A data processing system for acquiring target image labels

Abstract

The application relates to a data processing system for obtaining target portrait labels, which comprises a processor and a memory storing a computer program, and when the computer program is executed by the processor, the following steps are realized: receiving a label obtaining request, obtaining an initial user ID list sent by a first data platform, obtaining a first expanded ID set according to the initial user ID list, sending the first expanded ID set to a second data platform to obtain a second expanded ID set, obtaining a first target ID list sent by the first data platform according to the initial user ID, obtaining a second target ID list sent by the second data platform according to the second expanded ID list, and obtaining a target label set corresponding to the initial user ID according to the first target ID list and the second target ID list. According to the application, the user ID information of the two data platforms is encrypted and decrypted in a neutral environment, so that the user ID information leakage of the two data platforms is avoided.

Description

Technical Field

[0001] This invention relates to the field of user ID processing technology, and in particular to a data processing system for obtaining target profile tags. Background Technology

[0002] With the popularization and development of big data, it has become a global trend to use big data to promote economic development, improve social governance, and enhance government services and regulatory capabilities. As network data technology continues to advance, user ID information is stored in various databases. When two or more parties interact with data, there is a risk of personal information leakage. How to encrypt and protect user ID information in the database during data interaction, prevent the leakage of user ID information, and effectively obtain user ID tags has become a hot research topic.

[0003] Currently, the existing method for obtaining target profile tags involves: obtaining a list of target incremental IDs based on the initial ID, inputting it into a first database, and then obfuscating the initial ID and target incremental IDs in the first database to prevent third parties from decrypting the initial ID. The above method for obtaining target profile tags has the following problems:

[0004] On the one hand, the lack of a data interaction process makes data leakage possible when acquiring information;

[0005] On the other hand, the lack of encryption of the data provider's information and the failure to decrypt the obtained profile tags in a neutral environment resulted in the leakage of user ID information and data provider profile tags when obtaining target profile tags. Summary of the Invention

[0006] To address the aforementioned technical problems, the present invention adopts the following technical solution: a data processing system for acquiring target profile tags, the system comprising: a processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the following steps are implemented:

[0007] S100, Receive tag acquisition request, obtain the initial user ID list A = {A1, A2, ..., A...} sent by the first data platform. i , ..., A n}, A i Let be the i-th initial user ID, i = 1, 2, ..., n, where n is the number of initial user IDs, and the first data platform is the data platform corresponding to the party that obtained the user tag.

[0008] S200, Based on A, obtain the first expansion ID set LA = {LA1, LA2, ..., LA...} corresponding to A sent by the first data platform. i , ..., LA n}, LAi ={A i LA' i}, LA' i ={LA 1 i LA 2 i , ..., LA x i , ..., LA p(i) i}, LA x i For A i The corresponding x-th first expansion ID, x = 1, 2, ..., p(i), p(i) is A i The number of corresponding first expansion IDs.

[0009] S300, send LA to the second data platform, and obtain the second expansion ID set B = {B1, B2, ..., B...} corresponding to the LA sent by the second data platform. i , ..., B n}, B i ={B i1 B i2 , ..., B ij , ..., B im} and the intermediate image tag set DB = {DB1, DB2, ..., DB} corresponding to B. i , ..., DB n}, DB i ={DB i1 DB i2 , ..., DB ij , ..., DB im}, B ij For LA i The corresponding j-th second expansion ID, DB ij For B ij The corresponding intermediate profile tag list, j = 1, 2, ..., m, where m is the number of second expansion IDs, and the second data platform is the data platform corresponding to the provider of user tags.

[0010] S400, Based on A, obtain the first target ID list FA = {FA1, FA2, ..., FA} corresponding to A sent by the first data platform. i , ..., FA n}, FA i For A i The corresponding first target ID.

[0011] S500, based on B, obtain the second target ID list FB = {FB1, FB2, ..., FB} corresponding to B sent by the second data platform.i ..., FB n}, among which, FB i ={FB i1 FB i2 ..., FB ij ..., FB im}, FB ij For B ij The corresponding second target ID.

[0012] S600, based on FA and FB, obtain the target label set U = {U1, U2, ..., U} corresponding to A. i , ..., U n}, U i For A i The corresponding list of target tags.

