CN116304208A

CN116304208A - Multiparty user identification processing method, device, computer equipment and storage medium

Info

Publication number: CN116304208A
Application number: CN202310207361.2A
Authority: CN
Inventors: 王曾
Original assignee: Midea Group Co Ltd
Current assignee: Midea Group Co Ltd
Priority date: 2023-03-06
Filing date: 2023-03-06
Publication date: 2023-06-23

Abstract

The invention discloses a multiparty user identification processing method, a multiparty user identification processing device, computer equipment and a storage medium, wherein the method comprises the following steps: determining an initial association identifier list of a first party based on the association between user identifiers in a first identification identifier set of the first party; acquiring a user identification identifier intersection set and an index identifier set provided by a second party; and determining a target unique identification set of the first party according to the index identification set, the user identification intersection set and the initial association identification list. Therefore, privacy protection is realized, and simultaneously, user identification identifiers belonging to the same user as much as possible can be correctly associated, so that the accuracy of user identification is improved.

Description

Multiparty user identification processing method, device, computer equipment and storage medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a computer device, and a storage medium for processing a user identifier of multiple parties.

Background

With the gradual maturity of internet technology, the way that users connect to the internet is developed in a diversified way, and the same user may have user identification identifiers of service systems of a plurality of mutually independent different domains. The user identification marks are subjected to association processing, and the method has important significance for correctly identifying the same user in the multi-user identification mark scene.

In the related art, a user identification identifier is associated by a user identity linking (User Identity Linkage, UIL) method to identify a user. However, the accuracy of recognition and the like are to be improved.

Disclosure of Invention

The present invention aims to solve at least one of the technical problems in the related art to some extent. Therefore, a first object of the present invention is to provide a multiparty user identification processing method, which can effectively improve the accuracy of user identification by the UIL method.

A second object of the present invention is to propose a user identification handling device for multiple parties.

A third object of the invention is to propose a computer device.

A fourth object of the present invention is to propose a computer readable storage medium.

To achieve the above object, an embodiment of a first aspect of the present invention provides a method for processing a user identifier of a plurality of parties, where the parties include at least a first party and a second party that do not share data; the method comprises the following steps: determining an initial association identifier list of the first party based on the association between user identifiers in a first set of identifiers of the first party; acquiring a user identification identifier intersection set and an index identifier set provided by the second party; the user identification mark intersection is obtained by carrying out privacy intersection on the first identification mark set and a second identification mark set of the second party, and index marks in the index mark set are used for referring to unique user marks corresponding to the user identification marks in the user identification mark intersection; and determining a target unique identification set of the first party according to the index identification set, the user identification intersection set and the initial association identification list.

According to one embodiment of the present invention, the determining the target unique identifier set of the first party according to the index identifier set, the user identification identifier intersection set and the initial association identifier list includes: supplementing the initial association identifier list by using the index identifier set and the user identification identifier intersection set to obtain a target association identifier list; and determining a target unique identification set of the first party according to the target association identification list.

According to one embodiment of the present invention, the supplementing the initial association identifier list with the index identifier set and the user identification identifier intersection set to obtain a target association identifier list includes: sequentially carrying out one-to-one correspondence between index identifiers in the index identifier set and user identification identifiers in the user identification identifier intersection set to obtain a supplementary association identifier list corresponding to the user identification identifier intersection set; and merging the supplementary association identifier list with the initial association identifier list to obtain the target association identifier list.

According to one embodiment of the present invention, the determining the initial association identifier list of the first party based on the association between the user identifiers in the first identifier set of the first party includes: based on the association frequency between the user identification marks in the first identification mark set, combining any two user identification marks corresponding to the association frequency meeting the frequency threshold condition to obtain an initial association mark binary group corresponding to the any two user identification marks; and determining an initial association identifier list of the first party according to the initial association identifier binary groups corresponding to any two user identification identifiers in the first identification identifier set.

According to one embodiment of the present invention, before said determining the target unique identification set of the first party from the index identification set, the user identification intersection set and the initial association identification list, the user identification processing method of the plurality of parties further comprises: determining a first user unique identifier corresponding to a user identification identifier in the first identification identifier set according to the initial association identifier list of the first party; the determining the target unique identification set of the first party according to the index identification set, the user identification intersection set and the initial association identification list comprises the following steps: updating a first user unique identifier corresponding to the user identification identifier in the first identification identifier set according to the index identifier set, the user identification identifier intersection set and the initial association identifier list; and determining a target unique identification set of the first party according to the updated first user unique identification.

According to one embodiment of the present invention, the determining the target unique identifier set of the first party according to the index identifier set, the user identification identifier intersection set and the initial association identifier list includes: constructing an undirected graph of the first party; the vertex of the undirected graph is used for representing user identification marks in the first identification mark set, and the connecting edges between the vertices are determined according to the index mark set, the user identification mark intersection set and the initial association mark list; respectively carrying out depth association calculation on a plurality of first communication subgraphs in the undirected graph to obtain a plurality of second communication subgraphs corresponding to the undirected graph; wherein, the second linkage subgraphs are respectively allocated with corresponding target unique identifiers; and determining the target unique identifier set according to the target unique identifiers respectively corresponding to the second communication subgraphs.

According to one embodiment of the present invention, the vertices in the first communication subgraph correspond to initial index values; performing depth association calculation on the first communication subgraph, including: according to the initial index value corresponding to the vertex in the first communication sub-graph, determining the initial index value meeting the index value threshold condition as a target index value; and transmitting the target index value in the vertex of the first communication sub-graph so as to update the initial index value corresponding to the vertex in the first communication sub-graph to the target index value.

According to one embodiment of the invention, the user identification identifiers in the second identification identifier set correspond to second user unique identifiers, and the second user unique identifiers and the corresponding user identification identifiers in the second identification identifier set form an identifier corresponding relation list; the identifier corresponding relation list is used for determining a second user unique identifier corresponding to the user identification identifier in the user identification identifier intersection; and the identification information of the unique identification of the second user is the index identification.

To achieve the above object, an embodiment of a second aspect of the present invention provides a user identification processing apparatus for multiple parties, where the multiple parties include at least a first party and a second party that do not share data; the device comprises: an association identifier list determining module, configured to determine an initial association identifier list of the first party based on an association between user identifiers in a first set of identifiers that the first party has; the identification set acquisition module is used for acquiring a user identification intersection set and an index identification set provided by the second party; the user identification mark intersection is obtained by carrying out privacy intersection on the first identification mark set and a second identification mark set of the second party, and index marks in the index mark set are used for referring to unique user marks corresponding to the user identification marks in the user identification mark intersection; and the unique identification set determining module is used for determining a target unique identification set of the first party according to the index identification set, the user identification intersection set and the initial association identification list.

To achieve the above object, an embodiment of a third aspect of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method according to any one of the preceding embodiments when the processor executes the computer program.

To achieve the above object, a fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the method according to any one of the preceding embodiments.

According to the embodiments of the invention, by utilizing the association information of the user identification marks of multiple parties, any party can supplement the association information of the user identification marks of own parties, so that privacy protection is realized, and simultaneously, correct association of as many user identification marks belonging to the same user as possible can be realized, thereby effectively improving the integrity of data for constructing the unique user identification OneID by a UIL method, and further improving the accuracy of identifying the user.

Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.

Drawings

Fig. 1a is a schematic application scenario diagram of a multiparty user identification processing method provided in the present specification.

Fig. 1b is a flow chart of a method for processing user identification of multiple parties according to one embodiment of the present disclosure.

Fig. 1c is a schematic flow chart of a privacy intersection method according to an embodiment of the present disclosure.

Fig. 2 is a schematic flow chart of determining a set of unique identifiers of a target according to one embodiment of the present disclosure.

Fig. 3 is a schematic flow chart of obtaining a target association identifier list according to an embodiment of the present disclosure.

Fig. 4 is a schematic flow chart of determining an initial association identifier list of a first party according to one embodiment of the present disclosure.

Fig. 5 is a schematic flow chart of determining a set of target unique identifiers of a first party according to one embodiment of the present disclosure.

Fig. 6 is a schematic flow chart of determining a set of target unique identifiers of a first party according to one embodiment of the present disclosure.

Fig. 7a is a schematic flow chart of performing depth association calculation on the first communication subgraph according to an embodiment of the present disclosure.

Fig. 7b is a schematic structural diagram of a first communication sub-graph according to an embodiment of the present disclosure.

Fig. 7c is a schematic structural diagram of a second coupling diagram according to an embodiment of the present disclosure.

Fig. 8 is a block diagram of a multi-party subscriber identity processing unit according to one embodiment of the present disclosure.

Fig. 9 is a block diagram of a computer device according to one embodiment of the present disclosure.

Detailed Description

Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.

With the increasing maturity of internet technology, the way users connect to the internet has been a growing trend. In daily life, a user can be connected to the business systems of different domains of a party (such as a party enterprise) by any mode of a mobile phone APP, a personal computer, a WeChat applet and the like at any time and any place so as to browse, inquire or consult related interesting contents. Accordingly, mutually independent user identification marks may be generated in the business systems of different domains of the enterprise, that is, the same user may have the user identification marks of the business systems of a plurality of different domains. These subscriber identities may be isolated from each other before they are processed, and for some globally based services such as user portrayal research, user personalized marketing or recommendation, and risk control, they may not be effectively managed and utilized. Therefore, it is necessary to integrate the user identification identifiers generated in the service systems of different domains, and correlate the multiple user identification identifiers of the same user, so as to realize effective identification of the same user in the service systems of multiple different domains.

The user identity linking (User Identity Linkage, UIL) method is a common method for solving the problem of correct identification of the same user in the context of multi-user identification (e.g., app account, cell phone number, mailbox account, device number, etc.). The user unique identification can be built for a plurality of different user identification identifications of the same user through the UIL method to identify the user, so that the user identification efficiency in an actual service scene is improved, for example, the identification efficiency of abnormal user behaviors in a wind control scene is improved.

In the related art, the UIL method is mainly based on user data collected in an enterprise, and processes user identification marks through a data mining mode (such as a neural network, a graph algorithm, machine learning and the like) so as to correlate the user identification marks belonging to the same user, thereby realizing correct identification of the user. However, since the integrity of the user data collected inside the enterprise is not guaranteed, the accuracy of identifying the user by the UIL method may be impaired.

The user identification effect realized by the UIL method is reflected on the saturation of the unique user identification OneID constructed by the UIL method, and the lower the saturation s is, the weaker the capability of correctly identifying the user is indicated. Wherein the saturation s may be defined as follows:

Since the numerator depends in part on the objective state of the actual service and is generally not changeable, it is necessary to correctly correlate as many subscriber identification IDs belonging to the same subscriber as possible to reduce the denominator of the saturation. Thus, more relevant user identification ID association information of the same user needs to be introduced, for example, user identification ID association information of the same user provided by another enterprise may be introduced. However, in this process, it is necessary to ensure that private data such as user identification ID of the two-party corporation is protected locally and not leaked to another party not authorized by the user.

In order to effectively improve the accuracy and other effects of user identification by the UIL method, it is necessary to provide a multiparty user identification processing method, device, computer equipment and storage medium, wherein privacy intersection is carried out on the multiparty user identification so that the multiparty can acquire the user identification intersection belonging to the same user on the premise of privacy protection; the multiparty calculates the relation data between the user identification marks in the user identification mark intersection locally and refers to the relation data by using the index mark set, so that any party can acquire the association information between the user identification marks provided by other parties through the index mark set of the other party under the condition that the privacy data such as more user marks are not leaked; by utilizing the associated information of multiple parties, any party can supplement the associated information among the user identification identifiers of the own parties, so that the privacy protection is realized, and simultaneously, the correct association of as many user identification identifiers belonging to the same user as possible can be realized by combining the associated information of the user identification identifiers of the multiple parties, thereby effectively improving the integrity of data for constructing the unique user identification OneID by a UIL method, and further improving the accuracy of identifying the user.

Fig. 1a is a schematic application scenario diagram of a multiparty user identification processing method provided in the present specification. Taking multiparty including a first party A and a second party B as an example, the A party supplements the association information between the own user identification marks by using the association information provided by the B party, so as to finally construct the target unique mark OneID by a UIL method. Referring to fig. 1a, in this scenario example, the flow of the user identification processing method of the multiparty may include: firstly, respectively finishing initialization of an initial association identifier list in each local area by an A party and a B party; secondly, respectively carrying out user identification and identification processing of the first stage on the A side and the B side locally by a UIL method so as to respectively obtain user unique identification sets; thirdly, calculating user identification mark intersections of the A side and the B side by a privacy intersection method; step four, the B side determines the association information between the user identification marks in the user identification mark intersection set and provides the association information for the A side; and fifthly, supplementing the initial association identifier list of the own party by the A party by using the association information provided by the B party, and carrying out user identification identifier processing of a second stage locally through a UIL method to obtain a target unique identifier set.

Exemplary descriptions are given of how the a-party and the B-party respectively complete initialization of the initial association identification list locally. Party A has a first set of identification marks V ^A Party B has a second set of identification marks V ^B . The A party locally determines an initial association identifier list of the first party according to the association between the user identification identifiers in the first identification identifier set so as to finish the initialization of the initial association identifier list of the first party; party B atAnd determining an initial association identifier list of the second party according to the association between the user identification identifiers in the second identification identifier set locally so as to finish initialization of the initial association identifier list of the second party.

In this scenario example, taking party a as an example, party a may identify set V according to a first identification ^A The association frequency between any two user identification marks, the two user identification marks corresponding to the association frequency meeting the actual service requirement

And->

Performing association to generate corresponding initial association identification doublet->

Thus, the initial association identifier list +.A. of the A-party can be determined based on the initial association identifier binary group>

The party B can determine in the same way the initial association identity list +.>

And will not be described in detail herein.

In some embodiments, the a/B party may also place the user identification identities for which there is a correlation in the same set, thereby determining an initial list of correlation identities.

An example illustrates how parties a and B perform the first stage of user identification processing locally by the UIL method, respectively. Taking the A party as an example, the A party can determine a plurality of identification sets according to an initial association identification list of the A party, and consider that the user identification identifications in the sets have association, and the user identification identifications among the sets have no association. And the A party respectively distributes a user unique identifier for each identifier set so that the user identification identifiers in each identifier set correspond to the user unique identifiers. According to the user unique identifiers respectively corresponding to the plurality of identifier sets, the user unique identifier set of the A party can be determined.

