Data processing method, device and equipment and computer readable storage medium

Abstract

The invention discloses a data processing method, device and equipment and a computer readable storage medium. The method is applied to a first participant, and comprises the following steps: acquiring a joint identifier set which is a union set of a first identifier set and a second identifier set; encrypting the first transaction data corresponding to each joint object identifier in the joint identifier set to obtain a first transaction data ciphertext; sending the joint identifier set and the first transaction data ciphertext corresponding to the joint identifier set to the second participant; receiving a first joint data ciphertext sent by the second participant, the first joint data ciphertext being obtained by encrypting joint transaction data by using a random number, and the joint transaction data being determined based on the first transaction data ciphertext and the second transaction data; and performing joint calculation on the first joint data ciphertext to obtain a first joint calculation result. According to the embodiment of the invention, the safety of the transaction data can be ensured, and the joint calculation mode of the accuracy of the joint calculation result can be ensured.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a data processing method, device, equipment and computer-readable storage medium. Background Art

[0002] Usually, some financial institutions can store transaction data and conduct risk monitoring on merchants or users based on the transaction data. Among them, a single institution often cannot grasp the full amount of transaction data. Therefore, in order to better monitor risks, it is often necessary to jointly calculate the transaction data of multiple institutions and conduct risk monitoring based on the joint calculation results. In the joint calculation process, it is crucial to ensure the security of transaction data.

[0003] At present, joint computing is usually based on privacy-safe intersection algorithms or federated modeling. Both privacy-safe intersection algorithms and federated modeling methods are based on the intersection of data sets from multiple participants for joint computing, and the computing process often involves complex cryptographic methods to ensure the security and privacy of transaction data.

[0004] However, in some scenarios in the financial industry, the joint calculation results obtained based solely on intersection calculations may be less accurate and insufficient to achieve the purpose of risk monitoring. Therefore, there is an urgent need for a joint calculation method that can ensure both the security of transaction data and the accuracy of joint calculation results. Summary of the invention

[0005] The embodiments of the present application provide a data processing method, apparatus, device, computer-readable storage medium, and computer program product, which can ensure both the security of transaction data and the accuracy of joint calculation results.

[0006] In a first aspect, an embodiment of the present application provides a data processing method, which is applied to a first participant, and the method includes:

[0007] Acquire a joint identification set, the joint identification set being a union of a first identification set of the first participant and a second identification set of the second participant, the first identification set including a plurality of first object identifications of first objects to be monitored, the second identification set including a plurality of second object identifications of second objects to be monitored, and the joint identification set including a plurality of joint object identifications;

[0008] Encrypting first transaction data corresponding to each of the joint object identifiers using a homomorphic encryption key to obtain first transaction data ciphertext, where the first transaction data is transaction data of the first participant;

[0009] Sending the joint identification set and the first transaction data ciphertext corresponding to it to the second participant;

[0010] receiving a first joint data ciphertext sent by the second participant, where the first joint data ciphertext is obtained by encrypting joint transaction data using a random number, the joint transaction data is data determined based on the first transaction data ciphertext and the second transaction data for each joint object identifier, and the second transaction data is transaction data of the second participant;

[0011] A joint calculation is performed based on the first joint data ciphertext to obtain a first joint calculation result.

[0012] In a second aspect, an embodiment of the present application provides a data processing method, which is applied to a second participant, and the method includes:

[0013] Receive a joint identification set and a first transaction data ciphertext corresponding to it sent by a first participant, wherein the joint identification set is a union of a first identification set in the first participant and a second identification set in the second participant, wherein the first identification set includes a plurality of first object identifications of first objects to be monitored, the second identification set includes a plurality of second object identifications of second objects to be monitored, and the joint identification set includes a plurality of joint object identifications; the first transaction data ciphertext is obtained by encrypting the first transaction data corresponding to the joint object identification using a homomorphic encryption key, and the first transaction data is the transaction data of the first participant;

[0014] For each of the joint object identifiers, determining joint transaction data based on the first transaction data ciphertext and second transaction data, where the second transaction data is transaction data of the second participant;

[0015] Encrypting the joint transaction data using a random number to obtain a first joint data ciphertext;

[0016] The first joint data ciphertext is sent to the first participant, so that the first participant performs a joint calculation based on the first joint ciphertext to obtain a first joint calculation result.

[0017] In a third aspect, an embodiment of the present application provides a data processing device, applied to a first participant, the device comprising:

[0018] A first acquisition module is used to acquire a joint identification set, wherein the joint identification set is a union of a first identification set of the first participant and a second identification set of the second participant, wherein the first identification set includes a plurality of first object identifications of first objects to be monitored, the second identification set includes a plurality of second object identifications of second objects to be monitored, and the joint identification set includes a plurality of joint object identifications;

[0019] A first encryption module, configured to encrypt first transaction data corresponding to each of the joint object identifiers using a homomorphic encryption key to obtain first transaction data ciphertext, where the first transaction data is transaction data of the first participant;

[0020] A first sending module, configured to send the joint identification set and the first transaction data ciphertext corresponding thereto to the second participant;

[0021] a first receiving module, configured to receive a first joint data ciphertext sent by the second participant, wherein the first joint data ciphertext is obtained by encrypting joint transaction data using a random number, the joint transaction data is data determined based on the first transaction data ciphertext and the second transaction data for each joint object identifier, and the second transaction data is transaction data of the second participant;

[0022] The first calculation module is used to perform joint calculation based on the first joint data ciphertext to obtain a first joint calculation result.

[0023] In a fourth aspect, an embodiment of the present application provides a data processing device, applied to a second participant, the device comprising:

[0024] A second receiving module is used to receive a joint identification set and a first transaction data ciphertext corresponding to the joint identification set sent by a first participant, wherein the joint identification set is a union of a first identification set in the first participant and a second identification set in the second participant, wherein the first identification set includes a plurality of first object identifications of first objects to be monitored, the second identification set includes a plurality of second object identifications of second objects to be monitored, and the joint identification set includes a plurality of joint object identifications; the first transaction data ciphertext is obtained by encrypting the first transaction data corresponding to the joint object identification using a homomorphic encryption key, and the first transaction data is the transaction data in the first participant;

[0025] a first determining module, configured to determine, for each of the joint object identifiers, joint transaction data based on the first transaction data ciphertext and second transaction data, where the second transaction data is transaction data of the second participant;

[0026] A second encryption module, used to encrypt the joint transaction data using a random number to obtain a first joint data ciphertext;

[0027] The second sending module is used to send the first joint data ciphertext to the first participant, so that the first participant performs joint calculation based on the first joint ciphertext to obtain a first joint calculation result.

[0028] In a fifth aspect, an embodiment of the present application provides an electronic device, the device comprising: a processor and a memory storing computer program instructions;

[0029] When the processor executes the computer program instructions, the method in any possible implementation method of the first aspect or the second aspect is implemented.

[0030] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement a method in any possible implementation method of the first aspect or the second aspect mentioned above.

[0031] In a seventh aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes a method in any possible implementation method of the first aspect or the second aspect mentioned above.

[0032] In the embodiment of the present application, since the joint identification set is the union of the first identification set in the first participant and the second identification set in the second participant, by obtaining the joint identification set and performing joint calculation based on the transaction data corresponding to the joint identification set, the comprehensiveness of the joint calculation data can be guaranteed, thereby ensuring the accuracy of the joint calculation result. In addition, the joint transaction data is the data determined by the second participant for each joint object identifier based on the first transaction data ciphertext and the second transaction data. Therefore, by sending the joint identification set to the second participant and encrypting the first transaction data corresponding to each joint object identifier using the homomorphic encryption key to obtain the first transaction data ciphertext, receiving the first joint data ciphertext encrypted by the second participant using the random number to encrypt the joint transaction data, and performing joint calculation based on the first joint data ciphertext, that is, in the joint calculation process, the joint calculation process is optimized by one party holding the key and the other participants holding the random number, which can reduce the risk of data leakage, improve the data security of each participant, and enhance the mutual trust of all parties. In this way, through the embodiment of the present application, both the security of the transaction data and the accuracy of the joint calculation result can be guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0034] Figure 1 is a flowchart of a data processing method applied to a first participant provided in an embodiment of the present application;

[0035] Figure 2 is a flowchart of a data processing method applied to a second participant provided in an embodiment of the present application;

[0036] Figure 3 This is a schematic diagram of a process of performing joint calculation based on ID union provided in an embodiment of the present application;

[0037] Figure 4 This is another flowchart of joint calculation based on ID union provided in an embodiment of the present application;

[0038] Figure 5 is a structural schematic diagram of a data processing device applied to a first participant provided in an embodiment of the present application;

[0039] Figure 6 is a structural diagram of a data processing device applied to a second participant provided in an embodiment of the present application;

[0040] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0042] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0043] In addition, the acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0044] In financial data cooperation scenarios, when it comes to sensitive user information such as user ID numbers and mobile phone numbers, strict data protection regulations and privacy policies are usually required. In the data processing of these sensitive information, even if the data is encrypted by national encryption algorithms such as SM3 and SM4, due to the high attention paid to data security and strict requirements for privacy protection, the encrypted data is usually not allowed to be transmitted externally. At the same time, financial institutions need to carry out necessary data cooperation and sharing while protecting user privacy to support business development and risk management.

[0045] In the financial industry, the main application scenarios of current privacy computing technology focus on privacy security intersection and federated modeling:

[0046] Private Set Intersection (PSI): The Private Set Intersection algorithm allows two or more parties to find the intersection of their data sets without revealing the specific content of their respective data sets. Different financial institutions can share customer information and identify common customers through the PSI algorithm while protecting customer privacy.

[0047] Federated Modeling: Federated modeling allows multiple parties to jointly train a model without exchanging data. It can be used in scenarios such as risk scoring modeling, product preference modeling, intelligent pricing modeling, and precision marketing modeling.

[0048] The key to both privacy-safe intersection and federated modeling is based on the intersection of the data sets of the participants. The privacy-safe intersection algorithm focuses on securely finding and using the common elements in the data sets of each participant, namely the intersection data; federated modeling uses the intersection data as a common training set based on the confirmed intersection data, allowing multiple participants to jointly build and optimize machine learning models without directly exchanging original data. Their operation process involves complex cryptographic methods to ensure the security and privacy of data.

[0049] However, in some scenarios in the financial industry, privacy-safe intersection (PSI) and federated modeling based solely on the intersection of the data sets of the participants may not meet all needs. One situation is that in some cases, the data sets between the participants may have no or only little intersection. Another situation is that some business analysis or decision support needs may require a more comprehensive data perspective, not just the intersection part. In this case, if the joint calculation result is only based on the intersection calculation, it may be less accurate and insufficient to achieve the purpose of risk monitoring.

[0050] If the joint calculation results based on intersection calculation are not sufficient to achieve the purpose of risk monitoring, multiple institutions are required to manually transfer and merge the data of the non-intersection parts to ensure data security. However, multiple rounds of data exchange and manual operations are cumbersome, resulting in low efficiency of joint calculation.

[0051] In addition, if joint calculations are performed directly by combining data from multiple parties, there is a potential possibility that the data of the partners may be reversed, leading to data leakage. For example, through statistical methods or association analysis, data from different fragments may be combined to infer sensitive information.

[0052] In addition, due to data security and compliance management requirements, sensitive data of each organization cannot be transmitted externally even in encrypted form.

[0053] Therefore, there is an urgent need for a joint computing method that can ensure the security of transaction data, the accuracy of joint computing results, and the efficiency of joint computing.

[0054] Based on this, in order to solve the problems of the prior art, the embodiments of the present application provide a data processing method, apparatus, device, computer-readable storage medium and computer program product. The data processing method can be applied to the scenario of joint calculation of transaction data in multiple institutions. The data processing method can be executed by a server and / or processor in a data processing system.

[0055] The following is an introduction to the data processing system provided in the embodiments of the present application.

[0056] The data processing system provided in the embodiment of the present application may include a first participant and at least one second participant. The first participant may be the initiator of the joint computing task. One or more second participants may be the recipient and collaborator of the joint computing task. One or more second participants may perform joint computing or not, which is not limited here.

[0057] Specifically, the first participant may include a first data platform and a first privacy computing platform. The first data platform may be used to store a first data set. The first data set may include a first object identifier corresponding to each of a plurality of first monitored objects and first transaction data corresponding to each first object identifier. The first monitored objects may include merchants and users. In addition, the first privacy computing platform may be used to perform privacy computing based on the first data set.

[0058] Similarly, the second participant may include a second data platform and a second privacy computing platform. The second data platform may be used to store a second data set. The second data set may include a second object identifier corresponding to each of a plurality of second monitored objects and second transaction data corresponding to each second object identifier. The second monitored objects may include merchants and users. In addition, the second privacy computing platform may be used to perform privacy computing based on the second data set.

[0059] The following is an introduction to the data processing method applied to the first participant provided in an embodiment of the present application.

[0060] Figure 1 A flow chart of a data processing method applied to a first participant provided in an embodiment of the present application is shown. The data processing method can be executed by a server and / or processor in the first privacy computing platform. Figure 1 As shown, the data processing method provided in the embodiment of the present application includes the following steps:

[0061] S110, obtaining a joint identification set, where the joint identification set is a union of a first identification set of the first participant and a second identification set of the second participant, the first identification set includes a plurality of first object identifications of first objects to be monitored, the second identification set includes a plurality of second object identifications of second objects to be monitored, and the joint identification set includes a plurality of joint object identifications;

[0062] S120, encrypting first transaction data corresponding to each joint object identifier using a homomorphic encryption key to obtain first transaction data ciphertext, where the first transaction data is transaction data of the first participant;

[0063] S130, sending the joint identification set and the first transaction data ciphertext corresponding thereto to the second participant;

[0064] S140, receiving a first joint data ciphertext sent by the second participant, where the first joint data ciphertext is obtained by encrypting joint transaction data using a random number, the joint transaction data is data determined based on the first transaction data ciphertext and the second transaction data for each joint object identifier, and the second transaction data is transaction data of the second participant;

[0065] S150. Perform a joint calculation based on the first joint data ciphertext to obtain a first joint calculation result.

[0066] In the embodiment of the present application, since the joint identification set is the union of the first identification set in the first participant and the second identification set in the second participant, by obtaining the joint identification set and performing joint calculation based on the transaction data corresponding to the joint identification set, the comprehensiveness of the joint calculation data can be guaranteed, thereby ensuring the accuracy of the joint calculation result. In addition, the joint transaction data is the data determined by the second participant for each joint object identifier based on the first transaction data ciphertext and the second transaction data. Therefore, by sending the joint identification set to the second participant and encrypting the first transaction data corresponding to each joint object identifier using the homomorphic encryption key to obtain the first transaction data ciphertext, receiving the first joint data ciphertext encrypted by the second participant using the random number to encrypt the joint transaction data, and performing joint calculation based on the first joint data ciphertext, that is, in the joint calculation process, the joint calculation process is optimized by one party holding the key and the other participants holding the random number, which can reduce the risk of data leakage, improve the data security of each participant, and enhance the mutual trust of all parties. In this way, through the embodiment of the present application, both the security of the transaction data and the accuracy of the joint calculation result can be guaranteed.

[0067] The specific implementation methods of the above steps are introduced below.

[0068] In some embodiments, in S110, the first object to be monitored may be an object to be monitored for risk. The first object to be monitored may be a merchant or a user. The first object identifier may be used to uniquely identify the first object to be monitored. The first object identifier may include an ID number and / or a mobile phone number. Since both the ID number and the mobile phone number are sensitive information, in order to comply with strict data protection regulations and privacy policies, the ID number and / or the mobile phone number may be encrypted to obtain a first object identifier displayed in ciphertext information to ensure data security and user privacy security. The first identifier set may be recorded, for example, as: X = {IDx1, IDx2, IDx3, ..., IDxm}. Among them, IDx1, IDx2, IDx3, ..., IDxm may represent m first object identifiers.

[0069] The second object to be monitored may be an object to be monitored for risk. The second object to be monitored may be a merchant or a user. The second object identifier may be used to uniquely identify the second object to be monitored. The second object identifier may include an ID number and / or a mobile phone number. Since both the ID number and the mobile phone number are sensitive information, in order to comply with strict data protection regulations and privacy policies, the ID number and / or the mobile phone number may be encrypted to obtain a second object identifier displayed in ciphertext information to ensure data security and user privacy security. The second identifier set may be recorded, for example, as: Y = {IDy1, IDy2, IDy3, ..., IDyn}. Among them, IDy1, IDy2, IDy3, ..., IDyn may represent n second object identifiers.

[0070] As an example, by taking the union of the first identification set and the second identification set, a joint identification set can be obtained. The joint identification set can be recorded as X∪Y. The object identification in the joint identification set can be recorded as a joint object identification.

[0071] Based on this, in order to ensure both data transmission security and the first participant can obtain the joint identification set, in some embodiments, the above S110 may specifically include:

[0072] Obtain a first identification set in the first party;

[0073] Receive a target identification ciphertext set sent by the second participant, the target identification ciphertext set including a plurality of target object identification ciphertexts, the target object identification ciphertexts being obtained by encrypting the target object identification based on a one-way encryption algorithm, the target object identification being an object identification in the second identification set and not in the first identification set determined based on an anonymous query algorithm;

[0074] Based on the anonymous query algorithm, a target identification set corresponding to the target identification ciphertext set is searched in the data subset set, the data subset set includes multiple target object identification ciphertexts and their one-to-one corresponding target object identifications, and the target identification set includes the target object identification corresponding to each target object identification ciphertext;

[0075] The joint identifier set is determined according to the union of the first identifier set and the target identifier set.

[0076] In the data preparation stage, each participant can prepare the data set required for joint calculation. The data set can include at least the object identifier (i.e., key) of the object to be monitored and the transaction data (i.e., value) corresponding to the object identifier. The data set in the first participant can be recorded as the first data set, and the first data set can include the first identifier set and the first transaction data corresponding to each first object identifier. The first transaction data can include, for example, the merchant settlement transaction amount, the merchant acquisition transaction amount, the merchant settlement amount to the record account, etc. A piece of data in the first data set can be recorded as [IDx1, u1, v1, ...]. Among them, IDx1 can represent the first object identifier, u1, v1, ..., can represent the first transaction data. In addition, the data set in the second participant can be recorded as the second data set, and the second data set can include the second identifier set and the second transaction data corresponding to each second object identifier. A piece of data in the second data set can be recorded as [IDy1, u1, v1, ...]. Among them, IDy1 can represent the second object identifier, u1, v1, ..., can represent the second transaction data.

[0077] As an example, the first participant may obtain a first data set from a first data platform through a first privacy computing platform, and determine a first identification set in the first data set. Similarly, the second participant may obtain a second data set from a second data platform through a second privacy computing platform, and determine a second identification set in the second data set.

[0078] After the second participant obtains the second identifier set through the second privacy computing platform, the second participant can initiate the first anonymous query task. The first anonymous query task can be used to batch query whether the object identifier of a certain participant is in the data set of another participant. If the second participant initiates the first anonymous query task to the first participant, the query data column can be the second object identifier column, and the return value can be whether the second object identifier is in the first data set. By executing the first anonymous query task, the second privacy computing platform can determine which second object identifiers in the second identifier set are not in the first identifier set, that is, determine the target object identifier in the second identifier set that is different from the first object identifier. That is, the target object identifier can be an object identifier in the second identifier set but not in the first identifier set. Specifically, the second privacy computing platform can execute the first anonymous query task based on the anonymous query algorithm. Among them, the anonymous query algorithm can be, for example, the FATE SIR algorithm. Among them, FATE represents an open source privacy computing project, and SIR is an algorithm for batch anonymous query provided in the open source project. Since the second privacy computing platform uses anonymous query to query the target object identifier, the first participant cannot know which object identifiers the first participant has queried, which can ensure data security.

[0079] After determining multiple target object identifiers, the second party may determine a target identifier set based on the multiple target object identifiers. In order to ensure data security, the second party usually does not send the target identifier set directly to the first party, but encrypts each target object identifier in the target identifier set based on a one-way encryption algorithm to obtain a target identifier ciphertext set, and then sends the target identifier ciphertext set to the first party. The target identifier ciphertext set may include target object identifier ciphertexts corresponding to multiple target object identifiers one by one. The one-way encryption algorithm may include a hash algorithm.

[0080] As an example, the second party may obtain a hash value (i.e., a target object identification ciphertext) by performing a hash operation on the target object identification using the SM3 algorithm or other encryption algorithms, and determine a target identification ciphertext set based on multiple target object identification ciphertexts. Afterwards, the second party may send the target identification ciphertext set to the first party.

[0081] It should be noted that since the target object identification ciphertext is calculated once, if the second participant sends a target identification ciphertext set to the first participant, the first participant cannot know the target object identification corresponding to the target object identification ciphertext.

[0082] Therefore, in order to ensure that the first participant can obtain a target identification set including multiple target object identifications, on the one hand, after determining multiple target object identification ciphertexts, the second participant can determine a data subset set based on multiple target object identification ciphertexts and their one-to-one corresponding target object identifications. That is, the data subset set can include multiple target object identification ciphertexts and multiple target object identification ciphertexts corresponding to each other. On the other hand, after receiving the target identification ciphertext set, the second participant can initiate a second anonymous query task to the first participant. The second anonymous query task can use the target object identification ciphertext as a query condition to batch obtain the target object identifications in the data subset set. Specifically, the second participant can query the target identification set corresponding to the target identification ciphertext set in the data subset set based on the anonymous query algorithm (such as the FATE SIR algorithm) according to the corresponding relationship between the target object identification ciphertext and the target object identification stored in the data subset.

[0083] Since the target identification set includes multiple target object identifications that exist in the second identification set but not in the first identification set, the full object identification set corresponding to the first participant and the second participant, i.e., the joint identification set, can be obtained by performing a union calculation on the first identification set and the target identification set.

[0084] The embodiment of the present application can ensure data transmission security by receiving the target identification ciphertext set sent by the second participant, rather than the target identification set. Since the target object identification ciphertext is calculated once, if the second participant sends the target identification ciphertext set to the first participant, the first participant cannot know the target object identification corresponding to the target object identification ciphertext. Therefore, by querying the target identification set corresponding to the target identification ciphertext set in the data subset set based on the anonymous query algorithm, it can be ensured that the first participant can obtain the target identification set including multiple target object identifications, and then ensure that the first participant can obtain the full object identification set corresponding to the first participant and the second participant, that is, the joint identification set.

[0085] Based on this, in order to further improve the security of transaction data in the joint computing process, in some embodiments, the obtaining of the first identification set of the first participant may specifically include:

[0086] Acquire a third identification set from the first participant, where the third identification set includes multiple real object identifications of the first objects to be monitored;

[0087] Generate a first noise identifier set corresponding to the third identifier set, the first noise identifier set including a plurality of first noise identifiers;

[0088] The first identification set is determined according to the third identification set and the first noise identification set.

[0089] Here, the third identification set may be an identification set actually stored in the first data platform. The real object identification of the first object to be monitored in the third identification set may be recorded as the third object identification. In addition, the first noise identification set may be a noise identification set generated based on the third identification set.

[0090] As an example, the data set stored in the first data platform of the first participant can be recorded as the third data set, and the third data set can include a third identification set and third transaction data corresponding to each third object identification. Specifically, the first participant can obtain the third data set from the first data platform through the first privacy computing platform, and determine the third identification set in the third data set.

[0091] After obtaining the third data set, the first participant may randomly generate a first obfuscated data set corresponding to the third data set in a ratio of 1:N, where N may be a positive integer greater than or equal to 1. That is, the first participant may generate one or more obfuscated data corresponding to each piece of data in the third data set.

[0092] As an example, the first participant may randomly generate a first noise identifier corresponding to each third object identifier in the third identifier set in a ratio of 1:N. Wherein N may be a positive integer greater than or equal to 1. That is, the first participant may generate one or more first noise identifiers corresponding to each third object identifier. Wherein, the first noise identifier is different from the multiple third object identifiers. In addition, the first noise transaction data corresponding to the first noise identifier may be set to 0 or other meaningless values, as long as it does not affect subsequent calculations. In addition, in order to avoid the first noise transaction data from hitting the normal data set of other participants, the data features of the normal data set may be identified in advance based on the business scenarios of other participants, and the data generation rules of the first noise transaction data may be set based on the data features of the normal data set of other participants, and then the first noise transaction data may be generated based on the above data generation rules.

[0093] As a more specific example, the first noise identifier set can be recorded as S = {IDs1, IDs2, IDs3, ..., IDsp}, where IDs1, IDs2, IDs3, ..., IDsp can represent the first noise identifier. If the third identifier set is recorded as A, then X = A∪S.

[0094] In addition, the obfuscated data may include an obfuscation identifier to mark a piece of data in the mixed data set as obfuscated data. For example, a piece of obfuscated data in the first obfuscated data set may be recorded as [IDs1, u1, v1, ..., flag1]. Among them, IDs1 may represent the first noise identifier, u1, v1, ..., may represent the first noise transaction data, and flag1 may be used to mark a piece of data in the mixed data set as obfuscated data. In addition, the obfuscated data in the first data set may also include [IDx1+IDs1, u1, v1, ..., flag1].

[0095] The embodiment of the present application determines the first identification set based on the third identification set and the first noise identification set, so that in the subsequent joint calculation process, both the obfuscated data and the normal data are desensitized and encrypted in a consistent manner. Therefore, only the object identification column data is indistinguishable, thereby protecting the real object identifications of multiple first monitored objects in the third identification set and their corresponding first transaction data, further improving the security of the transaction data in the joint calculation process.

[0096] Based on this, in order to improve the similarity between the first noise identifier and the third object identifier and further improve the security of transaction data in the joint computing process, in some embodiments, the above-mentioned generating the first noise identifier set corresponding to the third identifier set may specifically include:

[0097] Based on the identification features of the real object identification in the third identification set, a first noise identification set corresponding to the third identification set is generated, and the first noise identification in the first noise identification set has the same identification features as the real object identification in the third identification set.

[0098] Here, the identification feature may include an identification type, an identification length, etc. For example, if the third object identification is a mobile phone number, the identification feature of the third object identification may include a numeric type, and the length is 11.

[0099] The embodiment of the present application generates a first noise identification set corresponding to the third identification set based on the identification features of the real object identification in the third identification set, so as to ensure that the first noise identification in the first noise identification set and the real object identification in the third identification set have the same identification features, thereby improving the similarity between the first noise identification and the third object identification, and further improving the security of transaction data in the joint calculation process.

[0100] In some embodiments, in S120, after the first participant obtains the joint identification set, the first participant can initiate a joint computing task. Specifically, for each joint object identifier in the joint identification set, the first participant can generate a homomorphic encryption key through the first privacy computing platform, and use the homomorphic encryption key to encrypt the first transaction data held by the first party to obtain the first transaction data ciphertext. For example, if the first transaction data corresponding to a joint object identifier is recorded as [ID, u1, v1], the first transaction data ciphertext corresponding to the joint object identifier can be [ID, enc(u1), enc(v1)].

[0101] It should be noted that, when other conditions remain unchanged, the calculation result based on the first transaction data is the same as the calculation result based on the ciphertext of the first transaction data. Therefore, by homomorphically encrypting the first transaction data, it does not affect the subsequent calculation results and can ensure data security.

[0102] In some embodiments, in S130, the first participant may send multiple joint object identifiers and the first transaction data ciphertext corresponding to each joint object identifier to the second participant in batches. On the one hand, the first transaction data for joint calculation may be provided to the second participant. On the other hand, the second participant may be triggered to return the second transaction data it owns, so that the first participant may perform joint calculation based on the second transaction data.