[0013] Compared with the prior art, the present invention has significant advantages. Through the above technical solution, the data processing system for obtaining target image tags provided by the present invention achieves considerable technological progress and practicality, and has broad industrial application value. It has at least the following advantages:

[0014] This invention provides a data processing system for acquiring target profile tags. The system includes a processor and a memory storing a computer program. When the computer program is executed by the processor, it performs the following steps: receiving a tag acquisition request; acquiring an initial user ID list sent by a first data platform; acquiring a first expanded ID set corresponding to the initial user ID list sent by the first data platform based on the initial user ID list; sending the first expanded ID set to a second data platform; acquiring a second expanded ID set corresponding to the first expanded ID set sent by the second data platform; acquiring a first target ID list corresponding to the initial user ID list sent by the first data platform based on the initial user ID set; acquiring a second target ID list corresponding to the second expanded ID set sent by the second data platform based on the second expanded ID set; and acquiring a target tag set corresponding to the initial user ID based on the first target ID list and the second target ID list. It can be seen that, on the one hand, a data interaction process is performed between the two parties, protecting the data of both parties and preventing information leakage during the acquisition of tag information; on the other hand, the information of the data party is encrypted, and the acquired profile tags are decrypted in a neutral environment, ensuring the confidentiality of data other than target data between the two parties, so that user ID information and profile tags are not leaked when acquiring target profile tags. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of the computer program executing a data processing system for acquiring target image tags, provided as an embodiment of the present invention.

[0017] Figure 2 A flowchart of S200 provided for an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0020] Example 1

[0021] This embodiment provides a data processing system for acquiring user tags. The system includes a processor and a memory storing a computer program. When the computer program is executed by the processor, it performs the following steps, such as... Figure 1 As shown:

[0022] S100, Receive tag acquisition request, obtain the initial user ID list A = {A1, A2, ..., A...} sent by the first data platform. i , ..., A n}, A iLet A be the i-th initial user ID, i = 1, 2, ..., n, where n is the number of initial user IDs. i =(A 1 i A 2 i , ..., A y i , ..., A q i A y i For A i The initial value corresponding to the y-th sequence position, y = 1, 2, ..., q, where q is the number of initial values ​​in the initial user ID.

[0023] Specifically, the initial user ID represents a unique identifier of the initial user's identity. For example, the initial user ID is the SIM card number corresponding to the initial user's mobile device.

[0024] Specifically, the tag acquisition request is a request issued by the first data platform to acquire user tags.

[0025] Furthermore, the first data platform is the data platform corresponding to the party that obtains the user tags.

[0026] Specifically, the value of n ranges from 80 to 120. Those skilled in the art can select the number of initial user IDs according to actual needs, which will not be elaborated here.

[0027] As described above, by setting a critical value for the number of initial user IDs, it is possible to ensure improved operating efficiency when the computer is executed by the processor, and to avoid situations where the operating efficiency is reduced or the computer cannot operate due to an excessive amount of initial user ID data sent by the first data platform.

[0028] S200, Based on A, obtain the first expansion ID set LA = {LA1, LA2, ..., LA...} corresponding to A sent by the first data platform. i , ..., LA n}, LA i ={A i LA' i}, LA' i ={LA 1 i LA 2 i , ..., LA x i , ..., LA p(i) i}, LA x i For A iThe corresponding x-th first expansion ID, x = 1, 2, ..., p(i), p(i) is A i The number of corresponding first expansion IDs.

[0029] Specifically, S200 also includes the following steps, such as Figure 2 As shown:

[0030] S201, Obtain the first intermediate expansion ID set A' = {A'1, A'2, ..., A'} corresponding to A. i , ..., A' n}, A' i ={A' i1 A' i2 , ..., A' ir , ..., A' iz}, A' ir =(A' 1 ir A' 2 ir , ..., A' y ir , ..., A' q ir ), A' y ir For A i The initial value corresponding to the y-th sequence position in the r-th first intermediate expansion ID, y = 1, 2, ..., q, where q is the number of initial values ​​in the first intermediate expansion ID, and r = 1, 2, ..., z, where z is the number of first intermediate expansion IDs.