In this scenario example, the set of identifications appears as a undirected-communication subgraph. Taking the A side as an example, the A side identifies a list E according to initial association ^A The set V can be identified by a first identification ^A User identification in the model is identified as a vertex, and an undirected graph G of the A side is generated ^A ＝(V ^A ,E ^A ). The A direction is undirected graph G ^A Each connected subgraph is respectively allocated with a user unique identifier to obtain a user unique identifier set of the A side, so that the user identification and identification processing of the first stage can be completed. Further, the user identification identifiers in each communication subgraph are associated with the corresponding unique user identifiers, so that an identifier corresponding relation list of the A side can be generated

Wherein U is ^A The set is uniquely identified for the user of party a.

In some embodiments, party A may assign a user unique identifier to undirected graph G before assigning each connected subgraph in the undirected graph ^A And the depth association calculation is respectively carried out on each connected sub-graph in the undirected graph so as to convert the more complex data structure of the connected sub-graph in the undirected graph into a simpler data structure, so that the query efficiency of the user identification mark with the association relation is higher.

The user identification and identification process of the B-party can be completed in the same manner in the first stage to obtain the unique user identification set of the B-party, which is not described herein.

An example illustrates how the user identification intersection of the a-party and the B-party is calculated by a privacy intersection method. Illustratively, a key agreement (Diffie-Hellman, DH) based PSI (Private Set Intersection, privacy set intersection) scheme may be employed to calculate the user identification identity intersections of the a-party and the B-party. Specifically, first, party a uses key P _s (sk _s ) For the first identification mark set D _s The user identification marks s in the first identification mark set are respectively encrypted to obtain the encrypted first identification mark setClosing device

Party A encrypts a first identification mark set D' _s Providing the solution to a party B; second, party B uses key P _r (sk _r ) For the second identification mark set D _r The user identification marks r in the database are respectively subjected to encryption operation to obtain a second encrypted identification mark set +.>

And using the key P _r (sk _r ) For the encrypted first identification mark set D' _s The elements in the first identification set are respectively subjected to encryption operation to obtain a first identification set after secondary encryption ∈10>

Party B encrypts a second identification mark set D' _r With the second encrypted first identification mark set D' _s Providing the solution to party A; party A then uses the key P _s (sk _s ) For the encrypted second identification mark set D' _r The elements in the first identification set are respectively subjected to encryption operation to obtain a second identification set +.>

Finally, the step of obtaining the product, the A side encrypts the second identification mark set D ', and the A side encrypts the second identification mark set D' _s And a second identification mark set D' after secondary encryption _r Performing intersection calculation to obtain a set D _s And set D _r An intersection of identical elements in (a) and (b). According to the user identification mark corresponding to the elements in the intersection, the A party can obtain a user identification mark intersection phi. The A side can also encrypt the second identification mark set D', which is encrypted for the second time _r And providing the user identification intersection phi for the party B, so that the party B can perform intersection calculation to obtain the user identification intersection phi.

An exemplary illustration of how party B determines association information between user identification in a user identification intersection. The B party can determine the unique user identification corresponding to the user identification in the user identification intersection according to the unique user identification corresponding to the user identification in the second identification set. The B side uses the index mark to refer to the unique user mark corresponding to the user identification mark in the user identification mark intersection, so that the index mark is used for representing the association information between the user identification marks in the user identification mark intersection, namely any two identical index marks can represent that the association exists between the two corresponding user identification marks. And the B side obtains an index identification set according to the index identification, and provides the index identification set for the A side.

In this scenario example, the B party may be able to list the correspondence according to the identification of the B party

And inquiring the identification corresponding relation binary group containing the user identification in the user identification intersection, and determining the user unique identification corresponding to the user identification in the user identification intersection. The B party can correlate the user identification marks in the user identification mark intersection with the corresponding user unique marks to obtain a corresponding relation list +.>

Party B refers to R with index identification ^B The user of the index is uniquely identified and the index is identified according to +.>

And (3) ordering the sequences to obtain an index identifier set of the second party, wherein the index identifier set is used for representing the association information between the user identification identifiers in the user identification identifier intersection set provided by the party B and providing the association information to the party A.

In some embodiments, the index identifier may be a subscript number of the user unique identifier in the relationship list.

An example illustrates how party a performs the second stage of user identification processing. And the A party carries out user identification processing at a second stage according to the association information between the user identification identifiers in the user identification identifier intersection set provided by the second party and the initial association identifier list of the A party so as to determine a target user unique identifier corresponding to the user identification identifier in the first identification identifier set.

In some embodiments, the a-party may obtain the supplementary association identifier list corresponding to the user identification identifier intersection according to the association information between the user identification identifiers in the user identification identifier intersection provided by the B-party. Illustratively, party A performs the same ordering of the user identifications in the user identification intersection Φ, and sequentially performs the ordering of the index identifications in the index identification set provided by party B

User identification mark +.>

One-to-one correspondence can be obtained

Party A according to->

Initial association identification list E with A-side ^A A final set of target unique identifications can be determined.

In this scenario example, the method for determining the target unique identifier set of the a party is the same as the method for determining the user unique identifier set of the a party through the user identification identifier processing of the first stage, and will not be described herein.

In other embodiments, the a-party may further put the user identification identifiers having the relevance in the user identification identifier intersection set into the same set according to the relevance information provided by the B-party, so as to obtain a supplementary relevance identifier list corresponding to the user identification identifier intersection set. The A party can use the supplementary association identification list and the initial association identification list to combine, and can also use the association information in the supplementary association identification list to update the association information in the initial association identification list. The unique target user identifier may be determined by the a party based on the association information between the user identifiers in the user identifier exchange set provided by the B party and the initial association identifier list of the first party, or may be determined after updating the unique user identifier determined by the a party in the first stage.

It should be noted that, in this scenario example, the a party may also determine association information between the user identification identifiers in the user identification identifier intersection, and provide the association information to the B party, so that the B party may supplement the initial association identifier list of the B party with the association information provided by the a party, and perform the user identification representation processing of the second stage locally, to obtain the target unique identifier set of the B party.

The embodiment of the specification provides a multiparty user identification processing method, wherein the multiparty user identification processing method at least comprises a first party and a second party which do not share data. Referring to fig. 1b, the method may include the following steps.

S110, determining an initial association identifier list of the first party based on the association between the user identification identifiers in the first identification identifier set of the first party.

The first identification set is a local identification set of the first party. The user identification mark can be related data such as a user account number and the like, and corresponds to a user. The association may be expressed as an association between a plurality of user identification identities if the plurality of user identification identities correspond to the same user.

Specifically, the first party has a first party user, and after obtaining permission or authorization of the first party user, the first party may collect user identification identifiers of the first party user to obtain a first identification identifier set. In the first identification mark set, if the user identification marks have relevance, the user identification marks with relevance are associated to determine an initial relevance mark list of the first party.