[0103] In some embodiments, in S140, in order to prevent the data of the second party from being reversed by other participants, after receiving the first transaction data ciphertext, the second party may generate a random number r, determine the joint transaction data according to the first transaction data ciphertext and the second transaction data, and then encrypt the joint transaction data using the random number r to obtain the first joint data ciphertext. For example, if the first transaction data ciphertext corresponding to a joint object identifier is recorded as [ID, enc(u1), enc(v1)], and the second transaction data ciphertext corresponding to the joint object identifier is recorded as [ID, u2, v2], then the joint transaction data corresponding to the joint object identifier may include u=u2+enc(u1), v=v2+enc(v1), and the first joint data ciphertext may include u'=r*u2+r*enc(u1), v'=r*v2+r*enc(v1).

[0104] After generating the first joint data ciphertext, the second participant may send the first joint data ciphertext to the second participant.

[0105] In the embodiment of the present application, the second party encrypts the joint transaction data using a random number to obtain a first joint data ciphertext, and sends the first joint data ciphertext to the first party, thereby preventing the data of the second party from being reversely deduced by the first party and ensuring data security.

[0106] Based on this, in order to improve the security of the first joint data ciphertext during the data transmission process, in some embodiments, the above S140 may specifically include:

[0107] receiving a second joint data ciphertext sent by the second participant, where the second joint data ciphertext is obtained by encrypting the first joint data ciphertext using the homomorphic encryption key;

[0108] The second joint data ciphertext is decrypted using the homomorphic encryption key to obtain the first joint data ciphertext.

[0109] Here, after generating the first joint data ciphertext, the second participant may also use the homomorphic encryption key to encrypt the first joint data ciphertext to obtain the second joint data ciphertext, and send the second joint data ciphertext to the first participant. After receiving the second joint data ciphertext, the second participant may decrypt the second joint data ciphertext using the homomorphic encryption key to obtain the first joint data ciphertext.

[0110] In the embodiment of the present application, after the second party generates the first joint data ciphertext, the first joint data ciphertext is encrypting the first joint data ciphertext with a homomorphic encryption key to obtain the second joint data ciphertext, and the second joint data ciphertext is sent to the first party, thereby improving the security of the first joint data ciphertext in the data transmission process.

[0111] In some embodiments, in S150, after determining the first joint data ciphertext, the second participant can perform a joint calculation on the first joint data ciphertext based on the joint calculation formula corresponding to the joint calculation task to obtain a first joint calculation result. The first joint calculation result can be a specific numerical value or a comparison result of the numerical value with a first preset range, which is not limited here. The first preset range can be a preset numerical range set in advance for risk monitoring of the first monitored object or the joint monitored objects. The first preset range can be recorded as (p, q), for example.

[0112] As an example, the joint calculation formula may include a division calculation formula. The division calculation formula may be used to offset the random number. The joint calculation formula may be, for example, as follows:

[0113]

[0114] By substituting u'=r*u2+r*enc(u1), v'=r*v2+r*enc(v1) into the above joint calculation formula, the random number r can be offset, thereby calculating the first joint calculation result. After obtaining the first joint calculation result, the first joint calculation result is compared with the first preset range to obtain a comparison result, and abnormal data is screened based on the comparison result, and risk monitoring is performed based on the screening result of the abnormal data. For example, if the first joint calculation result is k, if k is between p and q, it can be determined that k is abnormal data, and then it is determined that the monitored object corresponding to k is at risk.

[0115] Based on this, in order to improve the risk monitoring efficiency of the monitored object, in some embodiments, the above S150 may specifically include:

[0116] Performing a joint calculation based on the first joint data ciphertext to obtain a fifth joint calculation result;

[0117] The first joint calculation results that meet the first preset range are screened from the fifth joint calculation results.

[0118] Here, the joint calculation formula may be as follows, for example:

[0119]

[0120] By substituting u'=r*u2+r*enc(u1), v'=r*v2+r*enc(v1) into the above joint calculation formula, the random number r can be offset first, and the fifth joint calculation result can be calculated. Then, the fifth joint calculation result is compared with the size relationship between p and q to obtain the comparison result, and abnormal data can be screened based on the comparison result, and risk monitoring can be performed based on the screening results of abnormal data.

[0121] The embodiment of the present application can improve the efficiency of determining the comparison result by directly outputting the comparison result based on the joint calculation formula, thereby improving the risk monitoring efficiency of the risk monitoring of the monitored object.

[0122] In addition, it can be known from the above description that the first identification set can be the union of the third identification set and the first noise identification set. Similarly, based on the above-mentioned determination of the first noise identification set and the determination of the same or similar manner as the first identification set, the second participant can determine the second noise identification set and the second identification set including the second noise identification set. Therefore, the first joint calculation result can include the joint calculation result corresponding to the first noise identification and the second noise identification. In addition, the second noise identification is a noise identification in the second noise identification set.

[0123] Based on this, after the above S150, the following may also be included:

[0124] The joint calculation results corresponding to the first noise identifier and the second noise identifier in the first joint calculation result are deleted to obtain a third joint calculation result.

[0125] Here, as described above, the obfuscated data may include an obfuscation flag to mark a certain piece of data in the mixed data set as obfuscated data. Therefore, the third joint calculation result can be obtained by filtering the first joint calculation result through the Flag column of the obfuscated data. Specifically, the first noise flag and the second noise flag can be identified through the obfuscation flag in the obfuscated data, and then the joint calculation result corresponding to the first noise flag and the second noise flag in the first joint calculation result is deleted to obtain the third joint calculation result, and risk monitoring is performed based on the third joint calculation result.

[0126] In the embodiment of the present application, the accuracy of risk monitoring can be ensured by deleting the joint calculation results corresponding to the first noise identifier and the second noise identifier in the first joint calculation result to obtain a third joint calculation result, and performing risk monitoring based on the third joint calculation result.

[0127] The following is an introduction to the data processing method applied to the second participant provided in the embodiment of the present application.

[0128] Figure 2 A flow chart of a data processing method applied to a second participant provided in an embodiment of the present application is shown. The data processing method can be executed by a server and / or processor in the second privacy computing platform. Figure 2 As shown, the data processing method provided in the embodiment of the present application includes steps S210-S240.

[0129] S210, receiving a joint identification set and its corresponding first transaction data ciphertext sent by the first participant, the joint identification set is the union of the first identification set in the first participant and the second identification set in the second participant, the first identification set includes a plurality of first object identifications of first objects to be monitored, the second identification set includes a plurality of second object identifications of second objects to be monitored, and the joint identification set includes a plurality of joint object identifications; the first transaction data ciphertext is obtained by encrypting the first transaction data corresponding to the joint object identification using a homomorphic encryption key, and the first transaction data is the transaction data in the first participant.

[0130] Based on this, in order to ensure both data transmission security and the first participant can obtain a target identifier set including multiple target object identifiers, in some embodiments, before the above S210, the following may also be included:

[0131] Obtaining a second identification set from a second party;

[0132] Based on the anonymous query algorithm, determine the target object identifier that is different from the first object identifier in the second identifier set to obtain a target identifier set;

[0133] Based on a one-way encryption algorithm, each target object identifier in the target identifier set is encrypted to obtain a target identifier ciphertext set, wherein the target identifier ciphertext set includes target object identifier ciphertexts corresponding to multiple target object identifiers one by one;

[0134] A target identification ciphertext set is sent to the first participant, and a data subset set is determined according to a plurality of target object identification ciphertexts and their one-to-one corresponding target object identifications, so that the first participant determines the target identification set based on the target identification ciphertext set and the data subset set.

[0135] In the data preparation stage, each participant can prepare the data set required for joint calculation. The data set may include at least the object identifier (i.e., key) of the object to be monitored and the transaction data (i.e., value) corresponding to the object identifier. The data set in the second participant can be recorded as the second data set, and the second data set can include a second identifier set and second transaction data corresponding to each second object identifier. The second transaction data may, for example, include the merchant settlement transaction amount, the merchant acquisition transaction amount, the merchant settlement amount to the registered account, etc. A piece of data in the second data set may, for example, be recorded as [IDy1, u1, v1,...]. Among them, IDy1 can represent the second object identifier, and u1, v1,... can represent the second transaction data.

[0136] After the second participant obtains the second identification set through the second privacy computing platform, the second participant can initiate the first anonymous query task. The first anonymous query task can be used to batch query whether the object identification of a certain participant is in the data set of another participant. If the second participant initiates the first anonymous query task to the first participant, the query data column can be the second object identification column, and the return value can be whether the second object identification is in the first data set. By executing the first anonymous query task, the second privacy computing platform can determine which second object identifications in the second identification set are not in the first identification set, that is, determine the target object identification in the second identification set that is different from the first object identification. That is, the target object identification can be an object identification in the second identification set but not in the first identification set. Specifically, the second privacy computing platform can execute the first anonymous query task based on the anonymous query algorithm. Among them, the anonymous query algorithm can be, for example, the FATE SIR algorithm. Since the second privacy computing platform uses anonymous query to query the target object identification, the first participant cannot know which object identifications the first participant has queried, which can ensure data security.

[0137] After determining multiple target object identifiers, the second party may determine a target identifier set based on the multiple target object identifiers. In order to ensure data security, the second party usually does not send the target identifier set directly to the first party, but encrypts each target object identifier in the target identifier set based on a one-way encryption algorithm to obtain a target identifier ciphertext set, and then sends the target identifier ciphertext set to the first party. The target identifier ciphertext set may include target object identifier ciphertexts corresponding to multiple target object identifiers one by one. The one-way encryption algorithm may include a hash algorithm.

[0138] As an example, the second party may obtain a hash value (i.e., a target object identification ciphertext) by performing a hash operation on the target object identification using the SM3 algorithm or other encryption algorithms, and determine a target identification ciphertext set based on multiple target object identification ciphertexts. Afterwards, the second party may send the target identification ciphertext set to the first party.

[0139] In addition, after determining the multiple target object identification ciphertexts, the second participant may also determine a data subset set according to the multiple target object identification ciphertexts and the one-to-one corresponding target object identifications. That is, the data subset set may include the multiple target object identification ciphertexts and the one-to-one corresponding target object identifications.

[0140] The embodiment of the present application sends a target identification ciphertext set to the first participant, and determines a data subset set based on multiple target object identification ciphertexts and their one-to-one corresponding target object identifications, so that the first participant can determine the target identification set based on the target identification ciphertext set and the data subset set, which can ensure both the security of data transmission and the first participant can obtain the target identification set including multiple target object identifications.

[0141] Based on this, in order to further improve the security of transaction data in the joint computing process, in some embodiments, the obtaining of the second identification set of the second participant may specifically include:

[0142] Acquire a fourth identification set from the second participant, where the fourth identification set includes multiple real object identifications of second objects to be monitored;

[0143] Generate a second noise identifier set corresponding to the fourth identifier set, the second noise identifier set including a plurality of second noise identifiers;

[0144] The second identification set is determined according to the fourth identification set and the second noise identification set.

[0145] Here, the fourth identification set may be an identification set actually stored in the second data platform. The real object identification of the second monitored object in the fourth identification set may be recorded as the fourth object identification. In addition, the second noise identification set may be a noise identification set generated based on the fourth identification set.

[0146] As an example, the data set stored in the second data platform of the second participant can be recorded as the fourth data set, and the fourth data set can include a fourth identification set and fourth transaction data corresponding to each fourth object identification. Specifically, the second participant can obtain the fourth data set from the second data platform through the second privacy computing platform, and determine the fourth identification set in the fourth data set.

[0147] After acquiring the fourth data set, the second party may randomly generate a second obfuscated data set corresponding to the fourth data set in a ratio of 1:N, where N may be a positive integer greater than or equal to 1. That is, the second party may generate one or more obfuscated data corresponding to each piece of data in the fourth data set.

[0148] As an example, the second party may randomly generate a second noise identifier corresponding to each fourth object identifier in the fourth identifier set in a ratio of 1:N. Wherein N may be a positive integer greater than or equal to 1. That is, the second party may generate one or more second noise identifiers corresponding to each fourth object identifier. Wherein, the second noise identifier is different from the multiple fourth object identifiers. In addition, the second noise transaction data corresponding to the second noise identifier may be set to 0 or other meaningless values, which does not affect subsequent calculations. In addition, in order to avoid the second noise transaction data from hitting the normal data set of other participants, the data features of the normal data set may be identified in advance based on the business scenarios of other participants, and the data generation rules of the second noise transaction data may be set based on the data features of the normal data set of other participants, and then the second noise transaction data may be generated based on the above data generation rules.

[0149] As a more specific example, the second noise identifier set can be recorded as T = {IDt1, IDt2, IDt3, ..., IDtp}, where IDt1, IDt2, IDt3, ..., IDtp can represent the second noise identifier. If the fourth identifier set is recorded as B, then Y = B∪T.

[0150] In addition, the obfuscated data may include an obfuscation identifier to mark a piece of data in the mixed data set as obfuscated data. For example, a piece of obfuscated data in the second obfuscated data set may be recorded as [IDt1, u2, v2, ..., flag2]. Among them, IDt1 may represent the second noise identifier, u2, v2, ..., may represent the second noise transaction data, and flag2 may be used to mark a piece of data in the mixed data set as obfuscated data. In addition, the obfuscated data in the second data set may also include [IDy1+IDt1, u2, v2, ..., flag2].

[0151] The embodiment of the present application determines the second identification set based on the fourth identification set and the second noise identification set, so that in the subsequent joint calculation process, both the obfuscated data and the normal data are desensitized and encrypted in a consistent manner. Therefore, only the object identification column data is indistinguishable, thereby protecting the real object identifications of multiple second monitored objects in the fourth identification set and their corresponding second transaction data, further improving the security of the transaction data in the joint calculation process.

[0152] Based on this, in order to improve the similarity between the second noise identifier and the fourth object identifier and further improve the security of transaction data in the joint calculation process, in some embodiments, the above-mentioned generating the second noise identifier corresponding to the fourth identifier set may specifically include:

[0153] Based on the identification features of the real object identifications in the fourth identification set, a second noise identification set corresponding to the fourth identification set is generated, and the second noise identifications in the second noise identification set have the same identification features as the real object identifications in the fourth identification set.

[0154] Here, the identification feature may include an identification type, an identification length, etc. For example, if the fourth object identification is a mobile phone number, the identification feature of the fourth object identification may include a numeric type, and the length is 11.

[0155] The embodiment of the present application generates a second noise identification set corresponding to the fourth identification set based on the identification features of the real object identification in the fourth identification set, so as to ensure that the second noise identification in the second noise identification set has the same identification features as the real object identification in the fourth identification set, thereby improving the similarity between the second noise identification and the fourth object identification, and further improving the security of transaction data in the joint calculation process.

[0156] S220. For each joint object identifier, determine the joint transaction data based on the first transaction data ciphertext and the second transaction data, where the second transaction data is the transaction data of the second participant.

[0157] S230. Encrypt the joint transaction data using a random number to obtain a first joint data ciphertext.

[0158] S240. Send a first joint data ciphertext to the first participant, so that the first participant performs a joint calculation based on the first joint ciphertext to obtain a first joint calculation result.

[0159] Based on this, in order to improve the security of the first joint data ciphertext during the data transmission process, in some embodiments, before the above S240, the method may further include:

[0160] The first joint data ciphertext is encrypted using the homomorphic encryption key to obtain a second joint data ciphertext.

[0161] Based on this, the above S240 may specifically include:

[0162] The second joint data ciphertext is sent to the first participant, so that the first participant performs joint calculation based on the second joint ciphertext to obtain a first joint calculation result.

[0163] Here, after generating the first joint data ciphertext, the second participant may also use the homomorphic encryption key to encrypt the first joint data ciphertext to obtain the second joint data ciphertext, and send the second joint data ciphertext to the first participant. After receiving the second joint data ciphertext, the second participant may decrypt the second joint data ciphertext using the homomorphic encryption key to obtain the first joint data ciphertext.

[0164] In the embodiment of the present application, after the second party generates the first joint data ciphertext, the first joint data ciphertext is encrypting the first joint data ciphertext with a homomorphic encryption key to obtain the second joint data ciphertext, and the second joint data ciphertext is sent to the first party, thereby improving the security of the first joint data ciphertext in the data transmission process.

[0165] In addition, the other steps of the method in the embodiment of the present application can be seen above Figure 1 The relevant description of the illustrated embodiment will not be repeated here.

[0166] In the embodiment of the present application, since the joint identification set is the union of the first identification set in the first participant and the second identification set in the second participant, by obtaining the joint identification set and performing joint calculation based on the transaction data corresponding to the joint identification set, the comprehensiveness of the joint calculation data can be guaranteed, and then the accuracy of the joint calculation result can be guaranteed. In addition, the joint transaction data is the data determined by the second participant for each joint object identifier based on the first transaction data ciphertext and the second transaction data. Therefore, by receiving the joint identification set and the corresponding first transaction data ciphertext sent by the first participant, for each joint object identifier, the joint transaction data is determined based on the first transaction data ciphertext and the second transaction data, the joint transaction data is encrypted using a random number to obtain the first joint data ciphertext, and the first joint data ciphertext is sent to the first participant so that the first participant performs joint calculation based on the first joint ciphertext to obtain the first joint calculation result. That is, in the joint calculation process, the joint calculation process is optimized by one party holding a key and the other participants holding a random number, which can reduce the risk of data leakage, improve the data security of each participant, and enhance the mutual trust of all parties. In this way, through the embodiment of the present application, both the security of transaction data and the accuracy of the joint calculation result can be guaranteed.

[0167] In the above embodiment, the second participant can serve as a collaborator of the first participant and provide transaction data to the first participant. In addition, the second participant itself can also perform joint calculations to implement risk monitoring of the second monitoring object or the joint monitoring object.

[0168] Based on this, in order to implement risk monitoring of the second monitoring object or the joint monitoring object, in some embodiments, after the above S220, the method may further include:

[0169] A joint calculation is performed based on the joint transaction data to obtain a second joint calculation result.

[0170] The joint calculation based on the joint transaction data may be specifically performed by performing joint calculation on the joint transaction data based on the joint calculation formula corresponding to the joint calculation task. The joint calculation formula used to calculate the second joint calculation result and the joint calculation formula used to calculate the first joint calculation result may be the same or different, which is not limited here.

[0171] In addition, the second joint calculation result can be a specific numerical value, or a comparison result of the numerical value with a second preset range, which is not limited here. The second preset range can be a preset numerical range pre-set for risk monitoring of the second monitored object or the joint monitored object. The first preset range can be recorded as (p', q'), for example.

[0172] As described above, if the first transaction data ciphertext corresponding to a joint object identifier is recorded as [ID, enc(u1), enc(v1)], and the second transaction data ciphertext corresponding to the joint object identifier is recorded as [ID, u2, v2], then the joint transaction data corresponding to the joint object identifier may include u=u2+enc(u1), v=v2+enc(v1). In this way, by substituting u=u2+enc(u1), v=v2+enc(v1) into the joint calculation formula, the second joint calculation result can be obtained. After obtaining the second joint calculation result, the comparison result is obtained by comparing the second joint calculation result with the second preset range, and abnormal data screening is performed based on the comparison result, and risk monitoring is performed based on the screening result of the abnormal data. For example, if the second joint calculation result is k', if k' is between p' and q', it can be determined that k' is abnormal data, and then it is determined that the monitored object corresponding to k' has a risk. Among them, p' and p can be the same or different; q' and q can be the same or different.

[0173] Based on this, in order to improve the risk monitoring efficiency of the monitored object, in some embodiments, the above-mentioned joint calculation based on the joint transaction data to obtain the second joint calculation result may specifically include:

[0174] Perform joint calculation based on the joint transaction data to obtain a sixth joint calculation result;

[0175] The second joint calculation results that meet the second preset range are screened from the sixth joint calculation results.

[0176] Here, the joint calculation formula may be as follows, for example:

[0177]

[0178] By substituting u=u2+enc(u1), v=v2+enc(v1) into the above joint calculation formula, the sixth joint calculation result can be calculated, and the size relationship between the sixth joint calculation result and p' and q' can be compared to obtain a comparison result, and abnormal data screening can be performed based on the comparison result, and risk monitoring can be performed based on the screening results of abnormal data.

[0179] The embodiment of the present application can improve the efficiency of determining the comparison result by directly outputting the comparison result based on the joint calculation formula, thereby improving the risk monitoring efficiency of the risk monitoring of the monitored object.

[0180] In addition, as can be seen from the above description, the second identification set can be the union of the fourth identification set and the second noise identification set, and the first identification set can be the union of the third identification set and the first noise identification set. Therefore, the second joint calculation result can include the joint calculation result corresponding to the first noise identification and the second noise identification.

[0181] Based on this, after obtaining the second joint calculation result, the following steps may also be performed:

[0182] The joint calculation results corresponding to the first noise identifier and the second noise identifier in the second joint calculation result are deleted to obtain a fourth joint calculation result.

[0183] Here, as described above, the obfuscated data may include an obfuscation flag to mark a certain piece of data in the mixed data set as obfuscated data. Therefore, the fourth joint calculation result can be obtained by filtering the second joint calculation result through the Flag column of the obfuscated data. Specifically, the first noise flag and the second noise flag can be identified through the obfuscation flag in the obfuscated data, and then the joint calculation result corresponding to the first noise flag and the second noise flag in the second joint calculation result is deleted to obtain the fourth joint calculation result, and risk monitoring is performed based on the fourth joint calculation result.

[0184] In the embodiment of the present application, the accuracy of risk monitoring can be ensured by deleting the joint calculation results corresponding to the first noise identifier and the second noise identifier in the second joint calculation result to obtain a fourth joint calculation result, and performing risk monitoring based on the fourth joint calculation result.

[0185] Based on the above embodiments, it can be known that the embodiment of the present application proposes a method for calculating the union of ID (i.e., identification of the object to be monitored) data of two or more parties, combining the anonymous query algorithm and data obfuscation in privacy computing to calculate the union of data ID sets of two or more parties. At the same time, joint calculation is performed based on the union of data IDs. In the joint calculation, the task initiator holds the homomorphic encryption key, and the other participants hold random numbers to randomize the data, and construct a division calculation to offset the random number to realize the calculation of the joint calculation rules; finally, the final calculation result is obtained by removing the obfuscated ID.

[0186] In the process of joint data operation between two or more parties, the following key steps are usually involved:

[0187] (1) Data set preparation: Each participant prepares its own data set, including the ID and transaction data of the object to be monitored. The transaction data may include statistical data obtained by statistical analysis of the transaction data.

[0188] (2) ID alignment: Without directly exchanging original data, two or more parties need to align their different ID sets and find the intersection or union of the IDs in the set in order to integrate or analyze the data;

[0189] (3) Joint computing: two or more parties perform predetermined computing tasks based on their respective data sets, such as sum, average, maximum, minimum, etc.;

[0190] (4) Operation results: The results of the joint operation can be used for further data analysis, decision support or business process optimization.

[0191] This application mainly focuses on the two stages of ID alignment and joint operation. By using privacy computing, each participant calculates the union of their respective sets based on the principle of "minimum necessary" without disclosing other elements in their respective sets, and performs joint operations on the basis of the union to calculate the final statistical results.

[0192] In order to better describe the entire solution, some specific examples are given based on the above embodiments.

[0193] Taking two-party joint calculation as an example, a flowchart of a joint calculation based on ID union provided in an embodiment of the present application can be as follows: Figure 3 shown.

[0194] To describe the entire solution in more detail, a flowchart of a joint calculation based on an ID union provided in an embodiment of the present application can be as follows: Figure 4 shown.

[0195] The embodiment of the present application realizes the union operation based on privacy computing, which can improve the efficiency of calculation in multi-party data sharing joint operation. Compared with the operation mode of privacy computing security intersection, the operation based on ID union can obtain the required statistical or analysis results through a task operation based on the privacy computing platform of each party, thereby avoiding multiple rounds of data exchange and manual operation steps, avoiding the manual processing of non-intersection data and complex calculation logic in multi-party data calculation, improving the efficiency of calculation in business cooperation, and meeting the needs of actual business. In addition, in the joint calculation process, the calculation process is optimized by one party holding a key and other participants holding a random number, which can reduce the risk of data leakage, improve the data security of the participating parties, and enhance mutual trust among the parties.

[0196] Based on the data processing method applied to the first participant provided in the above embodiment, the present application also provides a specific implementation of the data processing device applied to the first participant. Please refer to the following embodiment.

[0197] like Figure 5 As shown, the data processing device 500 provided in the embodiment of the present application includes the following modules:

[0198] A first acquisition module 510 is used to acquire a joint identification set, where the joint identification set is a union of a first identification set of a first participant and a second identification set of a second participant, where the first identification set includes a plurality of first object identifications of first objects to be monitored, the second identification set includes a plurality of second object identifications of second objects to be monitored, and the joint identification set includes a plurality of joint object identifications;

[0199] A first encryption module 520 is used to encrypt first transaction data corresponding to each joint object identifier using a homomorphic encryption key to obtain a first transaction data ciphertext, where the first transaction data is transaction data of the first participant;

[0200] A first sending module 530, configured to send a joint identification set and a first transaction data ciphertext corresponding thereto to a second participant;

[0201] The first receiving module 540 is used to receive the first joint data ciphertext sent by the second participant, the first joint data ciphertext is obtained by encrypting the joint transaction data using a random number, the joint transaction data is data determined based on the first transaction data ciphertext and the second transaction data for each joint object identifier, and the second transaction data is the transaction data of the second participant;

[0202] The first calculation module 550 is used to perform a joint calculation based on the first joint data ciphertext to obtain a first joint calculation result.

[0203] The data processing device 500 is described in detail below, as follows:

[0204] In some embodiments, the first acquisition module 510 may specifically include:

[0205] A first acquisition submodule, used to acquire a first identification set of a first participant;

[0206] A first receiving submodule is used to receive a target identification ciphertext set sent by a second participant, the target identification ciphertext set includes a plurality of target object identification ciphertexts, the target object identification ciphertexts are obtained by encrypting the target object identification based on a one-way encryption algorithm, and the target object identification is an object identification in the second identification set and not in the first identification set, which is determined based on an anonymous query algorithm;

[0207] A query submodule, for querying a target identification set corresponding to a target identification ciphertext set in a data subset set based on an anonymous query algorithm, wherein the data subset set includes a plurality of target object identification ciphertexts and their one-to-one corresponding target object identifications, and the target identification set includes target object identifications corresponding one-to-one to the plurality of target object identification ciphertexts;

[0208] The first determination submodule is used to determine a joint identifier set according to a union of the first identifier set and the target identifier set.

[0209] In some embodiments, the first acquisition submodule may specifically include:

[0210] An acquisition unit, configured to acquire a third identification set from the first participant, wherein the third identification set includes a plurality of real object identifications of the first objects to be monitored;

[0211] A first generating unit, configured to generate a first noise identifier set corresponding to the third identifier set, wherein the first noise identifier set includes a plurality of first noise identifiers;

[0212] The determining unit is configured to determine the first identification set according to the third identification set and the first noise identification set.

[0213] In some embodiments, the first joint calculation result includes a joint calculation result corresponding to the first noise identifier and the second noise identifier, and the second noise identifier is a noise identifier in the second noise identifier set. Based on this, the data processing device 500 may also include:

[0214] The first deletion module is used to delete the joint calculation results corresponding to the first noise identifier and the second noise identifier in the first joint calculation result after obtaining the first joint calculation result, so as to obtain a third joint calculation result.

[0215] In some embodiments, the first generating unit may specifically include:

[0216] The generating subunit is used to generate a first noise identification set corresponding to the third identification set based on the identification features of the real object identification in the third identification set, wherein the first noise identification in the first noise identification set has the same identification features as the real object identification in the third identification set.

[0217] In some embodiments, the first receiving module 540 may specifically include:

[0218] A second receiving submodule is used to receive a second joint data ciphertext sent by a second participant, where the second joint data ciphertext is obtained by encrypting the first joint data ciphertext using a homomorphic encryption key;

[0219] The decryption submodule is used to decrypt the second joint data ciphertext using the homomorphic encryption key to obtain the first joint data ciphertext.

[0220] In some embodiments, the first calculation module 550 may specifically include:

[0221] A first calculation submodule, configured to perform a joint calculation based on the first joint data ciphertext to obtain a fifth joint calculation result;

[0222] The first screening submodule is used to screen the first joint calculation results that meet the first preset range from the fifth joint calculation results.

[0223] In the embodiment of the present application, since the joint identification set is the union of the first identification set in the first participant and the second identification set in the second participant, by obtaining the joint identification set and performing joint calculation based on the transaction data corresponding to the joint identification set, the comprehensiveness of the joint calculation data can be guaranteed, thereby ensuring the accuracy of the joint calculation result. In addition, the joint transaction data is the data determined by the second participant for each joint object identifier based on the first transaction data ciphertext and the second transaction data. Therefore, by sending the joint identification set to the second participant and encrypting the first transaction data corresponding to each joint object identifier using the homomorphic encryption key to obtain the first transaction data ciphertext, receiving the first joint data ciphertext encrypted by the second participant using the random number to encrypt the joint transaction data, and performing joint calculation based on the first joint data ciphertext, that is, in the joint calculation process, the joint calculation process is optimized by one party holding the key and the other participants holding the random number, which can reduce the risk of data leakage, improve the data security of each participant, and enhance the mutual trust of all parties. In this way, through the embodiment of the present application, both the security of the transaction data and the accuracy of the joint calculation result can be guaranteed.

[0224] Based on the data processing method applied to the second participant provided in the above embodiment, accordingly, the present application also provides a specific implementation of a data processing device applied to the second participant. Please refer to the following embodiment.

[0225] like Figure 6 As shown, the data processing device 600 provided in the embodiment of the present application includes the following modules:

[0226] The second receiving module 610 is used to receive a joint identification set and a first transaction data ciphertext corresponding to the joint identification set sent by the first participant, the joint identification set is a union of a first identification set in the first participant and a second identification set in the second participant, the first identification set includes a plurality of first object identifications of first objects to be monitored, the second identification set includes a plurality of second object identifications of second objects to be monitored, and the joint identification set includes a plurality of joint object identifications; the first transaction data ciphertext is obtained by encrypting the first transaction data corresponding to the joint object identification using a homomorphic encryption key, and the first transaction data is the transaction data in the first participant;

[0227] A first determination module 620, configured to determine, for each joint object identifier, joint transaction data based on the first transaction data ciphertext and the second transaction data, where the second transaction data is transaction data of the second participant;

[0228] The second encryption module 630 is used to encrypt the joint transaction data using a random number to obtain a first joint data ciphertext;

[0229] The second sending module 640 is used to send the first joint data ciphertext to the first participant, so that the first participant performs joint calculation based on the first joint ciphertext to obtain a first joint calculation result.

[0230] The data processing device 600 is described in detail below, as follows:

[0231] In some embodiments, the data processing device 600 may further include:

[0232] The second calculation module is used to determine the joint transaction data based on the first transaction data ciphertext and the second transaction data for each joint object identifier, and then perform joint calculation based on the joint transaction data to obtain a second joint calculation result.

[0233] In some embodiments, the data processing device 600 may further include:

[0234] A second acquisition module, used for acquiring a second identification set of a second party before receiving the joint identification set and the first transaction data ciphertext corresponding thereto sent by the first party;

[0235] A second determination module is used to determine a target object identifier that is different from the first object identifier in the second identifier set based on an anonymous query algorithm to obtain a target identifier set;

[0236] A third encryption module is used to encrypt each target object identifier in the target identifier set based on a one-way encryption algorithm to obtain a target identifier ciphertext set, wherein the target identifier ciphertext set includes target object identifier ciphertexts corresponding to multiple target object identifiers one by one;

[0237] The third sending module is used to send a target identification ciphertext set to the first participant, and determine a data subset set based on multiple target object identification ciphertexts and their one-to-one corresponding target object identifications, so that the first participant determines the target identification set based on the target identification ciphertext set and the data subset set.

[0238] In some embodiments, the second acquisition module may specifically include:

[0239] A second acquisition submodule is used to acquire a fourth identification set from the second participant, where the fourth identification set includes a plurality of real object identifications of second objects to be monitored;

[0240] A generating submodule, configured to generate a second noise identification set corresponding to the fourth identification set, wherein the second noise identification set includes a plurality of second noise identifications;

[0241] The second determining submodule is configured to determine a second identification set according to the fourth identification set and the second noise identification set.

[0242] In some embodiments, the second joint calculation result includes a joint calculation result corresponding to the second noise identifier and the first noise identifier, and the first noise identifier is a noise identifier in the first noise identifier set.

[0243] Based on this, the data processing device 600 may further include:

[0244] The second deletion module is used to delete the joint calculation results corresponding to the first noise identifier and the second noise identifier in the second joint calculation result after obtaining the second joint calculation result, so as to obtain a fourth joint calculation result.

[0245] In some embodiments, the generating submodule may specifically include:

[0246] The second generating unit is used to generate a second noise identification set corresponding to the fourth identification set based on the identification features of the real object identification in the fourth identification set, and the second noise identification in the second noise identification set has the same identification features as the real object identification in the fourth identification set.

[0247] In some embodiments, the data processing device 600 may further include:

[0248] The fourth encryption module is used to encrypt the first joint data ciphertext using a homomorphic encryption key before sending the first joint data ciphertext to the first participant to obtain a second joint data ciphertext.

[0249] Based on this, the second sending module 640 may specifically include:

[0250] The second sending submodule is used to send the second joint data ciphertext to the first participant, so that the first participant performs joint calculation based on the second joint ciphertext to obtain a first joint calculation result.

[0251] In some embodiments, the second calculation module may specifically include:

[0252] A second calculation submodule, configured to perform a joint calculation based on the joint transaction data to obtain a sixth joint calculation result;

[0253] The second screening submodule is used to screen the second joint calculation results that meet the second preset range from the sixth joint calculation results.

[0254] In the embodiment of the present application, since the joint identification set is the union of the first identification set in the first participant and the second identification set in the second participant, by obtaining the joint identification set and performing joint calculation based on the transaction data corresponding to the joint identification set, the comprehensiveness of the joint calculation data can be guaranteed, and then the accuracy of the joint calculation result can be guaranteed. In addition, the joint transaction data is the data determined by the second participant for each joint object identifier based on the first transaction data ciphertext and the second transaction data. Therefore, by receiving the joint identification set and the corresponding first transaction data ciphertext sent by the first participant, for each joint object identifier, the joint transaction data is determined based on the first transaction data ciphertext and the second transaction data, the joint transaction data is encrypted using a random number to obtain the first joint data ciphertext, and the first joint data ciphertext is sent to the first participant so that the first participant performs joint calculation based on the first joint ciphertext to obtain the first joint calculation result. That is, in the joint calculation process, the joint calculation process is optimized by one party holding a key and the other participants holding a random number, which can reduce the risk of data leakage, improve the data security of each participant, and enhance the mutual trust of all parties. In this way, through the embodiment of the present application, both the security of transaction data and the accuracy of the joint calculation result can be guaranteed.

[0255] Based on the data processing method provided in the above embodiment, the embodiment of the present application also provides a specific implementation of the electronic device. Figure 7 A schematic diagram of an electronic device 700 provided in an embodiment of the present application is shown.

[0256] The electronic device 700 may include a processor 710 and a memory 720 storing computer program instructions.

[0257] Specifically, the processor 710 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0258] The memory 720 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 720 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 720 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 720 may be inside or outside the electronic device 700. In a particular embodiment, the memory 720 is a non-volatile solid-state memory.

[0259] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect of the present application.

[0260] The processor 710 implements any one of the data processing methods in the above embodiments by reading and executing computer program instructions stored in the memory 720 .

[0261] In one example, the electronic device 700 may further include a communication interface 730 and a bus 740. Figure 7 As shown, the processor 710, the memory 720, and the communication interface 730 are connected via a bus 740 and communicate with each other.

[0262] The communication interface 730 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0263] Bus 740 includes hardware, software or both, and the parts of electronic equipment are coupled to each other.For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 740 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0264] Exemplarily, the electronic device 700 may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA).

[0265] The electronic device can execute the data processing method in the embodiment of the present application, thereby realizing the combination Figures 1 to 6 The data processing method and device described.

[0266] In addition, in combination with the data processing method in the above embodiments, the present application embodiment can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the data processing methods in the above embodiments is implemented.

[0267] In combination with the data processing method in the above embodiments, the present application embodiment can provide a computer program product to implement. When the instructions in the computer program product are executed by a processor of an electronic device, any one of the data processing methods in the above embodiments is implemented.

[0268] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0269] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0270] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0271] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0272] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A data processing method, characterized in that: Applied to a first participant, the method comprises: Acquire a joint identification set, the joint identification set being a union of a first identification set of the first participant and a second identification set of the second participant, the first identification set including a plurality of first object identifications of first objects to be monitored, the second identification set including a plurality of second object identifications of second objects to be monitored, and the joint identification set including a plurality of joint object identifications; Encrypting first transaction data corresponding to each of the joint object identifiers using a homomorphic encryption key to obtain first transaction data ciphertext, where the first transaction data is transaction data of the first participant; Sending the joint identification set and the first transaction data ciphertext corresponding to it to the second participant; receiving a first joint data ciphertext sent by the second participant, where the first joint data ciphertext is obtained by encrypting joint transaction data using a random number, the joint transaction data is data determined based on the first transaction data ciphertext and the second transaction data for each joint object identifier, and the second transaction data is transaction data of the second participant; A joint calculation is performed based on the first joint data ciphertext to obtain a first joint calculation result.

2. The method according to claim 1, characterized in that: The obtaining of the joint identification set includes: Obtaining the first identification set of the first party; receiving a target identification ciphertext set sent by the second participant, wherein the target identification ciphertext set includes a plurality of target object identification ciphertexts, wherein the target object identification ciphertexts are obtained by encrypting a target object identification based on a one-way encryption algorithm, and the target object identification is an object identification that is in the second identification set and is not in the first identification set and is determined based on a stealth query algorithm; Based on the anonymous query algorithm, searching for a target identification set corresponding to the target identification ciphertext set in a data subset set, wherein the data subset set includes the multiple target object identification ciphertexts and their one-to-one corresponding target object identifications, and the target identification set includes the target object identifications corresponding one-to-one to the multiple target object identification ciphertexts; The joint identifier set is determined according to a union of the first identifier set and the target identifier set.

3. The method according to claim 2, characterized in that The obtaining the first identification set of the first participant includes: Acquire a third identification set in the first participant, wherein the third identification set includes real object identifications of a plurality of first objects to be monitored; generating a first noise identifier set corresponding to the third identifier set, wherein the first noise identifier set includes a plurality of first noise identifiers; The first identification set is determined according to the third identification set and the first noise identification set.

4. The method according to claim 3, characterized in that The first joint calculation result includes a joint calculation result corresponding to the first noise identifier and a second noise identifier, and the second noise identifier is a noise identifier in the second noise identifier set; After obtaining the first joint calculation result, the method further includes: The joint calculation results corresponding to the first noise identifier and the second noise identifier in the first joint calculation results are deleted to obtain a third joint calculation result.

5. The method according to claim 3, characterized in that: The generating a first noise identification set corresponding to the third identification set includes: Based on the identification features of the real object identifications in the third identification set, a first noise identification set corresponding to the third identification set is generated, and the first noise identifications in the first noise identification set have the same identification features as the real object identifications in the third identification set.

6. The method according to any one of claims 1 to 5, characterized in that: The receiving the first joint data ciphertext sent by the second participant includes: receiving a second joint data ciphertext sent by the second participant, where the second joint data ciphertext is obtained by encrypting the first joint data ciphertext using a homomorphic encryption key; The second joint data ciphertext is decrypted using the homomorphic encryption key to obtain the first joint data ciphertext.

7. The method according to any one of claims 1 to 5, characterized in that: The performing joint calculation based on the first joint data ciphertext to obtain the first joint calculation result includes: Performing a joint calculation based on the first joint data ciphertext to obtain a fifth joint calculation result; The first joint calculation results that meet a first preset range are screened from the fifth joint calculation results.

8. A data processing method, characterized in that: Applied to the second party, the method comprises: Receive a joint identification set and a first transaction data ciphertext corresponding to it sent by a first participant, wherein the joint identification set is a union of a first identification set in the first participant and a second identification set in the second participant, wherein the first identification set includes a plurality of first object identifications of first objects to be monitored, the second identification set includes a plurality of second object identifications of second objects to be monitored, and the joint identification set includes a plurality of joint object identifications; the first transaction data ciphertext is obtained by encrypting the first transaction data corresponding to the joint object identification using a homomorphic encryption key, and the first transaction data is the transaction data of the first participant; For each of the joint object identifiers, determining joint transaction data based on the first transaction data ciphertext and second transaction data, where the second transaction data is transaction data of the second participant; Encrypting the joint transaction data using a random number to obtain a first joint data ciphertext; The first joint data ciphertext is sent to the first participant, so that the first participant performs a joint calculation based on the first joint ciphertext to obtain a first joint calculation result.

9. The method according to claim 8, characterized in that After determining the joint transaction data for each of the joint object identifiers based on the first transaction data ciphertext and the second transaction data, the method further includes: A joint calculation is performed based on the joint transaction data to obtain a second joint calculation result.

10. The method according to claim 9, characterized in that Before receiving the joint identification set sent by the first participant and the first transaction data ciphertext corresponding thereto, the method further includes: Obtaining the second identification set in the second participant; Based on the anonymous query algorithm, determine the target object identifier that is different from the first object identifier in the second identifier set to obtain a target identifier set; Based on a one-way encryption algorithm, encrypt each target object identifier in the target identifier set to obtain a target identifier ciphertext set, wherein the target identifier ciphertext set includes target object identifier ciphertexts corresponding to the multiple target object identifiers one by one; The target identification ciphertext set is sent to the first participant, and a data subset set is determined based on a plurality of target object identification ciphertexts and their one-to-one corresponding target object identifications, so that the first participant determines the target identification set based on the target identification ciphertext set and the data subset set.

11. The method according to claim 10, characterized in that The obtaining the second identification set of the second participant includes: Acquire a fourth identification set from the second participant, wherein the fourth identification set includes real object identifications of a plurality of second objects to be monitored; generating a second noise identifier set corresponding to the fourth identifier set, wherein the second noise identifier set includes a plurality of second noise identifiers; The second identification set is determined according to the fourth identification set and the second noise identification set.

12. The method according to claim 11, characterized in that The second joint calculation result includes a joint calculation result corresponding to the second noise identifier and the first noise identifier, and the first noise identifier is a noise identifier in the first noise identifier set; After obtaining the second joint calculation result, the method further includes: The joint calculation results corresponding to the first noise identifier and the second noise identifier in the second joint calculation results are deleted to obtain a fourth joint calculation result.

13. The method according to claim 11, characterized in that The generating a second noise identification set corresponding to the fourth identification set includes: Based on the identification features of the real object identifications in the fourth identification set, a second noise identification set corresponding to the fourth identification set is generated, and the second noise identifications in the second noise identification set have the same identification features as the real object identifications in the fourth identification set.

14. The method according to any one of claims 8 to 13, characterized in that: Before sending the first joint data ciphertext to the first participant, the method further includes: Encrypting the first joint data ciphertext using a homomorphic encryption key to obtain a second joint data ciphertext; The sending the first joint data ciphertext to the first participant includes: The second joint data ciphertext is sent to the first participant, so that the first participant performs a joint calculation based on the second joint ciphertext to obtain a first joint calculation result.

15. The method according to any one of claims 9 to 13, characterized in that: The performing joint calculation based on the joint transaction data to obtain a second joint calculation result includes: Performing joint calculation based on the joint transaction data to obtain a sixth joint calculation result; The second joint calculation results that meet a second preset range are screened from the sixth joint calculation results.

16. A data processing device, characterized in that: Applied to a first participant, the device comprises: A first acquisition module is used to acquire a joint identification set, wherein the joint identification set is a union of a first identification set of the first participant and a second identification set of the second participant, wherein the first identification set includes a plurality of first object identifications of first objects to be monitored, the second identification set includes a plurality of second object identifications of second objects to be monitored, and the joint identification set includes a plurality of joint object identifications; A first encryption module, configured to encrypt first transaction data corresponding to each of the joint object identifiers using a homomorphic encryption key to obtain first transaction data ciphertext, where the first transaction data is transaction data of the first participant; A first sending module, configured to send the joint identification set and the first transaction data ciphertext corresponding thereto to the second participant; a first receiving module, configured to receive a first joint data ciphertext sent by the second participant, wherein the first joint data ciphertext is obtained by encrypting joint transaction data using a random number, the joint transaction data is data determined based on the first transaction data ciphertext and the second transaction data for each joint object identifier, and the second transaction data is transaction data of the second participant; The first calculation module is used to perform joint calculation based on the first joint data ciphertext to obtain a first joint calculation result.

17. A data processing device, characterized in that: Applied to a second participant, the device comprises: A second receiving module is used to receive a joint identification set and a first transaction data ciphertext corresponding to the joint identification set sent by a first participant, wherein the joint identification set is a union of a first identification set in the first participant and a second identification set in the second participant, wherein the first identification set includes a plurality of first object identifications of first objects to be monitored, the second identification set includes a plurality of second object identifications of second objects to be monitored, and the joint identification set includes a plurality of joint object identifications; the first transaction data ciphertext is obtained by encrypting the first transaction data corresponding to the joint object identification using a homomorphic encryption key, and the first transaction data is the transaction data in the first participant; a first determining module, configured to determine, for each of the joint object identifiers, joint transaction data based on the first transaction data ciphertext and second transaction data, where the second transaction data is transaction data of the second participant; A second encryption module, used to encrypt the joint transaction data using a random number to obtain a first joint data ciphertext; The second sending module is used to send the first joint data ciphertext to the first participant, so that the first participant performs joint calculation based on the first joint ciphertext to obtain a first joint calculation result.

18. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the data processing method according to any one of claims 1-7 or 8-15 is implemented.

19. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the data processing method according to any one of claims 1-7 or 8-15 is implemented.

20. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the data processing method as described in any one of claims 1-7 or 8-15.

Images