[0031] Specifically, the number of initial values ​​in the first intermediate expansion ID is the same as the number of initial values ​​in the initial user ID.

[0032] Specifically, the first intermediate expansion ID is a randomly generated user ID that is inconsistent with the initial user ID, wherein the type of the first intermediate expansion ID is consistent with the type of the initial user ID.

[0033] Specifically, A' i1 ≠A' i2 ≠……≠A' ir ≠……≠A' iτ ≠……≠A' iz .

[0034] S202, Based on A', obtain the first target expansion ID set BA' = {BA'1, BA'2, ..., BA'} corresponding to A'. i , ..., BA' n}, BA' i ={BA' i1 BA'i2 , ..., BA' ir , ..., BA' iz}, BA' ir =(A' 1 ir A' 2 ir , ..., A' δ ir ), A' δ ir For A' ir The initial value corresponding to the δth sequence position in the sequence, where δ≤q; can be understood as: from A' ir Select the initial values ​​corresponding to the first δ positions in the sequence to construct BA'. ir .

[0035] S203, Based on BA', obtain the second intermediate expansion ID set AX = {AX1, AX2, ..., AX'} corresponding to BA'. i , ..., AX n}, AX i ={AX i1 AX i2 , ..., AX ic , ..., AX id(i)}, AX ic ={AX 1 ic AX 2 ic , ..., AX θ ic , ..., AX η ic}, AX θ ic for BA' i The corresponding c-th second intermediate expansion ID is the θ-th second intermediate expansion ID in the list, where θ = 1, 2, ..., η, and η is BA'. i The corresponding number of second intermediate expansion IDs in the c-th second intermediate expansion ID list, c = 1, 2, ..., d(i), where d(i) is BA' i The number of corresponding second intermediate expansion ID lists.

[0036] Specifically, S203 also includes the following steps:

[0037] S2031, perform deduplication on BA' and obtain the second target expansion ID set TA' = {TA'1, TA'2, ..., TA'} corresponding to BA'. i , ……, TA' n},TA' i ={TA' i1 ,TA'i2 , ……, TA' ic , ……, TA' id(i)},TA' ic for BA' i The c-th second target expansion ID in the corresponding second target expansion ID list; any deduplication method known to those skilled in the art falls within the protection scope of this invention, and will not be elaborated here.

[0038] As mentioned above, by deduplicating the obtained first target expansion ID, the amount of data can be reduced, which can improve the efficiency of subsequent matching and avoid repeated expansion due to data duplication.

[0039] S2033, according to TA' ic Get AX θ ic =(TA' ic AX θ1 ic , ..., AX θγ ic , ..., AX θξ ic ), AX θγ ic For AX θ ic The adjustment value corresponding to the γth sequence position, γ = 1, 2, ..., ξ, where ξ is AX θ ic The number of adjustment values.

[0040] Specifically, any of the adjustment values ​​mentioned can be any value between 0 and 9.

[0041] Furthermore, ξ = q - δ.

[0042] Furthermore, AX θγ ic The value is any value in [L1, L2], where L1 is the lower limit value corresponding to the type of the initial user ID, and L2 is the upper limit value corresponding to the type of the initial user ID. Those skilled in the art know that the lower limit and upper limit value of each value in the ID are determined according to the type of the ID, and will not be elaborated here. For example, when the initial user ID is the SIM card number corresponding to the initial user's mobile device, L1 = 0 and L2 = 9.

[0043] Specifically, AX 1 ic ≠AX 2 ic ≠……≠AX θ ic ≠……≠AX η icThis can be understood as: based on AX θ1 ic To AX θξ ic This generates different second intermediate expansion IDs.

[0044] Furthermore, η = C ξ q And W1 / z≤η≤W2 / z, where W1 is the lower limit of the number of first expansion IDs and W2 is the upper limit of the number of first expansion IDs.

[0045] Furthermore, p(i) = η × z.

[0046] S204, Based on AX, obtain the first key expansion ID set AX corresponding to AX. 0 ={AX 0 1, AX 0 2, ..., AX 0 i , ...,

[0047] AX 0 n}, AX 0 i ={AX 0 i1 AX 0 i2 , ..., AX 0 ic , ..., AX 0 id(i)}, AX 0 ic ={AX 1 ic AX 2 ic , ..., AX θ-1 ic AX

[0048] θ+1 ic , ..., AX η ic}, where AX 0 ic For when AX θ ic =A' ir At that time, from AX ic Delete AX θ ic Obtained.