The user identification may be a user ID. Illustratively, the user identification in the first set of identification identifications includes ID1, ID2, ID3, ID4, ID5. The IDs 1, 2, and 3 may be user identification identifiers of the user 1 collected by the first party, and the IDs 4 and 5 may be user identification identifiers of the user 2 collected by the first party. Then there is an association between ID1, ID2, ID3, corresponding to user 1; there is an association between ID4 and ID5, corresponding to user 2. An initial association identifier list can be obtained by associating ID1, ID2, and ID3, and associating ID4 and ID5.

In some embodiments, the IDs may be associated pairwise according to the strength of association between any two of IDs 1, ID2, ID 3. Illustratively, ID1, ID2 are associated to obtain a tuple (ID 1, ID 2); associating ID1 and ID3 to obtain a binary group (ID 1 and ID 3); ID4 and ID5 are associated to obtain a binary group (ID 4, ID 5). According to the binary group, an initial association identifier list can be obtained.

It will be appreciated that the second party has a second party user, and after obtaining permission or authorization of the second party user, the second party may collect the user identification of the second party user to obtain a second set of identification identifiers. In the second set of identification identifiers, if there is a correlation between the user identification identifiers, the user identification identifiers with the correlation are correlated to determine an initial correlation identifier list of the second party.

In some embodiments, the user identification may include an APP account number, a cell phone number, a mailbox account number, an IMIE (International Mobile Equipment Identity ) device number, and the like. Illustratively, the first set of identification identifiers may be represented as:

it should be noted that, the initial association identifier list of the first party is determined locally by the first party, and the initial association identifier list of the second party is determined locally by the second party.

S120, acquiring a user identification intersection set and an index identification set provided by a second party.

The user identification mark intersection is obtained by carrying out privacy intersection on the first identification mark set and the second identification mark set of the second party, and index marks in the index mark set are used for indicating unique user marks corresponding to the user identification marks in the user identification mark intersection.

The unique user identifier may be a unique user identifier corresponding to a user identifier in a second identifier set determined by the second party according to an initial association identifier list of the second party, and is used for uniquely characterizing the user identifier with association.

In some cases, the first party and the second party have a portion of the same user, and accordingly, in the first set of identification identifiers and the second set of identification identifiers, there are user identification identifiers corresponding to these same users, i.e., user identification identifiers commonly held by the first party and the second party. Because the first party is not the party obtaining the permission or the authorization of the user of the second party, and the second party is not the party obtaining the permission or the authorization of the user of the first party, in order to ensure that the first party and the second party can obtain the commonly held user identification mark without revealing other user identification marks of any party, the user identification mark intersection of the first identification mark set and the second identification mark set can be obtained by a privacy intersection method.

It will be appreciated that the user identification intersection is a subset of the second set of identifications, and therefore the user unique identification corresponding to the user identification in the user identification intersection can be determined from the user unique identifications corresponding to the user identifications in the second set of identifications. Further, to ensure that the specific user unique identifier corresponding to the user identification in the second set of identification identifiers is not leaked to the first party, the index identifier may be utilized to refer to the user unique identifier corresponding to the user identification in the user identification identifier intersection.

Specifically, the first party and the second party calculate to obtain a user identification intersection of the first identification set and the second identification set through a privacy intersection method. The second party can determine the unique user identifier corresponding to the user identification identifier in the user identification identifier intersection according to the corresponding relation between the user identification identifiers in the second identification identifier set and the unique user identifiers, and index identifiers are utilized to refer to the determined unique user identifiers one by one. The second party can obtain an index identification set of the second party according to the index identification, and the index identification set is provided for the first party.

Illustratively, the user identification intersection is { ID1, ID2, ID3, ID4, ID5, ID6, ID7, ID8, ID9}. The second party can determine that the unique user identifier corresponding to the ID1 in the user identification identifier intersection is OneID1 according to the corresponding relationship between the user identification identifiers in the second identification identifier set and the unique user identifiers; the unique user identifier corresponding to the ID2 is OneID2; the unique user identifier corresponding to the ID3 is OneID3; the unique user identifier corresponding to the ID4 is OneID1; the unique user identifier corresponding to the ID5 is OneID2; the unique user identifier corresponding to the ID6 is OneID1; the unique user identifier corresponding to the ID7 is OneID2; the unique user identifier corresponding to the ID8 is OneID1; the unique user identifier corresponding to ID9 is OneID2. The index identifier S1 is used for indicating the user unique identifier OneID1, the index identifier S2 is used for indicating the user unique identifier OneID2, and the index identifier S3 is used for indicating the user unique identifier OneID3, so that the index identifier set of the second party is { S1, S2, S3, S1, S2}, according to the user unique identifier corresponding to the user identification identifier in the user identification identifier intersection. In some embodiments, the index identification may be a subscript number of the user unique identification.

In some embodiments, the privacy intersection method may be a PSI (Private Set Intersection, privacy set intersection) scheme based on key agreement (Diffie-Hellman, DH). Specifically, referring to fig. 1c, the flow of the privacy intersection method may include: first, the first party uses the key P _s (sk _s ) For the first identification mark set D _s The user identification marks s in the database are respectively encrypted to obtain a first encrypted identification mark set

The first party encrypts a first identification mark set D' _s Providing to a second party; second, the second party uses the key P _r (sk _r ) For the second identification mark set D _r The user identification r in the database is respectively subjected to encryption operation,obtaining the encrypted second identification mark set

The second party encrypts a second identification mark set D' _r With the second encrypted first identification mark set D' _s Providing to a first party; then, the first party uses the key P _s (sk _s ) For the encrypted second identification mark set D' _r The elements in the first identification set are respectively subjected to encryption operation to obtain a second identification set +. >

Finally, the step of obtaining the product, the first party encrypts the second identification mark set D ', and the second party encrypts the second identification mark set D' _s And a second identification mark set D' after secondary encryption _r Performing intersection calculation to obtain a set D _s And set D _r An intersection of identical elements in (a) and (b). Since only the first set of identification marks D _s User identification s and second identification set D _r In the case that the user identification marks r are the same, the set D', is set _s And set D _r The corresponding elements in (a) will be the same. Therefore, the first party can determine the user identification marks respectively corresponding to the elements according to the elements in the intersection, so that the intersection of the user identification marks can be obtained.

The second party may also obtain the second identification set d″ after the second encryption provided by the first party _r Set D' _s And set D _r After intersection calculation, intersections composed of the same elements can be obtained. The second party can determine the user identification identifiers respectively corresponding to the elements according to the elements in the intersection, so that the user identification identifier intersection can be obtained.

In other embodiments, the privacy delivery method may also be a PSI scheme based on an unintentional transmission (Oblivious Transfer, OT), or a PSI scheme based on Bloom filters (Bloom filters), or the like.

S130, determining a target unique identification set of the first party according to the index identification set, the user identification intersection set and the initial association identification list.

It will be appreciated that the index identifiers in the set of index identifiers may be used to represent association information between the user identifiers in the user identification intersection, i.e. if any two user identifiers in the user identification intersection correspond to the same index identifier, then there is an association between the any two user identifiers.

In some cases, the user account or the like related data collected by the first party may be incomplete, resulting in an incomplete association between the user identification contained in the first party's initial association identification list. Therefore, the association information between the user identification marks in the user identification mark intersection set determined by the second party can be introduced through the user identification mark intersection set and the index mark set of the second party so as to perfect the association relationship between the user identification marks in the first identification mark set.

