CN113742665B - User identity recognition model construction and user identity verification methods and devices - Google Patents
User identity recognition model construction and user identity verification methods and devices Download PDFInfo
- Publication number
- CN113742665B CN113742665B CN202010509874.5A CN202010509874A CN113742665B CN 113742665 B CN113742665 B CN 113742665B CN 202010509874 A CN202010509874 A CN 202010509874A CN 113742665 B CN113742665 B CN 113742665B
- Authority
- CN
- China
- Prior art keywords
- user
- behavior
- sample data
- basic
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 99
- 238000010276 construction Methods 0.000 title claims description 15
- 238000012795 verification Methods 0.000 title claims description 7
- 239000013598 vector Substances 0.000 claims abstract description 106
- 230000008569 process Effects 0.000 claims abstract description 20
- 230000006399 behavior Effects 0.000 claims description 330
- 230000015654 memory Effects 0.000 claims description 63
- 238000013528 artificial neural network Methods 0.000 claims description 25
- 230000004927 fusion Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000001360 synchronised effect Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000013604 expression vector Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
- G06F21/316—User authentication by observing the pattern of computer usage, e.g. typical user behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computer Security & Cryptography (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Social Psychology (AREA)
- Collating Specific Patterns (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention relates to a method and a device for constructing a user identity recognition model and verifying user identity, wherein the method comprises the following steps: acquiring a plurality of pieces of basic behavior sample data generated in the process of using equipment by a user; obtaining a behavior embedding vector corresponding to each piece of basic behavior sample data based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data; acquiring user characteristic information and user behavior sequence information based on all behavior embedding vectors; according to the user characteristic information and the user behavior sequence information, the user identity recognition model is constructed, so that the user characteristic information and the behavior sequence information can be effectively utilized to train the identity recognition model, the user identity can be more accurately and actively verified, and the personal information safety and property safety of the user are ensured.
Description
Technical Field
The embodiment of the invention relates to the technical field of identity verification and data mining, in particular to a method and a device for constructing a user identity recognition model and verifying user identity.
Background
In recent years, along with the rapid development of the mobile internet, mobile phones have become an indispensable part of life of people, and particularly various software in mobile phones become important carriers of social relations and financial assets of people, and currently widely applied user authentication modes comprise password authentication, fingerprint authentication and face recognition, but because the fingerprint authentication and face recognition require special sensor support, passwords cannot be completely replaced in practical application, on the other hand, the authentication technologies such as password authentication, fingerprint authentication and face recognition only verify user identities when a system is logged in, an intruder can disguise as a normal user invaded system once the intruder breaks, and the system cannot verify the identities of the user in the use process for user experience, so that the intrusion behavior cannot be prevented.
Therefore, how to effectively and actively verify the identity of a user is an important problem in the research of the network security field.
Disclosure of Invention
In view of this, in order to solve the above technical problem that the user identity cannot be actively verified effectively, the embodiments of the present invention provide a method and apparatus for constructing a user identity recognition model and verifying the user identity.
In a first aspect, an embodiment of the present invention provides a method for constructing a user identification model, including:
acquiring a plurality of pieces of basic behavior sample data generated in the process of using equipment by a user;
obtaining a behavior embedding vector corresponding to each piece of basic behavior sample data based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data;
acquiring user characteristic information and user behavior sequence information based on all behavior embedding vectors;
and constructing the user identity recognition model according to the user characteristic information and the user behavior sequence information.
In one possible embodiment, the method further comprises:
classifying the plurality of pieces of basic behavior sample data according to preset dimensions;
and obtaining a behavior embedding vector corresponding to the ith basic behavior data according to a preset method corresponding to the category to which the ith basic behavior data belongs, wherein i is a numerical value which is greater than or equal to 1 and less than or equal to the total number of the basic behavior sample data.
In one possible embodiment, the method further comprises:
and dividing the plurality of basic behavior sample data into four data types of category single value, category multi-value, numerical value and vector according to the two dimensions of the value type and the value number.
In one possible embodiment, the method further comprises:
splicing and combining an ith behavior embedded vector in all the behavior embedded vectors with other embedded vectors in all the behavior embedded vectors according to a first preset rule to obtain a first result;
splicing and combining the ith basic behavior sample data and the characteristic value corresponding to the ith basic behavior sample data according to a second preset rule to obtain a second result;
and obtaining the user characteristic information according to the first result and the second result.
In one possible embodiment, the method further comprises:
generating ith behavior fusion sequence information by using a first preset neural network based on the ith behavior embedding vector;
and superposing the behavior fusion sequence information respectively corresponding to all the behavior embedding vectors and taking the superposition as the user behavior sequence information.
In one possible embodiment, the method further comprises:
and inputting the user characteristic information and the user behavior sequence information into a second preset neural network to construct the user identity recognition model.
In one possible embodiment, the method further comprises: and optimizing the user identity recognition model.
In one possible embodiment, the method further comprises:
and optimizing each layer of input data in the second neural network algorithm according to a BN algorithm, wherein the first layer of input data in the second neural network algorithm comprises the first result, the second result, a third result and the user characteristic information, and the third result is obtained by splicing and combining all behavior embedded vectors.
In a second aspect, an embodiment of the present invention provides a user authentication method, including:
acquiring a plurality of basic behavior data generated when a user using equipment currently uses the equipment;
classifying the plurality of base behavior data;
extracting h user characteristics corresponding to h-class basic behavior data;
inputting the h user characteristics into a user identity recognition model, and acquiring the h probability, wherein the h probability is the probability indicating that the user identity of the currently used equipment is the host identity corresponding to the equipment;
and adding all probabilities into a preset classifier, and finally identifying the user identity of the current equipment, wherein h is a positive integer.
In a third aspect, an embodiment of the present invention provides a device for constructing a user identification model, including:
The acquisition module is used for acquiring a plurality of pieces of basic behavior sample data generated in the process of using the equipment by a user;
the acquisition module is further used for obtaining a behavior embedding vector corresponding to each piece of basic behavior sample data based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data;
the determining module is used for acquiring user characteristic information and user behavior sequence information based on all the behavior embedding vectors;
and the construction module is used for constructing the user identity recognition model according to the user characteristic information and the user behavior sequence information.