[0049] S205, Based on A, obtain the second key expansion ID set YA = {YA1, YA2, ..., YA} corresponding to A. i , ..., YAn}, YA i ={YA 1 i YA 2 i , ..., YA u i , ..., YA ψ i}, YA u i For A i The u-th second key expansion ID in the corresponding second key expansion ID list, u = 1, 2, ..., ψ, where ψ is A i The number of corresponding second key expansion IDs.

[0050] Specifically, S205 also includes the following steps:

[0051] S2051, Based on A, obtain the first ID set CA = {CA1, CA2, ..., CA} corresponding to A. i , ..., CA n}, CA i For A i The corresponding first ID list; specifically, the steps in S2051 can be referred to in step S202, and will not be repeated here.

[0052] S2053, Based on CA, obtain the intermediate ID set CA' = {CA'1, CA'2, ..., CA'} corresponding to CA. i , ..., CA' n};CA' i For A i The corresponding intermediate ID list; specifically, the steps in S2053 can be referred to in step S203, and will not be repeated here.

[0053] S2055, based on CA', obtain the second key expansion ID set YA corresponding to CA'; specifically, the steps of S2055 can be referred to step S204, and will not be repeated here.

[0054] As described above, by performing secondary expansion on the initial user ID and adjusting the sequence bits of each first intermediate expansion ID corresponding to the initial user ID, the value of the adjusted bits can ensure the decryption of the first intermediate expansion ID after confidentiality, so that the initial user ID cannot be decrypted when the second intermediate expansion ID is decrypted, thus ensuring the security of the first expansion ID data.

[0055] S206, will YA i and AX 0 ir Insert into LA' i In the process, LA is generated.i .

[0056] S300, send LA to the second data platform, and obtain the second expansion ID set B = {B1, B2, ..., B...} corresponding to the LA sent by the second data platform. i , ..., B n}, B i ={B i1 B i2 , ..., B ij , ..., B im} and the intermediate image tag set DB = {DB1, DB2, ..., DB} corresponding to B. i , ..., DB n}, DB i ={DB i1 DB i2 , ..., DB ij , ..., DB im}, B ij For LA i The corresponding j-th second expansion ID, DB ij For B ij The corresponding intermediate image tag list, j = 1, 2, ..., m, where m is the number of second expansion IDs.

[0057] Specifically, the second data platform is the data platform corresponding to the provider of the user tags.

[0058] Specifically, m meets the following conditions:

[0059] m = p(i) + 1.

[0060] Furthermore, the S300 also includes the following steps:

[0061] S301, Obtain the sample ID list C = {C1, C2, ..., C...} sent by the second data platform. g , ..., C s}, where C g Let g be the ID of the g-th sample, where g = 1, 2, ..., s, and s is the number of sample IDs.

[0062] Furthermore, the sample ID refers to the user ID stored in the second data platform. The type of the sample ID is consistent with the type of the initial user ID. That is, when the initial user ID is the SIM card number corresponding to the initial user's mobile device, the sample ID is the SIM card number corresponding to the sample user's mobile device.

[0063] S302, traverse C and if A i =C g At that time, C gAs the second expansion ID insertion value B i And obtain C g Corresponding key ID list D g ={D g1 D g2 , ..., D gt , ..., D gk}, D gt For the Cth g The corresponding t-th key ID, t = 1, 2, ..., k, where k is the number of key IDs.

[0064] Furthermore, C g The corresponding key ID is when A i =C g Delete C from C g Any sample ID that follows.

[0065] Furthermore, k satisfies the following conditions:

[0066] k = s - 1.

[0067] S303, Traverse D g And when LA x i =D gt At that time, D gt As the second expansion ID insertion value B i middle.

[0068] S304, Obtain the sample label set C' = {C'1, C'2, ..., C'} corresponding to C. g , ..., C' s}, C' g C g The corresponding list of sample labels.

[0069] Furthermore, the sample tag list is a tag list constructed from all the profile tags of the user corresponding to the sample ID.

[0070] S305, when A i =C g At that time, C' g DB is inserted as an intermediate image tag list. i And obtain C' g The corresponding key tag set D' g ={D' g1 ,D' g2 , ...D' gt , ..., D' gk},D' gt For the Dth gt The corresponding list of keywords.

[0071] Furthermore, any D' g The list of keywords in the middle is when A i =C g Delete C' from C' g A list of labels for any of the following samples.

[0072] S306, when LA x i =D gt At that time, D' gt DB is inserted as an intermediate image tag list. i middle.

[0073] As described above, by comparing the processed initial user ID with the sample ID, the second expanded ID list corresponding to the processed initial user ID and the sample tag set corresponding to the second expanded ID list are obtained. During this process, the second data platform cannot know the information of the initial user ID, thus keeping the initial user ID confidential and ensuring data security.

[0074] S400, Based on A, obtain the first target ID list FA = {FA1, FA2, ..., FA} corresponding to A sent by the first data platform. i , ..., FA n}, FA i For A i The corresponding first target ID.

[0075] Specifically, in S400, the FA is obtained through the following steps. i :

[0076] S401, Get A i =(A 1 i A 2 i , ..., A y i , ..., A q i A y i For A i The initial value corresponding to the y-th sequence position.

[0077] S403, according to A i , obtain A i The corresponding ID string to be encrypted, A 0 i =(A 1 i A 2 i , ..., A y i , ..., A qi ,β), where β is the encrypted value of ID.

[0078] Furthermore, the value of β can be any integer from 0 to 9.

[0079] S405, for A 0 i Encryption processing is performed to obtain FA. i Wherein, those skilled in the art know that obtaining an encrypted ID using any encryption method in the prior art falls within the protection scope of the present invention; preferably, the encryption process is SM3 encryption.

[0080] S500, based on B, obtain the second target ID list FB = {FB1, FB2, ..., FB} corresponding to B sent by the second data platform. i ..., FB n}, among which, FB i ={FB i1 FB i2 ..., FB ij ..., FB im}, FB ij For B ij The corresponding second target ID.

[0081] Specifically, the FB is obtained in the S500 through the following steps. ij :

[0082] S501, obtain B ij = (B 1 ij B 2 ij , ..., B y ij , ..., B q ij ), B y ij For B ij The ID value corresponding to the y-th position in the sequence.

[0083] S503, according to B ij , obtain B ij The corresponding ID string to be encrypted, B 0 ij = (B 1 ij B 2 ij , ..., B y ij , ..., B q ij ,β), where B 0ij β and A 0 i The β values ​​are consistent.

[0084] S505, for B 0 ij Encryption processing is performed to obtain FB. ij Among them, FB ij The corresponding encryption processing method and FA i The corresponding encryption methods are the same, so they will not be repeated here.

[0085] As described above, by encrypting the list of second expansion IDs obtained from the sample IDs, the second expansion IDs sent from the second database can be protected during data interaction, thus preventing the leakage of second expansion ID information sent from the second database when obtaining the target profile tag corresponding to the initial ID.

[0086] S600, based on FA and FB, obtain the target label set U = {U1, U2, ..., U} corresponding to A. i , ..., U n}, U i For A i The corresponding list of target tags.

[0087] Specifically, in the S600, U is obtained through the following steps. i :

[0088] S601, Obtain the tag set FDB = {FDB1, FDB2, ..., FDB} corresponding to the FB sent by the second data platform. i , ..., FDB n}, FDB i ={FDB i1 FDB i2 , ..., FDB ij , ..., FDB im}, FDB ij For DB ij The corresponding list of tags to be parsed.

[0089] Specifically, the list of tags to be parsed is a list of tags after the intermediate image tag list has been encrypted. Those skilled in the art know that obtaining the encrypted ID using any encryption method in the prior art falls within the protection scope of this invention.

[0090] S603, FA i With Facebook ij Compare and obtain FA i With Facebook ij The comparison results between them.

[0091] Specifically, S603 also includes the following steps:

[0092] S6031, Obtain FA i The corresponding first target vector GFA i ={GFA i1 GFA i2 ..., GFA ie ..., GFA if GFA ie For FA i The corresponding bit value of the e-th bit in the first target vector, where e = 1, 2, ..., f, and f is FA. i The corresponding bit dimension in the first target vector.

[0093] S6033, Get FB ij The corresponding second target vector GFB ij ={GFB 1 ij GFB 2 ij ..., GFB e ij ..., GFB f ij}, GFB ije For FB ij The corresponding bit value of the e-th bit in the second target vector.

[0094] S6035, according to GFA i and GFB ij Obtain GFA i The corresponding target similarity F j i , of which F j i Meets the following conditions ：

[0095]

[0096] S6037, when F j i When =F0, determine FA. i =FB ij As FA i With Facebook ij The comparison results between them, where F0 is the preset similarity threshold.

[0097] Preferably, F0 = 100%.

[0098] S605, based on FA i With Facebook ijThe comparison results between them, for FDB ij Decryption is performed to obtain the FDB. ij Corresponding DB ij This can be understood as: in step S605, when FA... i =FB ij At that time, FDB ij Decryption is performed to obtain the FDB. ij Corresponding DB ij Those skilled in the art will know that any encryption and decryption method in the prior art can be used, and will not be described in detail here.

[0099] S607, DB ij Sending to the first data platform, enabling DB ij As U i .

[0100] As described above, through the data interaction process, the decryption of the profile tags is ultimately performed in an environment where there is no overlap with the first and second data platforms. This ensures the independence of the data from both sides, avoids data leakage, and achieves the security of data information between the first and second data platforms during the data interaction process.

[0101] This invention provides a data processing system for acquiring target profile tags. The system includes a processor and a memory storing a computer program. When the computer program is executed by the processor, it performs the following steps: receiving a tag acquisition request; acquiring an initial user ID list sent by a first data platform; acquiring a first expanded ID set corresponding to the initial user ID list sent by the first data platform based on the initial user ID list; sending the first expanded ID set to a second data platform; acquiring a second expanded ID set corresponding to the first expanded ID set sent by the second data platform; acquiring a first target ID list corresponding to the initial user ID list sent by the first data platform based on the initial user ID set; acquiring a second target ID list corresponding to the second expanded ID set sent by the second data platform based on the second expanded ID set; and acquiring a target tag set corresponding to the initial user ID based on the first target ID list and the second target ID list. It can be seen that, on the one hand, a data interaction process is performed between the two parties, protecting the data of both parties and preventing information leakage during the acquisition of tag information; on the other hand, the information of the data party is encrypted, and the acquired profile tags are decrypted in a neutral environment, ensuring the confidentiality of data other than target data between the two parties, so that user ID information and profile tags are not leaked when acquiring target profile tags.

[0102] While specific embodiments of the invention have been described in detail by way of example, those skilled in the art should understand that the above examples are for illustrative purposes only and are not intended to limit the scope of the invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A data processing system for acquiring target profile tags, characterized in that, The system includes a processor and a memory storing a computer program, which, when executed by the processor, performs the following steps: S100, Receive tag acquisition request, obtain the initial user ID list A = {A1, A2, ..., A...} sent by the first data platform. i , ..., A n }, A i Let i be the i-th initial user ID, i = 1, 2, ..., n, where n is the number of initial user IDs, and the first data platform is the data platform corresponding to the party that obtained the user tags; S200, Based on A, obtain the first expansion ID set LA = {LA1, LA2, ..., LA...} corresponding to A sent by the first data platform. i , ..., LA n }, LA i ={A i LA' i }, LA' i ={LA 1 i LA 2 i , ..., LA x i , ..., LA p(i) i }, LA x i For A i The corresponding x-th first expansion ID, x = 1, 2, ..., p(i), p(i) is A i The number of corresponding first expansion IDs; S300, send LA to the second data platform, and obtain the second expansion ID set B = {B1, B2, ..., B...} corresponding to the LA sent by the second data platform. i , ..., B n }, B i ={B i1 B i2 , ..., B ij , ..., B im } and the intermediate image tag set DB = {DB1, DB2, ..., DB} corresponding to B. i , ..., DB n }, DB i ={DB i1 DB i2 , ..., DB ij , ..., DB im }, B ij For LA i The corresponding j-th second expansion ID, DB ij For B ij The corresponding intermediate profile tag list, j = 1, 2, ..., m, where m is the number of second expansion IDs, and the second data platform is the data platform corresponding to the provider of user tags; S400, Based on A, obtain the first target ID list FA = {FA1, FA2, ..., FA} corresponding to A sent by the first data platform. i , ..., FA n }, FA i For A i The corresponding first target ID; S500, based on B, obtain the second target ID list FB = {FB1, FB2, ..., FB} corresponding to B sent by the second data platform. i ..., FB n }, among which, FB i ={FB i1 FB i2 ..., FB ij ..., FB im }, FB ij For B ij The corresponding second target ID; S600, based on FA and FB, obtain the target label set U = {U1, U2, ..., U} corresponding to A. i , ..., U n }, U i For A i The corresponding list of target tags.

2. The data processing system for acquiring target profile tags according to claim 1, characterized in that, S200 also includes the following steps: S201, Obtain the first intermediate expansion ID set A' = {A'1, A'2, ..., A'} corresponding to A. i , ..., A' n }, A' i ={A' i1 , THE' i2 ,……,THE' ir ,……,THE' iz },THE' ir =(A' 1 ir ,THE' 2 ir ,……,THE' y ir ,……,THE' q ir ),THE' y ir for A i corresponding The initial value corresponding to the y-th sequence position in the r-th first intermediate expansion ID, y = 1, 2, ..., q, where q is the number of initial values ​​in the first intermediate expansion ID, and r = 1, 2, ..., z, where z is the number of first intermediate expansion IDs; S202, Based on A', obtain the first target expansion ID set BA' = {BA'1, BA'2, ..., BA'} corresponding to A'. i , ..., NOT' n },NOT' i ={NOT' i1 ,NOT' i2 ,……,NOT' ir ,……,NOT' iz },NOT' ir =(A' 1 ir ,IN' 2 ir ,……,IN' δ ir ),IN' δ ir For A' ir The initial value corresponding to the δth sequence position in the sequence, where δ≤q; can be understood as: from A' ir Select the initial values ​​corresponding to the first δ positions in the sequence to construct BA'. ir ; S203, Based on BA', obtain the second intermediate expansion ID set AX = {AX1, AX2, ..., AX'} corresponding to BA'. i , ..., AX n },AX i ={AX i1 ,AX i2 ,……,AX ic ,……,AX id(i) },AX ic ={AX 1 ic ,AX 2 ic ,……,AX θ ic ,……, AX η ic }, AX θ ic for BA' i The corresponding c-th second intermediate expansion ID is the θ-th second intermediate expansion ID in the list, where θ = 1, 2, ..., η, and η is BA'. i The corresponding number of second intermediate expansion IDs in the c-th second intermediate expansion ID list, c = 1, 2, ..., d(i), where d(i) is BA' i The corresponding number of the second intermediate expansion ID list; S204, Based on AX, obtain the first key expansion ID set AX corresponding to AX. 0 ={AX 0 1, AX 0 2, ..., AX 0 i , ..., AX 0 n }, AX 0 i ={AX 0 i1 AX 0 i2 , ..., AX 0 ic , ..., AX 0 id(i) }, AX 0 ic ={AX 1 ic AX 2 ic , ..., AX θ-1 ic AX θ+1 ic , ..., AX η ic }, where AX 0 ic For when AX θ ic =A' ir At that time, from AX ic Delete AX θ ic Obtained; S205, Based on A, obtain the second key expansion ID set YA = {YA1, YA2, ..., YA} corresponding to A. i , ..., YA n }, YA i ={YA 1 i YA 2 i , ..., YA u i , ..., YA ψ i }, YA u i For A i The u-th second key expansion ID in the corresponding second key expansion ID list, u = 1, 2, ..., ψ, where ψ is A i The corresponding number of second key expansion IDs; S206, will YA i and AX 0 ir Insert into LA' i In the process, LA is generated. i .

3. The data processing system for acquiring target profile tags according to claim 1, characterized in that, The tag acquisition request is a request issued by the first data platform to acquire user tags.