Specifically, according to the correspondence between the index identifiers in the index identifier set and the user identifiers in the user identifier intersection, the relevance between the user identifiers in the user identifier intersection can be determined. According to the relevance and the relevance among the user identification identifications contained in the initial relevance identification list of the first party, a plurality of identification sets can be determined, and the user identification identifications in the sets are considered to have relevance, and the user identification identifications among the sets have no relevance. Each identification set is respectively allocated with a unique user identification, and the target unique identification set of the first party can be determined according to the unique user identifications respectively corresponding to the plurality of identification sets. It will be appreciated that the set of identities includes at least one user identification.

In some embodiments, the identification set may be a undirected communication subgraph.

In the embodiment, on the premise of privacy protection, the user identification relationship data of multiple parties are combined, so that user identification identifications belonging to the same user as many as possible are correctly associated, the integrity of data for constructing the unique user identification OneID is effectively improved, and the accuracy of user identification is improved.

In some embodiments, referring to fig. 2, determining the target unique identification set of the first party from the index identification set, the user identification intersection set, and the initial association identification list may include the following steps.

S210, supplementing the initial association identifier list by utilizing the index identifier set and the user identification identifier intersection set to obtain a target association identifier list.

Specifically, from the initial association identifier list of the first party, an initial association between user identification identifiers in the first set of identification identifiers may be determined. And according to the corresponding relation between the index identifications in the index identification set and the user identification identifications in the user identification intersection set, the supplementary relevance between the user identification identifications in the user identification intersection set can be determined. And supplementing the initial association by utilizing the supplemented association to obtain a target association identification list.

In some embodiments, the initial association identification list may be supplemented in a manner that combines supplemental associations with the initial associations.

Illustratively, the first set of identification tags is { ID1, ID2, ID3, ID4, ID5, ID6, ID7, ID8, ID9, ID10, ID11, ID12}. According to the initial association identifier list of the first party, it is determined that initial association exists between the IDs 1 and 4 in the user identification identifier, initial association exists between the IDs 2, 6 and 12, and initial association exists between the IDs 3, 7, 10 and 11. The intersection of user identification identifiers is { ID1, ID2, ID3, ID4, ID5, ID6, ID7, ID8, ID9, ID10}, and correspondingly, the set of index identifiers provided by the second party is { S1, S2, S3, S1, S3, S2, S3, S1, S2, S3}. According to the correspondence of the IDs 1, 4, and 8 to the index identifier S1, the IDs 2, 6, and 9 to the index identifier S2, and the IDs 3, 5, 7, and 10 to the index identifier S3, it can be determined that the IDs 1, 4, and 8 have complementary associations, the IDs 2, 6, and 9 have complementary associations, and the IDs 3, 5, 7, and 10 have complementary associations. Combining the initial relevance by utilizing the supplementary relevance, so that relevance among the ID1, the ID4 and the ID8 can be obtained; there is an association between ID2, ID6, ID 9; there is an association between ID2, ID6, ID 12; there is an association between ID3, ID7, ID10, ID 11; there is an association between ID3, ID5, ID7, ID 10. Thus, the initial association identifier list can be supplemented to obtain the target association identifier list.

In other embodiments, the initial association identity list may be supplemented by updating the initial association with a supplemental association.

Illustratively, updating the initial association with the supplemental association may result in an association between ID1, ID4, and ID 8; there is an association between ID2, ID6, ID9, ID 12; there is an association between ID3, ID5, ID7, ID10, ID 11. Thus, the initial association identifier list can be updated to obtain the target association identifier list.

S220, determining a target unique identification set of the first party according to the target association identification list.

Specifically, according to the relevance between the user identification identifiers contained in the target relevance identifier list, a plurality of identifier sets can be determined, and the user identification identifiers in the sets are considered to have relevance, and the user identification identifiers between the sets have no relevance. Each identification set is respectively allocated with a target unique identification, and the target unique identification set of the first party can be determined according to the target unique identifications respectively corresponding to the plurality of identification sets.

Illustratively, the identification set 1 is determined from the association between ID1, ID4, ID 8; determining an identification set 2 according to the relevance among the IDs 2, 6, 9 and 12; the identification set 3 is determined based on the association between ID3, ID5, ID7, ID10, ID 11. A user unique identifier OneID1 is allocated to the identifier set 1, a user unique identifier OneID2 is allocated to the identifier set 2, a user unique identifier OneID3 is allocated to the identifier set 3, and then the target unique identifier set can be determined to be { OneID1, oneID2, oneID3}.

In some embodiments, the presence of an association between user identification identifiers may be represented by a binary group of user identification identifiers. In still other embodiments, the association between user identification identifiers in the user identification representation intersection may be represented by a binary set of user identification identifiers and index identifiers.

In some embodiments, referring to fig. 3, the method for supplementing the initial association identifier list with the index identifier set and the user identification identifier intersection set to obtain the target association identifier list may include the following steps.

And S310, sequentially carrying out one-to-one correspondence association on the index identifiers in the index identifier set and the user identification identifiers in the user identification identifier intersection set to obtain a supplementary association identifier list corresponding to the user identification identifier intersection set.

S320, combining the supplementary association identifier list with the initial association identifier list to obtain a target association identifier list.

In some cases, to ensure the security of the private data of the parties, it is required that the respective user identification of the parties does not leave the respective local area of the parties, and the second party does not provide any other information to the first party than the set of index identifications. Therefore, the first party needs to associate the index identifiers in the index identifier set with the user identifiers in the user identifier intersection set to obtain association information between the user identifiers in the user identifier intersection set provided by the second party.

Specifically, according to the sequence of the user identification marks in the user identification mark intersection, the index marks in the index mark set and the user identification marks in the user identification mark intersection are sequentially associated in a one-to-one correspondence manner, so that association information among the user identification marks in the user identification mark intersection is obtained, and a supplementary association mark list can be obtained.

In some embodiments, to ensure accuracy of one-to-one association between the index identifiers in the index identifier set and the user identifiers in the user identifier intersection, after the first party and the second party respectively acquire the user identifier intersection, the first party and the second party respectively rank the user identifiers in the user identifier intersection in the same manner.

Specifically, the first party a and the second party B respectively obtain the first identification mark set V ^A With a second set of identification marks V ^B User identification mark intersection phi=v obtained by privacy intersection ^A ∩V ^B . The second party B can firstly identify the user in the acquired intersection phi

Ordering and then determining the ordered user identification mark +.>

Corresponding user unique identification

And will then be used to refer to the user unique identity + >

Index identifier +.>

And arranging the user identification identifiers in an order after the user identification identifiers are ordered to obtain an index identifier set, and providing the index identifier set for the first party. The first party uses the same ordering to identify the user identification mark +.>

Ordering, then sequentially ordering index marks +.>

With the ordered user identification mark +.>

One-to-one correspondence is carried out to obtain user identification mark +.>

And the association information between the two, thereby obtaining a supplementary association identification list. And combining the supplementary association identifier list with the initial association identifier list to obtain a target association identifier list. />

In some embodiments, the index identifies

Can be the unique user identifier +.>

Is a subscript number of (c).

