A patent/CN109598110A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130042327A1 (en) * | 2011-08-12 | 2013-02-14 | Palo Alto Research Center Incorporated | Guided implicit authentication |
| CN103812872A (en) * | 2014-02-28 | 2014-05-21 | 中国科学院信息工程研究所 | Network water army behavior detection method and system based on mixed Dirichlet process |
| CN107368718A (en) * | 2017-07-06 | 2017-11-21 | 同济大学 | A kind of user browsing behavior authentication method and system |
| CN108268762A (en) * | 2018-01-17 | 2018-07-10 | 同济大学 | The mobile social networking user identity of Behavior-based control modeling knows fake method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860350A (en) * | 2020-07-23 | 2020-10-30 | 深圳小辣椒科技有限责任公司 | Anti-fraud device and method integrating face recognition and voice recognition |
| CN111861240A (en) * | 2020-07-27 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Suspicious user identification method, device, equipment and readable storage medium |
| CN111935162A (en) * | 2020-08-14 | 2020-11-13 | 山东云海国创云计算装备产业创新中心有限公司 | Cloud file access method and device and related components |
| CN115578075A (en) * | 2022-11-01 | 2023-01-06 | 广州商学院 | AI intelligent English auxiliary learning method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598110A (en) | A kind of recognition methods of user identity and device | |
| CN108182279B (en) | Object classification method, device and computer equipment based on text feature | |
| US20210209512A1 (en) | Model shift prevention through machine learning | |
| CN108875327A (en) | One seed nucleus body method and apparatus | |
| CN106487747B (en) | User identification method, system, device and processing method, device | |
| CN103064987A (en) | Bogus transaction information identification method | |
| CN110210194A (en) | Electronic contract display methods, device, electronic equipment and storage medium | |
| CN112329816A (en) | Data classification method and device, electronic equipment and readable storage medium | |
| CN111401447A (en) | Artificial intelligence-based flow cheating identification method and device and electronic equipment | |
| CN109064217A (en) | Method, apparatus and electronic equipment are determined based on the core body strategy of user gradation | |
| Wang et al. | Identity theft detection in mobile social networks using behavioral semantics | |
| CN113837323A (en) | Satisfaction prediction model training method and device, electronic equipment and storage medium | |
| CN114090985A (en) | Method and device for setting user operation permission in block chain and electronic equipment | |
| CN110457601B (en) | Social account identification method and device, storage medium and electronic device | |
| Wang et al. | ‘I am not a number’: Conceptualising identity in digital surveillance | |
| CN111784360B (en) | Anti-fraud prediction method and system based on network link backtracking | |
| CN104091117B (en) | Clustering method based on security risk and clustering apparatus | |
| CN113569111A (en) | Object attribute identification method and device, storage medium and computer equipment | |
| CN110008980A (en) | Identification model generation method, recognition methods, device, equipment and storage medium | |
| Hakimi et al. | Identifying fake account in facebook using machine learning | |
| CN107945034A (en) | Financial analysis method, application server and computer-readable recording medium based on microblogging finance and economics event | |
| EP3879418B1 (en) | Identity verification method and device | |
| CN117372742A (en) | Domain generalization method, server and client | |
| Baeza-Yates et al. | The attention economy and the impact of artificial intelligence | |
| EP3783543A1 (en) | Learning system, learning method, and program |
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: 20190409 |
|
| RJ01 | Rejection of invention patent application after publication |