4. The data processing system for acquiring target profile tags according to claim 1, characterized in that, The S300 also includes the following steps: S301, Obtain the sample ID list C = {C1, C2, ..., C...} sent by the second data platform. g , ..., C s }, where C g Let g be the ID of the g-th sample, where g = 1, 2, ..., s, and s is the number of sample IDs; S302, traverse C and if A i =C g At that time, C g As the second expansion ID insertion value B i And obtain C g Corresponding key ID list D g ={D g1 D g2 , ..., D gt , ..., D gk }, D gt For the Cth g The corresponding t-th key ID, t = 1, 2, ..., k, where k is the number of key IDs; S303, Traverse D g And when LA x i =D gt At that time, D gt As the second expansion ID insertion value B i middle; S304, Obtain the sample label set C' = {C'1, C'2, ..., C'} corresponding to C. g , ..., C' s }, C' g C g The corresponding list of sample labels; S305, when A i =C g At that time, C' g DB is inserted as an intermediate image tag list. i And obtain C' g The corresponding key tag set D' g ={D' g1 ,D' g2 , ...D' gt , ..., D' gk },D' gt For the Dth gt The corresponding list of keywords; S306, when LA x i =D gt At that time, D' gt DB is inserted as an intermediate image tag list. i middle.

5. The data processing system for acquiring target profile tags according to claim 1, characterized in that, In S400, FA is obtained through the following steps. i : S401, Get A i =(A 1 i A 2 i , ..., A y i , ..., A q i A y i For A i The initial value corresponding to the y-th sequence position; S403, according to A i , obtain A i The corresponding ID string to be encrypted, A 0 i =(A 1 i A 2 i , ..., A y i , ..., A q i ,β), where β is the encrypted value of ID; S405, for A 0 i Encryption processing is performed to obtain FA. i .

6. The data processing system for acquiring target profile tags according to claim 5, characterized in that, The value of β can be any integer from 0 to 9.

7. The data processing system for acquiring target profile tags according to claim 1, characterized in that, In S500, obtain the FB through the following steps. ij : S501, obtain B ij = (B 1 ij B 2 ij , ..., B y ij , ..., B q ij ), B y ij For B ij The ID value corresponding to the y-th position in the sequence; S503, according to B ij , obtain B iji The corresponding ID string to be encrypted, B 0 ij = (B 1 ij B 2 ij , ..., B y ij , ..., B q ij ,β), where B 0 ij β and A 0 i β is consistent; S505, for B 0 ij Encryption processing is performed to obtain FB. ij .

8. The data processing system for acquiring target profile tags according to claim 7, characterized in that, The FB ij The corresponding encryption processing method and FA i The corresponding encryption methods are consistent.

9. The data processing system for acquiring target profile tags according to claim 1, characterized in that, In S600, U is also obtained through the following steps. i : S601, Obtain the tag set FDB = {FDB1, FDB2, ..., FDB} corresponding to the FB sent by the second data platform. i , ..., FDB n }, FDB i ={FDB i1 FDB i2 , ..., FDB ij , ..., FDB im }, FDB ij For DB ij The corresponding list of tags to be parsed; S603, FA i With Facebook ij Compare and obtain FA i With Facebook ij The comparison results between them; S605, based on FA i With Facebook ij The comparison results between them, for FDB ij Decryption is performed to obtain the FDB. ij Corresponding DB ij ; S607, DB ij Sending to the first data platform, enabling DB ij As U i .

10. The data processing system for acquiring target profile tags according to claim 9, characterized in that, S603 also includes the following steps: S6031, Obtain FA i The corresponding first target vector GFA i ={GFA i1 GFA i2 ..., GFA ie ..., GFA if GFA ie For FA i The corresponding bit value of the e-th bit in the first target vector, where e = 1, 2, ..., f, and f is FA. i The corresponding bit dimension in the first target vector; S6033, Get FB ij The corresponding second target vector GFB ij ={GFB 1 ij GFB 2 ij ..., GFB e ij ..., GFB f ij }, GFB ije For FB ij The corresponding bit value of the e-th bit in the second target vector; S6035, according to GFA i and GFB ij Obtain GFA i The corresponding target similarity F j i , of which F j i Meets the following conditions ： S6037, when F j i When =F0, determine FA. i =FB ij As FA i With Facebook ij The comparison results between them, where F0 is the preset similarity threshold.

Images