In this specification, the subscript i of the user identification in the first identification set and the subscript i of the user identification in the second identification set are not related to each other.

In the above embodiment, under the condition that the related data such as the user identification identifications of the parties do not leave the local places of the parties, any party can obtain the associated information between the user identification identifications in the user identification intersection provided by other parties, and in addition, no other information can be obtained, thereby ensuring the security of the private data of the parties.

In some embodiments, referring to fig. 4, determining an initial list of associated identifiers for a first party based on an association between user identities in a first set of identifiers that the first party has, comprises:

s410, based on the association frequency between the user identification marks in the first identification mark set, combining any two user identification marks corresponding to the association frequency meeting the frequency threshold condition to obtain an initial association mark binary group corresponding to any two user identification marks.

S420, determining an initial association identifier list of the first party according to the initial association identifier binary groups corresponding to any two user identification identifiers in the first identification identifier set.

The frequency threshold condition can be set according to the service requirement of the actual service scene.

Specifically, the first party a identifies the set V according to the first identification ^A Any two user identification marks in the system

And->

The association frequency between them can generate the initial association identification binary group +.>

Wherein the user identification mark in the same initial association mark binary group is +.>

And->

The association frequency reaches a certain service requirement and is judged to be corresponding to the user identification of the same user. According to the generated initial association identifier binary group corresponding to any two user identification identifiers, the initial association identifier list +. >

Further, the supplementary association identifier list may include a plurality of tuples formed by index identifiers and corresponding user identification identifiers. Specifically, sequentially extracting index identifiers in the obtained index identifier set

User identification mark +.>

A plurality of binary groups consisting of index marks and user identification marks can be obtained by carrying out one-to-one correspondence>

So that a supplementary associated identification list can be obtained from several tuples +.>

Supplementary associated identifier list +.>

With initial association identification list E ^A Combining to obtain a binary group +.>

Two-tuple->

Is provided.

In some embodiments, before determining the target unique identification set of the first party from the index identification set, the user identification intersection, and the initial association identification list, the method of user identification processing of the plurality of parties may further include: and determining a first user unique identifier corresponding to the user identification identifier in the first identification identifier set according to the initial association identifier list of the first party.

Specifically, according to the initial association identifier list of the first party, the user identification identifiers with initial association in the first identification identifier set can be put into the same identifier set to obtain a plurality of identifier sets, and the user identification identifiers in different sets are considered to have no initial association. And respectively allocating a first user unique identifier for each identifier set so that the user identification identifiers in each identifier set respectively correspond to the first user unique identifiers.

Illustratively, according to the initial association identifier list of the first party, the user identification identifiers ID1 and ID2 have initial association, the user identification identifiers ID2 and ID3 have initial association, the user identification identifiers ID2 and ID4 have initial association, the user identification identifiers ID5 and ID6 have initial association, the user identification identifiers ID5 and ID7 have initial association, and the user identification identifiers ID8 and ID9 have initial association. Therefore, the user identification identifiers ID1, ID2, ID3, and ID4 may be placed in the same identifier set C1, the user identification identifiers ID5, ID6, and ID7 may be placed in the same identifier set C2, and the user identification identifiers ID8 and ID9 may be placed in the same identifier set C3. Distributing a first user unique identifier OneID1 to the identifier set C1, wherein the user identification identifiers ID1, ID2, ID3 and ID4 correspond to the first user unique identifier OneID1; distributing a first user unique identifier OneID2 to the identifier set C2, wherein the user identification identifiers ID5, ID6 and ID7 correspond to the first user unique identifier OneID2; and (3) distributing a first user unique identifier OneID3 to the identifier set C3, wherein the user unique identifiers ID8 and ID9 correspond to the first user unique identifier OneID3.

Accordingly, referring to fig. 5, determining a target unique identifier set of a first party according to the index identifier set, the user identification identifier intersection set, and the initial association identifier list may include:

S510, updating a first user unique identifier corresponding to the user identification identifier in the first identification identifier set according to the index identifier set, the user identification identifier intersection set and the initial association identifier list.

S520, determining a target unique identification set of the first party according to the updated first user unique identification.

Specifically, according to the corresponding relation between the index identifications in the index identification set and the user identification identifications in the user identification intersection, the supplementary association between the user identification identifications in the user identification intersection can be determined. According to the supplementary association, the identifier set obtained according to the initial association identifier list of the first party may be updated, so that the first unique user identifiers corresponding to the user identification identifiers in the identifier set may be updated. And determining a target unique identifier set of the first party according to the first user unique identifiers respectively corresponding to the updated user identification identifiers.

Illustratively, the user identification identifiers ID1 and ID7 have complementary associations according to the correspondence between the index identifiers in the index identifier set and the user identification identifiers in the user identification identifier intersection. Therefore, the above-mentioned identification sets C1 and C2 are updated, the user identification identifications ID5, ID6, and ID7 are put into the identification set C1, and the first user unique identification OneID2 corresponding to the user identification identifications ID5, ID6, and ID7 is updated to the first user unique identification OneID1. Then, based on the updated first user unique identification, it may be determined that the target unique identification set of the first party is { OneID1, oneID3}.

For example, the user identification identifiers ID1, ID2, ID3, and ID4 may be placed in the identifier set C2, and the first user unique identifier OneID1 corresponding to the user identification identifiers ID1, ID2, ID3, and ID4 may be updated to the first user unique identifier OneID2. Then, based on the updated first user unique identification, it may be determined that the target unique identification set of the first party is { OneID2, oneID3}.

In some embodiments, referring to fig. 6, determining the target unique identification set of the first party from the index identification set, the user identification intersection set, and the initial association identification list may include the following steps.

S610, constructing an undirected graph of the first party; the vertex of the undirected graph is used for representing user identification marks in the first identification mark set, and the connecting edges between the vertices are determined according to the index mark set, the user identification mark intersection set and the initial association mark list.

Specifically, according to the index identification set, the user identification intersection set and the initial association identification list, the association between the user identification identifications in the first identification set is perfected. And taking the user identification marks in the first identification mark set as vertexes, and determining connecting edges between the vertexes according to perfect relevance so as to construct the undirected graph of the first party.

S620, respectively performing depth association calculation on a plurality of first communication subgraphs in the undirected graph to obtain a plurality of second communication subgraphs corresponding to the undirected graph; the second linkage subgraphs are respectively allocated with corresponding target unique identifiers.

S630, determining a target unique identifier set according to the target unique identifiers respectively corresponding to the second communication subgraphs.

It can be understood that the undirected graph of the first party comprises a plurality of first communication subgraphs, and user identification identifiers corresponding to vertexes in any first communication subgraph are communicated with each other, so that relevance exists.

In some cases, the first connected subgraph is used as a data structure, and queries are performed in the vertices of the first connected subgraph, so that the complexity of the query may be higher when the user identification identifiers respectively corresponding to the vertices can be associated with the user unique identifiers. Therefore, the depth association calculation can be performed on the first communication sub-graph to convert the data structure of the first communication sub-graph, so that the query efficiency of the user identification mark corresponding to the vertex in the communication sub-graph is higher.

Specifically, the depth association calculation is performed on the first communication sub-graph, so that user identification identifiers corresponding to all vertexes in the first communication sub-graph can be associated to the same root node identifier, and the data structure of the first communication sub-graph is converted to obtain a second communication sub-graph. All associated user identification marks can be conveniently queried through the root node of the second linkage subgraph. And respectively carrying out depth association calculation on the first communication subgraphs of the undirected graph to obtain second communication subgraphs corresponding to the undirected graph. And respectively distributing a target unique identifier for the plurality of second communication subgraphs, and determining a target unique identifier set according to the target unique identifiers respectively corresponding to the second communication subgraphs.

It should be noted that, the method for determining the target unique identifier and the target unique identifier set in the foregoing embodiment may also be used for the first party to determine the first unique user identifier corresponding to the user identification identifier in the first identification identifier set, and the second party to determine the second unique user identifier corresponding to the user identification identifier in the second identification identifier set, which are not described herein in detail.

In some implementations, the vertices in the first connected subgraph correspond to initial index values. Referring to fig. 7a, performing depth-related computation on the first communication subgraph may include the following steps.

S710, determining the initial index value meeting the index value threshold condition as a target index value according to the initial index value corresponding to the vertex in the first communication sub-graph.

Specifically, initializing an initial index value corresponding to the vertex in the first communication sub-graph, and determining the initial index value meeting the index value threshold condition as a target index value.

In some embodiments, the initial index value may be a subscript number of the user identification identifier corresponding to the vertex in the first communication sub-graph in the first identification identifier set. Illustratively, referring to FIG. 7b, vertex v is included in first connected subgraph G1 ₁ Vertex v ₂ Vertex v ₃ Vertex v ₄ Vertex v ₅ . Wherein the vertex v ₁ The corresponding user identification is ID1, vertex v ₂ The corresponding user identification is ID2, vertex v ₃ The corresponding user identification is ID3, vertex v ₄ The corresponding user identification is ID4, vertex v ₅ The corresponding user identification is ID5. If the subscript number of the user identification ID1 in the first identification set is 1, the corresponding vertex v may be determined ₁ Is initialized to 1; the subscript number of the user identification ID2 in the first identification set is 2, and the corresponding vertex v may be ₂ Is initialized to 2; if the subscript number of the user identification ID3 in the first identification set is 3, the corresponding vertex v may be determined ₃ Is initialized to 3; if the subscript number of the user identification ID4 in the first identification set is 4, the corresponding vertex v may be determined ₄ Is initialized to 4; the subscript number of the user identification ID5 in the first identification set is 5, and the corresponding vertex v may be ₅ Is initialized to 5. Among the above initial index values, an initial index value satisfying the index value threshold condition may be determined as a target index value.

In other embodiments, an initial index value may be allocated to each vertex in the first connected subgraph, so as to initialize the initial index value.

S720, propagating the target index value in the vertex of the first communication sub-graph to update the initial index value corresponding to the vertex in the first communication sub-graph to the target index value.

Specifically, according to the connection relationship between the vertices of the first connected subgraph, the target index value may be propagated in the vertices of the first connected subgraph, and after each propagation, the current index value corresponding to the vertex in the first connected subgraph is updated until the current index values respectively corresponding to all the vertices in the subgraph are the target index values, so that the target index value can be associated to all the vertices of the first connected subgraph.

In some embodiments, the initial index values corresponding to the vertices in the first communication subgraph may be ordered, and the minimum or maximum initial index value is determined as the target index value.

Illustratively, with continued reference to FIG. 7b, vertex v of sub-graph G1 is according to the first communication ₁ Vertex v ₂ Vertex v ₃ Vertex v ₄ Vertex v ₅ The connection relationship between the two can obtain an adjacent matrix A corresponding to the first communication sub-graph G1, and the adjacent matrix A is expressed as follows:

Vertex v ₁ The corresponding initial index value is 1, vertex v ₂ The corresponding initial index value is 2, vertex v ₃ The corresponding initial index value is 3, vertex v ₄ The corresponding initial index value is 4, vertex v ₅ The corresponding initial index value is 5. By a center ₀ Representing an index value matrix composed of initial index values corresponding to the 5 vertices of the first connected subgraph G1, respectively, then center ₀ Can be expressed as:

the initial index value 1 is determined as the target index value. According to the adjacent matrix A corresponding to the first connected subgraph G1 and the index value matrix center ₀ The target index value 1 may be propagated in the vertices of the first connected subgraph according to the following formula, so as to iterate the index values corresponding to the 5 vertices respectively:

wherein i and j are subscript values of 5 vertices in the first connected subgraph G1; t is the iteration number; n is the number of top points in the first connected subgraph; center (center) _t (i) Representing the current index value corresponding to each vertex.

After f rounds of iteration, the current index values respectively corresponding to the 5 vertexes in the first connected subgraph G1 are all target index value 1, and the index value matrix can be expressed as:

so far, the depth association calculation of the first communication sub-graph G1 is realized by adopting a mode of searching the communication sub-graph through information transmission between adjacent vertexes, and the target index value 1 can be associated to 5 vertexes in the first communication sub-graph G1.

Further, referring to fig. 7c, the vertex v corresponding to the target index value 1 may be used ₁ As root node, other vertexes in the first connected sub-graph G1 are respectively connected with the root node v ₁ And directly connecting to obtain a second linkage sub-graph obtained by converting the first linkage sub-graph. The data structure based on the second linkage subgraph can be passed through the root node v ₁ The corresponding root node ID1 can quickly inquire the user identification ID2, ID3, ID4 and ID5 which have relevance with the user identification ID 1. In some embodiments, the first association may also be identified by the target index value as the root nodeVertices in the general graph are directly connected with the root node identifiers respectively.

In other embodiments, the depth association calculation of the first communication subgraph may also be implemented by using a graph calculation method such as GNN (Graph Neural Networks, graph neural network).

In some embodiments, the user identities in the second set of identities have a second unique user identity, and the second unique user identity and the corresponding user identities in the second set of identities form an identity correspondence list.

The identifier corresponding relation list is used for determining a second user unique identifier corresponding to the user identification identifier in the user identification identifier intersection; the identification information of the unique identification of the second user is an index identification.

Wherein the identification information may be a subscript number of the second user unique identification in the second user unique identification set.

Specifically, the second user unique identifier set may be obtained according to the second user unique identifier. And associating the user identification identifier in the second identification identifier set with the corresponding second user unique identifier to obtain an identifier corresponding relationship list. Because the intersection of the user identification identifiers is a subset of the second identification identifier set, the second party can query the identifier correspondence list for the user identification identifier identical to the user identification identifier in the intersection of the user identification identifiers, so that the second unique user identifier corresponding to the user identification identifier can be determined. Further, the index identification set can be obtained by taking the index number corresponding to the determined unique identification of the second user as the index identification.

In some embodiments, identifying the correspondence list may be identifying a correspondence binary list. Specifically, the second identification set V ^B The user identification marks in the method are respectively associated with the corresponding second user unique marks, so that the user identification marks can be obtained

And the corresponding second user unique identifier +. >

Formed identification corresponding relation binary group

Thereby, the identification correspondence list +_ can be obtained>

Wherein U is ^B The set is uniquely identified for a second user of the second party. In the identification correspondence list, the user identification mark +.>

And determining a second unique user identifier corresponding to the user identification identifier in the user identification identifier intersection. In the present specification, the second identifier set V ^B The subscript i of the user identification in the user identification intersection phi is not related to the subscript i of the user identification in the user identification intersection phi.

Further, the second party may identify the user in the intersection Φ of user identifications

Respectively corresponding user unique identification +.>

The association is carried out, and a corresponding relation list can be obtained>

The second party may first list R ^B According to->

Ordering, then uniquely identifying the ordered user +.>

Corresponding subscript sequence number j is according to R ^B After ordering the order of (2) to obtain an index identity list for provision to the first party.

The embodiment of the specification provides a multiparty user identification processing device, wherein the multiparty user identification processing device at least comprises a first party and a second party which do not share data. Referring to fig. 8, the apparatus 800 for processing user identification of multiple parties includes: an associated identification list determination module 810, an identification set acquisition module 820, and a unique identification set determination module 830.

An association list determination module 810 is configured to determine an initial association list for the first party based on an association between user identities in a first set of identities that the first party has.

An identifier set acquisition module 820, configured to acquire a user identification identifier intersection set and an index identifier set provided by the second party; the user identification mark intersection is obtained by carrying out privacy intersection on the first identification mark set and the second identification mark set of the second party, and index marks in the index mark set are used for indicating unique user marks corresponding to the user identification marks in the user identification mark intersection.

The unique identifier set determining module 830 is configured to determine a target unique identifier set of the first party according to the index identifier set, the user identification identifier intersection set, and the initial association identifier list.

The specific definition of the user identification processing means for multiple parties may be referred to above as definition of the user identification processing method for multiple parties, and will not be described here again. The various modules in the multiparty subscriber identity module processing means described above may be implemented in whole or in part in software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

The present disclosure further provides a computer device, referring to fig. 9, where the computer device 900 includes a memory 910, a processor 920, and a computer program 930 stored in the memory 910 and capable of running on the processor 920, and when the processor 920 executes the computer program 930, the method for processing user identification of multiple parties according to any of the foregoing embodiments is implemented.

The embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for processing user identification of multiple parties as described in any of the foregoing embodiments.

It should be noted that the logic and/or steps represented in the flowcharts or otherwise described herein, for example, may be considered as a ordered listing of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.

In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly, through intermediaries, or both, may be in communication with each other or in interaction with each other, unless expressly defined otherwise. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.

While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.

Claims

1. A method for processing user identification of multiple parties, wherein the multiple parties at least comprise a first party and a second party which do not share data; the method comprises the following steps:

determining an initial association identifier list of the first party based on the association between user identifiers in a first set of identifiers of the first party;

acquiring a user identification identifier intersection set and an index identifier set provided by the second party; the user identification mark intersection is obtained by carrying out privacy intersection on the first identification mark set and a second identification mark set of the second party, and index marks in the index mark set are used for referring to unique user marks corresponding to the user identification marks in the user identification mark intersection;

and determining a target unique identification set of the first party according to the index identification set, the user identification intersection set and the initial association identification list.

2. The method of claim 1, wherein said determining a set of target unique identifications of the first party from the set of index identifications, the user identification intersection, and the initial associated identification list comprises:

Supplementing the initial association identifier list by using the index identifier set and the user identification identifier intersection set to obtain a target association identifier list;

and determining a target unique identification set of the first party according to the target association identification list.

3. The method of claim 2, wherein supplementing the initial association identifier list with the set of index identifiers and the intersection of user identification identifiers to obtain a target association identifier list comprises:

sequentially carrying out one-to-one correspondence between index identifiers in the index identifier set and user identification identifiers in the user identification identifier intersection set to obtain a supplementary association identifier list corresponding to the user identification identifier intersection set;

and merging the supplementary association identifier list with the initial association identifier list to obtain the target association identifier list.

4. The method of claim 1, wherein the determining the initial list of associated identities of the first party based on a correlation between user identities in a first set of identities that the first party has, comprises:

based on the association frequency between the user identification marks in the first identification mark set, combining any two user identification marks corresponding to the association frequency meeting the frequency threshold condition to obtain an initial association mark binary group corresponding to the any two user identification marks;

And determining an initial association identifier list of the first party according to the initial association identifier binary groups corresponding to any two user identification identifiers in the first identification identifier set.

5. The method of claim 1, wherein prior to said determining the set of target unique identifications of the first party from the set of index identifications, the user identification intersection, and the initial associated identification list, the method further comprises:

determining a first user unique identifier corresponding to a user identification identifier in the first identification identifier set according to the initial association identifier list of the first party;

the determining the target unique identification set of the first party according to the index identification set, the user identification intersection set and the initial association identification list comprises the following steps:

updating a first user unique identifier corresponding to the user identification identifier in the first identification identifier set according to the index identifier set, the user identification identifier intersection set and the initial association identifier list;

and determining a target unique identification set of the first party according to the updated first user unique identification.

6. The method of claim 1, wherein said determining a set of target unique identifications of the first party from the set of index identifications, the user identification intersection, and the initial associated identification list comprises:

Constructing an undirected graph of the first party; the vertex of the undirected graph is used for representing user identification marks in the first identification mark set, and the connecting edges between the vertices are determined according to the index mark set, the user identification mark intersection set and the initial association mark list;

respectively carrying out depth association calculation on a plurality of first communication subgraphs in the undirected graph to obtain a plurality of second communication subgraphs corresponding to the undirected graph; wherein, the second linkage subgraphs are respectively allocated with corresponding target unique identifiers;

and determining the target unique identifier set according to the target unique identifiers respectively corresponding to the second communication subgraphs.

7. The method of claim 6, wherein vertices in the first communication graph correspond to initial index values; performing depth association calculation on the first communication subgraph, including:

according to the initial index value corresponding to the vertex in the first communication sub-graph, determining the initial index value meeting the index value threshold condition as a target index value;

and transmitting the target index value in the vertex of the first communication sub-graph so as to update the initial index value corresponding to the vertex in the first communication sub-graph to the target index value.

8. The method according to any one of claims 1 to 7, wherein the user identities in the second set of identities correspond to a second unique user identity, the second unique user identity and the corresponding user identities in the second set of identities forming an identity correspondence list;

the identifier corresponding relation list is used for determining a second user unique identifier corresponding to the user identification identifier in the user identification identifier intersection; and the identification information of the unique identification of the second user is the index identification.

9. A user identification processing device for a plurality of parties, wherein the parties include at least a first party and a second party that do not share data; the device comprises:

an association identifier list determining module, configured to determine an initial association identifier list of the first party based on an association between user identifiers in a first set of identifiers that the first party has;

the identification set acquisition module is used for acquiring a user identification intersection set and an index identification set provided by the second party; the user identification mark intersection is obtained by carrying out privacy intersection on the first identification mark set and a second identification mark set of the second party, and index marks in the index mark set are used for referring to unique user marks corresponding to the user identification marks in the user identification mark intersection;

And the unique identification set determining module is used for determining a target unique identification set of the first party according to the index identification set, the user identification intersection set and the initial association identification list.

10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 8 when the computer program is executed.

11. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 8.