CN112422480A - Method and device for determining account attribute, storage medium and electronic device - Google Patents

Method and device for determining account attribute, storage medium and electronic device Download PDF

Info

Publication number
CN112422480A
CN112422480A CN201910780096.0A CN201910780096A CN112422480A CN 112422480 A CN112422480 A CN 112422480A CN 201910780096 A CN201910780096 A CN 201910780096A CN 112422480 A CN112422480 A CN 112422480A
Authority
CN
China
Prior art keywords
account
identified
parameter
truth
determining
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.)
Granted
Application number
CN201910780096.0A
Other languages
Chinese (zh)
Other versions
CN112422480B (en
Inventor
黄引刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN201910780096.0A priority Critical patent/CN112422480B/en
Publication of CN112422480A publication Critical patent/CN112422480A/en
Application granted granted Critical
Publication of CN112422480B publication Critical patent/CN112422480B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/12—Applying verification of the received information
    • H04L63/126—Applying verification of the received information the source of the received data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services

Abstract

The invention discloses a method and a device for determining account attributes, a storage medium and an electronic device. Wherein, the method comprises the following steps: acquiring an account to be identified related to a target identity; acquiring a truth probability corresponding to the account to be identified according to the truth parameter of the account to be identified, wherein the truth probability is used for expressing the probability that the account to be identified is the account used by the target identity; and determining a real account and/or a suspicious account corresponding to the target identity from the account to be identified according to the truth probability corresponding to the account to be identified, wherein the real account is an account used by the target identity, and the suspicious account is an account used for simulating the target identity. The invention solves the technical problem that the fake account on the social network platform cannot be actively identified.

Description

Method and device for determining account attribute, storage medium and electronic device
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for determining account attributes, a storage medium and an electronic device.
Background
With the development of internet technology, fake identity accounts often appear on a social network platform, and rumor spreading or fraud activities are performed. In the prior art, no effective scheme can actively identify the fake accounts, and the fake accounts can only be passively found in a reporting mode of a user, so that an alarm prompt cannot be timely sent to a victim.
Aiming at the problem that the false account on the social network platform cannot be actively identified in the prior art, no effective solution is provided at present.
Disclosure of Invention
The embodiment of the invention provides a method and a device for determining account attributes, a storage medium and an electronic device, which are used for at least solving the technical problem that fake accounts on a social network platform cannot be actively identified.
According to an aspect of the embodiments of the present invention, a method for determining account attributes is provided, including: acquiring an account to be identified related to a target identity; acquiring a truth probability corresponding to the account to be identified according to the truth parameter of the account to be identified, wherein the truth probability is used for expressing the probability that the account to be identified is the account used by the target identity; and determining a real account and/or a suspicious account corresponding to the target identity from the account to be identified according to the truth probability corresponding to the account to be identified, wherein the real account is an account used by the target identity, and the suspicious account is an account used for simulating the target identity.
According to another aspect of the embodiments of the present invention, there is also provided an apparatus for determining an account attribute, including:
the first acquisition module is used for acquiring the account to be identified related to the target identity;
a second obtaining module, configured to obtain, according to the truth parameter of the account to be recognized, a truth probability corresponding to the account to be recognized, where the truth probability is used to represent a probability that the account to be recognized is an account used by the target identity;
a first determining module, configured to determine, according to the truth probability corresponding to the account to be identified, a real account and/or a suspicious account corresponding to the target identity from the account to be identified, where the real account is an account used by the target identity, and the suspicious account is an account used to simulate the target identity.
Optionally, the second obtaining module includes:
the device comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring a first trueness parameter of the account to be identified on the relative dimension in the social network data, and the first trueness parameter is associated with a first interaction operation between the account to be identified and the account having the relative relationship with the account to be identified in the social network data;
a second obtaining unit, configured to obtain a second degree of reality parameter of the account to be identified in a co-worker dimension in social network data, where the second degree of reality parameter is associated with a second interaction operation between the account to be identified and an account having a co-worker relationship with the account to be identified in the social network data;
a third obtaining unit, configured to obtain a third authenticity parameter of the account to be identified in a feature dimension, where the third authenticity parameter is associated with a feature value of the account to be identified;
and the fourth obtaining unit is used for obtaining the truth probability corresponding to the account to be identified according to the first truth parameter, the second truth parameter and the third truth parameter.
Optionally, the first trueness parameter is positively correlated with an operation parameter of a first interactive operation between the account to be recognized and an account having a relationship with the account to be recognized in the social network data, where the operation parameter of the first interactive operation at least includes one of: the number of times, frequency and operation duration of the first interactive operation;
the second truth parameter positively correlates with an operation parameter of a second interactive operation between the account to be identified and an account having a co-worker relationship with the account to be identified in the social network data, wherein the operation parameter of the second interactive operation at least includes one of the following: the number of times, frequency, and operation duration of the second interactive operation.
Optionally, the fourth obtaining unit includes:
and the weighting subunit is configured to perform weighted summation on the first, second, and third trueness parameters to obtain the trueness probability, where preset weights corresponding to the first, second, and third trueness parameters are β 1, β 2, and β 3, respectively, where β 1+ β 2+ β 3 is equal to 1, β 1 is greater than or equal to 0, and β 2 is less than or equal to 1, and β 3 is greater than or equal to 1.
Optionally, the first obtaining unit includes:
the first acquiring subunit is used for acquiring a first account set having a relationship with the account to be identified from the social network data;
a first determining subunit, configured to determine, according to a first interaction operation between the account i to be identified and an account t in the first account set in the social network data, a first affinity parameter between the account i to be identified and the account t;
a second determining subunit, configured to determine, according to a first affinity parameter between the account i to be recognized and the account t, a first reliability parameter p1 for the account t to perform identity authentication on the account i to be recognizedt，iWherein the first credibility parameter p1t，iIs positively correlated with the value of the first intimacy parameter;
a third determining subunit, configured to determine, by running the following formula multiple times, a first authenticity parameter PR1(i) of an ith account in the account to be identified:
Figure BDA0002176293500000031
wherein the initial value of PR1(i) is a random value between 0 and 1, p1t，iAnd performing identity authentication on the ith account in the account to be identified for the tth account in the first account set, wherein PR1(t) is a first authenticity parameter of the tth account, and alpha1 is a constant.
Optionally, the second obtaining unit includes:
the second acquiring subunit is configured to acquire, from the social network data, a second account set in which the account to be identified has a coworker relationship;
a fourth determining subunit, configured to determine, according to a second interaction operation between the account i to be identified and an account k in the second account set in the social network data, a second affinity parameter between the account i to be identified and the account k;
a fifth determining subunit, configured to determine, according to a second affinity parameter between the account i to be recognized and the account k, a second reliability parameter p2 for the account k to perform identity authentication on the account i to be recognizedk，iWherein the second credibility parameter p2k，iThe value of (a) is positively correlated with the value of the second intimacy parameter;
a sixth determining subunit, configured to determine, by running the following formula multiple times, a second trueness parameter PR2(i) of an ith account in the account to be recognized:
Figure BDA0002176293500000041
wherein the initial value of PR2(i) is a random value between 0 and 1, p2k，iAnd a second credibility parameter for performing identity authentication on the ith account in the account to be identified for the kth account in the second account set, wherein PR2(k) is a second authenticity parameter of the kth account, and the alpha2 is a constant.
Optionally, the third obtaining unit includes:
an input subunit, configured to input the feature value of the account to be recognized into a target network model, so as to obtain the third authenticity parameter of the account to be recognized, where the third authenticity parameter of the account to be recognized is output by the target network model, the target network model is obtained by training an initial network model using the feature value of a sample account, an error between the third authenticity parameter of the sample account output by the target network model and a predetermined third authenticity parameter of the sample account when the training is completed satisfies a first condition, and the feature value of the account to be recognized at least includes one of: the first truth parameter of the account to be identified, the second truth parameter of the account to be identified, whether the account to be identified is reported or not and whether the parameter information of the account to be identified is consistent with the identity card information or not.
Optionally, the first determining module includes:
the first determining unit is used for determining that the account to be identified with the maximum truth probability is the real account corresponding to the target identity;
and the second determining unit is used for determining that the account to be identified is a suspicious account corresponding to the target identity, wherein the truth probability is smaller than a preset value.
Optionally, the apparatus further comprises:
the third acquisition module is used for acquiring a first suspicious account a and a second suspicious account b in the suspicious accounts;
the establishing module is used for establishing a friend relationship network formed by accounts having friend relationship with the a and/or the b by taking the a and the b as double centers, wherein the friend relationship network comprises n vertexes and s edges, each vertex is used for representing one account in the friend relationship network, each edge is connected with two vertexes having friend relationship, and n and s are integers larger than 1;
a marking module, configured to mark an adjacency matrix a of the friend relationship network, where a is directly connected to b when there is an edge between a and ba，bWhen there is no edge between a and b, a is 1a，bWhen a is 0, A is ba，b＝1；
A second determining module, configured to determine a weight value γ of each vertex in the friendship network according to the following formula: ax ═ γ x, where x is an n-dimensional vector, where x includes probability of truth for n vertices in the friendship network, [ PR (1), PR (2), PR (3), ….. PR (n) ], PR (i) is probability of truth for vertex i in the friendship network, 1 ≦ i ≦ n;
a third determination module for determining the matrix Ba，bDetermining the relative magnitude of the degree of truth of the a and the B, wherein Ba，b＝exp(γa)/exp(γb)，γaIs the weight value of the a in the friend relationship network, gammabIs the weight value of the B in the friend relationship network, Ba，bThe larger the probability of truth representing a versus b.
Optionally, the apparatus further comprises:
an iteration module, configured to perform N iterations on the matrix B to obtain a matrix C, where C is equal to BNN is an integer greater than 1;
the calculation module is used for calculating the truth score of the suspicious account according to the following formula:
Figure BDA0002176293500000061
wherein xn represents the number of the accounts to be identified in the target account set;
and the fourth determining module is used for determining the truth probability value of the suspicious account according to the truth score, wherein the truth probability value and the truth score are in a direct proportion relation.
Optionally, the apparatus further comprises:
and the sending module is used for sending prompt information to the account which carries out information interaction with the suspicious account, wherein the prompt information is used for prompting the existence of the suspicious account to the account.
According to still another aspect of the embodiments of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is configured to execute the above method for determining account attributes when running.
According to another aspect of the embodiments of the present invention, there is also provided an electronic apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for determining the account attribute through the computer program.
In the embodiment of the invention, the set of the target accounts related to the target identity is obtained, then the truth probability of the account to be identified in the set is calculated in multiple dimensions, and whether the account to be identified is a suspicious account or not is determined through the truth probability, namely, a fake account imitating the real account of the target identity is determined, so that the aim of actively and effectively identifying the fake account on the social network platform is fulfilled, the technical effect of reducing the probability of the incidents of rumor propagation and/or telecom fraud and the like caused by fake accounts in the social network platform is realized, and the technical problem that the fake account on the social network platform cannot be actively identified is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a diagram illustrating a hardware environment of an alternative account attribute determination method according to an embodiment of the present invention;
FIG. 2 is a flow chart of an alternative account attribute determination method according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating an application environment of an alternative account attribute determination method according to an embodiment of the present invention;
FIG. 4 is an input-output diagram of an alternative target network model according to an embodiment of the invention;
FIG. 5 is a schematic diagram of an alternative two-hub network in accordance with embodiments of the present invention;
FIG. 6 is an alternative interaction flow diagram of a method for determining account attributes according to an embodiment of the present invention;
fig. 7 is a block diagram of an alternative configuration of the account attribute determination apparatus according to an embodiment of the present invention;
fig. 8 is a block diagram of still another alternative structure of the account attribute determination apparatus according to the embodiment of the present invention;
fig. 9 is a schematic structural diagram of an alternative electronic device according to an embodiment of the invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In order to solve the foregoing technical problem, an embodiment of the present invention provides a method for determining an account attribute. Fig. 1 is a schematic diagram of a hardware environment of an alternative account attribute determination method according to an embodiment of the present invention, and as shown in fig. 1, the hardware environment may include, but is not limited to, a first user device 102, a network 110, a server 112, and a second user device 202, where the first user device 102 may include, but is not limited to, a memory 104, a processor 106, and a display 108, the server 112 may include, but is not limited to, a database 114 and a processing engine 116, and the second user device 202 may include, but is not limited to, a memory 204, a processor 206, and a display 208. The user device may be, but not limited to, a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, and a Mobile Internet Device (MID), a PAD, etc. In the instant messaging scenario shown in fig. 1, an account is logged in the first user equipment 102, an account is logged in the second user equipment 202, and the two accounts may interact with each other, where an optional implementation step of the method for determining the account attribute in the embodiment of the present invention is as follows:
step S102, the account on the first user equipment 102 sends the first data information to the network 110, and instructs the network 110 to send the first data information to the account on the second user equipment 202, optionally, the first data information may be call origination information, for example, "ha, u";
step S104, the network 110 forwards the first data information to the server 112;
step S106, after receiving the first data message, the server 112 identifies an account on the first user equipment 102 and an account on the second user equipment 202, determines whether the two accounts are suspicious accounts, directly sends the first data message to the second user equipment 202 if the accounts on the two equipment are both real accounts, and sends a prompt message while sending the first data message to the second user equipment 202 if the accounts on the first user equipment 102 are judged to be suspicious accounts, which indicates that the account of the first user equipment 102 is suspicious;
step S108, the server 112 determines that the accounts on the two devices are both real accounts, directly sends the second data message returned by the second user device 202 to the network, and if the account on the second user device 202 is determined to be a suspicious account, sends a prompt message while sending the second data message, where the prompt message is used to indicate that the account on the second user device 202 is a suspicious account;
in step S110, the network 110 feeds back the information received from the server 112 to the first user equipment 102.
It should be noted that the above scenario may not only be applied to interaction of instant messaging, but also be applied to any interaction operations between any two accounts on a social network platform, such as private letter, message leaving, approval, comment, forwarding, red package sending, account transferring, and rewarding.
Optionally, in the embodiment of the present invention, the above method for determining the account attribute may be, but is not limited to, applied to the server 112, and the first user device 102 and the second user device 202 may be, but is not limited to, terminal devices such as a mobile phone, a tablet computer, a notebook computer, and a PC that support running an application client. The server 112, the first user device 102 and the second user device 202 may, but are not limited to, enable data interaction through a network, which may include, but is not limited to, a wireless network or a wired network. Wherein, this wireless network includes: bluetooth, WIFI, and other networks that enable wireless communication. Such wired networks may include, but are not limited to: wide area networks, metropolitan area networks, and local area networks. The above is merely an example, and this is not limited in this embodiment.
Optionally, in step S106, the server 112 identifies the account on the first user device 102 and the account on the second user device 202, and determines whether the two accounts are suspicious accounts, which may be implemented by the following steps: acquiring an account to be identified related to a target identity; acquiring a truth probability corresponding to the account to be identified according to the truth parameter of the account to be identified, wherein the truth probability is used for expressing the probability that the account to be identified is the account used by the target identity; and determining a real account and/or a suspicious account corresponding to the target identity from the account to be identified according to the truth probability corresponding to the account to be identified, wherein the real account is an account used by the target identity, and the suspicious account is an account used for simulating the target identity.
Fig. 2 is a flowchart of an optional account attribute determination method according to an embodiment of the present invention. As shown in fig. 2, the method includes:
step S202, acquiring an account to be identified related to a target identity;
step S204, acquiring a truth probability corresponding to the account to be identified according to the truth parameter of the account to be identified, wherein the truth probability is used for expressing the probability that the account to be identified is the account used by the target identity;
step S206, determining a real account and/or a suspicious account corresponding to the target identity from the account to be identified according to the truth probability corresponding to the account to be identified, wherein the real account is an account used by the target identity, and the suspicious account is an account used for simulating the target identity.
Optionally, the target identity may include, but is not limited to, an individual user, an enterprise user, a private organization user, an official organization user, and any user that can register an account on the social network platform, which is not limited in this embodiment of the present invention.
Optionally, in this embodiment, the method for determining the account attribute may be applied to a hardware environment formed by the first client 302, the server 304, and the second client 306 shown in fig. 3, and the execution subject of each step shown in fig. 2 may be, but is not limited to, the server 304. As shown in fig. 3, the server 304 receives the first data message sent by the client 302, identifies the account on the first client 302 and the account on the second client 306, determines whether the two accounts are suspicious accounts, directly sends the first data message to the second client 306 if the accounts on the two clients are both real accounts, and sends a prompt message while sending the first data message to the second client 306 if the account on the first client 302 is determined to be suspicious, which indicates that the account of the first client 302 is suspicious. The server 304 determines that the accounts on the two devices are both real accounts, and directly sends the second data information returned by the second client 306 to the first client 302, and if the accounts on the second client 306 are determined to be suspicious accounts, sends the prompt message while sending the second data information.
The processing steps in the server 304 include:
step S301, acquiring an account to be identified related to a target identity;
step S302, acquiring a truth probability corresponding to the account to be identified according to the truth parameter of the account to be identified, wherein the truth probability is used for expressing the probability that the account to be identified is the account used by the target identity;
step S303, determining a real account and/or a suspicious account corresponding to the target identity from the account to be identified according to the truth probability corresponding to the account to be identified, wherein the real account is an account used by the target identity, and the suspicious account is an account used for simulating the target identity.
In an optional embodiment, determining a real account and/or a suspicious account corresponding to a target identity from an account to be identified according to a probability of validity corresponding to the account to be identified includes:
determining the account to be identified with the maximum truth probability as a real account corresponding to the target identity;
and determining the suspicious account corresponding to the target identity as the account to be identified with the truth probability smaller than the preset value.
In the acquired accounts to be identified, there may be only one real account, or there may be multiple real accounts, or all of them may be suspicious accounts, and the target identity does not register an account in the social platform.
In an optional embodiment, acquiring the account to be identified may be implemented by acquiring a target account set associated with a target identity, and mainly includes the following steps:
s1, acquiring first parameter information of the first account, where the first parameter information matches with the target identity, and the first parameter information at least includes one of: account head, account nickname and account signature;
s2, screening a second account with the same or similar parameter information as the first account in the social network data;
and S3, determining the first account and the second account as accounts to be identified in the target account set.
Alternatively, the first parameter information may be an avatar, a nickname, a signature, etc. used by the account number, or may be any parameter information that can determine the identity of the target, such as a background picture, a cover picture, etc. For example, star a has registered an account 1 on a first social networking platform, using his own photograph as an avatar, and his own real name "AXX" as a nickname. If account 2 is screened from the social network data, the head portrait and the nickname used are completely consistent with account 1, and account 2 and account 1 can be identified to have the same parameter information. If the screened account 3 uses a different head portrait from that of account 1 but also is a photo of star a, the used nickname is "a _ XX", and one underline is added relative to the nickname of account 1, so that account 3 can be identified to have similar parameter information with account 1. And placing the accounts 1, 2 and 3 into a target account set to be used as accounts to be identified to wait for identification.
Optionally, the trueness parameter of the account may be multidimensional, which may further ensure the credibility of the trueness probability value. Multidimensional trueness parameters may include, but are not limited to: the truth parameters of the account to be identified in the parent dimension, the co-worker dimension and the attribute dimension of the account to be identified can also comprise the truth parameters in the friend dimension.
In an optional embodiment, obtaining the authenticity probability corresponding to the account to be identified according to the authenticity parameters of the account to be identified in the target account set in multiple dimensions may be implemented by the following steps:
s1, acquiring a first truth parameter of the account to be identified on the relative dimension in the social network data, wherein the first truth parameter is associated with a first interaction operation between the account to be identified and the account having the relative relationship with the account to be identified in the social network data;
s2, acquiring a second degree of reality parameter of the account to be identified on a co-worker dimension in the social network data, wherein the second degree of reality parameter is associated with a second interaction operation between the account to be identified in the social network data and an account having a co-worker relationship with the account to be identified;
s3, acquiring a third truth parameter of the account to be identified in the feature dimension, wherein the third truth parameter is associated with the feature value of the account to be identified;
and S4, acquiring the truth probability corresponding to the account to be identified according to the first truth parameter, the second truth parameter and the third truth parameter.
Optionally, the first trueness parameter is positively correlated with an operation parameter of a first interaction operation between the account to be identified and an account having a relationship with the account to be identified in the social network data, where the operation parameter of the first interaction operation at least includes one of the following: the number of times, frequency, duration of operation of the first interactive operation. The first interaction may include, but is not limited to, any interaction such as instant messaging, private letter, message leaving, approval, comment, forwarding, red packet, transfer, reward, and the like. The relationship may be a relationship having a direct blood relationship with the account to be identified, or may have no blood relationship but a relationship having a relationship, for example, "brother" of the account to be identified, or "sao" of the account to be identified. The more the first interactive operation times between the account to be identified and the account having the relationship, the higher the frequency and the longer the interactive time, the larger the value of the first truth parameter of the account to be identified is.
Optionally, the second degree of truth parameter is positively correlated with an operation parameter of a second interactive operation between the account to be identified and the account having a co-worker relationship with the account to be identified in the social network data, where the operation parameter of the second interactive operation at least includes one of: the number of second interactions, frequency, duration of operation. The second interaction may include, but is not limited to, any interaction such as instant messaging, private letter, message leaving, approval, comment, forwarding, red packet, transfer, reward, and the like. The determination of the relationship of the colleagues may be that the account to be identified belongs to the same company or administrative department, or that the account does not belong to the same company but is located in the same work group. The larger the second interactive operation frequency, the higher the frequency and the longer the interactive time between the account to be identified and the account having the co-worker relationship, the larger the value of the second truth parameter of the account to be identified is.
Optionally, when the target identity is an enterprise user or other organization user, the co-worker relationship or the relative relationship may be set as an account having a cooperative relationship, for example, a supplier, a client, a subsidiary company, a parent company, a direct supervision department, and the like of an enterprise, as long as the user can verify the truth of the account, which is not limited in the embodiment of the present invention.
Alternatively, the characteristic value of the account to be identified may be a characteristic value used for verifying the attribute of the account to be identified, for example: whether the real head portrait of the account is consistent with the head portrait of the target identity card corresponding to the real head portrait, whether the real name of the account is consistent with the name of the target identity card corresponding to the real name of the account, whether the account is reported as a fake account, and the like, and the characteristic value can also comprise a first truth parameter and/or a second truth parameter of the account to be identified.
Optionally, obtaining the truth probability corresponding to the account to be identified according to the first truth parameter, the second truth parameter and the third truth parameter may be implemented by the following steps: and performing weighted summation on the first, second and third truth parameters to obtain the truth probability, wherein the preset weights corresponding to the first, second and third truth parameters are respectively beta 1, beta 2 and beta 3, beta 1+ beta 2+ beta 3 is 1, and beta 1, beta 2 and beta 3 are more than or equal to 0 and less than or equal to 1.
The corresponding formula is as follows:
score(i)＝β1*PR1(i)+β2*PR2(i)+β3*PR3(i)。
wherein β 1, β 2, β 3 are constants that are set in advance, and the values of β 1, β 2, β 3 can be specifically set according to the specific situation of the target identity. For example, when the number of relatives of the target identity is large and the number of coworkers is small, the value of β 1 may be set to be large and the value of β 2 may be set to be small, and when the number of relatives of the target identity is small and the number of coworkers is large, the value of β 1 may be set to be small and the value of β 2 may be set to be large. When the value of the beta 1 is 0, the fact that the account to be identified has no dimension of relatives, namely the truth parameter, is shown, and when the value of the beta 2 is 0, the fact that the account to be identified has no dimension of coworkers, namely the first truth verification parameter.
Optionally, a liveness parameter for the influential buddy dimension may also be set. For example, account a and account B are in a friend relationship, the identity of account B is a relatively influential celebrity or organization, and if account B verifies the authenticity of account a, it can be used as an authenticity parameter with a reference value.
In an optional embodiment, obtaining a first trueness parameter of an account to be identified in a dimension of a relative of the social network data may be implemented by the following steps:
s1, acquiring a first account set having a relationship with the account to be identified from the social network data;
s2, determining a first affinity parameter between the account i to be identified and the account t in the first account set according to a first interaction operation between the account i to be identified and the account t in the first account set in the social network data;
s3, according to the first intimacy parameter between the account i to be identified and the account t, determining the first possibility that the account t carries out identity authentication on the account i to be identifiedConfidence parameter p1t，iWherein the first credibility parameter p1t，iThe value of (a) is positively correlated with the value of the first intimacy parameter;
s4, determining a first truth parameter PR1(i) of the ith account in the accounts to be identified by running the following formula for multiple times:
Figure BDA0002176293500000141
wherein the initial value of PR1(i) is a random value between 0 and 1, p1t，iThe first credibility parameter is used for carrying out identity authentication on the ith account in the account to be identified for the tth account in the first account set, PR1(t) is a first authenticity parameter of the tth account, and alpha1 is a constant.
Optionally, the obtaining of the first account set having a relationship with the account to be identified may be extracting a relationship network having a relationship with the account to be identified from the social network data, and the method for extracting the relationship network may use an existing method in the prior art, which is not limited in the embodiment of the present invention.
Alternatively, the first affinity parameter between the account i to be recognized and the account t may be implemented by the following formula:
Figure BDA0002176293500000151
the method comprises the following steps that a terminal account is a first account set, a first account set is a second account set, wherein the terminal account is a second account set, the terminal account is a third account set, the terminal account is a fourth account set, and the terminal account is a third account set. Optionally, the more the number of first interaction operations between the account i and the account t is, the higher the frequency is, and the longer the interaction duration is, the closer the contact between the account i and the account t is, and the larger the first affinity parameter between the account i and the account t is.
First credibility parameter p1 for account t to identify account i to be recognizedt，iCan pass throughThe following formula is calculated:
Figure BDA0002176293500000152
wherein r ist，iIs the probability value r of the relationship between account t and account ij，iThe probability value of the relationship between the account j and the account i, the tightness (t, i) is a first intimacy parameter between the account t and the account i, and the tightness (j, i) is a first intimacy parameter between the account j and the account t. r ist，iThe larger the number is, the more the account t actively contacts with the account i, the larger the tightness (t, i) is, the larger the first intimacy parameter of the account t and the account i is, and the p1t，iThe larger the value, the higher the trustworthiness of account t in verifying account i.
The first credibility parameter p1 to be acquiredt，iSubstituting the formula:
Figure BDA0002176293500000153
and obtaining a first truth parameter PR1(i) of the ith account in the account to be identified through a plurality of iterations.
In an optional embodiment, the obtaining of the second trueness parameter of the account to be identified on the dimension of the coworkers in the social network data may be implemented by the following steps:
s1, acquiring a second account set with co-worker relationship of the account to be identified from the social network data;
s2, determining a second affinity parameter between the account i to be identified and the account k in the second account set according to a second interaction operation between the account i to be identified and the account k in the social network data;
s3, according to the second intimacy parameter between the account i to be identified and the account k, determining a second credibility parameter p2 for the account k to perform identity authentication on the account i to be identifiedk，iWherein the second confidence level p2k，iThe value of (a) is positively correlated with the value of the second intimacy degree parameter;
determining a second truth parameter PR2(i) of the ith account in the account to be identified by running the following formula for a plurality of times:
Figure BDA0002176293500000161
wherein the initial value of PR2(i) is a random value between 0 and 1, p2k，iAnd a second credibility parameter for performing identity authentication on the ith account in the account to be identified for the kth account in the second account set, wherein PR2(k) is a second authenticity parameter of the kth account, and the alpha2 is a constant.
Alternatively, the calculation method of the parameters in the above formula is similar to that in the first degree of truth parameter calculation method, and the second degree of truth parameter may be calculated by the formula in the first degree of truth parameter calculation method.
Alternatively, the probability values that account i and account k are colleagues may be counted in the following manner:
Figure BDA0002176293500000162
in the direct co-workers, cnt (k, i) + 1, and in the same workgroup, cnt (k, i) + 1.
In an optional embodiment, the obtaining of the third trueness parameter of the account to be identified in the feature dimension may be implemented by the following steps:
s1, inputting the characteristic value of the account to be recognized into a target network model to obtain a third truth parameter of the account to be recognized output by the target network model, wherein the target network model is obtained by training the initial network model by using the characteristic value of the sample account, when the training is completed, the error between the third truth parameter of the sample account output by the target network model and the predetermined third truth parameter of the sample account meets a first condition, and the characteristic value of the account to be recognized at least comprises one of the following values: the first truth parameter of the account to be identified, the second truth parameter of the account to be identified, whether the account to be identified is reported or not and whether the parameter information of the account to be identified is consistent with the identity card information or not.
Fig. 4 is a schematic input/output diagram of an optional target network model according to an embodiment of the present invention, and as shown in fig. 4, before inputting the feature value of the account to be recognized into the target network model, the target network model may be trained by the following method:
collecting a negative sample, a positive sample and a characteristic value of a known identity account, wherein the negative sample is a suspicious account, and the positive sample is a real account;
collecting the collected data<Xi,yi>And performing model training by substituting the training samples into the following formulas to obtain parameters W1, W2, W3, b1, b2 and b3 of the target network model:
Figure BDA0002176293500000171
F(Xi)＝f(f(Xi*W1+b1)*W2+b2)*W3+b3
wherein f is an activation function, F (xi) represents the credibility parameter of the user selecting x friend certificates, the larger F (xi) is, the higher the credibility is, and 0<F (Xi) 1 ≦ Xi, which is the characteristic value of the ith account, yiIs the y variable collected from the ith record, when account i is a suspicious account, yiThe value is 0, when the user i is a real account, yiThe value is 1;
and stopping the training of the target network model when the training times reach a first preset threshold value and/or the parameter change of the target network model is smaller than a second preset threshold value.
Alternatively, the input characteristic values may include, but are not limited to, a first authenticity parameter PR1, a second authenticity parameter PR2, whether the real avatar of the account is consistent with the avatar of the target identity corresponding thereto, whether the real name of the account is consistent with the avatar of the target identity corresponding thereto, whether the account has been reported as a fake account, and the like.
In an optional embodiment, after determining a suspicious account in the account to be identified according to the truth probability corresponding to the account to be identified, the account with the highest truth probability value may be determined according to the truth probability value, and other accounts may all be determined as suspicious accounts, and if the relative suspicious probability between any two accounts in the set is to be compared, the method may be implemented by the following steps:
s1, acquiring a first suspicious account a and a second suspicious account b in the suspicious accounts;
s2, establishing a friend relationship network formed by accounts having friend relationship with the first suspicious account a and/or the second suspicious account b by taking the first suspicious account a and the second suspicious account b as double centers, wherein the friend relationship network comprises n vertexes and S edges, each vertex is used for representing one account in the friend relationship network, each edge is connected with two vertexes having friend relationship, and n and S are integers greater than 1; as shown in fig. 5, it can be considered as a schematic diagram of an ego network (ego network) with user i and user j as dual centers;
s3, marking an adjacency matrix A of the friend relation network, wherein A is directly connected with b when a is in direct connection with ba，bWhen there is no edge between a and b, a is 1a，b0 when a is ba，b＝1；
S4, determining the weight value gamma of each vertex in the friend relationship network according to the following formula: ax is n-dimensional vector, x comprises the truth probability corresponding to n vertexes in the friend relationship network, x is [ PR (1), PR (2), PR (3), ….. PR (n) ], PR (i) is the truth probability corresponding to the vertex i in the friend relationship network, and i is more than or equal to 1 and less than or equal to n;
s5, according to the matrix Ba，bDetermining the relative sizes of the truth degrees of the first suspicious account a and the second suspicious account B, wherein Ba，b＝exp(γa)/exp(γb)，γaIs the weight value of the a in the friend relationship network, gammabIs the weighted value of the second suspicious account B in the friend relationship network, Ba，bThe larger the probability of truth representing a versus b.
Optionally according to matrix Ba，bAfter determining the relative sizes of the truth degrees of the first suspicious account a and the first suspicious account b, the method further comprises the following steps:
s1, for matrix B warpAnd repeating N times of iterations to obtain a matrix C, wherein C is BNN is an integer greater than 1;
s2, calculating the truth score of the suspicious account according to the following formula:
Figure BDA0002176293500000191
Figure BDA0002176293500000192
wherein xn represents the number of the accounts to be identified in the target account set;
and S3, determining the truth probability value of the suspicious account according to the truth score, wherein the truth probability value and the truth score are in a direct proportion relation.
In an optional embodiment, after determining a suspicious account in the account to be identified according to the probability of validity corresponding to the account to be identified, the method further includes: and sending prompt information to the account which carries out information interaction with the suspicious account, wherein the prompt information is used for prompting the existence of the suspicious account to the account.
Fig. 6 is an alternative interaction flowchart of the method for determining account attributes according to the embodiment of the present invention, as shown in fig. 6, the method includes:
step S601, the account A initiates communication to the account B on the social platform C;
step S602, the social platform C identifies all accounts related to the identity of the account B, which may not be limited to one of the social platforms, and may acquire the account related to the account B from a comprehensive database of a plurality of social platforms;
step S603, if the account B is identified as a suspicious account, sending prompt information to the account A to remind the account A of paying attention to risks, and if the account B is identified as a real account, not sending the prompt information and normally performing exchange forwarding;
step S604, if the account B is a true account, and the false account B from other suspicious accounts is identified, sending a prompt message to the account B to remind the account B of counterfeit account and paying attention to risks.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
According to another aspect of the embodiment of the present invention, there is further provided an account attribute determining apparatus for implementing the account attribute determining method. Fig. 7 is a block diagram of an alternative structure of an account attribute determining apparatus according to an embodiment of the present invention, as shown in fig. 7, the apparatus includes:
a first obtaining module 702, configured to obtain an account to be identified related to a target identity;
a second obtaining module 704, configured to obtain, according to the truth parameter of the account to be identified, a truth probability corresponding to the account to be identified, where the truth probability is used to indicate a probability that the account to be identified is an account used by the target identity;
the first determining module 706 is configured to determine, according to the truth probability corresponding to the account to be identified, a real account and/or a suspicious account corresponding to the target identity from the account to be identified, where the real account is an account used by the target identity, and the suspicious account is an account used by the simulated target identity.
Optionally, as shown in fig. 8, the second obtaining module 704 includes:
a first obtaining unit 7041, configured to obtain a first trueness parameter of the account to be identified in the social network data in the relative dimension, where the first trueness parameter is associated with a first interaction operation between the account to be identified in the social network data and an account having a relative relationship with the account to be identified;
a second obtaining unit 7042, configured to obtain a second degree of reality parameter of the account to be identified on a co-worker dimension in the social network data, where the second degree of reality parameter is associated with a second interaction operation between the account to be identified in the social network data and an account having a co-worker relationship with the account to be identified;
a third obtaining unit 7043, configured to obtain a third authenticity parameter of the account to be identified in the feature dimension, where the third authenticity parameter is associated with the feature value of the account to be identified;
a fourth obtaining unit 7044, configured to obtain, according to the first degree of truth parameter, the second degree of truth parameter, and the third degree of truth parameter, the degree of truth probability corresponding to the account to be identified.
Optionally, the first trueness parameter is positively correlated with an operation parameter of a first interaction operation between the account to be identified and an account having a relationship with the account to be identified in the social network data, where the operation parameter of the first interaction operation at least includes one of the following: the frequency, frequency and operation duration of the first interactive operation;
the second truth parameter positively correlates with an operation parameter of a second interactive operation between the account to be identified and the account having a co-worker relationship with the account to be identified in the social network data, wherein the operation parameter of the second interactive operation at least includes one of the following: the number of second interactions, frequency, duration of operation.
Optionally, the fourth obtaining unit includes:
and the weighting subunit is used for weighting and summing the first truth parameter, the second truth parameter and the third truth parameter to obtain the truth probability, wherein the preset weights corresponding to the first truth parameter, the second truth parameter and the third truth parameter are respectively beta 1, beta 2 and beta 3, beta 1+ beta 2+ beta 3 is 1, beta 1 is more than or equal to 0 and less than or equal to 1, beta 2 is more than or equal to 0 and less than or equal to 1, and beta 3 is more than or equal to 0 and less than or equal to 1.
Optionally, the first obtaining unit includes:
the first acquiring subunit is used for acquiring a first account set having a relationship with an account to be identified from the social network data;
the first determining subunit is configured to determine, according to a first interaction operation between an account i to be identified in the social network data and an account t in the first account set, a first affinity parameter between the account i to be identified and the account t;
a second determining subunit, configured to determine, according to the first affinity parameter between the account i to be recognized and the account t, a first reliability parameter p1 for the account t to perform identity authentication on the account i to be recognizedt，iWherein the first credibility parameter p1t，iThe value of (a) is positively correlated with the value of the first intimacy parameter;
a third determining subunit, configured to determine the first degree of truth parameter PR1(i) of the ith account in the account to be recognized by running the following formula multiple times:
Figure BDA0002176293500000221
wherein the initial value of PR1(i) is a random value between 0 and 1, p1t，iAnd performing identity authentication on the ith account in the account to be identified for the tth account in the first account set, wherein PR1(t) is a first authenticity parameter of the tth account, and alpha1 is a constant.
Optionally, the second obtaining unit includes:
the second acquiring subunit is used for acquiring a second account set of which the account to be identified has a co-worker relationship from the social network data;
a fourth determining subunit, configured to determine, according to a second interaction operation between the account i to be identified in the social network data and the account k in the second account set, a second affinity parameter between the account i to be identified and the account k;
a fifth determining subunit, configured to determine, according to the second affinity parameter between the account i to be recognized and the account k, a second reliability parameter p2 for the account k to perform identity authentication on the account i to be recognizedk，iWherein the second confidence level p2k，iThe value of (a) is positively correlated with the value of the second intimacy degree parameter;
a sixth determining subunit, configured to determine a second trueness parameter PR2(i) of an ith account in the account to be recognized by running the following formula multiple times:
Figure BDA0002176293500000222
wherein the initial value of PR2(i) is a random value between 0 and 1, p2k，iAnd a second credibility parameter for performing identity authentication on the ith account in the account to be identified for the kth account in the second account set, wherein PR2(k) is a second authenticity parameter of the kth account, and alpha2 is a constant.
Optionally, the third obtaining unit includes:
the input subunit is configured to input the feature value of the account to be recognized into a target network model, so as to obtain a third validity parameter of the account to be recognized output by the target network model, where the target network model is obtained by training the initial network model using the feature value of the sample account, an error between the third validity parameter of the sample account output by the target network model and a predetermined third validity parameter of the sample account when training is completed satisfies a first condition, and the feature value of the account to be recognized at least includes one of: the first truth parameter of the account to be identified, the second truth parameter of the account to be identified, whether the account to be identified is reported or not and whether the parameter information of the account to be identified is consistent with the identity card information or not.
Optionally, the first determining module includes:
the first determining unit is used for determining the account to be identified with the maximum truth probability as the real account corresponding to the target identity;
and the second determining unit is used for determining the suspicious account corresponding to the target identity as the account to be identified with the truth probability smaller than the preset value.
Optionally, the apparatus further comprises:
the third acquisition module is used for acquiring a first suspicious account a and a second suspicious account b in the suspicious accounts;
the system comprises an establishing module, a judging module and a judging module, wherein the establishing module is used for establishing a friend relationship network formed by accounts having friend relationship with a first suspicious account a and/or a second suspicious account b by taking the first suspicious account a and the second suspicious account b as double centers, the friend relationship network comprises n vertexes and s edges, each vertex is used for representing one account in the friend relationship network, each edge is connected with two vertexes having friend relationship, and n and s are integers larger than 1;
a marking module for marking an adjacency matrix A of the friend relation network, wherein A is directly connected with b when aa，bWhen there is no edge between a and b, a is 1a，bWhen a is 0, A is ba，b＝1；
A second determining module, configured to determine a weight value γ of each vertex in the buddy relationship network according to the following formula: ax is n-dimensional vector, x comprises the truth probability corresponding to n vertexes in the friend relationship network, x is [ PR (1), PR (2), PR (3), ….. PR (n) ], PR (i) is the truth probability corresponding to the vertex i in the friend relationship network, and i is more than or equal to 1 and less than or equal to n;
a third determination module for determining the matrix Ba，bDetermining the relative sizes of the truth degrees of the first suspicious account a and the second suspicious account B, wherein Ba，b＝exp(γa)/exp(γb)，γaIs the weighted value, gamma, of the first suspicious account a in the friend relationship networkbIs the weighted value of the second suspicious account B in the friend relationship network, Ba，bThe larger the probability of truth representing a versus b.
Optionally, the apparatus further comprises:
an iteration module, configured to perform N iterations on the matrix B to obtain a matrix C, where C is equal to BNN is an integer greater than 1;
the calculation module is used for calculating the truth score of the suspicious account according to the following formula:
Figure BDA0002176293500000241
wherein xn represents the number of accounts to be identified in the target account set;
and the fourth determining module is used for determining the truth probability value of the suspicious account according to the truth score, wherein the truth probability value and the truth score are in a direct proportion relation.
Optionally, the first obtaining module includes:
a fifth obtaining unit, configured to obtain first parameter information of the first account, where the first parameter information matches the target identity, and the first parameter information at least includes one of: account head, account nickname and account signature;
the screening unit is used for screening a second account which has the same or similar parameter information with the first account in the social network data;
and the determining unit is used for determining the first account and the second account as accounts to be identified in the target account set.
Optionally, the apparatus further comprises:
and the sending module is used for sending prompt information to the account which carries out information interaction with the suspicious account, wherein the prompt information is used for prompting the existence of the suspicious account to the account.
According to another aspect of the embodiment of the present invention, there is also provided an electronic apparatus for implementing the method for determining account attributes, where the electronic apparatus may be applied to, but is not limited to, the server 112 shown in fig. 1. As shown in fig. 9, the electronic device comprises a memory 902 and a processor 904, the memory 902 having a computer program stored therein, the processor 904 being arranged to perform the steps of any of the above-described method embodiments by means of the computer program.
Optionally, in this embodiment, the electronic apparatus may be located in at least one network device of a plurality of network devices of a computer network.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, acquiring the account to be identified related to the target identity;
s2, acquiring the authenticity probability corresponding to the account to be identified according to the authenticity parameter of the account to be identified, wherein the authenticity probability is used for expressing the probability that the account to be identified is the account used by the target identity;
and S3, determining a real account and/or a suspicious account corresponding to the target identity from the account to be identified according to the truth probability corresponding to the account to be identified, wherein the real account is an account used by the target identity, and the suspicious account is an account used for simulating the target identity.
Alternatively, it can be understood by those skilled in the art that the structure shown in fig. 9 is only an illustration, and the electronic device may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 9 is a diagram illustrating a structure of the electronic device. For example, the electronic device may also include more or fewer components (e.g., network interfaces, etc.) than shown in FIG. 9, or have a different configuration than shown in FIG. 9.
The memory 902 may be configured to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for determining account attributes in the embodiment of the present invention, and the processor 904 executes various functional applications and data processing by running the software programs and modules stored in the memory 902, that is, implementing the above-mentioned data request processing method. The memory 902 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 902 may further include memory located remotely from the processor 904, which may be connected to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The memory 902 may be, but is not limited to, program steps for storing the determination method of the account attribute. As an example, as shown in fig. 9, the memory 902 may include, but is not limited to, the first obtaining module 702, the second obtaining module 704, and the first determining module 706 in the determination device of the account attribute. In addition, other module units in the above-mentioned account attribute determination apparatus may also be included, but are not limited to this, and are not described in detail in this example.
Optionally, the transmitting device 906 is used for receiving or sending data via a network. Examples of the network may include a wired network and a wireless network. In one example, the transmission device 906 includes a Network adapter (NIC) that can be connected to a router via a Network cable and other Network devices to communicate with the internet or a local area Network. In one example, the transmission device 906 is a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In addition, the electronic device further includes: a display 908 for displaying alert pushes of suspicious accounts; and a connection bus 910 for connecting the respective module parts in the above-described electronic apparatus.
Embodiments of the present invention also provide a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
Alternatively, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:
s1, acquiring the account to be identified related to the target identity;
s2, acquiring the authenticity probability corresponding to the account to be identified according to the authenticity parameter of the account to be identified, wherein the authenticity probability is used for expressing the probability that the account to be identified is the account used by the target identity;
and S3, determining a real account and/or a suspicious account corresponding to the target identity from the account to be identified according to the truth probability corresponding to the account to be identified, wherein the real account is an account used by the target identity, and the suspicious account is an account used for simulating the target identity.
Optionally, the storage medium is further configured to store a computer program for executing the steps included in the method in the foregoing embodiment, which is not described in detail in this embodiment.
Alternatively, in this embodiment, a person skilled in the art may understand that all or part of the steps in the methods of the foregoing embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a storage medium, and including instructions for causing one or more computer devices (which may be personal computers, servers, network devices, or the like) to execute all or part of the steps of the method described in the embodiments of the present application.
In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims (15)

1. A method for determining account attribute is characterized by comprising the following steps:
acquiring an account to be identified related to a target identity;
acquiring a truth probability corresponding to the account to be identified according to the truth parameter of the account to be identified, wherein the truth probability is used for expressing the probability that the account to be identified is the account used by the target identity;
and determining a real account and/or a suspicious account corresponding to the target identity from the account to be identified according to the truth probability corresponding to the account to be identified, wherein the real account is an account used by the target identity, and the suspicious account is an account used for simulating the target identity.
2. The method according to claim 1, wherein the obtaining the authenticity probability corresponding to the account to be identified according to the authenticity parameter of the account to be identified comprises:
acquiring a first truth parameter of the account to be identified on the relative dimension in the social network data, wherein the first truth parameter is associated with a first interaction operation between the account to be identified and the account having the relative relationship with the account to be identified in the social network data;
acquiring a second truth parameter of the account to be identified on a co-worker dimension in social network data, wherein the second truth parameter is associated with a second interaction operation between the account to be identified and an account having a co-worker relationship with the account to be identified in the social network data;
acquiring a third truth parameter of the account to be identified on a characteristic dimension, wherein the third truth parameter is associated with a characteristic value of the account to be identified;
and acquiring the truth probability corresponding to the account to be identified according to the first truth parameter, the second truth parameter and the third truth parameter.
3. The method of claim 2,
the first trueness parameter is positively correlated with an operation parameter of a first interactive operation between the account to be identified and an account having a relationship with the account to be identified in the social network data, wherein the operation parameter of the first interactive operation at least includes one of the following: the number of times, frequency and operation duration of the first interactive operation;
the second truth parameter positively correlates with an operation parameter of a second interactive operation between the account to be identified and an account having a co-worker relationship with the account to be identified in the social network data, wherein the operation parameter of the second interactive operation at least includes one of the following: the number of times, frequency, and operation duration of the second interactive operation.
4. The method according to claim 2, wherein the obtaining the authenticity probability corresponding to the account to be identified according to the first authenticity parameter, the second authenticity parameter, and the third authenticity parameter includes:
and performing weighted summation on the first, second and third truth parameters to obtain the truth probability, wherein the preset weights corresponding to the first, second and third truth parameters are β 1, β 2 and β 3, respectively, β 1+ β 2+ β 3 is 1, β 1 is greater than or equal to 0, and β 2 is less than or equal to 1.
5. The method according to claim 2, wherein the obtaining of the first trueness parameter of the account to be identified in the social network data in the relative dimension comprises:
acquiring a first account set having a relationship with the account to be identified from the social network data;
determining a first affinity parameter between the account i to be identified and the account t in the first account set according to a first interactive operation between the account i to be identified and the account t in the first account set in the social network data;
according to the first intimacy parameter between the account i to be recognized and the account t, determining a first credibility parameter p1 for the account t to perform identity authentication on the account i to be recognizedt，iWherein the first credibility parameter p1t，iIs positively correlated with the value of the first intimacy parameter;
determining a first truth parameter PR1(i) of the ith account in the account to be identified by operating the following formula for a plurality of times:
Figure FDA0002176293490000031
wherein the initial value of PR1(i) is a random value between 0 and 1, p1t，iAnd performing identity authentication on the ith account in the account to be identified for the tth account in the first account set, wherein PR1(t) is a first authenticity parameter of the tth account, and alpha1 is a constant.
6. The method of claim 2, wherein the obtaining of the second trueness parameter of the account to be identified in the dimension of the coworkers in the social network data comprises:
acquiring a second account set of which the account to be identified has a co-worker relationship from the social network data;
determining a second affinity parameter between the account i to be identified and the account k in the second account set according to a second interaction operation between the account i to be identified and the account k in the second account set in the social network data;
according to a second intimacy parameter between the account i to be identified and the account k, determining a second credibility parameter p2 for the account k to perform identity authentication on the account i to be identifiedk，iWherein the second credibility parameter p2k，iThe value of (a) is positively correlated with the value of the second intimacy parameter;
determining a second truth parameter PR2(i) of the ith account in the account to be identified by operating the following formula for a plurality of times:
Figure FDA0002176293490000032
wherein the initial value of PR2(i) is a random value between 0 and 1, p2k，iAnd a second credibility parameter for performing identity authentication on the ith account in the account to be identified for the kth account in the second account set, wherein PR2(k) is a second authenticity parameter of the kth account, and the alpha2 is a constant.
7. The method according to claim 2, wherein the obtaining of the third trueness parameter of the account to be recognized in the feature dimension comprises:
inputting the feature value of the account to be recognized into a target network model to obtain the third truth parameter of the account to be recognized output by the target network model, wherein the target network model is obtained by training an initial network model by using the feature value of a sample account, when the training is completed, an error between the third truth parameter of the sample account output by the target network model and a predetermined third truth parameter of the sample account satisfies a first condition, and the feature value of the account to be recognized at least comprises one of the following values: the first truth parameter of the account to be identified, the second truth parameter of the account to be identified, whether the account to be identified is reported or not and whether the parameter information of the account to be identified is consistent with the identity card information or not.
8. The method according to any one of claims 1 to 7, wherein the determining a true account and/or a suspicious account corresponding to the target identity from the account to be recognized according to the probability of validity corresponding to the account to be recognized comprises:
thereafter, the method further comprises:
determining the account to be identified with the maximum truth probability as a real account corresponding to the target identity;
and determining that the account to be identified is a suspicious account corresponding to the target identity, wherein the truth probability is smaller than a preset value.
9. The method according to claim 8, wherein after determining that the probability of truth is smaller than a preset value, the account to be identified is a suspicious account corresponding to the target identity, the method further comprises:
acquiring a first suspicious account a and a second suspicious account b in the suspicious accounts;
establishing a friend relationship network formed by accounts having friend relationship with a or b by taking a and b as double centers, wherein the friend relationship network comprises n vertexes and s edges, each vertex is used for representing one account in the friend relationship network, each edge is connected with two vertexes having friend relationship, and n and s are integers greater than 1;
marking an adjacency matrix A of the friend relation network, wherein A is directly connected with the b when the a and the b have edgesa，bWhen there is no edge between a and b, a is 1a，bWhen a is 0, A is ba，b＝1；
Determining a weight value γ of the each vertex in the friendship network according to the following formula: ax ═ γ x, where x is an n-dimensional vector, where x includes probability of truth for n vertices in the friendship network, [ PR (1), PR (2), PR (3), ….. PR (n) ], PR (i) is probability of truth for vertex i in the friendship network, 1 ≦ i ≦ n;
according to matrix Ba，bDetermining the relative magnitude of the degree of truth of the a and the B, wherein Ba，b＝exp(γa)/exp(γb)，γaIs the weight value of the a in the friend relationship network, gammabIs the weight value of the B in the friend relationship network, Ba，bThe larger the probability of truth representing a versus b.
10. The method of claim 9, wherein the matrix B is based ona，bAfter determining the relative magnitude of the degree of truth of the a and the b, the method further comprises:
performing N iterations on the matrix B to obtain a matrix C, wherein C is BNN is an integer greater than 1;
calculating the truth score of the suspicious account according to the following formula:
Figure FDA0002176293490000051
Figure FDA0002176293490000052
wherein xn represents the number of the accounts to be identified in the target account set;
and determining the truth probability value of the suspicious account according to the truth score, wherein the truth probability value and the truth score are in a direct proportion relation.
11. The method according to claim 8, wherein after determining that the probability of validity is smaller than a preset value, the account to be identified is a suspicious account corresponding to the target identity, the method further comprises:
and sending prompt information to an account which performs information interaction with the suspicious account, wherein the prompt information is used for prompting the existence of the suspicious account to the account.
12. An apparatus for determining account attributes, comprising:
the first acquisition module is used for acquiring the account to be identified related to the target identity;
a second obtaining module, configured to obtain, according to the truth parameter of the account to be recognized, a truth probability corresponding to the account to be recognized, where the truth probability is used to represent a probability that the account to be recognized is an account used by the target identity;
a first determining module, configured to determine, according to the truth probability corresponding to the account to be identified, a real account and/or a suspicious account corresponding to the target identity from the account to be identified, where the real account is an account used by the target identity, and the suspicious account is an account used to simulate the target identity.
13. The apparatus of claim 12, wherein the second obtaining module comprises:
the device comprises a first obtaining unit, a second obtaining unit and a third obtaining unit, wherein the first obtaining unit is used for obtaining a first truth parameter of the account to be identified on the relative dimension in the social network data, and the first truth parameter is associated with a first interaction operation between the account to be identified and the account having the relative relationship with the account to be identified in the social network data;
a second obtaining unit, configured to obtain a second degree of reality parameter of the account to be identified in a co-worker dimension in social network data, where the second degree of reality parameter is associated with a second interaction operation between the account to be identified and an account having a co-worker relationship with the account to be identified in the social network data;
a third obtaining unit, configured to obtain a third authenticity parameter of the account to be identified in a feature dimension, where the third authenticity parameter is associated with a feature value of the account to be identified;
and the fourth obtaining unit is used for obtaining the truth probability corresponding to the account to be identified according to the first truth parameter, the second truth parameter and the third truth parameter.
14. A storage medium comprising a stored program, wherein the program when executed performs the method of any one of claims 1 to 11.
15. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method of any of claims 1 to 11 by means of the computer program.
CN201910780096.0A 2019-08-22 2019-08-22 Method and device for determining account attribute, storage medium and electronic device Active CN112422480B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910780096.0A CN112422480B (en) 2019-08-22 2019-08-22 Method and device for determining account attribute, storage medium and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910780096.0A CN112422480B (en) 2019-08-22 2019-08-22 Method and device for determining account attribute, storage medium and electronic device

Publications (2)

Publication Number Publication Date
CN112422480A true CN112422480A (en) 2021-02-26
CN112422480B CN112422480B (en) 2022-09-13

Family

ID=74778996

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910780096.0A Active CN112422480B (en) 2019-08-22 2019-08-22 Method and device for determining account attribute, storage medium and electronic device

Country Status (1)

Country Link
CN (1) CN112422480B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113205188A (en) * 2021-05-07 2021-08-03 上海明略人工智能(集团)有限公司 Method and device for determining target account, storage medium and electronic device

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140196110A1 (en) * 2013-01-08 2014-07-10 Yigal Dan Rubinstein Trust-based authentication in a social networking system
CN104092601A (en) * 2014-07-28 2014-10-08 北京微众文化传媒有限公司 Method and device for recognizing social-media account
CN104657369A (en) * 2013-11-19 2015-05-27 深圳市腾讯计算机系统有限公司 User attribute information generating method and system
CN105847127A (en) * 2016-05-04 2016-08-10 腾讯科技（深圳）有限公司 User attribute information determination method and server
WO2017029786A1 (en) * 2015-08-18 2017-02-23 日本電気株式会社 Method and device for evaluating trustworthiness of online account
CN109829593A (en) * 2017-11-23 2019-05-31 广州腾讯科技有限公司 The credit rating of target object determines method, apparatus, storage medium and electronic device
US20190197633A1 (en) * 2016-10-31 2019-06-27 Tencent Technology (Shenzhen) Company Limited Social media account filtering method and apparatus

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140196110A1 (en) * 2013-01-08 2014-07-10 Yigal Dan Rubinstein Trust-based authentication in a social networking system
CN104657369A (en) * 2013-11-19 2015-05-27 深圳市腾讯计算机系统有限公司 User attribute information generating method and system
CN104092601A (en) * 2014-07-28 2014-10-08 北京微众文化传媒有限公司 Method and device for recognizing social-media account
WO2017029786A1 (en) * 2015-08-18 2017-02-23 日本電気株式会社 Method and device for evaluating trustworthiness of online account
CN105847127A (en) * 2016-05-04 2016-08-10 腾讯科技（深圳）有限公司 User attribute information determination method and server
US20190197633A1 (en) * 2016-10-31 2019-06-27 Tencent Technology (Shenzhen) Company Limited Social media account filtering method and apparatus
CN109829593A (en) * 2017-11-23 2019-05-31 广州腾讯科技有限公司 The credit rating of target object determines method, apparatus, storage medium and electronic device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
徐乾等: "基于带权超图的跨网络用户身份识别方法", 《计算机应用》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113205188A (en) * 2021-05-07 2021-08-03 上海明略人工智能(集团)有限公司 Method and device for determining target account, storage medium and electronic device

Also Published As

Publication number Publication date
CN112422480B (en) 2022-09-13

Similar Documents

Publication Publication Date Title
CN107872772B (en) Method and device for detecting fraud short messages
CN106878309B (en) Safety early warning method and device applied to network payment
CN105630977B (en) Application program recommended method, apparatus and system
CN108353019B (en) Method, terminal and server for associating users
CN104618312B (en) A kind of remote login methods, devices and systems of M2M application
CN111476572B (en) Block chain-based data processing method, device, storage medium and equipment
CN104184705A (en) Verification method, apparatus, server, user data center and system
CN108540431A (en) The recognition methods of account type, device and system
CN109600336A (en) Store equipment, identifying code application method and device
CN108898728A (en) Intelligent interaction device and its voting method, device and system
US9246925B2 (en) Method and system for third-party service platform login
CN107347049A (en) A kind of account method for authenticating and server
CN107682328A (en) A kind of data verification method and client
CN105681257B (en) Information reporting method, device, equipment and system based on instant messaging interaction platform and computer storage medium
CN108600399A (en) Information-pushing method and Related product
CN108306886A (en) A kind of auth method, device and storage medium
CN112446736A (en) Click through rate CTR prediction method and device
CN110457601B (en) Social account identification method and device, storage medium and electronic device
CN112422480B (en) Method and device for determining account attribute, storage medium and electronic device
CN114168295A (en) Hybrid architecture system and task scheduling method based on historical task effect
CN111951021A (en) Method and device for discovering suspicious communities, storage medium and computer equipment
CN108804501A (en) A kind of method and device of detection effective information
CN105512208B (en) Information publishing method, device and system
CN116436689A (en) Vulnerability processing method and device, storage medium and electronic equipment
CN113254989B (en) Fusion method and device of target data and server

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 40038369

Country of ref document: HK

SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant