Labeling method and device of federal chart node, computer device and medium

Abstract

The present application relates to the technical field of communication, and especially relates to a federal graph node marking method and device, computer equipment and medium. The method constructs user graph structure data of each marking participant according to user identity information, corresponding marking information and marking propagation relationship of each marking participant, then sends local user graph structure data to other marking participants, receives user graph structure data sent by other marking participants, and finally marks nodes of local user graph structure data according to marking information in user graph structure data of each marking participant and known marking propagation relationship. In the case of limited directly available node marking information, the node marking can be completed completely, the marking time cost is reduced, and the marking efficiency of federal graph node information is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and in particular to a federal graph node marking method and device, computer equipment and medium. BACKGROUND

[0002] The existing federal graph node marking method receives user identity information and corresponding marking information sent by each marking participant, compares the user identity information sent by each marking participant with the user identity information stored in the local node, and marks the marking information corresponding to the user identity information with the same user identity information in the local node.

[0003] However, due to the relatively miscellaneous federal graph node information, and the possibility of information loss in the storage process and the transmission process, the actual information available for node marking is limited, and the node marking effect is poor. In order to improve the marking effect, the existing method needs to perform multiple repeated node information transmissions between the local node and multiple marking participants when marking the node, which is time-consuming and costly, resulting in low node marking efficiency. Therefore, how to improve the marking efficiency of the federal graph node has become a problem to be solved. SUMMARY

[0004] Therefore, the embodiments of the present application provide a federal graph node marking method, device, computer equipment and medium to solve the problem of low marking efficiency of the federal graph node.

[0005] In a first aspect, the embodiments of the present application provide a federal graph node marking method, which comprises:

[0006] Obtaining the identity information and corresponding marking information of each user in the local node;

[0007] Taking each user as a node, taking the identity information and the marking information of each user as node information of each user, connecting each node with known marking propagation relationship according to the node information to obtain local user graph structure data;

[0008] Sending the local user graph structure data to N marking participants, N being an integer greater than 0, so that each marking participant marks the nodes of the user graph structure data according to the marking information in the local user graph structure data and the known marking propagation relationship;

[0009] Receiving the user graph structure data of the N marking participants;

[0010] Marking the nodes of the local user graph structure data according to the marking information in the user graph structure data of the N marking participants and the known marking propagation relationship.

[0011] In a second aspect, an embodiment of the present application provides a marking device for a federated graph node, the marking device comprising:

[0012] a user information obtaining module configured to obtain identity information and corresponding marking information of each user in a local area;

[0013] a graph structure data constructing module configured to take each user as a node, take the identity information and the marking information of each user as node information of each user, connect each node having a known marking propagation relationship according to the node information, and obtain user graph structure data in the local area;

[0014] a graph structure data sending module configured to send the user graph structure data in the local area to N marking participants, N being an integer greater than 0, so that each marking participant performs node marking on user graph structure data of each marking participant according to marking information and the known marking propagation relationship in the user graph structure data in the local area;

[0015] a graph structure data receiving module configured to receive user graph structure data of the N marking participants;

[0016] a node marking module configured to perform node marking on the user graph structure data in the local area according to marking information and the known marking propagation relationship in the user graph structure data of the N marking participants.

[0017] In a third aspect, an embodiment of the present application provides a computer device, which comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the marking method according to the first aspect when executing the computer program.

[0018] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the marking method according to the first aspect.

[0019] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0020] The embodiment of the present application uses user graph structure data to transmit node information and then performs node marking, so that the marking propagation relationship between node information can be effectively utilized when performing node marking, thereby mining potential node marking information, i.e., node marking information that is not directly given but can be inferred according to known node information and the marking propagation relationship. In the case where direct node marking information is limited, the embodiment of the present application can completely perform node marking and reduce marking time cost, thereby effectively improving the marking efficiency of federated graph node information. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0022] Figure 1 is an application environment schematic diagram of a federal graph node marking method provided by an embodiment of the present application;

[0023] Figure 2 is a flow schematic diagram of a federal graph node marking method provided by an embodiment of the present application;

[0024] Figure 3 is a flow schematic diagram of a federal graph node marking update information transmission method provided by an embodiment of the present application;

[0025] Figure 4 is a structure schematic diagram of a federal graph node marking device provided by an embodiment of the present application;

[0026] Figure 5 is a structure schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0027] In the following description, specific details are set forth in order to provide a thorough understanding of the embodiments of the present application. However, persons skilled in the art will understand that the present application can be practiced without these specific details. In other instances, well-known structures, devices, circuits, and methods have not been described in detail in order to avoid obscuring the present application.

[0028] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0029] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0030] As used in the description of the application and the appended claims, the term "if' can be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the described condition or event]" or "in response to detecting [the described condition or event]," depending on the context.

[0031] In addition, the description in the description and the appended claims of the application, the term "first", "second", "third" and the like are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0032] In the description of the application, the reference "one embodiment" or "some embodiments" and the like means that the specific features, structures or characteristics described in connection with the embodiment are included in one or more embodiments of the application. Therefore, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in additional some embodiments" and the like appearing in different places in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "include", "contain", "have" and their variants mean "include but not limited to", unless otherwise specifically emphasized.

[0033] It should be understood that the size of the serial number of each step in the following embodiments does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the application.

[0034] In order to illustrate the technical solutions of the application, the following specific embodiments are described.

[0035] The marking method of the federal graph node provided by the embodiment one of the application can be applied in the application environment of Figure 1 , wherein the computer devices of the marking participants communicate with each other. The computer devices include but are not limited to palmtop computers, desktop computers, notebook computers, ultra-mobile personal computers (UMPC), netbooks, cloud terminal devices, personal digital assistants (PDA) and the like.

[0036] Referring to Figure 2 is a flowchart of the marking method of the federal graph node provided by the embodiment one of the application, and the marking method can be applied in Figure 1The computer device in the local database is connected to a corresponding database to obtain corresponding user identity information, corresponding label information, and label propagation relationships in the database. As shown in FIG. 13, the labeling method can include the following steps. Figure 2

[0037] In step S201, the identity information and corresponding label information of each user in the local are obtained.

[0038] The identity information of the user can be user ID and user name and the like, and the label information corresponding to the identity information of the user can be category digital label, category letter label, and category one-hot encoding label and the like.

[0039] The identity information and corresponding label information of each user are stored in the database of the local server. In this embodiment, the identity information and corresponding label information of each user are stored in the form of a vector, specifically a one-dimensional vector of 2 columns and 1 row. The element in the first column and the first row is the identity information of the user, and the element in the second column and the first row is the label information corresponding to the identity information of the user. It should be noted that the local database can only contain the identity information of a user but not the corresponding label information. In this case, the element in the second column and the first row of the corresponding storage vector is , indicating that there is no corresponding label information.

[0040] In an embodiment, the identity information and corresponding label information of each user can also be stored in the form of an index, a vector, and a tree connection, and the like.

[0041] In step S202, each user is taken as a node, the identity information and label information of each user are taken as node information of each user, and each node with a known label propagation relationship is connected according to the node information to obtain the local user graph structure data.

[0042] The known label propagation relationship is a relationship in which the node label information is the same.

[0043] For example, the local database contains K users, K≥2, K graph nodes are constructed, the information in the kth node is the identity information and corresponding label information of the kth user, k∈{1,2,…,K}, and when the label information of the k1th node is the same as that of the k2th node and is not k1∈{1,2,…,K}, k2∈{1,2,…,K}, the k1th node and the k2th node are connected, an edge between the nodes is formed, and the local user graph structure data is obtained.

[0044] Optionally, taking the identity information and label information of each user as node information of each user includes:

[0045] ​Obtaining a unique identifier of each user as identity information of the user;

[0046] Detecting a category label corresponding to the identity information of the user in the local database, if the category label exists, determining the category label as the marking information corresponding to the identity information of the user, and if the category label does not exist, using a preset label as the marking information corresponding to the identity information of the user.

[0047] Wherein, the unique identifier of each user indicates that the identifier of each user is uniquely determined, the identifiers of different users are different, and the identifier of any user is consistent in the database of all marking participants, so as to omit the user identity information alignment step when each marking participant interacts information, improve the information interaction efficiency, for example, for user A, if the user identifier of user A is A, the identifiers of other users are not A, and in the marking participant database containing user A, the identifier of the user in different marking participant databases is A.

[0048] In an embodiment, the category label uses a category one-hot encoding label to adapt to the training task in a federated scenario, and the preset label is also a category one-hot encoding label, but is a fixed one-hot encoding value and is different from the category one-hot encoding label of the user, so as to interact information of each marking participant in the same data form, for example, if there are four kinds of category labels for local users, the category one-hot encoding value of the preset label is set to 0000, and the one-hot encoding values of other category labels are 0001, 0010, 0100 and 1000, it is detected whether each local user has a corresponding category label, if yes, the one-hot encoding value is determined according to the category label, and if not, the one-hot encoding value is determined according to the preset label.

[0049] Optionally, connecting each node with a known marking propagation relationship comprises:

[0050] When the marking information between the nodes to be connected is the same and neither is the preset label, the preset first connection mode is used to connect between the nodes to be connected;

[0051] When the marking information between the nodes to be connected is different and neither is the preset label, the preset second connection mode is used to connect between the nodes to be connected;

[0052] When the marking information of any node to be connected is the preset label, the node to be connected is not connected with any node.

[0053] Wherein, the preset first connection mode and the preset second connection mode can be a line segment, a curve, a one-way arrow and a two-way arrow, etc. which can be used to represent the connection relationship, and the forms of the preset first connection mode and the preset second connection mode are different.

[0054] For example, the preset first connection mode adopts a bidirectional arrow, the preset second connection mode adopts a unidirectional arrow, if the one-hot encoding value of the category label of user A is 0001, and the one-hot encoding value of the category label of user B is 0001, then the bidirectional arrow is adopted to connect the user A node and the user B node, if the one-hot encoding value of the category label of user A is 0001, and the one-hot encoding value of the category label of user B is 0010, then the unidirectional arrow is adopted to connect the user A node and the user B node, if the one-hot encoding value of the category label of user A is 0001, and user B has no category label, then the user A node and the user B node are not connected, the determination of the edges between the nodes in the preset first connection mode, the preset second connection mode and the non-connection mode can further enrich the content of the known label propagation relationship, and then the efficiency of mining the potential label information of the nodes according to the label propagation relationship is improved.

[0055] The above takes each user as a node, takes the identity information and the label information of each user as the node information of each user, connects each node with the known label propagation relationship according to the node information, and obtains the local user graph structure data. The local user graph structure data is constructed in the form of the local user graph structure data, the label propagation relationship between the node information can also be taken as the to-be-transmitted information, and then the content of the to-be-transmitted information is enriched, so that the subsequent node labeling of other label participants is facilitated.

[0056] In step S203, the local user graph structure data is sent to N label participants, so that each label participant labels the nodes of the user graph structure data of each label participant according to the label information and the known label propagation relationship in the local user graph structure data.

[0057] N is an integer greater than 0.

[0058] Specifically, after the N label participants receive the local user graph structure data, the node information and the edge information of the local user graph structure data are extracted, the local user identity information, the corresponding label information and the local known label propagation relationship are obtained, the label information corresponding to the user identity information is directly or indirectly obtained according to the local user identity information, the corresponding label information and the local known label propagation relationship, and the node labeling of the user graph structure data of each label participant is performed.

[0059] For example, the process of directly obtaining the label information corresponding to the user identity information according to the local user identity information, the corresponding label information and the local known label propagation relationship is as follows:

[0060] The database of the first marking participant contains user identity information and corresponding marking information 0001 of user A, and user identity information and corresponding marking information 0001 of user B, but the marking information of user A is lost in the database or lost in the transmission process;

[0061] The database of the second marking participant contains only user identity information of user A and user B. Since there is an edge between user A and user B constructed according to the known marking propagation relationship, the second marking participant can directly obtain the marking information of user B as 0001 and infer the marking information of user A as 0001 after receiving the user graph structure data sent by the first marking participant.

[0062] Further, an example is given to illustrate the process of indirectly obtaining the marking information corresponding to the user identity information according to the local user identity information, corresponding marking information and local known marking propagation relationship under the condition that the edges of the nodes with known marking propagation relationship are constructed in the preset first connection mode, the preset second connection mode and no connection, which is as follows:

[0063] The database of the first marking participant contains user identity information and corresponding marking information 0001 of user A, and user identity information and corresponding marking information 0010 of user B, but the marking information of user A is lost in the database or lost in the transmission process, and the known marking propagation relationship between user A and user B is the preset second connection mode;

[0064] The database of the second marking participant contains user identity information of user A, user identity information and corresponding marking information 0100 of user C, user identity information and corresponding marking information 1000 of user D, and the known marking propagation relationship between user A and user C is the preset second connection mode and the known marking propagation relationship between user A and user D is the preset second connection mode;

[0065] Therefore, the second marking participant can infer that the marking information of user A is 0001 after receiving the user graph structure data sent by the first marking participant.

[0066] Optionally, sending the local user graph structure data to N marking participants includes:

[0067] generating N groups of first public keys p i and first private keys s i , i ∈ {1, 2, …, N}, and sending the first public key p i to the corresponding i-th marking participant;

[0068] receiving the first data sent by the i-th marking participant, the first data being the first public key p iBlind the node information in the user graph structure data of the i-th labeled participant to obtain data;

[0069] adopt the first private key s i Encrypt the first data sent by the i-th labeled participant and the local user graph structure data respectively, and transmit the encrypted local user graph structure data and the first data sent by the i-th labeled participant to the i-th labeled participant.

[0070] Wherein, the first public key p i and the first private key s i The public key and the private key generated when the information transmission is carried out by using the asymmetric encryption algorithm, and the asymmetric encryption algorithm can be selected from the existing asymmetric encryption algorithms such as RSA encryption algorithm, ElGamal encryption algorithm and elliptic encryption algorithm.

[0071] For example, the node information blind processing process is that the i-th labeled participant generates a random number r i , selects a blind function F, and calculates F(A, p i , r i ) as the data obtained by blind processing the node information, wherein A is the user identity information in the node information of the i-th labeled participant.

[0072] For example, the process of encrypting the first data sent by the i-th labeled participant and the local user graph structure data by using the first private key s i is that the local labeled participant selects an encryption function E, calculates E(F(A, p i , r i ), s i ) as the encrypted first data sent by the i-th labeled participant, and calculates E(A, s i ), E(B, s i ), E(A, s i )-E(B, s i ) and E(A, s i ):0001 as the encrypted local user graph structure data and transmits them to the i-th labeled participant.

[0073] The data is blinded and encrypted in this embodiment, which is beneficial to ensure the security of the user graph structure data transmission process of each labeled participant and avoid data interception leading to information leakage or data tampering.

[0074] The step of sending the local user graph structure data to the N label participants allows the N label participants to mine potential label information of the node according to the label propagation relationship between the node information, the potential label information being label information of the user that cannot be directly obtained according to the storage vector of the single user, but can be inferred by the known label propagation relationship, thereby improving the integrity of the single node label of each label participant and improving the efficiency of the node label of each label participant.

[0075] In step S204, the user graph structure data of the N label participants is received.

[0076] The user graph structure data of the N label participants includes the node information and the edge information of each label participant.

[0077] Optionally, the user graph structure data of the N label participants includes:

[0078] The second public key sent by the N label participants is received, and the second data obtained by blinding the local node information by using the second public key is transmitted to the corresponding label participant.

[0079] The encrypted user graph structure data and the encrypted second data sent by the N label participants are received, the encrypted user graph structure data being data obtained by encrypting the user graph structure data of the corresponding label participant by using the second private key, and the encrypted second data being data obtained by encrypting the second data of the corresponding label participant by using the second private key.

[0080] For example, the process of receiving the second public key sent by the N label participants, blinding the local node information by using the second public key to obtain the second data, and transmitting the second data to the corresponding label participant is as follows: the local end receives the second public key P i i sent by the i-th label participant, generates a random number R i , selects a blinding function F', calculates F(A, P i i, R i ) and F(B, P i i, R i ) as data obtained by blinding the node information, and sends the data to the i-th label participant as the second data, where A and B are user identity information in the node information of the local user graph structure data.

[0081] The process of receiving the encrypted user graph structure data and the encrypted second data sent by the N label participants is as follows: the encrypted second data E'(F(A, P i i, R i ), S i) and E'(F(B, P i ,R i ), S i ), where E' is an encryption function selected by the i-th label participant, S i is a second private key of the i-th label participant, and the encrypted user graph structure data of the i-th label participant sent by the i-th label participant is received, i.e., E'(A, S i ), where A is user identity information in the user graph structure data node information of the i-th label participant.

[0082] The above step of receiving the user graph structure data of the N label participants can mine potential label information of nodes according to the label propagation relationship between node information in the user graph structure data of the N label participants, enrich the content of available information, and facilitate subsequent node labeling locally.

[0083] In step S205, the user graph structure data locally is node-labeled according to the label information in the user graph structure data of the N label participants and the known label propagation relationship.

[0084] The local end obtains user identity information, corresponding label information and known label propagation relationship of each label participant according to the node information and edge information of the N label participants, and directly or indirectly obtains label information corresponding to the user identity information according to the user identity information, corresponding label information and known label propagation relationship of each label participant, and performs node labeling of the local user graph structure data.

[0085] Optionally, before the node labeling of the local user graph structure data according to the user graph structure data of the N label participants, the method further includes:

[0086] The encrypted second data of the N label participants is data-deblinded according to the blinded random number and the second public key, and the deblinded second data is obtained.

[0087] For example, the data deblinding process is that the local end obtains a deblinding function G, calculates G(E'(F(A, P i ,R i ), S i ), P i ,R i ) = E'(A, S i ) and G(E'(F(B, P i ,R i ), S i ), P i ,R i ) = E'(B, S i) as the second data after the de-blinding processing.

[0088] comparing the encrypted user graph structure data E'(A, S of the i-th labeled participant sent by the i-th labeled participant with the local user graph structure data, determining the user identity information that is consistent between the user identity information in the user graph structure data of the i-th labeled participant and the user identity information in the local user graph structure data. i

[0089] detecting whether the label information corresponding to the consistent user identity information exists in the user graph structure data of the i-th labeled participant.

[0090] if the label information exists, obtaining the label information corresponding to the user identity information, and if the label information does not exist, determining whether the label information corresponding to the user identity information can be obtained according to the known propagation relationship in the user graph structure data sent by the i-th labeled participant, and if so, obtaining the label information corresponding to the user identity information.

[0091] The label information is obtained by comparing the de-blinded encrypted data, which can determine the label information corresponding to the user identity information without knowing the specific user identity information, thereby improving the security and privacy of the federated graph node labeling.

[0092] The node labeling step of the local user graph structure data according to the label information in the user graph structure data of the N labeled participants and the known label propagation relationship can comprehensively label the nodes of multiple labeled participants, avoid information loss, and reduce the time cost of local node labeling.

[0093] The embodiment uses user graph structure data to transmit node information and then performs node labeling, so that the label propagation relationship between the node information can be effectively utilized when labeling the nodes, thereby mining the potential label information of the nodes, and in the case that the directly available node label information is limited, the node labeling can be performed completely, the label time cost is reduced, and the labeling efficiency of the federated graph node information is effectively improved.

[0094] Referring to Figure 3 is a flowchart of the local user graph structure data sending process provided by the second embodiment of the present application, and the sending process includes the following steps:

[0095] In step S301, the identity information and corresponding label information of each user are obtained.

[0096] In step S302, each user is taken as a node, the identity information and label information of each user are taken as the node information of each user, and each node with a known label propagation relationship is connected according to the node information, thereby obtaining the local user graph structure data.​

[0097] Step S303, the local user graph structure data is sent to the N label participants, so that each label participant performs node labeling of the user graph structure data of each label participant according to the label information in the local user graph structure data and the known label propagation relationship.

[0098] Step S304, the user graph structure data of the N label participants is received.

[0099] Step S305, the local user graph structure data is node labeled according to the label information in the user graph structure data of the N label participants and the known label propagation relationship.

[0100] Step S306, the local user graph structure data is updated according to the node-labeled label information, to obtain updated local user graph structure data.

[0101] Step S307, the updated local user graph structure data is sent to the N label participants.

[0102] Steps S301 to S305 are the same as the contents of steps S201 to S205, and refer to steps S201 to S205 for details, which will not be repeated here.

[0103] In step S306, the local user graph structure data updating method is as follows:

[0104] The updateable label information corresponding to each user identity information is determined according to the user graph structure data of the N label participants.

[0105] It is determined that the node information in which the user identity information corresponding to the updateable label information does not exist in the local graph structure data.

[0106] The label information obtained is updated to the node information in the local graph structure data.

[0107] For example, assume that the label information obtained according to the user graph structure data of the N label participants is [A, 0001], and the node information in the local graph structure data is [A, φ], then the node information in the local graph structure data is updated to [A, 0001].

[0108] In an embodiment, when the label information obtained through the user graph structure data of the N label participants is inconsistent, the label information sent by the label participant with the largest number of label participants is selected as the label information for subsequent updating.

[0109] In step S307, the edges in the updated local user graph structure data are connected according to the updated node information.

[0110] The marking method corresponding to the above embodiment, Figure 4 A structural block diagram of a marking device of a federation graph node provided by the third embodiment of the present application is shown, and the marking device is applied to a computer device which is connected to a database of a server end through a preset application program interface. For the convenience of description, only parts related to the embodiments of the present application are shown.

[0111] Referring to Figure 4 The marking device comprises:

[0112] A user information acquisition module 41 is configured to acquire identity information and corresponding marking information of each user in the local area;

[0113] A graph structure data construction module 42 is configured to take each user as a node, take the identity information and the marking information of each user as node information of each user, connect each node with a known marking propagation relationship according to the node information, and obtain user graph structure data in the local area;

[0114] A graph structure data sending module 43 is configured to send the user graph structure data in the local area to N marking participants, where N is an integer greater than 0, so as to enable each marking participant to mark nodes of user graph structure data of each marking participant according to the marking information and the known marking propagation relationship in the user graph structure data in the local area;

[0115] A graph structure data receiving module 44 is configured to receive user graph structure data of the N marking participants;

[0116] A node marking module 45 is configured to mark nodes of the user graph structure data in the local area according to the marking information and the known marking propagation relationship in the user graph structure data of the N marking participants.

[0117] Optionally, the graph structure data construction module 42 comprises:

[0118] A unique identifier acquisition unit is configured to acquire a unique identifier of each user as the identity information of the user;

[0119] A marking information acquisition unit is configured to detect a category label corresponding to the identity information of the user in the local database, determine the category label as the marking information corresponding to the identity information of the user if the category label exists, and take a preset label as the marking information corresponding to the identity information of the user if the category label does not exist.

[0120] Optionally, the graph structure data construction module 42 further comprises:

[0121] The first connection unit is configured to connect the to-be-connected nodes in a preset first connection mode when the marking information between the to-be-connected nodes is the same and neither is the preset label.

[0122] The second connection unit is configured to connect the to-be-connected nodes in a preset second connection mode when the marking information between the to-be-connected nodes is different and neither is the preset label.

[0123] The third connection unit is configured to not connect any node to the to-be-connected nodes when the marking information of any to-be-connected node is the preset label.

[0124] Optionally, the graph structure data sending module 43 includes:

[0125] The key generation unit is configured to generate N groups of first public keys p i and first private keys s i , i∈{1, 2, …, N}, and send the first public key p i to the corresponding i-th marking participant.

[0126] The first data receiving unit is configured to receive the first data sent by the i-th marking participant, the first data being data obtained by performing blind processing on the node information in the user graph structure data of the i-th marking participant by using the first public key p i .

[0127] The private key encryption unit is configured to encrypt the first data sent by the i-th marking participant and the local user graph structure data by using the first private key s i , and transmit the encrypted local user graph structure data and the first data sent by the i-th marking participant to the i-th marking participant.

[0128] Optionally, the graph structure data receiving module 44 includes:

[0129] The second data transmission unit is configured to receive the second public keys sent by the N marking participants, obtain second data by performing blind processing on the local node information by using the second public keys, and transmit the second data to the corresponding marking participants.

[0130] The encrypted data receiving unit is configured to receive the encrypted user graph structure data and the encrypted second data sent by the N marking participants, the encrypted user graph structure data being data obtained by encrypting the user graph structure data of the corresponding marking participant by using the second private key, and the encrypted second data being data obtained by encrypting the second data of the corresponding marking participant by using the second private key.

[0131] Optionally, the marking device further includes:

[0132] The blinding processing module is configured to perform data unblinding processing on the encrypted second data of the N marked participants according to the blinded random number and the second public key, to obtain unblinded second data.

[0133] Optionally, the marking device further comprises:

[0134] The data updating module is configured to update the local user graph structure data according to the marked information of the node, to obtain updated local user graph structure data.

[0135] The updated data sending module is configured to send the updated local user graph structure data to the N marked participants.

[0136] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of the present application, and the specific functions and technical effects brought by them can be referred to the method embodiments part, which will not be repeated here.

[0137] Figure 5 A structural schematic diagram of a computer device according to Embodiment Four of the present application is shown in FIG. 4. Figure 5 As shown in FIG. 4, the computer device according to the embodiment includes at least one processor (only one processor is shown in the figure), a memory, and a computer program stored in the memory and executable on the at least one processor, and the processor executes the computer program to implement the steps in any of the marking methods of the federated graph nodes. Figure 5

[0138] The computer device can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that, Figure 5 The computer device is only an example and does not limit the computer device, which can include more or fewer components than shown, or combine certain components, or include different components, such as a network interface, a display screen, and an input device, etc.

[0139] The processor can be a CPU, and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any other conventional processor.

[0140] ​The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory can be a memory of the computer device, and the internal memory provides an environment for running of the operating system and the computer-readable instructions in the readable storage medium. The readable storage medium can be a hard disk of the computer device, and in other embodiments, can also be an external storage device of the computer device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory can include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a BootLoader, data, and other programs, such as program codes of computer programs, etc. The memory can also be used to temporarily store data that has been output or will be output.

[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-described functions. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the unit and module in the above device can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here. If the integrated unit is realized in the form of software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the present application realizes all or part of the processes in the above-mentioned embodiment methods, which can be completed by a computer program to instruct related hardware. The computer program can be stored in a computer readable storage medium, and when the processor executes the computer program, the steps of the above-mentioned method embodiment can be realized. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form, etc. The computer readable medium can at least include any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0142] The present application realizes all or part of the processes in the above-mentioned embodiment methods, which can also be completed by a computer program product. When the computer program product runs on the computer device, it makes the computer device execute the steps in the above-mentioned method embodiment.

[0143] In the above-mentioned embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0144] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0145] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / computer device and method can be implemented in other manners. For example, the described apparatus / computer device embodiments are merely schematic. For example, the division of the modules or units can be different, and each can include a plurality of sub-units. Some or all of the modules or units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0146] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e. 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 embodiments.

[0147] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for labeling nodes in a federated graph, characterized in that, The method includes: Obtain the identity information and corresponding tag information of each local user; Using each user as a node, the identity information and the tag information of each user are used as the node information of each user. Based on the node information, the nodes with known tag propagation relationships are connected to obtain the local user graph structure data. The local user graph structure data is sent to N marking participants, where N is an integer greater than 0, so that each marking participant can mark the nodes of its user graph structure data according to the marking information in the local user graph structure data and the known marking propagation relationship. Receive user graph structure data with N marked participants; Based on the labeling information in the user graph structure data of N labeling participants and the known labeling propagation relationship, the local user graph structure data is labeled with nodes; The connection of nodes with known marker propagation relationships includes: When the tagging information between the nodes to be connected is the same and none of them are preset tags, the nodes to be connected are connected using a preset first connection method. When the tagging information between the nodes to be connected is different and none of them are preset tags, the nodes to be connected are connected using a preset second connection method. When the tag information of any node to be connected is a preset tag, the node to be connected does not connect to any node. The first connection method is a bidirectional connection, and the second connection method is a unidirectional connection.

2. The method for marking nodes in a federated graph according to claim 1, characterized in that, The step of using the identity information and the tag information of each user as the node information of each user includes: Obtain each user's unique identifier as the user's identity information; The system detects the category tag corresponding to the user's identity information in the local database. If the category tag exists, it is determined that the category tag is the tag information corresponding to the user's identity information. If the category tag does not exist, a preset tag is used as the tag information corresponding to the user's identity information.

3. The method for marking nodes in a federated graph according to claim 1, characterized in that, Sending the local user graph structure data to N marked participants includes: Generate N sets of first public keys and the first private key , and the first public key Send it to the corresponding i-th marked participant; Receive the first data sent by the i-th marker participant, the first data being generated using the first public key. The data obtained by blinding the node information in the user graph structure data of the i-th labeled participant; Using the first private key The first data sent by the i-th marking participant and the local user graph structure data are encrypted respectively, and the encrypted local user graph structure data and the first data sent by the i-th marking participant are transmitted to the i-th marking participant.

4. The method for marking nodes in a federated graph according to claim 1, characterized in that, The user graph structure data received from N marked participants includes: Receive the second public key sent by N marking participants, blind the local node information using the second public key, and transmit the second data to the corresponding marking participants; The system receives encrypted user graph structure data and encrypted second data from N marked participants. The encrypted user graph structure data is obtained by encrypting the user graph structure data of the corresponding marked participant using a second private key, and the encrypted second data is obtained by encrypting the second data of the corresponding marked participant using a second private key.

5. The method for marking federated graph nodes according to claim 4, characterized in that, Before labeling nodes in the local user graph structure data based on the user graph structure data of N labeling participants, the following steps are also included: Based on the random number generated during the blinding process and the second public key, the encrypted second data of the N marked participants is deblinded to obtain the deblinded second data.

6. The method for marking nodes in a federated graph according to any one of claims 1-5, characterized in that, After labeling the local user graph structure data with nodes based on the user graph structure data of N labeling participants, the process also includes: Based on the tagging information after node tagging, update the local user graph structure data to obtain the updated local user graph structure data; The updated local user graph structure data is sent to N marked participants.

7. A marking device for nodes in a federated graph, characterized in that, The labeling device for the federated graph nodes includes: The user information acquisition module is used to acquire the identity information and corresponding tag information of each local user. The graph structure data construction module is used to take each user as a node, use the identity information and the tag information of each user as the node information of each user, and connect each node with a known tag propagation relationship according to the node information to obtain local user graph structure data. The graph structure data sending module is used to send the local user graph structure data to N marking participants, where N is an integer greater than 0, so that each marking participant can mark the nodes of the user graph structure data of each marking participant according to the marking information in the local user graph structure data and the known marking propagation relationship. The graph structure data receiving module is used to receive user graph structure data from N marked participants; The node labeling module is used to label the local user graph structure data based on the labeling information in the user graph structure data of N labeling participants and the known labeling propagation relationship; The graph structure data construction module includes: The first connection unit is used to connect the nodes to be connected using a preset first connection method when the tagging information between the nodes to be connected is the same and none of them are preset tags. The second connection unit is used to connect the nodes to be connected using a preset second connection method when the tagging information between the nodes to be connected is different and none of them are preset tags. The third connection unit is used to ensure that when the tag information of any node to be connected is a preset tag, the node to be connected does not connect to any node. The first connection method is a bidirectional connection, and the second connection method is a unidirectional connection.

8. A computer device, characterized in that, The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for marking federated graph nodes as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the labeling method for federated graph nodes as described in any one of claims 1 to 6.

Images