CN110874387B - Method and device for constructing sparse graph of co-occurrence relation of identifiers of mobile equipment - Google Patents

Method and device for constructing sparse graph of co-occurrence relation of identifiers of mobile equipment Download PDF

Info

Publication number
CN110874387B
CN110874387B CN201811011882.6A CN201811011882A CN110874387B CN 110874387 B CN110874387 B CN 110874387B CN 201811011882 A CN201811011882 A CN 201811011882A CN 110874387 B CN110874387 B CN 110874387B
Authority
CN
China
Prior art keywords
identifier
mobile equipment
mobile
occurrence
identifiers
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201811011882.6A
Other languages
Chinese (zh)
Other versions
CN110874387A (en
Inventor
王灿
沈鑫
冼伟钊
杨红霞
王中要
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.)
Zhejiang University ZJU
Original Assignee
Zhejiang University ZJU
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 Zhejiang University ZJU filed Critical Zhejiang University ZJU
Priority to CN201811011882.6A priority Critical patent/CN110874387B/en
Publication of CN110874387A publication Critical patent/CN110874387A/en
Application granted granted Critical
Publication of CN110874387B publication Critical patent/CN110874387B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W8/00Network data management
    • H04W8/22Processing or transfer of terminal data, e.g. status or physical capabilities

Abstract

The application discloses a method and a device for constructing a co-occurrence relation sparse graph of a mobile equipment identifier, and a mobile equipment identification method. The method for constructing the co-occurrence relation sparse graph of the mobile equipment identifier comprises the following steps: the method comprises the steps of obtaining a set of identifier information of the mobile device, using the set of identifier information of the mobile device as nodes of a co-occurrence relationship sparse graph, obtaining nodes containing a first identifier, connecting the nodes containing the first identifier, and deleting the connection relationship among the nodes containing the first identifier when the number of the nodes containing the first identifier reaches or exceeds a preset node number threshold value to obtain the co-occurrence relationship sparse graph. The sparsity of the graph is guaranteed, and the complexity of an algorithm for identifying the mobile equipment by using the graph is reduced, so that the parallelization processing of large-scale data is facilitated.

Description

Method and device for constructing sparse graph of co-occurrence relation of identifiers of mobile equipment
Technical Field
The application relates to the field of mobile equipment entity identification, in particular to a method and a device for constructing a co-occurrence sparse graph of a mobile equipment identifier, electronic equipment and storage equipment. The application also relates to a mobile equipment identification method and device, electronic equipment and storage equipment.
Background
In the using process of the mobile device, the problems of reinstalling a system, replacing the mobile device, emulating an airplane, simulating an attack and the like are frequently encountered, the existence of the problems often causes the loss of partial data information of the mobile device, and the calculation of a commonly used mobile device entity identification algorithm based on a mobile device identifier is complicated.
In order to solve the above problem, in a conventional scheme in the art, an APP is generally used to randomly generate a unique identifier according to hardware and system information during installation, or an Android system unique device identifier Android ID is used, or an IDFA unique identifier of an apple system is used to perform entity identification on a mobile device, and the identifier is found to uniquely correspond to the mobile device, so that all relevant data information lost by the mobile device is recalled. However, the above conventional technical solutions can only eliminate the problem of mobile device data information loss caused by some abnormal reasons, and the operation process of the algorithm for identifying the mobile device based on the mobile device identifier is still complicated, so that large-scale data cannot be processed.
Disclosure of Invention
The application provides a method and a device for constructing a co-occurrence relation sparse graph of a mobile equipment identifier, electronic equipment and storage equipment, and aims to solve the problems that in the prior art, the complexity of an entity identification algorithm of the mobile equipment is too high, parallel computation is not facilitated, and large-scale data cannot be processed. The application further provides a mobile device identification method and device, an electronic device and a storage device.
The method for constructing the co-occurrence relation sparse graph of the mobile equipment identifier comprises the following steps:
acquiring a set of identifier information of mobile equipment, and taking the set of identifier information of the mobile equipment as a node of the co-occurrence relation sparse graph;
acquiring a node containing a first identifier;
connecting the nodes including the first identifier;
and when the number of the nodes containing the first identifier reaches or exceeds a preset node number threshold value, deleting the connection relation among the nodes containing the first identifier to obtain the co-occurrence relation sparse graph.
Optionally, the set of identifier information of the mobile device includes software and hardware identifier information corresponding to the mobile device.
Optionally, the software and hardware identifier information corresponding to the mobile device specifically includes at least one of the following identifier information:
an equipment identity, IMEI, for uniquely identifying the mobile equipment;
a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the mobile device;
an advertisement Identifier (IDFA) for tracking the mobile device operation information;
a software identifier UTDID for uniquely identifying the mobile device.
Optionally, the set of identifier information of the mobile device uniquely represents a real physical mobile device.
Optionally, the first identifier includes at least one of:
an equipment identity, IMEI, for uniquely identifying the first mobile equipment;
a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile device;
an advertisement Identifier (IDFA) for tracking the first mobile device operation information;
a software identifier UTDID for uniquely identifying the first mobile device.
Correspondingly, the application also provides a mobile equipment identification method, which comprises the following steps:
obtaining the number of edges in a co-occurrence relationship sparse graph, wherein the co-occurrence relationship sparse graph is obtained by connecting nodes containing the same identifier by taking a set of identifier information of the mobile equipment as a node, and deleting the connection relationship among the nodes containing the same identifier, the number of which reaches or exceeds a preset node number threshold;
according to the number of edges in the co-occurrence relation sparse graph, obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center;
if the characteristics of the mobile equipment centers of a plurality of identifiers are the same, determining the plurality of identifiers to be a plurality of identifiers of the same mobile equipment;
and determining the mobile equipment uniquely corresponding to the identifiers according to the similarity between the characteristics of the mobile equipment center to which the identifiers belong and the characteristics of each equipment center.
Optionally, the obtaining, according to the number of edges in the co-occurrence sparse graph, the feature of the mobile device center to which the identifier belongs and the feature of each mobile device center includes:
establishing an objective function of an unsupervised learning algorithm;
and inputting the number of edges in the co-occurrence relation sparse graph as a parameter into an objective function of an unsupervised learning algorithm to carry out parallelized iterative optimization algorithm training, and obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center.
Optionally, the expression of the objective function of the unsupervised learning algorithm is as follows:
Figure BDA0001785301120000031
wherein x isiIs a feature of each set of identifiers, ciThe method comprises the steps that the identifier belongs to the center of the mobile equipment, g is a distance function, i and j are identifications of any two nodes of the co-occurrence sparse graph, V represents a value range of any node of the co-occurrence sparse graph, and E represents a value range of any two nodes of the co-occurrence sparse graph.
Correspondingly, the present application also provides a device for constructing a sparse co-occurrence graph of identifiers of mobile devices, including:
a first obtaining unit, configured to obtain a set of identifier information of a mobile device, and use the set of identifier information of the mobile device as a node of the sparse co-occurrence graph;
a second acquisition unit configured to acquire a node including the first identifier;
a connecting unit for connecting the nodes including the first identifier;
and the deleting unit is used for deleting the connection relation among the nodes containing the first identifier when the number of the nodes containing the first identifier reaches or exceeds a preset node number threshold value, so as to obtain the co-occurrence relation sparse graph.
Correspondingly, the present application also provides an electronic device, comprising:
a processor; and
a memory for storing a program of a co-occurrence sparse graph construction method of a mobile device identifier, wherein after the device is powered on and runs the program of the co-occurrence sparse graph construction method of the mobile device identifier through the processor, the following steps are executed:
acquiring a set of identifier information of mobile equipment, and taking the set of identifier information of the mobile equipment as a node of the co-occurrence relation sparse graph;
acquiring a node containing a first identifier;
connecting the nodes including the first identifier;
and when the number of the nodes containing the first identifier reaches or exceeds a preset node number threshold value, deleting the connection relation among the nodes containing the first identifier to obtain the co-occurrence relation sparse graph.
Correspondingly, the present application also provides a storage device, in which a program of a method for constructing a sparse co-occurrence map of a mobile device identifier is stored, where the program is executed by a processor to perform the following steps:
acquiring a set of identifier information of mobile equipment, and taking the set of identifier information of the mobile equipment as a node of the co-occurrence relation sparse graph;
acquiring a node containing a first identifier;
connecting the nodes including the first identifier;
and when the number of the nodes containing the first identifier reaches or exceeds a preset node number threshold value, deleting the connection relation among the nodes containing the first identifier to obtain the co-occurrence relation sparse graph.
Correspondingly, the mobile equipment identification device comprises:
a first obtaining unit configured to obtain the number of edges in a co-occurrence-relationship sparse graph, where the co-occurrence-relationship sparse graph is obtained by connecting nodes including the same identifier using a set of identifier information of the mobile device as nodes, and deleting a connection relationship between the nodes including the same identifier whose number reaches or exceeds a preset node number threshold;
the second obtaining unit is used for obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center according to the number of edges in the co-occurrence relation sparse graph;
the first determining unit is used for determining a plurality of identifiers as a plurality of identifiers of the same mobile equipment if the characteristics of the mobile equipment centers to which the plurality of identifiers belong are the same;
and the second determining unit is used for determining the mobile equipment uniquely corresponding to the identifiers according to the similarity between the characteristics of the mobile equipment centers to which the identifiers belong and the characteristics of each equipment center.
Correspondingly, the present application also provides an electronic device, comprising:
a processor; and
a memory for storing a program of a mobile device identification method, the device being powered on and executing the program of the mobile device identification method by the processor, and performing the steps of:
obtaining the number of edges in a co-occurrence relationship sparse graph, wherein the co-occurrence relationship sparse graph is obtained by connecting nodes containing the same identifier by taking a set of identifier information of the mobile equipment as a node, and deleting the connection relationship among the nodes containing the same identifier, the number of which reaches or exceeds a preset node number threshold;
according to the number of edges in the co-occurrence relation sparse graph, obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center;
if the characteristics of the mobile equipment centers of a plurality of identifiers are the same, determining the plurality of identifiers to be a plurality of identifiers of the same mobile equipment;
and determining the mobile equipment uniquely corresponding to the identifiers according to the similarity between the characteristics of the mobile equipment center to which the identifiers belong and the characteristics of each equipment center.
Accordingly, the present application also provides a storage device storing a program of a mobile device identification method, the program being executed by a processor and performing the steps of:
obtaining the number of edges in a co-occurrence relationship sparse graph, wherein the co-occurrence relationship sparse graph is obtained by connecting nodes containing the same identifier by taking a set of identifier information of the mobile equipment as a node, and deleting the connection relationship among the nodes containing the same identifier, the number of which reaches or exceeds a preset node number threshold;
according to the number of edges in the co-occurrence relation sparse graph, obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center;
if the characteristics of the mobile equipment centers of a plurality of identifiers are the same, determining the plurality of identifiers to be a plurality of identifiers of the same mobile equipment;
and determining the mobile equipment uniquely corresponding to the identifiers according to the similarity between the characteristics of the mobile equipment center to which the identifiers belong and the characteristics of each equipment center.
Correspondingly, the present application also provides a mobile device identification system, including: the apparatus for constructing a sparse co-occurrence graph of mobile device identifiers of any of the above claims 11-16, and the apparatus for identifying mobile devices of the above claims 19-22.
Compared with the prior art, the method has the following advantages:
the method comprises the steps of acquiring a set of identifier information of the mobile equipment, taking the set of the identifier information of the mobile equipment as a node of a co-occurrence relation sparse graph, acquiring a node containing a first identifier, connecting the node containing the first identifier, and deleting the connection relation between the nodes containing the first identifier when the number of the nodes containing the first identifier reaches or exceeds a preset node number threshold value to obtain the co-occurrence relation sparse graph. The sparsity of the co-occurrence relation sparse graph of the mobile equipment identifier is ensured, and the complexity of an algorithm for identifying the mobile equipment by using the graph is reduced, so that the parallelization processing of large-scale data is facilitated.
In addition, the application also provides a mobile device identification method, the number of edges in the co-occurrence relation sparse graph is obtained, the characteristics of the mobile device center to which the identifier belongs and the characteristics of each mobile device center are obtained according to the number of edges in the co-occurrence relation sparse graph, if the characteristics of the mobile device centers to which a plurality of identifiers belong are the same, the plurality of identifiers are determined to be the plurality of identifiers of the same mobile device, and the mobile devices uniquely corresponding to the plurality of identifiers are determined according to the similarity between the characteristics of the mobile device centers to which the plurality of identifiers belong and the characteristics of each device center. The entity recognition is carried out on the mobile equipment by utilizing the constructed co-occurrence relation sparse graph and the unsupervised learning algorithm, and marked data is not needed to be used as input, so that the complexity of the entity recognition of the mobile equipment is reduced, and the accuracy of the entity recognition of the mobile equipment is greatly improved.
Drawings
Fig. 1 is a flowchart of a method for constructing a sparse co-occurrence graph of identifiers of mobile devices according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a mobile device identification method according to an embodiment of the present application;
fig. 3 is a schematic diagram of a device for constructing a sparse co-occurrence graph of identifiers of mobile devices according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of an electronic device for constructing a sparse co-occurrence graph of identifiers of mobile devices according to an embodiment of the present application;
fig. 5 is a schematic diagram of an identification apparatus for a mobile device according to an embodiment of the present application;
fig. 6 is a schematic diagram of a mobile device identification electronic device according to an embodiment of the present application;
fig. 7 is a flowchart illustrating a mobile device identification system according to an embodiment of the present application;
fig. 8 is a structural diagram constructed by a method for constructing a sparse co-occurrence graph of identifiers of mobile devices according to an embodiment of the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.
In order to make those skilled in the art better understand the solution of the present application, the following describes an embodiment of the method for constructing a sparse graph of co-occurrence relationships based on the mobile device identifier of the present application in detail. In addition, in the following description, detailed explanation will be made separately for each step of the present method. Please refer to fig. 1, which is a flowchart illustrating a method for constructing a sparse co-occurrence graph of mobile device identifiers according to an embodiment of the present application.
Step S101, acquiring a set of identifier information of the mobile device, and taking the set of identifier information of the mobile device as a node of the co-occurrence sparse graph.
In this embodiment, if a sparse graph of the co-occurrence relationship of the mobile device identifiers is to be constructed, all the software and hardware mobile device identifiers need to be extracted from all the mobile device access logs, and the set of mobile device identifier information recorded in each access log is used as a node in the graph. The set of mobile device identifier information is an identifier set for uniquely representing a physical mobile device, and includes a hardware identifier and a software identifier, and specifically, the set of mobile device identifier information includes at least one identifier selected from a device identifier IMEI for uniquely identifying a mobile device, a subscriber identifier IMSI for uniquely identifying mobile subscriber information corresponding to a mobile device, an advertisement identifier IDFA for tracking operation information of a mobile device, and a software identifier UTDID for uniquely identifying a mobile device. And taking the set of the identifier information of the mobile equipment as the nodes of the sparse graph of the co-occurrence relationship of the identifiers of the mobile equipment, namely, each node in the sparse graph of the co-occurrence relationship of the identifiers of the mobile equipment represents a set of the identifier information of the mobile equipment.
In step S102, a node including the first identifier is acquired.
In this embodiment, the first identifier specifically includes: an equipment identity IMEI for uniquely identifying a first mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile equipment, at least one of an advertisement identifier IDFA for tracking the first mobile equipment operational information and a software identifier UTDID for uniquely identifying the first mobile equipment.
And step S103, connecting the nodes containing the first identifier.
In this embodiment, for each identifier we traverse through all the sets of mobile device identifier information (i.e., nodes in the graph), finding all the nodes containing this identifier to connect. It should be noted that in the embodiment of the present application, four identifiers, i.e., IMEI, IMSI, IDFA, and UTDID, are mainly extracted, if one identifier appears in two different nodes, the two nodes are connected into one edge, and the found nodes are connected in pairs in sequence to form a composition. When one identifier appears in a large number of nodes, namely excessive nodes are associated, in this case, edges are not connected, and the excessive connected nodes are deleted, so that the sparsity of the graph is ensured, and the time complexity is reduced. The IMEI is a mobile equipment identity, and the IMEI is a mark for distinguishing a mobile subscriber, is stored in the SIM card, and can be used for distinguishing valid information of the subscriber.
And step S104, when the number of the nodes containing the first identifier reaches or exceeds a preset node number threshold, deleting the connection relation among the nodes containing the first identifier to obtain the co-occurrence relation sparse graph.
In this embodiment, the preset threshold value of the number of nodes is 1000, in order to reduce the time complexity, when the number of nodes including any one identifier of the four identifiers, i.e., IMEI, IMSI, IDFA, UTDID, reaches or exceeds 1000, that is, if an identifier appears in more than one thousand nodes, the nodes including any identifier are not connected in the sub-loop, and the connection relationship between the nodes including the same identifier is deleted, so as to obtain a constructed sparse graph of the co-occurrence relationship of the mobile device, as shown in fig. 8, which is a structural graph constructed by the method for constructing the sparse graph of the co-occurrence relationship of the identifier of the mobile device provided in the embodiment of the present application.
The method comprises the steps of acquiring a set of identifier information of the mobile equipment, taking the set of the identifier information of the mobile equipment as a node of a co-occurrence relation sparse graph, acquiring a node containing a first identifier, connecting the node containing the first identifier, and deleting the connection relation between the nodes containing the first identifier when the number of the nodes containing the first identifier reaches or exceeds a preset node number threshold value to obtain the co-occurrence relation sparse graph. The sparsity of the co-occurrence relation sparse graph of the mobile equipment identifier is guaranteed, the complexity of an algorithm for identifying the mobile equipment by using the graph is reduced, and parallelization processing of big data is facilitated.
Corresponding to the above-mentioned method for constructing a sparse graph of co-occurrence relationship of identifiers of mobile devices, an embodiment of the present application further provides a method for identifying a mobile device, please refer to fig. 2, which is a flowchart of the method for identifying a mobile device according to the embodiment of the present application.
Step S201: and obtaining the number of edges in a co-occurrence relation sparse graph, wherein the co-occurrence relation sparse graph is obtained by connecting nodes containing the same identifier by taking a set of identifier information of the mobile equipment as a node, and deleting the connection relation among the nodes containing the same identifier, the number of which reaches or exceeds a preset node number threshold value.
In this embodiment, by constructing a sparse graph of the co-occurrence relationship of the identifiers of the mobile devices and using a brand-new unsupervised learning algorithm, the structural characteristics of the sparse graph of the co-occurrence relationship and the attribute characteristics of the nodes are integrated to perform entity identification of the mobile devices. Due to the sparsity of the graph, the number of edges in the sparse graph of the co-occurrence relation of the identifiers of the mobile equipment is approximate to the number of points, and each iteration of the unsupervised learning algorithm is only needed to be carried out on the edges of the graph, so that the lower time complexity is ensured.
Step S202: and obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center according to the number of edges in the co-occurrence relation sparse graph.
In this embodiment, the obtaining of the feature of the mobile device center to which the identifier belongs and the feature of each mobile device center according to the number of edges in the co-occurrence relationship sparse graph specifically includes establishing an objective function of an unsupervised learning algorithm, and inputting the number of edges in the constructed co-occurrence relationship sparse graph as a parameter into the objective function of the unsupervised learning algorithm for parallelized iterative optimization algorithm training to obtain the feature of the mobile device center to which the identifier belongs and the feature of each mobile device center.
It should be noted that the objective function of the unsupervised learning algorithm refers to an algorithm function that does not need marked data as input and performs learning directly in the modeling process, and is often used in cases where the manual labeling type or the manual labeling cost is too high. The application provides a brand new algorithm objective function through unsupervised learning calculation, and the formula of the algorithm objective function is as follows:
Figure BDA0001785301120000091
wherein x isiIs a feature of each set of identifiers, ciThe method comprises the steps that the mobile equipment center is characterized in that an identifier belongs to, g is a distance function, i and j are identifications of any two nodes of the co-occurrence sparse graph, V represents a value range of any node of the co-occurrence sparse graph, and E represents a value range of an edge formed by connecting any two nodes of the co-occurrence sparse graph. Wherein the first term of the above objective function formula constrains each set of identifier information (nodes in the co-occurrence sparse graph) to be as similar as possible to its corresponding mobile device center point, and the second term of the above objective function formula should be similar as possible to its corresponding mobile device center pointThe term constrains that edge-connected nodes should be as similar as possible, and the third term constrains the range of characteristics of the mobile device center node.
In this embodiment, the algorithm objective function can implement a parallelized iterative optimization algorithm, and quickly identify the central feature of the device to which each identifier belongs. And performing entity identification of the mobile equipment according to the solved central characteristics of the equipment to which each identifier belongs, namely, if the characteristics of the centers of the equipment to which the two identifiers belong are consistent, the two identifiers also belong to the same equipment.
Wherein, the solving algorithm mainly adopts an alternative direction multiplier method, and the original ADMM is deformed and improved to obtain the graph (V, E) and the attribute characteristic x of each nodeiInputting the central characteristics c of each mobile device into the solving algorithm to be optimized and solvedi
Specifically, in this embodiment, inputting the number of edges corresponding to nodes in the co-occurrence sparse graph as a parameter into an objective function of the unsupervised learning algorithm to perform parallelized iterative optimization algorithm training, and obtaining the features of the mobile device center to which the identifier belongs and the features of each mobile device center specifically includes:
setting an Euclidean distance function as a distance function, introducing a dual variable z, and rewriting an expression of an objective function of the unsupervised learning algorithm into the following form:
Figure BDA0001785301120000101
s.t.ci-zij=0
wherein xiIs a feature of each set of identifiers, ciIs the central feature of each device, sijIs any two nodes x of the co-occurrence sparse graphiAnd xjV represents the value range of any node of the co-occurrence sparse graph, E represents the value range of an edge formed by connecting any two nodes of the co-occurrence sparse graph, L (c, z) is an objective function for introducing a dual variable z, and L (c, z) is used for approximating toBundle ci*zji=0。
And performing Lagrange transformation on the expression of the target function of the rewritten unsupervised learning algorithm to obtain a function formula in an unconstrained and augmented Lagrange form:
Figure BDA0001785301120000102
where z is a dual variable and y and p are penalty parameters introduced in the Lagrangian transformation.
And performing parallelization iterative optimization algorithm training according to the objective function of the unsupervised learning algorithm in the unconstrained and augmented Lagrange form to obtain the characteristics of the mobile equipment center to which the identifier belongs.
Step S203: and if the characteristics of the mobile equipment centers to which the multiple identifiers belong are the same, determining that the multiple identifiers are multiple identifiers of the same mobile equipment.
Step S204: and determining the mobile equipment uniquely corresponding to the identifiers according to the similarity between the characteristics of the mobile equipment center to which the identifiers belong and the characteristics of each equipment center.
And (4) identifying the mobile equipment entity, and corresponding a plurality of mobile equipment identifiers in an access log to a unique real mobile equipment. In this embodiment, the following formula is obtained by letting u be y/ρ according to the function of the above-described unconstrained augmented lagrange form:
Figure BDA0001785301120000111
and c, z and u are updated in a parallel iteration mode to obtain the result of the target function. Where λ denotes a penalty parameter, ciThe characteristics of the mobile equipment center to which the identifier belongs, z is an introduced dual variable, and u is a punishment parameter after Lagrange scaling transformation.
Figure BDA0001785301120000112
In the above formula, there is an analytical solution for c and z, namely:
Figure BDA0001785301120000121
wherein c isiIs the characteristic of the mobile equipment center to which the identifier belongs, z is an introduced dual variable, u is a punishment parameter after Lagrange scaling transformation, and c*、z*Is the last solved analytical solution, and θ is a temporary variable for intermediate calculations.
And after the feature of each mobile equipment center is solved, according to the obtained feature of the mobile equipment center to which each identifier belongs and the feature of each mobile equipment center, the identifier contained in each node is corresponding to the mobile equipment with the closest feature similarity, so that the final result of the entity identification of the mobile equipment based on the sparse graph of the co-occurrence relationship of the identifiers of the mobile equipment is determined.
The embodiment can eliminate the influence caused by the abnormal problem of the identifiers of various mobile devices to a certain extent, and greatly improve the identification precision of the mobile devices. Among them, the abnormal problems that can be solved include but are not limited to: the problem of dual-card dual-standby, the problem of reinstalling a system, the problem of replacing a mobile phone, the problem of emulational machine, the problem of simulator attack and the like. In the dual-card dual-standby problem, the four combinations of the IMEI and the IMSI form a strong association relationship in the graph; after the system is reinstalled, all software identifiers related to the mobile equipment corresponding to the IMEI identifier and the IMSI identifier can be recalled through hardware identifiers such as the IMEI identifier and the IMSI identifier; after the mobile phone is replaced, all backup data of the mobile equipment corresponding to the IMSI can be recalled by utilizing the IMSI and the access attribute; the huge link relation caused by the emulational machine problem and the simulator problem is partially solved when the picture is constructed. Meanwhile, the unsupervised learning algorithm provided by the embodiment of the application supports parallelization processing of data and can be suitable for large-scale data processing. If we do not use the constructed sparse graph of the co-occurrence relationship of the identifiers of the mobile devices, the complexity of an algorithm for entity identification of the mobile devices is too high, parallel computing is not facilitated, and large-scale data cannot be processed.
According to the mobile equipment identification method, the number of edges in the co-occurrence relation sparse graph is obtained, the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center are obtained according to the number of edges in the co-occurrence relation sparse graph, if the characteristics of the mobile equipment centers to which the identifiers belong are the same, the identifiers are determined to be the identifiers of the same mobile equipment, and the mobile equipment uniquely corresponding to the identifiers is determined according to the similarity between the characteristics of the mobile equipment centers to which the identifiers belong and the characteristics of each equipment center. The entity recognition is carried out on the mobile equipment by utilizing the constructed co-occurrence relation sparse graph structure attribute and the unsupervised learning algorithm, and marked data is not needed to be used as input, so that the complexity of the entity recognition of the mobile equipment is reduced, and the accuracy of the entity recognition of the mobile equipment is greatly improved.
Corresponding to the method for constructing the co-occurrence relationship sparse graph of the mobile equipment identifier, the application also provides a device for constructing the co-occurrence relationship sparse graph of the mobile equipment identifier, and the method for constructing the co-occurrence relationship sparse graph of the mobile equipment identifier can be applied to the device. Since the embodiment of the apparatus is similar to the embodiment of the method, the description is simple, and the related points should be referred to the part of the embodiment of the method for description, and the following description of the embodiment of the apparatus is only illustrative. Please refer to fig. 3, which is a schematic diagram of an apparatus for constructing a sparse co-occurrence graph of mobile device identifiers according to an embodiment of the present disclosure.
The co-occurrence relation sparse graph construction device of the mobile equipment identifier comprises the following parts:
a first obtaining unit 301, configured to obtain a set of identifier information of a mobile device, and use the set of identifier information of the mobile device as a node of the sparse co-occurrence graph.
In this embodiment, the set of identifier information of the mobile device includes software and hardware identifier information corresponding to the mobile device. The software and hardware identifier information corresponding to the mobile device specifically includes: at least one of an equipment identity IMEI for uniquely identifying the mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the mobile equipment, an advertisement identifier IDFA for tracking the mobile equipment operational information, and a software identifier UTDID for uniquely identifying the mobile equipment. It should be noted that the set of identifier information of the mobile device uniquely represents an actual physical mobile device.
A second obtaining unit 302, configured to obtain a node including the first identifier.
In this embodiment, the first identifier includes at least one of an equipment identity IMEI for uniquely identifying the first mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile equipment, an advertisement identifier IDFA for tracking operation information of the first mobile equipment, and a software identifier UTDID for uniquely identifying the first mobile equipment.
A connecting unit 303, configured to connect the nodes including the first identifier.
In this embodiment, for each identifier we traverse through all the sets of mobile device identifier information (i.e., nodes in the graph), finding all the nodes containing this identifier to connect. It should be noted that in the embodiment of the present application, four identifiers, i.e., IMEI, IMSI, IDFA, and UTDID, are mainly extracted, if one identifier appears in two different nodes, the two nodes are connected into one edge, and the found nodes are connected in pairs in sequence to form a composition. When one identifier appears in a large number of nodes, namely excessive nodes are associated, in this case, edges are not connected, and the excessive connected nodes are deleted, so that the sparsity of the graph is ensured, and the time complexity is reduced.
A deleting unit 304, configured to delete the connection relationship between the nodes including the first identifier when the number of the nodes including the first identifier reaches or exceeds a preset node number threshold, so as to obtain the sparse co-occurrence relationship graph.
In this embodiment, the preset node number threshold is 1000, in order to reduce the time complexity, when the number of nodes including any one identifier of the four identifiers, i.e., IMEI, IMSI, IDFA, UTDID, reaches or exceeds 1000, that is, if one identifier appears in more than one thousand nodes, the nodes including any identifier are not connected in the sub-loop, and the connection relationship between the nodes including the same identifier is deleted, so as to obtain the constructed co-occurrence relationship sparse graph of the mobile device.
Corresponding to the above method for constructing a sparse graph of co-occurrence relationship of identifiers of mobile devices, an embodiment of the present application further provides an electronic device, please refer to fig. 4, which is a schematic diagram of an electronic device constructed by a sparse graph of co-occurrence relationship of identifiers of mobile devices according to an embodiment of the present application.
The electronic equipment constructed by the co-occurrence relation sparse graph of the mobile equipment identifier comprises the following parts:
a processor 401; and
a memory 402, configured to store a program of a method for constructing a sparse co-occurrence map of a mobile device identifier, where after the device is powered on and the program of the method for constructing a sparse co-occurrence map of a mobile device identifier is executed by the processor, the following steps are performed:
acquiring a set of identifier information of mobile equipment, and taking the set of identifier information of the mobile equipment as a node of the co-occurrence relation sparse graph;
acquiring a node containing a first identifier;
connecting the nodes including the first identifier;
and when the number of the nodes containing the first identifier reaches or exceeds a preset node number threshold value, deleting the connection relation among the nodes containing the first identifier to obtain the co-occurrence relation sparse graph.
It should be noted that, for the detailed description of the electronic device provided in the embodiment of the present application, reference may be made to the related description of the method for constructing the sparse graph of the co-occurrence relationship of the mobile device identifier provided in the embodiment of the present application, and details are not repeated here.
Corresponding to the mobile equipment identification method, the application also provides a mobile equipment identification device, and the mobile equipment identification method can be applied to the device. Since the embodiment of the apparatus is similar to the embodiment of the method, the description is simple, and the related points should be referred to the part of the embodiment of the method for description, and the following description of the embodiment of the apparatus is only illustrative. Please refer to fig. 5, which is a schematic diagram of an identification apparatus for a mobile device according to an embodiment of the present application.
The mobile equipment identification device comprises the following parts:
the first obtaining unit 501 obtains the number of edges in a co-occurrence relationship sparse graph, where the co-occurrence relationship sparse graph is obtained by connecting nodes including the same identifier with a set of identifier information of the mobile device as nodes, and deleting the connection relationships between the nodes including the same identifier whose number reaches or exceeds a preset node number threshold.
In this embodiment, the obtaining the feature of the mobile device center to which the identifier belongs and the feature of each mobile device center according to the number of edges in the co-occurrence relationship sparse graph specifically includes: and establishing an objective function of the unsupervised learning algorithm, inputting the number of edges in the co-occurrence relation sparse graph as a parameter into the objective function of the unsupervised learning algorithm for parallelized iterative optimization algorithm training, and obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center.
The second obtaining unit 502 obtains the feature of the mobile device center to which the identifier belongs and the feature of each mobile device center according to the number of edges in the co-occurrence relationship sparse graph.
In this embodiment, the obtaining of the feature of the mobile device center to which the identifier belongs and the feature of each mobile device center according to the number of edges in the co-occurrence relationship sparse graph specifically includes establishing an objective function of an unsupervised learning algorithm, and inputting the number of edges in the constructed co-occurrence relationship sparse graph as a parameter into the objective function of the unsupervised learning algorithm for parallelized iterative optimization algorithm training to obtain the feature of the mobile device center to which the identifier belongs and the feature of each mobile device center.
A first determining unit 503, configured to determine that the multiple identifiers are multiple identifiers of the same mobile device if the features of the mobile device centers to which the multiple identifiers belong are the same.
A second determining unit 504, configured to determine, according to a similarity between a feature of a mobile device center to which the plurality of identifiers belong and a feature of each device center, the mobile device to which the plurality of identifiers uniquely correspond.
In this embodiment, an iterative optimization algorithm training is performed in parallel according to an objective function of an unsupervised learning algorithm in an unconstrained augmented lagrange form to obtain an analytic solution, where the analytic solution is a feature of each mobile device center obtained in the current iteration, and after a feature of each mobile device center is obtained, according to the obtained feature of the mobile device center to which each identifier belongs and the feature of each mobile device center, an identifier included in each node is corresponding to a unique mobile device with the closest feature similarity, so as to determine a final result of mobile device entity identification based on a mobile device identifier co-occurrence relationship sparse graph.
Corresponding to the above-mentioned mobile device identification method, an embodiment of the present application further provides an electronic device, please refer to fig. 6, which is a schematic diagram of an electronic device identified by a mobile device according to an embodiment of the present application.
The electronic equipment identified by the mobile equipment comprises the following parts:
a processor 601; and
a memory 602 for storing a program of a mobile device identification method, the device being powered on and the program of the mobile device identification method being executed by the processor to perform the steps of:
obtaining the number of edges in a co-occurrence relationship sparse graph, wherein the co-occurrence relationship sparse graph is obtained by connecting nodes containing the same identifier by taking a set of identifier information of the mobile equipment as a node, and deleting the connection relationship among the nodes containing the same identifier, the number of which reaches or exceeds a preset node number threshold;
according to the number of edges in the co-occurrence relation sparse graph, obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center;
if the characteristics of the mobile equipment centers of a plurality of identifiers are the same, determining the plurality of identifiers to be a plurality of identifiers of the same mobile equipment;
and determining the mobile equipment uniquely corresponding to the identifiers according to the similarity between the characteristics of the mobile equipment center to which the identifiers belong and the characteristics of each equipment center.
It should be noted that, for the detailed description of the electronic device provided in the embodiment of the present application, reference may be made to the related description of the mobile device identification method provided in the embodiment of the present application, and details are not repeated here.
Corresponding to the above-mentioned method and apparatus for identifying a mobile device, an embodiment of the present application further provides a system for identifying a mobile device, please refer to fig. 7, which is a flowchart illustrating a working process of the system for identifying a mobile device according to the embodiment of the present application.
In this embodiment, the mobile device identification system includes: the embodiment mentioned above refers to a co-occurrence sparse graph construction apparatus for any one of the mobile device identifiers, and a mobile device identification apparatus.
Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application, and those skilled in the art can make variations and modifications without departing from the spirit and scope of the present application, therefore, the scope of the present application should be determined by the claims that follow.

Claims (14)

1. A method for constructing a sparse graph of co-occurrence relationships of identifiers of mobile devices is characterized by comprising the following steps:
acquiring a set of mobile equipment identifier information, and taking the set of mobile equipment identifier information as a node of the co-occurrence sparse graph;
acquiring a node containing a first identifier;
connecting the nodes including the first identifier; wherein the first identifier comprises at least one of an equipment identity IMEI for uniquely identifying a first mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile equipment, an advertisement identifier IDFA for tracking the first mobile equipment operation information, and a software identifier UTDID for uniquely identifying the first mobile equipment;
and when the number of the connected nodes containing the first identifier reaches or exceeds a preset node number threshold value, deleting the connection relation among the nodes containing the first identifier to obtain the co-occurrence relation sparse graph.
2. The method of claim 1, wherein the set of mobile device identifier information comprises software and hardware identifier information corresponding to the mobile device.
3. The method according to claim 2, wherein the software and hardware identifier information corresponding to the mobile device specifically includes at least one of the following identifier information:
an equipment identity, IMEI, for uniquely identifying the mobile equipment;
a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the mobile device;
an advertisement Identifier (IDFA) for tracking the mobile device operation information;
a software identifier UTDID for uniquely identifying the mobile device.
4. The method of claim 1, wherein the set of mobile device identifier information uniquely represents a real physical mobile device.
5. A mobile device identification method, comprising:
obtaining the number of edges in a co-occurrence relation sparse graph, wherein the co-occurrence relation sparse graph is obtained by connecting nodes containing the same identifier by taking the set of the mobile equipment identifier information as nodes and deleting the connection relation among the nodes containing the same identifier, the number of which reaches or exceeds a preset node number threshold; wherein the node comprises at least one of an equipment identity IMEI for uniquely identifying a first mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile equipment, an advertisement identifier IDFA for tracking the first mobile equipment operation information, and a software identifier UTDID for uniquely identifying the first mobile equipment;
according to the number of edges in the co-occurrence relation sparse graph, obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center;
if the characteristics of the mobile equipment centers of a plurality of identifiers are the same, determining the plurality of identifiers to be a plurality of identifiers of the same mobile equipment;
and determining the mobile equipment uniquely corresponding to the identifiers according to the similarity between the characteristics of the mobile equipment center to which the identifiers belong and the characteristics of each equipment center.
6. The method according to claim 5, wherein the obtaining features of the mobile device center to which the identifier belongs and features of each mobile device center according to the number of edges in the co-occurrence sparse graph comprises:
establishing an objective function of an unsupervised learning algorithm;
and inputting the number of edges in the co-occurrence relation sparse graph as a parameter into an objective function of an unsupervised learning algorithm to carry out parallelized iterative optimization algorithm training, and obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center.
7. The mobile device identification method of claim 6, wherein the expression of the objective function of the unsupervised learning algorithm is as follows:
Figure FDA0003325477630000021
wherein x isiIs a feature of each set of identifiers, ciThe method comprises the steps that the identifier belongs to the center of the mobile equipment, g is a distance function, i and j are identifications of any two nodes of the co-occurrence sparse graph, V represents a value range of any node of the co-occurrence sparse graph, and E represents a value range of any two nodes of the co-occurrence sparse graph.
8. An apparatus for constructing a sparse graph of co-occurrence relationships of identifiers of mobile devices, comprising:
a first obtaining unit, configured to obtain a set of mobile device identifier information, and use the set of mobile device identifier information as a node of the co-occurrence sparse graph;
a second acquisition unit configured to acquire a node including the first identifier;
a connecting unit for connecting the nodes including the first identifier; wherein the first identifier comprises at least one of an equipment identity IMEI for uniquely identifying a first mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile equipment, an advertisement identifier IDFA for tracking the first mobile equipment operation information, and a software identifier UTDID for uniquely identifying the first mobile equipment;
and the deleting unit is used for deleting the connection relation among the nodes containing the first identifier when the number of the connected nodes containing the first identifier reaches or exceeds a preset node number threshold value, so as to obtain the co-occurrence relation sparse graph.
9. An electronic device, comprising:
a processor; and
a memory for storing a program of a co-occurrence sparse graph construction method of a mobile device identifier, wherein after the device is powered on and runs the program of the co-occurrence sparse graph construction method of the mobile device identifier through the processor, the following steps are executed:
acquiring a set of mobile equipment identifier information, and taking the set of mobile equipment identifier information as a node of the co-occurrence sparse graph;
acquiring a node containing a first identifier;
connecting the nodes including the first identifier; wherein the first identifier comprises at least one of an equipment identity IMEI for uniquely identifying a first mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile equipment, an advertisement identifier IDFA for tracking the first mobile equipment operation information, and a software identifier UTDID for uniquely identifying the first mobile equipment;
and when the number of the connected nodes containing the first identifier reaches or exceeds a preset node number threshold value, deleting the connection relation among the nodes containing the first identifier to obtain the co-occurrence relation sparse graph.
10. A storage device, characterized in that,
a program storing a method for constructing a sparse graph of co-occurrence relationships of mobile device identifiers, the program being executed by a processor and performing the steps of:
acquiring a set of mobile equipment identifier information, and taking the set of mobile equipment identifier information as a node of the co-occurrence sparse graph;
acquiring a node containing a first identifier;
connecting the nodes including the first identifier; wherein the first identifier comprises at least one of an equipment identity IMEI for uniquely identifying a first mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile equipment, an advertisement identifier IDFA for tracking the first mobile equipment operation information, and a software identifier UTDID for uniquely identifying the first mobile equipment;
and when the number of the connected nodes containing the first identifier reaches or exceeds a preset node number threshold value, deleting the connection relation among the nodes containing the first identifier to obtain the co-occurrence relation sparse graph.
11. An apparatus for identifying a mobile device, comprising:
a first obtaining unit configured to obtain the number of edges in a co-occurrence-relationship sparse graph, where the co-occurrence-relationship sparse graph is obtained by connecting nodes including the same identifier with a set of the mobile device identifier information as nodes, and deleting a connection relationship between the nodes including the same identifier, where the number of the nodes reaches or exceeds a preset node number threshold; wherein the node comprises at least one of an equipment identity IMEI for uniquely identifying a first mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile equipment, an advertisement identifier IDFA for tracking the first mobile equipment operation information, and a software identifier UTDID for uniquely identifying the first mobile equipment;
the second obtaining unit is used for obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center according to the number of edges in the co-occurrence relation sparse graph;
the first determining unit is used for determining a plurality of identifiers as a plurality of identifiers of the same mobile equipment if the characteristics of the mobile equipment centers to which the plurality of identifiers belong are the same;
and the second determining unit is used for determining the mobile equipment uniquely corresponding to the identifiers according to the similarity between the characteristics of the mobile equipment centers to which the identifiers belong and the characteristics of each equipment center.
12. An electronic device, comprising:
a processor; and
a memory for storing a program of a mobile device identification method, the device being powered on and executing the program of the mobile device identification method by the processor, and performing the steps of:
obtaining the number of edges in a co-occurrence relation sparse graph, wherein the co-occurrence relation sparse graph is obtained by connecting nodes containing the same identifier by taking the set of the mobile equipment identifier information as nodes and deleting the connection relation among the nodes containing the same identifier, the number of which reaches or exceeds a preset node number threshold; wherein the node comprises at least one of an equipment identity IMEI for uniquely identifying a first mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile equipment, an advertisement identifier IDFA for tracking the first mobile equipment operation information, and a software identifier UTDID for uniquely identifying the first mobile equipment;
according to the number of edges in the co-occurrence relation sparse graph, obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center;
if the characteristics of the mobile equipment centers of a plurality of identifiers are the same, determining the plurality of identifiers to be a plurality of identifiers of the same mobile equipment;
and determining the mobile equipment uniquely corresponding to the identifiers according to the similarity between the characteristics of the mobile equipment center to which the identifiers belong and the characteristics of each equipment center.
13. A storage device storing a program for a mobile device identification method, the program being executed by a processor to perform the steps of:
obtaining the number of edges in a co-occurrence relation sparse graph, wherein the co-occurrence relation sparse graph is obtained by connecting nodes containing the same identifier by taking the set of the mobile equipment identifier information as nodes and deleting the connection relation among the nodes containing the same identifier, the number of which reaches or exceeds a preset node number threshold; wherein the node comprises at least one of an equipment identity IMEI for uniquely identifying a first mobile equipment, a subscriber identity IMSI for uniquely identifying mobile subscriber information corresponding to the first mobile equipment, an advertisement identifier IDFA for tracking the first mobile equipment operation information, and a software identifier UTDID for uniquely identifying the first mobile equipment;
according to the number of edges in the co-occurrence relation sparse graph, obtaining the characteristics of the mobile equipment center to which the identifier belongs and the characteristics of each mobile equipment center;
if the characteristics of the mobile equipment centers of a plurality of identifiers are the same, determining the plurality of identifiers to be a plurality of identifiers of the same mobile equipment;
and determining the mobile equipment uniquely corresponding to the identifiers according to the similarity between the characteristics of the mobile equipment center to which the identifiers belong and the characteristics of each equipment center.
14. A mobile device identification system, comprising: the apparatus for constructing a sparse co-occurrence map of mobile device identifiers as claimed in claim 8, and the apparatus for identifying mobile devices as claimed in claim 11.
CN201811011882.6A 2018-08-31 2018-08-31 Method and device for constructing sparse graph of co-occurrence relation of identifiers of mobile equipment Active CN110874387B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811011882.6A CN110874387B (en) 2018-08-31 2018-08-31 Method and device for constructing sparse graph of co-occurrence relation of identifiers of mobile equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811011882.6A CN110874387B (en) 2018-08-31 2018-08-31 Method and device for constructing sparse graph of co-occurrence relation of identifiers of mobile equipment

Publications (2)

Publication Number Publication Date
CN110874387A CN110874387A (en) 2020-03-10
CN110874387B true CN110874387B (en) 2022-01-14

Family

ID=69715903

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811011882.6A Active CN110874387B (en) 2018-08-31 2018-08-31 Method and device for constructing sparse graph of co-occurrence relation of identifiers of mobile equipment

Country Status (1)

Country Link
CN (1) CN110874387B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112601215A (en) * 2020-12-01 2021-04-02 深圳市和讯华谷信息技术有限公司 Method and device for unifying equipment identifications
CN113254318B (en) * 2021-07-06 2021-10-22 北京达佳互联信息技术有限公司 Method and device for determining equipment identification information, electronic equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105824802A (en) * 2016-03-31 2016-08-03 清华大学 Method and device for acquiring knowledge graph vectoring expression
CN106951920A (en) * 2017-03-06 2017-07-14 江南大学 It is a kind of based on semi-supervised sparse subspace clustering algorithm
CN107276938A (en) * 2017-06-28 2017-10-20 北京邮电大学 A kind of digital signal modulation mode recognition methods and device

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105930812A (en) * 2016-04-27 2016-09-07 东南大学 Vehicle brand type identification method based on fusion feature sparse coding model
CN107808664B (en) * 2016-08-30 2021-07-30 富士通株式会社 Sparse neural network-based voice recognition method, voice recognition device and electronic equipment
CN107561576B (en) * 2017-08-31 2023-10-20 中油奥博(成都)科技有限公司 Seismic signal recovery method based on dictionary learning regularized sparse representation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105824802A (en) * 2016-03-31 2016-08-03 清华大学 Method and device for acquiring knowledge graph vectoring expression
CN106951920A (en) * 2017-03-06 2017-07-14 江南大学 It is a kind of based on semi-supervised sparse subspace clustering algorithm
CN107276938A (en) * 2017-06-28 2017-10-20 北京邮电大学 A kind of digital signal modulation mode recognition methods and device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Mobile Access Record Resolution on Large-Scale Identifier-Linkage Graphs;SHEN Xin;《KDD 2018》;20180719;论文第1-5节 *

Also Published As

Publication number Publication date
CN110874387A (en) 2020-03-10

Similar Documents

Publication Publication Date Title
CN110287688B (en) Associated account analysis method and device and computer-readable storage medium
CN109783604B (en) Information extraction method and device based on small amount of samples and computer equipment
CN109117854B (en) Key point matching method and device, electronic equipment and storage medium
CN105069457B (en) Image recognition method and device
CN109685805B (en) Image segmentation method and device
CN109002784B (en) Street view identification method and system
CN111461164B (en) Sample data set capacity expansion method and model training method
CN110874387B (en) Method and device for constructing sparse graph of co-occurrence relation of identifiers of mobile equipment
CN109783805B (en) Network community user identification method and device and readable storage medium
CN110457704B (en) Target field determination method and device, storage medium and electronic device
CN112364014A (en) Data query method, device, server and storage medium
CN106572486B (en) Handheld terminal flow identification method and system based on machine learning
WO2019061667A1 (en) Electronic apparatus, data processing method and system, and computer-readable storage medium
CN111177436A (en) Face feature retrieval method, device and equipment
CN105302715A (en) Application user interface acquisition method and apparatus
CN110874465B (en) Mobile equipment entity identification method and device based on semi-supervised learning algorithm
CN108830302B (en) Image classification method, training method, classification prediction method and related device
CN114781517A (en) Risk identification method and device and terminal equipment
CN115830618A (en) Text recognition method and device, computer equipment and storage medium
CN107329946B (en) Similarity calculation method and device
CN113159211B (en) Method, computing device and computer storage medium for similar image retrieval
CN114528973A (en) Method for generating business processing model, business processing method and device
CN112148724A (en) Equipment identification processing method and system, computer equipment and readable storage medium
CN108154177B (en) Service identification method, device, terminal equipment and storage medium
CN111199189A (en) Target object tracking method and system, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Wang Can

Inventor after: Shen Xin

Inventor after: Wei Zhao Xian

Inventor after: Yang Hongxia

Inventor after: Wang Zhongyao

Inventor before: Shen Xin

Inventor before: Wei Zhao Xian

Inventor before: Yang Hongxia

Inventor before: Wang Zhongyao

GR01 Patent grant
GR01 Patent grant