In a fourth aspect, an embodiment of the present invention provides a user authentication apparatus, including:
the acquisition module is used for acquiring a plurality of basic behavior data generated when a user using the equipment currently uses the equipment;
the acquisition module is further used for classifying the plurality of basic behavior data; extracting h user characteristics corresponding to h-class basic behavior data; inputting the h user characteristics into a user identity recognition model, and acquiring the h probability, wherein the h probability is the probability indicating that the user identity of the currently used equipment is the host identity corresponding to the equipment;
And the identification module is used for adding all the probabilities into a preset classifier and finally identifying the user identity of the current equipment, wherein h is a positive integer.
In a fifth aspect, an embodiment of the present invention provides an intelligent device, including: the processor is used for executing the user identification model construction program stored in the memory so as to realize the user identification model construction method in any one of the first aspects.
In a sixth aspect, an embodiment of the present invention provides an intelligent device, including: the processor is used for executing the user identity verification program stored in the memory so as to realize the user identity verification method in the second aspect.
In a seventh aspect, an embodiment of the present invention provides a storage medium, where one or more programs are stored, where the one or more programs are executable by one or more processors to implement the method for building a user identification model according to any one of the first aspect or implement the method for verifying a user identification according to the second aspect.
The user identity recognition model construction method provided by the embodiment of the invention is characterized by acquiring a plurality of pieces of basic behavior sample data generated in the process of using equipment by a user; obtaining a behavior embedding vector corresponding to each piece of basic behavior sample data based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data; acquiring user characteristic information and user behavior sequence information based on all behavior embedding vectors; according to the user characteristic information and the user behavior sequence information, the user identity recognition model is built, so that the user characteristic information and the behavior sequence information can be effectively utilized to train the identity recognition model, the identity of the user currently using the intelligent device can be accurately and actively verified, and the personal information safety and property safety of the user are ensured.
Drawings
FIG. 1 is a schematic flow chart of a method for constructing a user identification model according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of another method for constructing a user identification model according to an embodiment of the present invention;
fig. 3 is a flow chart of a user authentication method according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a device for constructing a user identification model according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a user authentication device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an intelligent device according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of another intelligent device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
For the purpose of facilitating an understanding of the embodiments of the present invention, reference will now be made to the following description of specific embodiments, taken in conjunction with the accompanying drawings, which are not intended to limit the embodiments of the invention.
Fig. 1 is a flow chart of a method for constructing a user identity recognition model according to an embodiment of the present invention, as shown in fig. 1, where the method specifically includes:
s11, acquiring a plurality of pieces of basic behavior sample data generated in the process of using the equipment by the user.
Acquiring input behavior data obtained at least according to input behaviors of a user in the process of using the intelligent equipment, searching behavior data obtained according to searching behaviors, and APP use behavior data obtained according to APP use behaviors, wherein the APP use behavior data is used as basic behavior sample data of the user.
And S12, obtaining a behavior embedding vector corresponding to each piece of basic behavior sample data based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data.
And extracting corresponding behavior characteristics of each piece of basic behavior sample data, processing the behavior characteristics corresponding to each piece of basic behavior sample data by utilizing a preset behavior embedding layer aiming at different behavior data to obtain corresponding behavior characteristic expression vectors, and then splicing all the characteristic expression vectors to obtain the behavior embedding vectors.
S13, acquiring user characteristic information and user behavior sequence information based on all behavior embedding vectors.
And obtaining user characteristic information and user behavior sequence information by carrying out a series of processes on the obtained behavior embedding vector according to a preset rule.
S14, constructing the user identity recognition model according to the user characteristic information and the user behavior sequence information.
And constructing a user identity recognition model by using a multi-layer perceptron according to the obtained user characteristic information and the user behavior sequence information, and further optimizing the model by using a loss function and an Adam algorithm, wherein the model can realize the prediction of the user identity.
The user identity recognition model construction method provided by the embodiment of the invention is characterized by acquiring a plurality of pieces of basic behavior sample data generated in the process of using equipment by a user; obtaining a behavior embedding vector corresponding to each piece of basic behavior sample data based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data; acquiring user characteristic information and user behavior sequence information based on all behavior embedding vectors; according to the user characteristic information and the user behavior sequence information, the user identity recognition model is built, so that the user characteristic information and the behavior sequence information can be effectively utilized to train the identity recognition model, the identity of the user currently using the intelligent device can be accurately and actively verified, and the personal information safety and property safety of the user are ensured.
Fig. 2 is a flow chart of another method for constructing a user identification model according to an embodiment of the present invention, as shown in fig. 2, where the method specifically includes:
s21, acquiring a plurality of pieces of basic behavior sample data generated in the process of using the equipment by the user.
According to input behavior, search behavior and APP use behavior of a user in the process of using the intelligent equipment, input behavior data, search behavior data and APP use behavior data are obtained, and the input behavior data, the search behavior data and the APP use behavior data are used as basic behavior sample data of the user.
Wherein the input behavior feature comprises at least: reverse order of input, input pinyin errors, and input syllables or pinyin omissions. The search behavior feature may include: input speed, number of keywords, search text length, part-of-speech patterns, syntactic patterns or time intervals, etc. APP use behavior characteristics through several kinds of APP that the user used every day, each APP corresponds the different usage in user's life, embodies user's characteristics to user's time of rest is relatively fixed, calculates APP's frequency of use and obtains APP use behavior characteristics.
Further, the semantics of the pinyin input strings and the search text are modeled using an existing pre-trained language model (Bidirectional Encoder Representation from Transformers, BERT) to obtain text semantic vectors.
S22, dividing the plurality of basic behavior sample data into four data types of category single value, category multi-value, numerical value and vector according to two dimensions of the value type and the value number.
And taking the obtained text semantic vector as a behavior characteristic, and dividing basic behavior sample data such as input behavior data, search behavior data and APP use behavior data of a user into four data types of category single value, category multi-value, numerical value and vector according to two dimensions of the value type and the value quantity.
S23, according to a preset method corresponding to the category to which the ith basic behavior data belongs, obtaining a behavior embedding vector corresponding to the ith basic behavior data, wherein i is a numerical value which is greater than or equal to 1 and less than or equal to the total number of the basic behavior sample data.
According to the embodiment of the invention, according to the preset behavior embedding layer suitable for various types of data, the behavior characteristics of the four types of data are respectively processed to obtain the embedded vectors corresponding to different behavior characteristics.
For example, there are d basic user features in the sample s, i.e., s= [ f 1 ，f 2 ，...，f d ]For the ith basic user feature f i Acquiring a characteristic f by adopting a mode corresponding to a numerical value type characteristic in behavior embedding representation i Corresponding embedded vector emb (f i ) Wherein the book (f) i ) For obtaining f i Vector of unique correspondence, v i Representing user characteristics f i Can be expressed by the following formula:
emb(f i )＝v i ×lookup(f i ) (equation 1)
S24, splicing and combining the ith behavior embedded vector in all the behavior embedded vectors with other embedded vectors in all the behavior embedded vectors according to a first preset rule, and obtaining a first result.
In the embodiment of the invention, in order to make the model more fully use the obvious features with stronger difference, the embedded vectors corresponding to any two features are subjected to element product and summation to obtain second-order combined information among the features of the user, and the second-order combined information is recorded as rep 2 Wherein +.is the product of elements representing the multiplication of two corresponding positions of the vectors, any two bitsThe sign-corresponding embedded vector may be expressed as emb (f i ) And emb (f) j ) There are d behavior embedding vectors in total, and then there is formula 2, see specifically below:
s25, splicing and combining the ith basic behavior sample data and the characteristic value corresponding to the ith basic behavior sample data according to a second preset rule, and obtaining a second result.
In the embodiment of the invention, each piece of basic behavior sample data and the characteristic value corresponding to each piece of basic behavior sample data are spliced together according to the fact that each user characteristic value is multiplied by the corresponding weight, and are recorded as rep 1 See in particular equation 3 below:
rep 1 ＝[w 1 v 1 ，w 2 v 2 ，...，w n v n ](equation 3)
Wherein w represents the weight corresponding to the user characteristic value, and v represents the user characteristic value.
S26, obtaining the user characteristic information according to the first result and the second result.
Second order combination information rep according to user characteristics 2 And the result rep of the concatenation of each characteristic value of the user and the corresponding weight 1 And obtaining the characteristic information of the user.
S27, generating the ith behavior fusion sequence information by using a first preset neural network based on the ith behavior embedding vector.
Behavior sequence information plays an important role in judging the identity of a user, continuous behaviors are related, in the embodiment of the invention, an embedded representation emb (a) comprising various behavior characteristics and semantic vectors is fused into a behavior a by using a behavior embedding method layer, a behavior sequence a is modeled by using a Long Short-Term Memory (LSTM), and the outputs of two LSTMs are spliced together to form the behavior a i Table of fused sequence informationShow h i As shown in the following formula 4:
s28, overlapping the behavior fusion sequence information respectively corresponding to all the behavior embedding vectors and taking the overlapping result as the user behavior sequence information.
Specifically, for example, there are m behaviors in the behavior sequence, and the superposition of behavior fusion sequence information corresponding to the embedded vectors of all m behaviors is recorded as rep as the whole representation of the user behavior sequence information seq Then there is equation 5:
s29, inputting the user characteristic information and the user behavior sequence information into a second preset neural network, and constructing the user identity recognition model.
And S210, optimizing each layer of input data in the second neural network algorithm according to a BN algorithm, wherein the first layer of input data in the second neural network algorithm comprises the first result, the second result, a third result and the user characteristic information, and the third result is obtained by splicing and combining all behavior embedded vectors.
In the embodiment of the invention, the obtained user characteristic second-order combination information rep is used for generating the user characteristic second-order combination information rep 2 The result rep of the concatenation of each characteristic value of the user and the corresponding weight 1 Superposition and rep of behavior fusion sequence information respectively corresponding to all behavior embedding vectors seq And embedding vectors emb (f i ) The embedded vector splice vector formed by splicing together is denoted rep f Input to a first layer of a multi-layer perceptron (Multilayer Perceptron, MLP), the first layer input being denoted as x 1 The following equation 6 is obtained:
x 1 ＝[rep seq ；rep f ；rep 2 ；rep 1 ](equation 6)
Wherein the embedded vectors of all user features in the sample emb (f i ) The embedded vector splice vector rep formed by splicing together f The calculation formula of (2) is shown as the following, and is expressed as formula 7:
rep f ＝[emb(f 1 )；emb(f 2 )；...；emb(f d )](equation 7)
Further, to enable faster convergence of the model and avoid trapping of local minima, the input is processed using BN (Batch Normalization) for each layer in the multi-layer perceptron, the calculation formula for the i-th layer is as follows, where x i Representing input of the ith layer, W i And b i The parameters representing the i-th layer, ρ represents BN, δ represents an activation function, relu (Rectified Linear Units) activation function is used in the present invention, and the processing formula is expressed as formula 8 as follows:
out i ＝δ(W i ρ(x i )+b i ) (equation 8)
Further, rep is to 1 And rep 2 Spliced together with the output of a multi-layer perceptron MLP, through a non-linear transformation layer, using softmax to predict the probability that a sample belongs to a user, wherein out mlp Representing the output of MLP, W and b represent parameters of the nonlinear transformation layer, resulting in equation 9:
further, the identity recognition model needs to be optimized, cross entropy is used as a loss function, and an objective function is minimized through an Adam algorithm, so that fewer resources are needed, convergence is faster, learning speed and effect of a machine are fundamentally accelerated, for example, for M samples containing N users, a calculation formula 10 is obtained:
wherein y is j，i Indicating whether the jth sample belongs to the ith user, if so, the value is 1, otherwise 0,the representation model predicts the probability that the jth sample belongs to the ith user.
The user identity recognition model construction method provided by the embodiment of the invention is characterized by acquiring a plurality of pieces of basic behavior sample data generated in the process of using equipment by a user; obtaining a behavior embedding vector corresponding to each piece of basic behavior sample data based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data; acquiring user characteristic information and user behavior sequence information based on all behavior embedding vectors; according to the user characteristic information and the user behavior sequence information, the user identity recognition model is built, so that the user characteristic information and the behavior sequence information can be effectively utilized to train the identity recognition model, the identity of the user currently using the intelligent device can be accurately and actively verified, and the personal information safety and property safety of the user are ensured.
Fig. 3 is a flow chart of a user authentication method according to an embodiment of the present invention, as shown in fig. 3, where the method specifically includes:
s31, acquiring a plurality of basic behavior data generated when a user using the equipment currently uses the equipment.
The method for acquiring the current user generated in the process of using the equipment at least comprises the following steps: input behavior data, search behavior data, APP usage behavior data, and the like.
For example, a section of behavior record of the current user includes 10 input behaviors, 6 search behaviors and 9 APP use behaviors, and these behavior data are obtained as basic behavior data to be detected.
S32, classifying the plurality of basic behavior data.
The basic behavior data are crossly displayed in the behavior records of the user according to the time sequence, the behavior data are required to be classified, and the input behavior times, the search behavior times and the APP use behavior times are obtained through statistics.
S33, extracting the h user characteristics corresponding to the h-class basic behavior data.
Extracting user characteristics of different categories corresponding to the classified behaviors, wherein the input behavior characteristics are obtained from aspects of reversing the input sequence of the user, inputting pinyin errors, inputting syllables or omitting pinyin and the like; the search behavior characteristics are obtained from the aspects of input speed, keyword number, search text length, part-of-speech mode, syntax mode or time interval and the like; the APP use behavior characteristics are obtained by calculating the use frequency of different APPs.
S34, inputting the h user characteristics into a user identity recognition model, and acquiring the h probability, wherein the h probability is the probability indicating that the user identity of the currently used equipment is the host identity corresponding to the equipment.
Inputting the obtained different user characteristics corresponding to different types of behaviors into an identity recognition model, and obtaining the probability that the user identity indicated by the user characteristics of the user of the current using device corresponds to the host identity of the original device according to the calculation output result of the model.
For example, the APP usage behavior characteristics of the user currently using the device, the probability of the identity corresponding to the original device owner predicted by the identity recognition model is 30%; the input behavior characteristics of the user of the current using device are predicted by the identity recognition model, and the probability of the identity corresponding to the owner of the original device is 90%; the probability of the identity of the original equipment owner predicted by the identity recognition model is 70% according to the search behavior characteristics of the user of the equipment currently used.
And S35, adding all probabilities into a preset classifier, and finally identifying the user identity of the current equipment, wherein h is a positive integer.
And inputting the obtained multiple probability information of which the user identities indicated by the different user characteristics of the user of the current equipment are corresponding to the original equipment owner identities and the behavior number contained in the different behavior data into a preset two-layer classifier, and finally judging whether the user identities of the current equipment are the original equipment owners or not through calculation of the two-layer classifier.
The two-layer classifier may be a gradient lifting tree model, a logistic regression model or a neural network model, and the two-layer classifier may be selected according to the situation in the implementation process of the scheme, which is not limited in detail in this embodiment.
According to the user identity verification method provided by the embodiment of the invention, the user using the equipment currently obtains a plurality of basic behavior data generated in the process of using the equipment; classifying the plurality of base behavior data; extracting different user characteristics corresponding to different types of basic behavior data; carrying out identity prediction by using an identity recognition model trained on various user characteristics to obtain judgment of the user identity based on various data; and adding all probabilities into a preset classifier, and finally identifying the user identity of the current equipment, so that the method can accurately and actively verify whether the user of the current equipment is the original equipment owner according to various behavior data of the current user.
Fig. 4 is a schematic structural diagram of a device for constructing a user identity recognition model according to an embodiment of the present invention, which specifically includes:
an obtaining module 401, configured to obtain a plurality of pieces of basic behavior sample data generated during a process of using the device by a user;
the obtaining module 401 is further configured to obtain a behavior embedding vector corresponding to each piece of basic behavior sample data based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data;
a determining module 402, configured to obtain user feature information and user behavior sequence information based on all the behavior embedding vectors;
and the construction module 403 is configured to construct the user identification model according to the user characteristic information and the user behavior sequence information.
The acquisition module is specifically used for classifying the plurality of pieces of basic behavior sample data according to preset dimensions; and obtaining a behavior embedding vector corresponding to the ith basic behavior data according to a preset method corresponding to the category to which the ith basic behavior data belongs, wherein i is a numerical value which is greater than or equal to 1 and less than or equal to the total number of the basic behavior sample data.
In one possible implementation manner, the obtaining module is further configured to divide the plurality of pieces of basic behavior sample data into four data types including a category single value, a category multiple value, a numerical value and a vector according to the two dimensions of the value type and the value number.
The determining module is specifically configured to splice and combine an ith behavior embedded vector in all the behavior embedded vectors with other embedded vectors in all the behavior embedded vectors according to a first preset rule, so as to obtain a first result; splicing and combining the ith basic behavior sample data and the characteristic value corresponding to the ith basic behavior sample data according to a second preset rule to obtain a second result; and obtaining the user characteristic information according to the first result and the second result.
In one possible implementation manner, the determining module is further configured to generate, based on the ith behavior embedding vector, ith behavior fusion sequence information by using a first preset neural network; and superposing the behavior fusion sequence information respectively corresponding to all the behavior embedding vectors and taking the superposition as the user behavior sequence information.
The construction module is specifically configured to input the user characteristic information and the user behavior sequence information into a second preset neural network, and construct the user identity recognition model.
In a possible implementation manner, the construction module is further configured to optimize the user identification model.
In a possible implementation manner, the construction module is further configured to perform optimization processing on each layer of input data in the second neural network algorithm according to a BN algorithm, where the first layer of input data in the second neural network algorithm includes the first result, the second result, a third result, and the user feature information, and the third result is a result obtained by performing stitching and combining on all behavior embedded vectors.
The apparatus for constructing a user identification model provided in this embodiment may be the apparatus for constructing a user identification model as shown in fig. 4, and may perform all steps of the method for constructing a user identification model as shown in fig. 1-2, thereby achieving the technical effects of the method for constructing a user identification model as shown in fig. 1-2, and detailed descriptions with reference to fig. 1-2 are omitted herein for brevity.
Fig. 5 is a schematic structural diagram of a user authentication device according to an embodiment of the present invention, which specifically includes:
an obtaining module 501, configured to obtain a plurality of basic behavior data generated when a user currently uses the device;
in a possible implementation manner, the obtaining module is further configured to classify the plurality of basic behavior data; extracting h user characteristics corresponding to h-class basic behavior data; inputting the h user characteristics into a user identity recognition model, and acquiring the h probability, wherein the h probability is the probability indicating that the user identity of the currently used equipment is the host identity corresponding to the equipment;
And the identifying module 502 is configured to add all probabilities to a preset classifier, and finally identify the user identity of the currently used device, where h is a positive integer.
The user authentication device provided in this embodiment may be a user authentication device as shown in fig. 5, and may perform all steps of the user authentication method as shown in fig. 3, so as to achieve the technical effects of the user authentication method as shown in fig. 3, and the details of the user authentication method are specifically described with reference to fig. 3, and are not repeated herein for brevity.
Fig. 6 is a schematic structural diagram of an intelligent device according to an embodiment of the present invention, and an intelligent device 600 shown in fig. 6 includes: at least one processor 601, memory 602, at least one network interface 604, and other user interfaces 603. The various components in the smart device 600 are coupled together by a bus system 605. It is understood that the bus system 605 is used to enable connected communications between these components. The bus system 605 includes a power bus, a control bus, and a status signal bus in addition to a data bus. But for clarity of illustration the various buses are labeled as bus system 605 in fig. 6.
The user interface 603 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, a trackball, a touch pad, or a touch screen, etc.).
It is to be appreciated that the memory 602 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a Read-only memory (ROM), a programmable Read-only memory (ProgrammableROM, PROM), an erasable programmable Read-only memory (ErasablePROM, EPROM), an electrically erasable programmable Read-only memory (ElectricallyEPROM, EEPROM), or a flash memory, among others. The volatile memory may be a random access memory (RandomAccessMemory, RAM) that acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic random access memory (DynamicRAM, DRAM), synchronous dynamic random access memory (SynchronousDRAM, SDRAM), double data rate synchronous dynamic random access memory (ddr SDRAM), enhanced Synchronous Dynamic Random Access Memory (ESDRAM), synchronous link dynamic random access memory (SynchlinkDRAM, SLDRAM), and direct memory bus random access memory (DirectRambusRAM, DRRAM). The memory 602 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some implementations, the memory 602 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 6021 and application programs 6022.
The operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application 6022 includes various application programs such as a media player (MediaPlayer), a Browser (Browser), and the like for realizing various application services. The program for implementing the method of the embodiment of the present invention may be included in the application 6022.
In the embodiment of the present invention, the processor 601 is configured to execute the method steps provided by the method embodiments by calling a program or an instruction stored in the memory 602, specifically, a program or an instruction stored in the application 6022, for example, including:
acquiring a plurality of pieces of basic behavior sample data generated in the process of using equipment by a user; obtaining a behavior embedding vector corresponding to each piece of basic behavior sample data based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data; acquiring user characteristic information and user behavior sequence information based on all behavior embedding vectors; and constructing the user identity recognition model according to the user characteristic information and the user behavior sequence information.
In one possible implementation manner, the plurality of pieces of basic behavior sample data are classified according to preset dimensions; and obtaining a behavior embedding vector corresponding to the ith basic behavior data according to a preset method corresponding to the category to which the ith basic behavior data belongs, wherein i is a numerical value which is greater than or equal to 1 and less than or equal to the total number of the basic behavior sample data.
In one possible implementation manner, the plurality of basic behavior sample data are divided into four data types of category single value, category multi-value, numerical value and vector according to the two dimensions of the value type and the value number.
In a possible implementation manner, the ith behavior embedded vector in all the behavior embedded vectors is spliced and combined with other embedded vectors in all the behavior embedded vectors according to a first preset rule, so as to obtain a first result; splicing and combining the ith basic behavior sample data and the characteristic value corresponding to the ith basic behavior sample data according to a second preset rule to obtain a second result; and obtaining the user characteristic information according to the first result and the second result.
In one possible implementation manner, generating the ith behavior fusion sequence information by using a first preset neural network based on the ith behavior embedding vector; and superposing the behavior fusion sequence information respectively corresponding to all the behavior embedding vectors and taking the superposition as the user behavior sequence information.
In one possible implementation manner, the user characteristic information and the user behavior sequence information are input into a second preset neural network to construct the user identification model.
In one possible implementation, the user identification model is optimized.
In one possible implementation manner, each layer of input data in the second neural network algorithm is optimized according to a BN algorithm, wherein the first layer of input data in the second neural network algorithm includes the first result, the second result, a third result and the user characteristic information, and the third result is a result obtained by splicing and combining all behavior embedded vectors.
The method disclosed in the above embodiment of the present invention may be applied to the processor 601 or implemented by the processor 601. The processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 601 or instructions in the form of software. The processor 601 may be a general purpose processor, a digital signal processor (DigitalSignalProcessor, DSP), an application specific integrated circuit (application specific IntegratedCircuit, ASIC), an off-the-shelf programmable gate array (FieldProgrammableGateArray, FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software elements in a decoding processor. The software elements may be located in a random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 602, and the processor 601 reads information in the memory 602 and performs the steps of the above method in combination with its hardware.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the processing units may be implemented within one or more application specific integrated circuits (ApplicationSpecificIntegratedCircuits, ASIC), digital signal processors (DigitalSignalProcessing, DSP), digital signal processing devices (dspev), programmable logic devices (ProgrammableLogicDevice, PLD), field programmable gate arrays (Field-ProgrammableGateArray, FPGA), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units configured to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
The intelligent device provided in this embodiment may be an intelligent device as shown in fig. 6, and may perform all steps of the user identification model building method shown in fig. 1-2, so as to achieve the technical effects of the user identification model building method shown in fig. 1-2, and detailed descriptions with reference to fig. 1-2 are omitted herein for brevity.
Fig. 7 is a schematic structural diagram of an intelligent device according to an embodiment of the present invention, and an intelligent device 700 shown in fig. 7 includes: at least one processor 701, memory 702, at least one network interface 704, and other user interfaces 703. The various components in the smart device 700 are coupled together by a bus system 705. It is appreciated that the bus system 705 is used to enable connected communications between these components. The bus system 705 includes a power bus, a control bus, and a status signal bus in addition to the data bus. But for clarity of illustration, the various buses are labeled as bus system 705 in fig. 7.
The user interface 703 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, a trackball, a touch pad, or a touch screen, etc.).
It is to be appreciated that memory 702 in embodiments of the invention may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and Direct memory bus RAM (DRRAM). The memory 702 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some implementations, the memory 702 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 7021 and application programs 7022.
The operating system 7021 contains various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application programs 7022 include various application programs such as a Media Player (Media Player), a Browser (Browser), and the like for realizing various application services. A program for implementing the method of the embodiment of the present invention may be contained in the application program 7022.
In the embodiment of the present invention, the processor 701 is configured to execute the method steps provided by the method embodiments by calling a program or an instruction stored in the memory 702, specifically, a program or an instruction stored in the application program 7022, for example, including:
acquiring a plurality of basic behavior data generated when a user using equipment currently uses the equipment; classifying the plurality of base behavior data; extracting h user characteristics corresponding to h-class basic behavior data; inputting the h user characteristics into a user identity recognition model, and acquiring the h probability, wherein the h probability is the probability indicating that the user identity of the currently used equipment is the host identity corresponding to the equipment; and adding all probabilities into a preset classifier, and finally identifying the user identity of the current equipment, wherein h is a positive integer.
The method disclosed in the above embodiment of the present invention may be applied to the processor 701 or implemented by the processor 701. The processor 701 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 701 or by instructions in the form of software. The processor 701 described above may be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software elements in a decoding processor. The software elements may be located in a random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 702, and the processor 701 reads information in the memory 702 and performs the steps of the method in combination with its hardware.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the processing units may be implemented within one or more application specific integrated circuits (Application Specific Integrated Circuits, ASIC), digital signal processors (Digital Signal Processing, DSP), digital signal processing devices (dspev, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field-Programmable Gate Array, FPGA), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
The server provided in this embodiment may be an intelligent device as shown in fig. 7, and may perform all steps of the user authentication method as shown in fig. 3, so as to achieve the technical effects of the user authentication method as shown in fig. 3, and the detailed description with reference to fig. 3 is omitted herein for brevity.
The embodiment of the invention also provides a storage medium (computer readable storage medium). The storage medium here stores one or more programs. Wherein the storage medium may comprise volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid state disk; the memory may also comprise a combination of the above types of memories.
When one or more programs in the storage medium are executable by one or more processors, the method for constructing the user identification model executed on the intelligent device side is realized.
The processor is used for executing a user identity recognition model building program or a user identity verification program stored in the memory so as to realize the following steps of a user identity recognition model building method or a user identity verification method executed on the intelligent equipment side:
acquiring a plurality of pieces of basic behavior sample data generated in the process of using equipment by a user; obtaining a behavior embedding vector corresponding to each piece of basic behavior sample data based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data; acquiring user characteristic information and user behavior sequence information based on all behavior embedding vectors; and constructing the user identity recognition model according to the user characteristic information and the user behavior sequence information.
In one possible implementation manner, the plurality of pieces of basic behavior sample data are classified according to preset dimensions; and obtaining a behavior embedding vector corresponding to the ith basic behavior data according to a preset method corresponding to the category to which the ith basic behavior data belongs, wherein i is a numerical value which is greater than or equal to 1 and less than or equal to the total number of the basic behavior sample data.
In one possible implementation manner, the plurality of basic behavior sample data are divided into four data types of category single value, category multi-value, numerical value and vector according to the two dimensions of the value type and the value number.
In a possible implementation manner, the ith behavior embedded vector in all the behavior embedded vectors is spliced and combined with other embedded vectors in all the behavior embedded vectors according to a first preset rule, so as to obtain a first result; splicing and combining the ith basic behavior sample data and the characteristic value corresponding to the ith basic behavior sample data according to a second preset rule to obtain a second result; and obtaining the user characteristic information according to the first result and the second result.
In one possible implementation manner, generating the ith behavior fusion sequence information by using a first preset neural network based on the ith behavior embedding vector; and superposing the behavior fusion sequence information respectively corresponding to all the behavior embedding vectors and taking the superposition as the user behavior sequence information.
In one possible implementation manner, the user characteristic information and the user behavior sequence information are input into a second preset neural network to construct the user identification model.
In one possible implementation, the user identification model is optimized.
In one possible implementation manner, each layer of input data in the second neural network algorithm is optimized according to a BN algorithm, wherein the first layer of input data in the second neural network algorithm includes the first result, the second result, a third result and the user characteristic information, and the third result is a result obtained by splicing and combining all behavior embedded vectors.
Or alternatively, the first and second heat exchangers may be,
acquiring a plurality of basic behavior data generated when a user using equipment currently uses the equipment; classifying the plurality of base behavior data; extracting h user characteristics corresponding to h-class basic behavior data; inputting the h user characteristics into a user identity recognition model, and acquiring the h probability, wherein the h probability is the probability indicating that the user identity of the currently used equipment is the host identity corresponding to the equipment; and adding all probabilities into a preset classifier, and finally identifying the user identity of the current equipment, wherein h is a positive integer.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of function in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (11)
1. The method for constructing the user identity recognition model is characterized by comprising the following steps of:
acquiring a plurality of pieces of basic behavior sample data generated in the process of using equipment by a user;
based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data, obtaining a behavior embedding vector corresponding to each piece of basic behavior sample data specifically comprises: classifying the plurality of pieces of basic behavior sample data according to preset dimensions; according to a preset method corresponding to the category to which the ith basic behavior data belongs, obtaining a behavior embedding vector corresponding to the ith basic behavior data, wherein i is a numerical value which is greater than or equal to 1 and less than or equal to the total number of the basic behavior sample data;
based on all the behavior embedding vectors, user characteristic information and user behavior sequence information are obtained, including: splicing and combining an ith behavior embedded vector in all the behavior embedded vectors with other embedded vectors in all the behavior embedded vectors according to a first preset rule to obtain a first result; splicing and combining the ith basic behavior sample data and the characteristic value corresponding to the ith basic behavior sample data according to a second preset rule to obtain a second result; obtaining the user characteristic information according to the first result and the second result, and generating the ith behavior fusion sequence information by using a first preset neural network based on the ith behavior embedding vector; superposing the behavior fusion sequence information respectively corresponding to all the behavior embedding vectors and taking the superposition as the user behavior sequence information;
And constructing the user identity recognition model according to the user characteristic information and the user behavior sequence information.
2. The method according to claim 1, wherein the preset dimensions include two dimensions of a value type and a value number, and the classifying the plurality of pieces of basic behavior sample data according to the preset dimensions specifically includes:
and dividing the plurality of basic behavior sample data into four data types of category single value, category multi-value, numerical value and vector according to the two dimensions of the value type and the value number.
3. The method according to claim 1, wherein the constructing the user identification model according to the user characteristic information and the user behavior sequence information specifically includes:
and inputting the user characteristic information and the user behavior sequence information into a second preset neural network to construct the user identity recognition model.
4. A method according to claim 3, wherein after said constructing said user identification model based on said user characteristic information and said user behavior sequence information, said method further comprises: and optimizing the user identity recognition model.
5. The method according to claim 4, wherein optimizing the user identification model specifically comprises:
and optimizing each layer of input data in the second preset neural network according to a BN algorithm, wherein the first layer of input data in the second preset neural network comprises the first result, the second result, a third result and the user characteristic information, and the third result is obtained by splicing and combining all behavior embedded vectors.
6. A method of user authentication, the method comprising:
acquiring a plurality of basic behavior data generated when a user using equipment currently uses the equipment;
classifying the plurality of base behavior data;
extracting h user characteristics corresponding to h-class basic behavior data;
inputting the h user characteristic into the user identity recognition model according to any one of claims 1-5, and obtaining an h probability, wherein the h probability is a probability indicating that the user identity of the currently used device is the host identity corresponding to the device;
and adding all probabilities into a preset classifier, and finally identifying the user identity of the current equipment, wherein h is a positive integer.
7. A user identification model construction apparatus, comprising:
the acquisition module is used for acquiring a plurality of pieces of basic behavior sample data generated in the process of using the equipment by a user;
the obtaining module is further configured to obtain, based on each piece of basic behavior sample data in the plurality of pieces of basic behavior sample data, a behavior embedding vector corresponding to each piece of basic behavior sample data, and specifically includes: classifying the plurality of pieces of basic behavior sample data according to preset dimensions; according to a preset method corresponding to the category to which the ith basic behavior data belongs, obtaining a behavior embedding vector corresponding to the ith basic behavior data, wherein i is a numerical value which is greater than or equal to 1 and less than or equal to the total number of the basic behavior sample data;
the determining module is used for acquiring user characteristic information and user behavior sequence information based on all the behavior embedding vectors, and comprises the following steps: splicing and combining an ith behavior embedded vector in all the behavior embedded vectors with other embedded vectors in all the behavior embedded vectors according to a first preset rule to obtain a first result; splicing and combining the ith basic behavior sample data and the characteristic value corresponding to the ith basic behavior sample data according to a second preset rule to obtain a second result; obtaining the user characteristic information according to the first result and the second result, and generating the ith behavior fusion sequence information by using a first preset neural network based on the ith behavior embedding vector; superposing the behavior fusion sequence information respectively corresponding to all the behavior embedding vectors and taking the superposition as the user behavior sequence information;
And the construction module is used for constructing the user identity recognition model according to the user characteristic information and the user behavior sequence information.
8. A user authentication apparatus, comprising:
the acquisition module is used for acquiring a plurality of basic behavior data generated when a user using the equipment currently uses the equipment;
the acquisition module is further used for classifying the plurality of basic behavior data; extracting h user characteristics corresponding to h-class basic behavior data; inputting the h user characteristic into the user identity recognition model according to any one of claims 1-6, and obtaining an h probability, wherein the h probability is a probability indicating that the user identity of the currently used device is the host identity corresponding to the device;
and the identification module is used for adding all the probabilities into a preset classifier and finally identifying the user identity of the current equipment, wherein h is a positive integer.
9. An intelligent device, comprising: a processor and a memory, the processor being configured to execute a user identification model construction program stored in the memory, to implement the user identification model construction method according to any one of claims 1 to 5.
10. An intelligent device, comprising: a processor and a memory, the processor being configured to execute a user authentication program stored in the memory to implement the user authentication method as claimed in claim 6.
11. A storage medium storing one or more programs executable by one or more processors to implement the user identity model construction method of any one of claims 1-5 or the user identity verification method of claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010509874.5A CN113742665B (en) | 2020-06-05 | 2020-06-05 | User identity recognition model construction and user identity verification methods and devices |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010509874.5A CN113742665B (en) | 2020-06-05 | 2020-06-05 | User identity recognition model construction and user identity verification methods and devices |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113742665A CN113742665A (en) | 2021-12-03 |
| CN113742665B true CN113742665B (en) | 2024-03-26 |
Family
ID=78727932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010509874.5A Active CN113742665B (en) | 2020-06-05 | 2020-06-05 | User identity recognition model construction and user identity verification methods and devices |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113742665B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699823A (en) * | 2014-01-08 | 2014-04-02 | 同济大学 | Identity authentication system based on user behavior pattern and method thereof |
| CN105335630A (en) * | 2014-07-09 | 2016-02-17 | 阿里巴巴集团控股有限公司 | Identity recognition method and identity recognition device |
| CN107819945A (en) * | 2017-10-30 | 2018-03-20 | 同济大学 | The handheld device navigation patterns authentication method and system of comprehensive many factors |
| CN108549709A (en) * | 2018-04-20 | 2018-09-18 | 福州大学 | Fusion method of the multi-source heterogeneous data based on range learning algorithm inside and outside block chain |
| CN108549806A (en) * | 2018-04-11 | 2018-09-18 | 西安电子科技大学 | The identity identifying method of behavior is slided and clicked based on user |
| CN108595923A (en) * | 2018-04-20 | 2018-09-28 | 北京元心科技有限公司 | Identity identifying method, device and terminal device |
| CN108647800A (en) * | 2018-03-19 | 2018-10-12 | 浙江工业大学 | A kind of online social network user missing attribute forecast method based on node insertion |
| EP3410328A1 (en) * | 2017-05-31 | 2018-12-05 | Deutsche Telekom AG | Method and system to distinguish between a human and a robot as a user of a mobile smart device |
| CN109858212A (en) * | 2019-01-21 | 2019-06-07 | 深圳市能信安科技股份有限公司 | Personal identification method, device and terminal for numerical ciphers soft keyboard |
| CN110163611A (en) * | 2019-03-18 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of personal identification method, device and relevant device |
| CN110516422A (en) * | 2019-08-30 | 2019-11-29 | 北京字节跳动网络技术有限公司 | Recognition methods, device, electronic equipment and the storage medium of user identity |
| CN110659742A (en) * | 2019-09-10 | 2020-01-07 | 阿里巴巴集团控股有限公司 | Method and device for acquiring sequence representation vector of user behavior sequence |
| CN110765939A (en) * | 2019-10-22 | 2020-02-07 | Oppo广东移动通信有限公司 | Identity recognition method and device, mobile terminal and storage medium |
| CN110796269A (en) * | 2019-09-30 | 2020-02-14 | 北京明略软件系统有限公司 | Method and device for generating model, and method and device for processing information |
| CN111163057A (en) * | 2019-12-09 | 2020-05-15 | 中国科学院信息工程研究所 | User identification system and method based on heterogeneous information network embedding algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2069993B1 (en) * | 2006-10-04 | 2016-03-09 | Behaviometrics AB | Security system and method for detecting intrusion in a computerized system |
-
2020
- 2020-06-05 CN CN202010509874.5A patent/CN113742665B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699823A (en) * | 2014-01-08 | 2014-04-02 | 同济大学 | Identity authentication system based on user behavior pattern and method thereof |
| CN105335630A (en) * | 2014-07-09 | 2016-02-17 | 阿里巴巴集团控股有限公司 | Identity recognition method and identity recognition device |
| EP3410328A1 (en) * | 2017-05-31 | 2018-12-05 | Deutsche Telekom AG | Method and system to distinguish between a human and a robot as a user of a mobile smart device |
| CN107819945A (en) * | 2017-10-30 | 2018-03-20 | 同济大学 | The handheld device navigation patterns authentication method and system of comprehensive many factors |
| CN108647800A (en) * | 2018-03-19 | 2018-10-12 | 浙江工业大学 | A kind of online social network user missing attribute forecast method based on node insertion |
| CN108549806A (en) * | 2018-04-11 | 2018-09-18 | 西安电子科技大学 | The identity identifying method of behavior is slided and clicked based on user |
| CN108549709A (en) * | 2018-04-20 | 2018-09-18 | 福州大学 | Fusion method of the multi-source heterogeneous data based on range learning algorithm inside and outside block chain |
| CN108595923A (en) * | 2018-04-20 | 2018-09-28 | 北京元心科技有限公司 | Identity identifying method, device and terminal device |
| CN109858212A (en) * | 2019-01-21 | 2019-06-07 | 深圳市能信安科技股份有限公司 | Personal identification method, device and terminal for numerical ciphers soft keyboard |
| CN110163611A (en) * | 2019-03-18 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of personal identification method, device and relevant device |
| CN110516422A (en) * | 2019-08-30 | 2019-11-29 | 北京字节跳动网络技术有限公司 | Recognition methods, device, electronic equipment and the storage medium of user identity |
| CN110659742A (en) * | 2019-09-10 | 2020-01-07 | 阿里巴巴集团控股有限公司 | Method and device for acquiring sequence representation vector of user behavior sequence |
| CN110796269A (en) * | 2019-09-30 | 2020-02-14 | 北京明略软件系统有限公司 | Method and device for generating model, and method and device for processing information |
| CN110765939A (en) * | 2019-10-22 | 2020-02-07 | Oppo广东移动通信有限公司 | Identity recognition method and device, mobile terminal and storage medium |
| CN111163057A (en) * | 2019-12-09 | 2020-05-15 | 中国科学院信息工程研究所 | User identification system and method based on heterogeneous information network embedding algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113742665A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Žliobaitė | Measuring discrimination in algorithmic decision making | |
| US10609050B2 (en) | Methods and systems for malware detection | |
| CN109684554B (en) | Method for determining potential users of news and news pushing method | |
| CN110377632B (en) | Litigation result prediction method, litigation result prediction device, litigation result prediction computer device and litigation result prediction storage medium | |
| CN109905385B (en) | Webshell detection method, device and system | |
| CN110990560B (en) | Judicial data processing method and system | |
| US20200193340A1 (en) | Business default prediction system and operation method thereof | |
| Chang et al. | Language model pre-training for hierarchical document representations | |
| CN112256886B (en) | Probability calculation method and device in atlas, computer equipment and storage medium | |
| Harane et al. | Comprehensive survey on deep learning approaches in predictive business process monitoring | |
| Althar et al. | Design and Development of Artificial Intelligence Knowledge Processing System for Optimizing Security of Software System | |
| CN112990530B (en) | Regional population quantity prediction method, regional population quantity prediction device, electronic equipment and storage medium | |
| Hao et al. | A novel method using LSTM-RNN to generate smart contracts code templates for improved usability | |
| CN112288279A (en) | Business risk assessment method and device based on natural language processing and linear regression | |
| CN113742665B (en) | User identity recognition model construction and user identity verification methods and devices | |
| Al Zaabi et al. | Android malware detection using static features and machine learning | |
| CN110969549B (en) | Judicial data processing method and system | |
| CN116542783A (en) | Risk assessment method, device, equipment and storage medium based on artificial intelligence | |
| CN116777642A (en) | Vehicle risk parameter prediction method and device based on ensemble learning model | |
| Gao et al. | Sharing runtime permission issues for developers based on similar-app review mining | |
| CN113408263A (en) | Criminal period prediction method and device, storage medium and electronic device | |
| CN117093715B (en) | Word stock expansion method, system, computer equipment and storage medium | |
| US20230080992A1 (en) | Content based security requirements | |
| Muntasir et al. | AntiPhishTuner: Multi-level approaches focusing on optimization by parameters tuning in phishing URLs detection | |
| CN113487316B (en) | Distributed payment system security processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |