Multi-party data processing method, multi-party joint recommendation method, equipment and readable medium

Abstract

The invention relates to a multi-party data processing method, a multi-party joint recommendation method, equipment and a readable medium, and relates to the technical field of multi-party security computing and privacy computing. According to the method, the intersection potential of a first sample set of a requester and a second sample set of a data party under characteristic value screening of an initial threshold value is determined through hidden tracing privacy intersection, plaintext information of all parties is not leaked, and privacy leakage is avoided; and performing business index calculation according to the intersection potential and the first sample number of the first user sample, evaluating the screening effect of the initial threshold through the screened intersection number to determine the target threshold, and determining the characteristic value distribution fully meeting the business demand of the requester according to the target threshold on the basis of not leaking the plaintext information. And the data party performs division of different fourth sample sets based on the target threshold value and the characteristic value, and different business index levels corresponding to the requester can be realized, so that the data party can provide support for differentiated business requirements of the requester in subsequent multi-party combination.

Description

Technical Field

[0001] The present disclosure relates to the technical fields of multi-party secure computing and privacy computing, and in particular to a multi-party data processing method, a multi-party joint recommendation method, a device, and a readable medium. Background Art

[0002] In scenarios involving multiple parties, each party has the problem of data silos.

[0003] At present, in order to break down data silos, all parties are usually required to exchange and analyze at least part of the data in plain text, which leads to certain risks of privacy leakage in multi-party joint scenarios. Summary of the Invention

[0004] The purpose of the present disclosure is to provide a multi-party data processing method, a multi-party joint recommendation method, an electronic device and a computer-readable medium, which can avoid the leakage of private data in multi-party joint recommendation.

[0005] According to the first aspect of the present disclosure, a multi-party data processing method is provided, which can be applied to a requesting party. The requesting party forms a first sample set with a first sample quantity of first user samples. The method may include: initiating an anonymous privacy intersection to the data party based on each initial threshold, and calculating the intersection potential of the first sample set and the second sample set corresponding to the initial threshold; the second sample set is obtained by the data party after screening a local third sample set according to the initial threshold and the characteristic value; the third sample set includes second user samples, and each second user sample has a corresponding characteristic value; based on the intersection potential and the first sample quantity in the first sample set, determining the business indicator corresponding to the initial threshold; determining at least one target threshold in the initial threshold based on the business indicator; and providing the target threshold to the data party so that the data party divides the third sample set into at least two fourth sample sets based on the target threshold and the characteristic value.

[0006] Optionally, based on each initial threshold, a hidden privacy intersection is initiated to the data party, and the intersection potential of the first sample set and the second sample set corresponding to the initial threshold is calculated, including: based on each initial threshold, a hidden privacy intersection is initiated to the data party, the first sample set is randomly rearranged, a predetermined elliptic curve mapping is performed, and encryption processing is performed based on the first private key to obtain a first encryption result; the first encryption result is sent to the data party; a second encryption result provided by the data party is obtained, and the second encryption result is obtained by the data party randomly rearranging the second sample set corresponding to the initial threshold, a predetermined elliptic curve mapping is performed, and encryption processing is performed based on the second private key; the second encryption result is randomly rearranged and encryption processing is performed based on the first private key to obtain a third encryption result; a fourth encryption result provided by the data party is obtained, and the fourth encryption result is obtained by the data party randomly rearranging the first encryption result and encryption processing based on the second private key; the third encryption result is compared with the fourth encryption result to obtain the intersection potential of the first sample set and the second sample set.

[0007] Optionally, the first sample set includes a positive sample subset and a negative sample subset, and an anonymous privacy intersection is initiated to the data party based on each initial threshold, and the intersection potential of the first sample set and the second sample set corresponding to the initial threshold is calculated, including: initiating two anonymous privacy intersections to the data party based on each initial threshold, and calculating the positive sample intersection potential of the positive sample subset and the second sample set corresponding to the initial threshold, and calculating the negative sample intersection potential of the negative sample subset and the second sample set corresponding to the initial threshold; the first sample number includes the number of positive samples and the number of negative samples, and based on the intersection potential and the number of first samples in the first sample set, the business indicator corresponding to the initial threshold is determined, including: determining the business indicator corresponding to the initial threshold based on the positive sample intersection potential, the negative sample intersection potential, the number of positive samples in the first sample set, and the number of negative samples in the first sample set.

[0008] Optionally, the second sample number of the second user sample in the third sample set is greater than the first sample number, and before initiating an anonymous privacy intersection to the data party based on each initial threshold, calculating the positive sample intersection potential and the negative sample intersection potential of the second sample set corresponding to the first sample set and the initial threshold, it also includes: obtaining the second sample number provided by the data party; and aligning the sample numbers of the first sample set and the second sample set based on the second sample number.

[0009] Optionally, before initiating an anonymous privacy intersection to the data party based on each initial threshold and calculating the positive sample intersection potential and the negative sample intersection potential of the first sample set and the second sample set corresponding to the initial threshold, it also includes: obtaining the eigenvalue range provided by the data party; determining at least one initial threshold based on the eigenvalue range; and providing the initial threshold to the data party.

[0010] Optionally, the business indicator includes at least one of hit rate, accuracy, and improvement.

[0011] Optionally, the data cubes include at least two; wherein, the feature type corresponding to each data cube is the same; or, the feature type corresponding to at least one data cube is different from the feature type corresponding to other data cubes.

[0012] According to the second aspect of the present disclosure, a multi-party joint recommendation method is provided, which can be applied to the requesting party. The method may include: initiating an anonymous query to the data party for the user to be recommended, and determining the priority corresponding to the user to be recommended; after each priority corresponds to providing the target threshold to the data party in the multi-party data processing method of the first aspect, the data party divides a fourth sample set based on the target threshold and the characteristic value; and delivering to the user to be recommended based on the priority.

[0013] According to a third aspect of the present disclosure, an electronic device is provided, which can act as a requester. The requester forms a first sample set with a first sample quantity of first user samples. The electronic device may include: a privacy intersection module, which is used to initiate a hidden privacy intersection to the data party based on each initial threshold, and calculate the intersection potential of the first sample set and the second sample set corresponding to the initial threshold; the second sample set is obtained by the data party after screening the local third sample set according to the initial threshold and the characteristic value; the third sample set includes second user samples, and each second user sample has a corresponding characteristic value; an indicator calculation module, which is used to determine the business indicator corresponding to the initial threshold based on the intersection potential and the first sample quantity in the first sample set; a threshold determination module, which is used to determine at least one target threshold in the initial threshold based on the business indicator; and a data sending module, which is used to provide the target threshold to the data party, so that the data party divides the third sample set into at least two fourth sample sets based on the target threshold and the characteristic value.

[0014] Optionally, the privacy intersection module is specifically used to initiate a hidden privacy intersection to the data party based on each initial threshold, randomly rearrange the first sample set, perform predetermined elliptic curve mapping, and encrypt based on the first private key to obtain a first encryption result; send the first encryption result to the data party; obtain the second encryption result provided by the data party, and the second encryption result is obtained by the data party randomly rearranging the second sample set corresponding to the initial threshold, performing predetermined elliptic curve mapping, and encrypting based on the second private key; randomly rearrange the second encryption result and encrypt based on the first private key to obtain a third encryption result; obtain the fourth encryption result provided by the data party, and the fourth encryption result is obtained by the data party randomly rearranging the first encryption result and encrypting based on the second private key; compare the third encryption result with the fourth encryption result to obtain the intersection potential of the first sample set and the second sample set.

[0015] Optionally, the first sample set includes a positive sample subset and a negative sample subset, and a privacy intersection module is specifically used to initiate two anonymous privacy intersections to the data party based on each initial threshold, and respectively calculate the positive sample intersection potential of the positive sample subset and the second sample set corresponding to the initial threshold, and calculate the negative sample intersection potential of the negative sample subset and the second sample set corresponding to the initial threshold; the first sample number includes the number of positive samples and the number of negative samples, and the indicator calculation module is specifically used to determine the business indicator corresponding to the initial threshold based on the positive sample intersection potential, the negative sample intersection potential, the number of positive samples in the first sample set, and the number of negative samples in the first sample set.

[0016] Optionally, the second sample quantity of the second user sample in the third sample set is greater than the first sample quantity, and the electronic device also includes a data receiving module and a sample alignment module; wherein the data receiving module is used to obtain the second sample quantity provided by the data party; the sample alignment module is used to align the sample quantities of the first sample set and the second sample set based on the second sample quantity.

[0017] Optionally, the electronic device also includes a data receiving module and an initial threshold module; wherein the data receiving module is used to obtain the characteristic value range provided by the data party; the initial threshold module is used to determine at least one initial threshold based on the characteristic value range; and the data sending module is also used to provide the initial threshold to the data party.

[0018] Optionally, the business indicator includes at least one of hit rate, accuracy, and improvement.

[0019] Optionally, the data cubes include at least two; wherein, the feature type corresponding to each data cube is the same; or, the feature type corresponding to at least one data cube is different from the feature type corresponding to other data cubes.

[0020] According to the fourth aspect of the present disclosure, an electronic device is provided, which serves as a requesting party. The electronic device may include: a query module, used to initiate an anonymous query to the data party for the user to be recommended, and determine the priority corresponding to the user to be recommended; after the electronic device corresponding to the third aspect of each priority provides a target threshold to the data party, the data party divides a fourth sample set based on the target threshold and the characteristic value; a delivery module, used to deliver to the user to be recommended based on the priority.

[0021] According to a fifth aspect of the present disclosure, there is provided an electronic device, including: processor; a memory for storing computer programs for the processor; The processor is configured to implement the multi-party data processing method of the first aspect or the multi-party joint recommendation method of the second aspect by executing a computer program.

[0022] According to a sixth aspect of the present disclosure, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the multi-party data processing method of the first aspect or the multi-party joint recommendation method of the second aspect is implemented.

[0023] According to a seventh aspect of the present disclosure, a computer program product is provided, which, when executed on an electronic device, enables the electronic device to execute the multi-party data processing method of the first aspect or the multi-party joint recommendation method of the second aspect.

[0024] The present disclosure provides a multi-party data processing method, in which a requesting party forms a first sample set with first user samples of a first sample quantity, and initiates an anonymous privacy intersection request to the data party based on each initial threshold to determine the intersection potential of the first sample set and the second sample set corresponding to the initial threshold; wherein the second sample set is obtained by the data party after screening a local third sample set according to the initial threshold and the characteristic value, and the third sample set includes second user samples, and each second user sample has a corresponding characteristic value; on this basis, the business indicator corresponding to the initial threshold is determined based on the intersection potential and the first sample quantity in the first sample set, and the target threshold is determined in the initial threshold based on the business indicator and provided to the data party, so that the data party can divide the third sample set into at least two fourth sample sets based on the target threshold and the characteristic value. The method determines the intersection potential between the first sample set of the requester and the second sample set of the data party under the initial threshold value feature value screening through the anonymous privacy intersection between the requester and the data party, without providing or obtaining the plaintext information of each party, thereby avoiding the privacy leakage of each party; on this basis, the business index is calculated based on the intersection potential and the first sample number of the first user sample, and the screening effect of the initial threshold on the sample is evaluated through the screened intersection number, so as to determine the target threshold, and the feature value distribution that fully meets the business needs of the requester can be determined based on the target threshold without leaking the plaintext information; further, different fourth sample sets are divided by the data party based on the target threshold and the feature value, which can correspond to different business indicator levels of the requester, so that the data party can provide support for the differentiated business needs of the requester in the subsequent multi-party alliance.

[0025] The multi-party joint recommendation method provided by the present disclosure can be applied to the requesting party, which initiates an anonymous query to the data party for the user to be recommended to determine the priority corresponding to the user to be recommended; each priority corresponds to a fourth sample set divided by the data party based on the target threshold and the characteristic value after providing the target threshold to the data party in the aforementioned multi-party data processing method; the recommended users are delivered based on the priority. In this method, different fourth sample sets are divided by the data party based on the target threshold and the characteristic value, and each corresponds to a priority, so that different priorities can correspond to different business indicator levels of the requesting party; on this basis, the requesting party obtains the priority through anonymous query without leaking the information of the user to be recommended, nor does it obtain the characteristic value of the data party, thereby avoiding privacy leakage of all parties; further, based on the priority, the characteristic value distribution of the data party and the recommendation business needs of the requesting party can be comprehensively considered to carry out differentiated delivery of the recommended users, thereby improving the business quality.

[0026] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0028] Figure 1 This is one of the step flow charts of a multi-party data processing method provided in an embodiment of the present disclosure.

[0029] Figure 2 A schematic diagram of the process of anonymous privacy intersection in a multi-party data processing method provided in an embodiment of the present disclosure.

[0030] Figure 3 A schematic diagram of the interactive flow of a multi-party data processing method provided in an embodiment of the present disclosure.

[0031] Figure 4 This is a second step flow chart of a multi-party data processing method provided in an embodiment of the present disclosure.

[0032] Figure 5 A flowchart of the steps of a multi-party joint recommendation method provided in an embodiment of the present disclosure.

[0033] Figure 6 This is one of the structural block diagrams of the electronic device provided in the embodiment of the present disclosure.

[0034] Figure 7This is the second structural block diagram of the electronic device provided in the embodiment of the present disclosure.

[0035] Figure 8 A schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present disclosure will be more comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or that other methods, components, devices, steps, etc. may be employed. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0037] In addition, the accompanying drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0038] It should be noted that the data obtained by the requesting party and the data party of this disclosure are accessed, collected, stored and used for subsequent analysis and processing with the consent and authorization of the user or the relevant data owner after the user or the relevant data owner is clearly informed of the data collection content, data purpose, processing method and other information. The user or the relevant data owner can also be sent the ways to access, correct, delete the data, as well as the method to revoke consent and authorization.

[0039] In multi-party joint scenarios, due to the problem of data silos between the parties, it is usually necessary for each party to exchange and analyze at least some plaintext data, resulting in the risk of privacy leakage in the multi-party joint data processing and analysis, and low data security.

[0040] In an embodiment of the present disclosure, in the joint data processing between the requesting party and one or more data parties, the requesting party and the data party perform anonymous privacy intersection to determine the intersection potential of the data party samples and the requesting party samples screened by different initial thresholds. On this basis, the business indicators are calculated using the intersection potential to evaluate whether the eigenvalue distribution under the initial threshold division meets the business needs of the requesting party, so as to determine the target threshold in the initial threshold.

[0041] Furthermore, the embodiments of the present disclosure also provide a joint recommendation method between the requesting party and one or more data parties, where the data party can divide the data party samples into different priorities based on the aforementioned target thresholds and characteristic values, so that the requesting party can obtain the priority corresponding to the user to be recommended by initiating an anonymous query to the data party, thereby performing differentiated delivery based on different priorities.

[0042] The joint recommendation method of the embodiment of the present disclosure can be applied to various scenarios involving a requesting party jointly with one or more data parties for delivery.

[0043] For example, in a credit marketing scenario, the requester may possess credit marketing characteristics, while the data provider may possess credit conversion characteristics. The requester can build a highly discriminatory and accurate marketing response model based on these characteristics, thereby screening out users with high credit business intent. However, this may result in underestimation of credit conversion. This creates a data silo between the requester and the data provider.

[0044] Currently, when a requester collaborates with a data provider for credit marketing, they typically need to provide the data provider with a small sample of users in advance to obtain the data provider's credit conversion characteristic distribution. This allows them to conduct a joint assessment by querying the data provider's corresponding characteristic distribution information for the target users. Providing a small sample of users may result in user information being leaked to the data provider, and the requester may also infer additional information based on the credit conversion characteristics returned by the data provider, such as the correlation between the requester's variables and the credit conversion characteristics.

[0045] In the disclosed embodiments, the requester can perform an anonymous and private intersection with the data provider to determine the intersection potential between the data provider samples filtered at different initial thresholds and the requester's samples. Based on this intersection potential, business indicators are calculated to assess whether the distribution of credit characteristics under the initial thresholds meets the requester's business needs, thereby determining a target threshold within the initial thresholds. Furthermore, the data provider can categorize the data provider samples into different priorities based on the aforementioned target thresholds and credit characteristics. The requester can then obtain the priority level corresponding to the target user by initiating an anonymous query to the data provider, thereby implementing differentiated marketing campaigns based on different priorities.

[0046] In another credit marketing scenario, the requesting party may hold credit marketing characteristics, and the data party may hold post-loan risk characteristics.

[0047] The embodiments of the present disclosure can also be applied to other marketing scenarios, such as the product recommendation scenario of e-commerce business, where the requester can hold product recommendation features and the data party can hold revenue and expenditure conversion features; such as the music recommendation scenario of multimedia business, where the requester can hold music recommendation features and the data party can hold music product consumption features, etc.

[0048] Those skilled in the art can implement the multi-party data processing method and the multi-party joint recommendation method provided by the present disclosure in different application scenarios according to actual needs.

[0049] In combination with the above application scenarios, Figure 1 A multi-party data processing method according to an exemplary embodiment of the present disclosure is described.

[0050] Figure 1 This is one of the step flow charts of a multi-party data processing method provided in an embodiment of the present disclosure. The method can be applied to a requesting party, which forms a first sample set with a first number of first user samples.

[0051] In the embodiments of the present disclosure, the requester may be the initiator of data processing and analysis in conjunction with one or more data parties. The requester may hold user information and analyze the user information by integrating the feature information held by the data party to support user-related classification, reasoning, recommendation and other services. In the multi-party data processing process initiated by the requester to the data party, the requester may form a first sample set with a first sample quantity of first user samples, and each first user sample may correspond to a piece of user information, such as each first user sample corresponds to a user identifier. The first sample set may include all or part of the user information held by the requester.

[0052] In the embodiments of the present disclosure, the requesting party may also hold local feature information in addition to the user information. The feature information held by the requesting party and the feature information held by the data provider may be of the same feature type or different feature types, and the embodiments of the present disclosure do not impose any specific restrictions on this.

[0053] like Figure 1 As shown, the method may include steps 101 to 104 .

[0054] In step 101, based on each initial threshold, an anonymous privacy intersection is initiated to the data party to calculate the intersection potential of the first sample set and the second sample set corresponding to the initial threshold; the second sample set is obtained by the data party after screening the local third sample set according to the initial threshold and the characteristic value; the third sample set includes second user samples, and each second user sample has a corresponding characteristic value.

[0055] In an embodiment of the present disclosure, the data party locally holds a third sample set. The third sample set consists of a local second user sample set, each of which has a corresponding feature value. This feature value represents the characteristic information held by the data party. Based on this, the data party performs sample screening on the local third sample set based on the initial threshold and the feature value to obtain a second sample set. Thus, each initial threshold has a corresponding second sample set, and the feature values ​​corresponding to all second samples in the second sample set corresponding to the initial threshold have a consistent comparison relationship with the initial threshold. This comparison relationship can be selected based on actual computing conditions, business requirements, and the like. For example, the comparison relationship can be such that if the feature value is greater than or equal to the initial threshold, then the feature values ​​corresponding to all second samples in the second sample set corresponding to each initial threshold are greater than or equal to the initial threshold. Similarly, the comparison relationship can also be less than or equal to, greater than, less than, equal to, etc. For each initial threshold, the data party can determine a second sample set. The initial threshold can be determined by the data party and provided to the requesting party, determined by the requesting party and provided to the data party, or jointly determined by the requesting party and the data party.

[0056] In the disclosed embodiments, the requesting party may initiate a private set intersection with the data party based on each initial threshold. Each round of private set intersection is initiated for each initial threshold. In each round of private set intersection, the requesting party and the data party calculate the intersection potential between the first sample set and the second sample set corresponding to the initial threshold in that round. The intersection potential reflects the number of intersections between the second user samples obtained by the data party based on the initial threshold and the first user samples from the requesting party.

[0057] In step 102, a business indicator corresponding to an initial threshold is determined based on the intersection potential and the number of first samples in the first sample set.

[0058] In the embodiments of the present disclosure, for one or more initial thresholds, each initial threshold can be calculated using an anonymized intersection method to calculate the corresponding intersection potential. Based on this, the business indicator corresponding to the initial threshold can be determined based on the intersection potential and the number of first samples in the first sample set. Because the initial threshold filters the characteristic value range of the second user sample, the intersection potential can represent the number of first user samples that meet this characteristic value range. Furthermore, the intersection potential and the number of first samples can reflect the distribution of first user samples that meet this characteristic range within the first sample set. Business indicators can be set based on the business needs of the requesting party. The effect of the initial threshold on the screening of first user samples can be represented by describing the comparative relationship between the intersection potential and the number of first samples. For example, a business indicator can be the proportional relationship between the intersection potential and the number of first samples. A business indicator can also be the quantitative relationship between the number of first user samples and the intersection potential corresponding to different types of first user samples. The type of first user samples can be set based on business needs and can include gender, region, age range, occupation, consumer behavior, etc. The number of business indicators can be one or more. Those skilled in the art can set the content and number of business indicators based on actual needs, and the embodiments of the present disclosure do not impose specific limitations on this.

[0059] In step 103, at least one target threshold is determined in the initial threshold based on the business indicator.

[0060] In the embodiment of the present disclosure, for one or more initial thresholds, whether they meet business requirements can be determined based on their business indicators, and then the target threshold can be determined.

[0061] For example, taking the business indicator as the proportional relationship between the intersection potential and the first sample quantity as an example, when the ratio of the intersection potential to the first sample quantity is greater than or equal to the preset ratio, it is considered that the initial threshold meets the business requirements, and then the initial threshold is determined as the target threshold.

[0062] Furthermore, when the requesting party has differentiated business requirements, multiple target thresholds may be determined. In this case, multiple preset ratios may be set based on different business requirements to determine target thresholds that meet business requirements at different levels.

[0063] Exemplarily, a first preset ratio and a second preset ratio are set, and the first preset ratio is greater than the second preset ratio. When the ratio of the intersection potential to the first sample number is greater than or equal to the first preset ratio, the initial threshold is determined as the first target threshold; when the ratio of the intersection potential to the first sample number is less than or equal to the second preset ratio, the initial threshold is determined as the second target threshold.

[0064] In step 104 , a target threshold is provided to the data entity, so that the data entity divides the third sample set into at least two fourth sample sets based on the target threshold and the feature value.

[0065] In an embodiment of the present disclosure, the requesting party provides the data party with a target threshold value that can be determined. On this basis, the data party divides the third sample set into at least two fourth sample sets based on the target threshold value. For example, when the target threshold value is one, the third sample set can be divided into two fourth sample sets, each including a second user sample with a characteristic value greater than or equal to the target threshold value, and a second user sample with a characteristic value less than the target threshold value; when the target threshold value is two, the third sample set can be divided into three fourth sample sets, each including a second user sample with a characteristic value greater than or equal to the first target threshold value, a second user sample with a characteristic value less than the first target threshold value and greater than the second target threshold value, and a second user sample with a characteristic value less than or equal to the second target threshold value; and the same applies when the target threshold value is three. On this basis, based on the target threshold value, the second user samples of the data party are divided into different fourth sample sets based on the characteristic value distribution. This division method meets the business needs of the requesting party.

[0066] In the disclosed embodiment, the requesting party initiates a Private Set Intersection (PSI) to the data party to calculate the intersection potential, which can determine the number of elements in the intersection between multiple parties without disclosing the data content of each party. In practical applications, the intersection potential calculation can be implemented by using homomorphic encryption, ECDH (Elliptic Curve Diffie–Hellman keyExchange) protocol, etc. Taking the ECDH protocol as an example, Figure 2 This is a flow chart of an anonymous privacy intersection in a multi-party data processing method provided by an embodiment of the present disclosure. Figure 2 As shown, on the requesting party side, the anonymity privacy request in the aforementioned step 101 may include the following steps 201 to 206.

[0067] In step 201, based on each initial threshold, a hidden privacy intersection is initiated to the data party, and a first sample set is randomly rearranged, mapped using a predetermined elliptic curve, and encrypted based on a first private key to obtain a first encryption result.

[0068] In the embodiment of the present disclosure, when the requesting party initiates a secret intersection request to the data party for each initial threshold, the requesting party can prepare a first private key in each round of secret intersection request, and randomly rearrange the local first sample set so that the rearranged first sample set is randomly sorted compared to before the rearrangement. Furthermore, the requesting party can perform a predetermined elliptic curve mapping on the randomly rearranged first sample set. The predetermined elliptic curve can be an elliptic curve on a finite field pre-negotiated by the requesting party and the data party, and is used for ECDH encryption calculation. The requesting party can hash each first user sample in the first sample set and map it to the corresponding point on the predetermined elliptic curve. On this basis, encryption is performed again based on the first private key to obtain the first encryption result of the first sample set after ECDH encryption.

[0069] In step 202, the first encryption result is sent to the data source.

[0070] In the disclosed embodiment, the requesting party may send the first encryption result to the data party. When there are multiple data parties, the requesting party may use the same first private key and predetermined elliptic curve for the multiple data parties; or, based on negotiation, may use different predetermined elliptic curves and prepare different first private keys, and then send the first encryption result obtained by performing ECDH encryption based on the corresponding predetermined elliptic curve and the first private key to the corresponding data party.

[0071] In step 203, a second encryption result provided by the data party is obtained. The second encryption result is obtained by the data party performing random rearrangement, predetermined elliptic curve mapping, and encryption processing based on the second private key on the second sample set corresponding to the initial threshold.

[0072] In the embodiment of the present disclosure, the requesting party can obtain the second encryption result provided by the data party. When the requesting party initiates a secret intersection request to the data party for each initial threshold, the data party can prepare a second private key in each round of secret intersection request, and randomly rearrange the second sample set corresponding to the local initial threshold, so that the rearranged second sample set is randomly sorted compared to before the rearrangement. Furthermore, the data party can perform a predetermined elliptic curve mapping on the randomly rearranged second sample set. The data party can hash each second user sample in the second sample set and map it to the corresponding point on the predetermined elliptic curve. On this basis, encryption is performed again based on the second private key to obtain the second encryption result of the second sample set encrypted by ECDH, and the second encryption result is provided to the requesting party.

[0073] In step 204, the second encryption result is randomly rearranged and encrypted based on the first private key to obtain a third encryption result.

[0074] In the disclosed embodiment, the requesting party may randomly rearrange the obtained second encryption result and further encrypt the second encryption result using the first private key to obtain a third encryption result. Based on this, the third encryption result undergoes two rearrangements at the requesting party and the data party, and two encryptions using the first private key and the second private key, respectively.

[0075] In step 205, a fourth encryption result provided by the data party is obtained. The fourth encryption result is obtained by the data party performing random rearrangement on the first encryption result and performing encryption processing based on the second private key.

[0076] In the disclosed embodiment, the requesting party can obtain a fourth encryption result provided by the data party. After obtaining the first encryption result provided by the requesting party in step 203, the data party can randomly rearrange the first encryption result and encrypt it using the second private key to obtain a fourth encryption result and provide it to the requesting party. In this manner, the fourth encryption result undergoes two rearrangements by the requesting party and the data party, and two encryptions using the first private key and the second private key, respectively.

[0077] In step 206, the third encryption result and the fourth encryption result are compared to obtain the intersection potential of the first sample set and the second sample set.

[0078] In the disclosed embodiment, the requesting party can obtain a third encryption result and a fourth encryption result respectively. The third encryption result is obtained by rearranging and encrypting the second sample set twice, and the fourth encryption result is obtained by rearranging and encrypting the first sample set twice. Since ECDH encryption is commutative, when the elements of the first sample set and the second sample set overlap, the fourth encryption result and the third encryption result also have corresponding elements that overlap, so the intersection potential of the first sample set and the second sample set can be obtained by comparing the third encryption result and the fourth encryption result. In the process of anonymous intersection, the requesting party and the data party can each randomly sort, so that the requesting party cannot infer the correspondence between the first sample set and the fourth encryption result through the bit order when obtaining the fourth encryption result, thereby not leaking the intersection plaintext but only outputting the intersection potential.

[0079] In an optional embodiment of the present disclosure, the first sample set includes a positive sample subset and a negative sample subset. On this basis, the aforementioned step 101 may include the following step A1.

[0080] In step A1, two anonymous privacy intersections are initiated to the data party based on each initial threshold, and the positive sample intersection potential of the positive sample subset and the second sample set corresponding to the initial threshold is calculated, and the negative sample intersection potential of the negative sample subset and the second sample set corresponding to the initial threshold is calculated.

[0081] In the disclosed embodiments, the first sample set can be partitioned to obtain a subset of positive samples and a subset of negative samples. The positive and negative samples can be configured based on the data subject's feature type and the requesting party's business needs. For example, in a credit marketing scenario, if the data subject holds credit conversion features, the positive sample subset can include samples of first users who have completed credit conversion, and the negative sample subset can include samples of first users who have not completed credit conversion. If the data subject holds post-loan risk features, the positive sample subset can include samples of first users who have not been overdue after the loan, and the negative sample subset can include samples of first users who have been overdue after the loan. Based on this, when a trace-private intersection is initiated with the data subject based on each initial threshold, two trace-private intersections can be performed in each round, respectively, to calculate the positive sample intersection potential between the positive sample subset and the second sample set corresponding to the initial threshold, and to calculate the negative sample intersection potential between the negative sample subset and the second sample set corresponding to the initial threshold. The calculation of each trace-private intersection can refer to the description of steps 201 to 206 above and will not be repeated here to avoid repetition.

[0082] Furthermore, the first sample quantity includes the number of positive samples and the number of negative samples. Based on the aforementioned step A1, the aforementioned step 102 includes the following step A2.

[0083] In step A2, a business indicator corresponding to the initial threshold is determined based on the positive sample intersection potential, the negative sample intersection potential, the number of positive samples in the first sample set, and the number of negative samples in the first sample set.

[0084] In the embodiment of the present disclosure, the number of first samples in the first sample set can also be divided into the number of positive samples and the number of negative samples. The number of positive samples corresponds to the number of first user samples in the positive sample subset, and the number of negative samples corresponds to the number of first user samples in the negative sample subset. On this basis, the positive sample intersection potential represents the number of elements that overlap with the first user sample and the positive sample subset within the eigenvalue range after the initial threshold screening, and the negative sample intersection potential represents the number of elements that overlap with the first user sample and the negative sample subset within the eigenvalue range after the initial threshold screening. At this point, based on the positive sample intersection potential, the negative sample intersection potential, the number of positive samples, and the number of negative samples, business indicators can be designed more finely to evaluate the distribution of the eigenvalues ​​of the data party on the first sample set.

[0085] For example, take three initial thresholds T1, T2 and T3 from small to large as an example, Figure 3 The following is a flow chart of the interaction of a multi-party data processing method provided by the embodiment of the present disclosure. Figure 3 As shown, the interaction process between the requester and the data provider is shown in steps 301 to 309 below.

[0086] Step 301: The requesting party initiates two anonymous privacy intersections with the data party based on the initial threshold T1, and respectively calculates the positive sample intersection potential 1 between the positive sample subset and the second sample set corresponding to the initial threshold T1, and calculates the negative sample intersection potential 1 between the negative sample subset and the second sample set corresponding to the initial threshold T1.

[0087] Step 302: The requesting party calculates business indicator 1 based on the positive sample intersection potential 1, the negative sample intersection potential 1, the number of positive samples, and the number of negative samples.

[0088] Step 303: The requesting party initiates two anonymous privacy intersections with the data party based on the initial threshold T2, and respectively calculates the positive sample intersection potential 2 between the positive sample subset and the second sample set corresponding to the initial threshold T2, and calculates the negative sample intersection potential 2 between the negative sample subset and the second sample set corresponding to the initial threshold T2.

[0089] Step 304: The requesting party calculates business indicator 2 based on the positive sample intersection potential 2, the negative sample intersection potential 2, the number of positive samples, and the number of negative samples.

[0090] Step 305: The requesting party initiates two anonymous privacy intersections with the data party based on the initial threshold T3, and respectively calculates the positive sample intersection potential 3 between the positive sample subset and the second sample set corresponding to the initial threshold T3, and calculates the negative sample intersection potential 3 between the negative sample subset and the second sample set corresponding to the initial threshold T3.

[0091] Step 306: The requesting party calculates the business indicator 3 based on the positive sample intersection potential 3, the negative sample intersection potential 3, the number of positive samples, and the number of negative samples.

[0092] Step 307 : The requester determines the initial thresholds T1 and T3 as target thresholds among the initial thresholds T1 , T2 , and T3 based on the business indicator 1 , the business indicator 2 , and the business indicator 3 .

[0093] Step 308: The requesting party provides the target thresholds T1 and T3 to the data party.

[0094] Step 309: The data cube is divided based on the target thresholds T1 and T3 to obtain a fourth sample set corresponding to the characteristic values ​​[T3, max], [T1, T3), and [min, T1) respectively.

[0095] Figure 4 This is a second step flow chart of a multi-party data processing method provided in an embodiment of the present disclosure. The method can be applied to a requesting party, which forms a first sample set with a first number of first user samples.

[0096] In the embodiment of the present disclosure, the requesting party, the first user sample, and the first sample set may correspond to the aforementioned Figure 1To avoid repetition, the relevant description will not be repeated here.

[0097] Exemplarily, the requesting party prepares a small batch of first user samples from local user samples x Form the first sample set At this time, the first sample size is m .

[0098] And, the data party holds the second user sample locally y and the corresponding eigenvalues , then there is a third sample set At this time, the second sample size is n .

[0099] like Figure 4 As shown, in an optional embodiment of the present disclosure, the second sample quantity of the second user sample in the third sample set is greater than the first sample quantity, and the method may include the following steps 401 to 402.

[0100] In step 401, a second sample quantity provided by a data source is obtained.

[0101] In an embodiment of the present disclosure, when the second sample size is greater than the first sample size, the requesting party may perform sample size alignment during data preparation. The sample size alignment is performed based on the second sample size provided by the data party, and the data party may synchronize the second sample size to the requesting party.

[0102] For example, in When getting data, the data is synchronized n .

[0103] In step 402 , the first sample set and the second sample set are aligned in terms of sample quantity based on the second sample quantity.

[0104] In the disclosed embodiment, sample number alignment ensures that the first sample set and the second sample set have the same number of elements. This can be achieved by using invalid data to fill gaps in the first sample set. After sample number alignment, the first sample set, in addition to the first user samples of the first sample number, also includes invalid data whose number satisfies the difference between the first sample number and the second sample number.

[0105] For example, based on n Fill in the first sample set ( n - m ) invalid data, obtain the first sample set .

[0106] Furthermore, when the first sample set includes a positive sample subset and a negative sample subset, invalid data may be filled into the corresponding sets in a ratio of the number of positive samples to the number of negative samples to align the number of samples.

[0107] For example, the number of positive samples accounts for 80% of the first number of samples, and the number of negative samples accounts for 20% of the first number of samples. n In the positive sample set Middle filling invalid data, and in the negative sample set Middle filling Invalid data.

[0108] like Figure 4 As shown, in an optional embodiment of the present disclosure, the method may include the following steps 403 to 405.

[0109] In step 403, the feature value range provided by the data source is obtained.

[0110] In step 404 , at least one initial threshold is determined based on the feature value range.

[0111] In step 405, an initial threshold is provided to the data provider.

[0112] In the disclosed embodiments, the feature value range may be the total range of feature values ​​corresponding to the second user sample held by the data subject. Based on this, the requesting party may determine one or more initial thresholds based on business needs, historical experience, and other factors. The specific number of initial thresholds may be determined through negotiation between the requesting party and the data subject.

[0113] In an optional embodiment of the present disclosure, when providing feature values, the data provider may also provide the requester with one or more recommended initial thresholds based on feature value distribution, business experience, etc. The requester may adopt, adjust, or re-draft the initial thresholds, integrating the experience and needs of the requester and the data provider during the preparation phase to improve the efficiency and accuracy of subsequent target threshold determination.

[0114] For example, the requester obtains the characteristic value range provided by the data party, and synchronizes the characteristic value range to the data party based on the characteristic value range. k Initial threshold .in, k Can be a value [3,6].

[0115] On this basis, the data party can prepare k Second sample set .in, , that is, each second sample set includes a second user sample whose characteristic value is greater than the corresponding initial threshold, and each second user sample includes the corresponding characteristic value. On this basis, invalid data is used to align the sample quantity of each second sample set.

[0116] For example, the initial threshold For example, the second sample set Y 1 include score Greater than or equal to of Second user samples, and Invalid data.

[0117] like Figure 4 As shown, the method may further include the following steps 406 to 409.

[0118] In step 406, based on each initial threshold, an anonymous privacy intersection is initiated to the data party to calculate the intersection potential of the first sample set and the second sample set corresponding to the initial threshold; the second sample set is obtained by the data party after screening the local third sample set according to the initial threshold and the characteristic value; the third sample set includes the second user samples, and each second user sample has a corresponding characteristic value.

[0119] In the embodiment of the present disclosure, step 406 may correspond to the relevant description of the aforementioned step 101, and will not be described again here to avoid repetition.

[0120] In the embodiment of the present disclosure, based on k The initial threshold request direction initiates k rounds of anonymous privacy intersection calculations to the data party. Among them, the first sample set includes and For example, in i Anonymous privacy request The specific process of executing the ECDH protocol can be shown in Table 1 below: Table 1

[0121] And so on, in the i Anonymous privacy request Execute the ECDH protocol, and the requester outputs the positive sample intersection potential .

[0122] In step 407, based on the intersection potential and the number of first samples in the first sample set, a business indicator corresponding to the initial threshold is determined.

[0123] In the embodiment of the present disclosure, step 407 may correspond to the relevant description of the aforementioned step 102, and will not be described again here to avoid repetition.

[0124] In an optional embodiment of the present disclosure, the business indicator includes at least one of a hit rate, an accuracy rate, and an improvement rate.

[0125] In the embodiment of the present disclosure, the business indicators may include a hit rate, which represents the hit ratio in the first user sample after the initial threshold screening, such as the hit ratio of the intersection elements in the total number of samples, the hit ratio of the positive sample intersection elements in the number of positive samples, etc.; it may also include an accuracy rate, which represents the ratio of samples that meet the business requirements of the requesting party after the initial threshold screening, such as the proportion of the positive sample intersection potential in the total intersection potential; it may also include a lift, which represents the lift effect of user samples that meet the business requirements after the reference data party feature values ​​and user samples that meet the business requirements without the reference data party feature values, such as the proportion of the positive sample intersection potential in the total intersection potential, and the ratio between the proportion of the positive sample number in the first sample number.

[0126] For example, the hit rate hit_rate It can be calculated by the following formula (1): (1) in, is the number of positive samples in the first sample of the requester. In this case, the hit rate is expressed as the ratio of the intersection potential of positive samples to the number of positive samples.

[0127] For example, the accuracy precision It can be calculated by the following formula (2): (2) At this time, the accuracy is expressed as the proportion of the positive sample intersection potential in the sum of the positive sample intersection potential and the negative sample intersection potential.

[0128] For example, the improvement lift It can be calculated by the following formula (3): (3) At this time, the lift is expressed as the ratio of the positive sample intersection potential to the sum of the positive sample intersection potential and the negative sample intersection potential, and the ratio of the number of positive samples to the number of first samples.

[0129] In step 408, at least one target threshold is determined among the initial thresholds based on the business indicator.

[0130] In the embodiment of the present disclosure, step 408 may correspond to the description of step 103, and will not be described again to avoid repetition. A multi-dimensional analysis may be performed based on one business indicator or a combination of multiple business indicators to determine the target threshold, thereby improving the accuracy of the target threshold determination.

[0131] For example, at the initial threshold When the improvement degree is >1.5, the precision rate is >20%, and the hit rate is >90%, it is considered that based on the initial threshold Filter out user samples that meet the business needs of the requester, and use the test threshold Determine the target threshold.

[0132] In step 409 , the target threshold is provided to the data provider, so that the data provider divides the third sample set into at least two fourth sample sets based on the target threshold and the feature value.

[0133] In the embodiment of the present disclosure, step 409 may correspond to the relevant description of the aforementioned step 104, and will not be described again here to avoid repetition.

[0134] In an optional embodiment of the present disclosure, the data cubes include at least two; wherein, the feature type corresponding to each data cube is the same; or, the feature type corresponding to at least one data cube is different from the feature type corresponding to other data cubes.

[0135] In the embodiments of the present disclosure, the requesting party may perform joint data processing with one or more data parties. When the number of data parties is greater than or equal to 2, the feature type of each data party may be the same, or there may be at least one data party with a different feature type. For example, in a credit marketing scenario, the requesting party may perform joint data processing with multiple data parties that provide credit conversion features, or the requesting party may perform joint data processing with the data party that provides credit conversion features and the data party that provides post-loan risk features. The above feature types are for example only, and those skilled in the art may select the data party to be combined with the requesting party based on actual business needs and data conditions, and the embodiments of the present disclosure do not impose specific restrictions on this.

[0136] The present disclosure provides a multi-party data processing method, in which a requesting party forms a first sample set with first user samples of a first sample quantity, and initiates an anonymous privacy intersection request to the data party based on each initial threshold to determine the intersection potential of the first sample set and the second sample set corresponding to the initial threshold; wherein the second sample set is obtained by the data party after screening a local third sample set according to the initial threshold and the characteristic value, and the third sample set includes second user samples, and each second user sample has a corresponding characteristic value; on this basis, the business indicator corresponding to the initial threshold is determined based on the intersection potential and the first sample quantity in the first sample set, and the target threshold is determined in the initial threshold based on the business indicator and provided to the data party, so that the data party can divide the third sample set into at least two fourth sample sets based on the target threshold and the characteristic value. The method determines the intersection potential between the first sample set of the requester and the second sample set of the data party under the initial threshold value feature value screening through the anonymous privacy intersection between the requester and the data party, without providing or obtaining the plaintext information of each party, thereby avoiding the privacy leakage of each party; on this basis, the business index is calculated based on the intersection potential and the first sample number of the first user sample, and the screening effect of the initial threshold on the sample is evaluated through the screened intersection number, so as to determine the target threshold, and the feature value distribution that fully meets the business needs of the requester can be determined based on the target threshold without leaking the plaintext information; further, different fourth sample sets are divided by the data party based on the target threshold and the feature value, which can correspond to different business indicator levels of the requester, so that the data party can provide support for the differentiated business needs of the requester in the subsequent multi-party alliance.

[0137] Figure 5 This is a flowchart of a multi-party joint recommendation method provided by an embodiment of the present disclosure, which can be applied to a requesting party. The method can include the following steps 501 to 502.

[0138] In step 501, an anonymous query is initiated to the data party for the user to be recommended to determine the priority level of the user to be recommended; each priority level corresponds to a fourth sample set divided by the data party based on the target threshold and the characteristic value after providing the target threshold to the data party in the aforementioned multi-party data processing method.

[0139] In the embodiment of the present disclosure, the requesting party and the data party are based on the above Figure 1 、 Figure 4The multi-party data processing method determines the target threshold, and after the data party divides the fourth sample set based on the target threshold and the characteristic value, a corresponding priority can be set for each fourth sample set. The setting of priority can be implemented based on the differentiated business needs of the requesting party, such as the fourth sample set whose business indicators are more in line with the business needs of the requesting party has a higher priority. Exemplarily, taking a target threshold as an example, the data party divides and obtains two fourth sample sets. When the business indicator is greater than or equal to the target threshold and the business needs of the requesting party are better met by the characteristic value, the fourth sample set containing the second user sample corresponding to the characteristic value greater than or equal to the target threshold is given a higher priority than the other fourth sample set.

[0140] On this basis, the requester can conduct multi-party joint recommendations with the data provider. The requester can initiate an anonymous query to the data provider for local users to be recommended. Without revealing the user to be recommended, the requester can obtain the priority returned by the data provider based on the fourth sample set hit by the user to be recommended. This anonymous query can be implemented using a keyword matching anonymous query scheme, implemented through homomorphic encryption, and transmitted in homomorphic ciphertext during communication. This prevents the data provider from determining the specific information of the user to be recommended, thus protecting the privacy of the requester.

[0141] In step 502, delivery is performed to the recommended users based on priority.

[0142] In the disclosed embodiment, the requesting party may deliver services to the recommended users based on their priorities, such as eliminating low-priority user groups from multiple users to be recommended and only delivering services to high-priority user groups, or delivering a small amount to low-priority user groups and a large amount to high-priority user groups; the requesting party may also combine local feature information of the requesting party, weight the local feature information by priority and then deliver differentiated services, or eliminate low-priority user groups and deliver services to high-priority user groups after evaluating them based on local feature information.

[0143] For example, in a credit marketing scenario, when the requesting party holds a marketing response feature and the data party holds a credit conversion feature, the requesting party can anonymously query the data party about the priority of the users to be recommended, and then eliminate the user groups with relatively low priorities, and use the marketing response feature to determine the periodic marketing delivery volume for different users to be recommended in the user groups with relatively high priorities.

[0144] The multi-party joint recommendation method provided by the present disclosure can be applied to the requesting party, which initiates an anonymous query to the data party for the user to be recommended to determine the priority corresponding to the user to be recommended; each priority corresponds to a fourth sample set divided by the data party based on the target threshold and the characteristic value after providing the target threshold to the data party in the aforementioned multi-party data processing method; the recommended users are delivered based on the priority. In this method, different fourth sample sets are divided by the data party based on the target threshold and the characteristic value, and each corresponds to a priority, so that different priorities can correspond to different business indicator levels of the requesting party; on this basis, the requesting party obtains the priority through anonymous query without leaking the information of the user to be recommended, nor does it obtain the characteristic value of the data party, thereby avoiding privacy leakage of all parties; further, based on the priority, the characteristic value distribution of the data party and the recommendation business needs of the requesting party can be comprehensively considered to carry out differentiated delivery of the recommended users, thereby improving the business quality.

[0145] Figure 6 This is one of the structural block diagrams of an electronic device 600 provided in an embodiment of the present disclosure. The electronic device 600 serves as a requester, and the requester forms a first sample set with a first sample quantity of first user samples. The electronic device 600 may include: a privacy intersection module 601, which is used to initiate a private intersection to the data party based on each initial threshold, and calculate the intersection potential of the first sample set and the second sample set corresponding to the initial threshold; the second sample set is obtained by the data party after screening a local third sample set according to the initial threshold and the characteristic value; the third sample set includes second user samples, and each second user sample has a corresponding characteristic value; an indicator calculation module 602, which is used to determine the business indicator corresponding to the initial threshold based on the intersection potential and the first sample quantity in the first sample set; a threshold determination module 603, which is used to determine at least one target threshold in the initial threshold based on the business indicator; and a data sending module 604, which is used to provide the target threshold to the data party, so that the data party divides the third sample set into at least two fourth sample sets based on the target threshold and the characteristic value.

[0146] In an optional embodiment of the present disclosure, the privacy intersection module 601 is specifically used to initiate a hidden privacy intersection to the data party based on each initial threshold, randomly rearrange the first sample set, perform predetermined elliptic curve mapping, and encrypt based on the first private key to obtain a first encryption result; send the first encryption result to the data party; obtain a second encryption result provided by the data party, the second encryption result is obtained by the data party randomly rearranging the second sample set corresponding to the initial threshold, performing predetermined elliptic curve mapping, and encrypting based on the second private key; randomly rearrange the second encryption result and encrypt based on the first private key to obtain a third encryption result; obtain a fourth encryption result provided by the data party, the fourth encryption result is obtained by the data party randomly rearranging the first encryption result and encrypting based on the second private key; compare the third encryption result with the fourth encryption result to obtain the intersection potential of the first sample set and the second sample set.

[0147] In an optional embodiment of the present disclosure, the first sample set includes a positive sample subset and a negative sample subset, and the privacy intersection module 601 is specifically used to initiate two anonymous privacy intersections to the data party based on each initial threshold, and respectively calculate the positive sample intersection potential of the positive sample subset and the second sample set corresponding to the initial threshold, and calculate the negative sample intersection potential of the negative sample subset and the second sample set corresponding to the initial threshold; the first sample number includes the number of positive samples and the number of negative samples, and the indicator calculation module 602 is specifically used to determine the business indicator corresponding to the initial threshold based on the positive sample intersection potential, the negative sample intersection potential, the number of positive samples in the first sample set, and the number of negative samples in the first sample set.

[0148] In an optional embodiment of the present disclosure, the second sample quantity of the second user sample in the third sample set is greater than the first sample quantity, and the electronic device further includes a data receiving module and a sample alignment module; wherein the data receiving module is used to obtain the second sample quantity provided by the data party; and the sample alignment module is used to align the sample quantities of the first sample set and the second sample set based on the second sample quantity.

[0149] In an optional embodiment of the present disclosure, the electronic device 600 also includes a data receiving module and an initial threshold module; wherein the data receiving module is used to obtain the characteristic value range provided by the data party; the initial threshold module is used to determine at least one initial threshold based on the characteristic value range; the data sending module 604 is also used to provide the initial threshold to the data party.

[0150] In an optional embodiment of the present disclosure, the business indicator includes at least one of a hit rate, an accuracy rate, and an improvement rate.

[0151] In an optional embodiment of the present disclosure, the data cubes include at least two; wherein, the feature type corresponding to each data cube is the same; or, the feature type corresponding to at least one data cube is different from the feature type corresponding to other data cubes.

[0152] The electronic device 600 provided in the present disclosure can act as a requesting party to form a first sample set with a first sample quantity of first user samples, and initiate an anonymous privacy intersection request to the data party based on each initial threshold to determine the intersection potential of the first sample set and the second sample set corresponding to the initial threshold; wherein the second sample set is obtained by the data party after screening a local third sample set according to the initial threshold and the characteristic value, and the third sample set includes second user samples, and each second user sample has a corresponding characteristic value; on this basis, the business indicator corresponding to the initial threshold is determined based on the intersection potential and the first sample quantity in the first sample set, and the target threshold is determined in the initial threshold based on the business indicator and provided to the data party, so that the data party can divide the third sample set into at least two fourth sample sets based on the target threshold and the characteristic value. The method determines the intersection potential between the first sample set of the requester and the second sample set of the data party under the initial threshold value feature value screening through the anonymous privacy intersection between the requester and the data party, without providing or obtaining the plaintext information of each party, thereby avoiding the privacy leakage of each party; on this basis, the business index is calculated based on the intersection potential and the first sample number of the first user sample, and the screening effect of the initial threshold on the sample is evaluated through the screened intersection number, so as to determine the target threshold, and the feature value distribution that fully meets the business needs of the requester can be determined based on the target threshold without leaking the plaintext information; further, different fourth sample sets are divided by the data party based on the target threshold and the feature value, which can correspond to different business indicator levels of the requester, so that the data party can provide support for the differentiated business needs of the requester in the subsequent multi-party alliance.

[0153] Figure 7 The second structural block diagram of the electronic device 700 provided in the embodiment of the present disclosure, the electronic device 700 serves as the requesting party, and the electronic device 700 may include: a query module 701, used to initiate an anonymous query to the data party for the user to be recommended, and determine the priority corresponding to the user to be recommended; after the electronic device corresponding to each priority level provides the target threshold to the data party, the data party divides a fourth sample set based on the target threshold and the characteristic value; a delivery module 702, used to deliver to the user to be recommended based on the priority.

[0154] The electronic device 700 provided in the present disclosure can act as a requester to initiate an anonymous query to the data party for the user to be recommended, and determine the priority corresponding to the user to be recommended; each priority corresponds to a fourth sample set divided by the data party based on the target threshold and the characteristic value after providing the target threshold to the data party in the aforementioned multi-party data processing method; and the recommended users are delivered based on the priority. In this method, different fourth sample sets are divided by the data party based on the target threshold and the characteristic value, and each corresponds to a priority, so that different priorities can correspond to different business indicator levels of the requester; on this basis, the requester obtains the priority through anonymous query without leaking the information of the user to be recommended, nor does it obtain the characteristic value of the data party, thereby avoiding privacy leakage of all parties; further, based on the priority, the characteristic value distribution of the data party and the recommended business needs of the requester can be comprehensively considered to carry out differentiated delivery to the recommended users, thereby improving business quality.

[0155] It should be noted that although several modules or units of the device for action execution are mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0156] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0157] Through the description of the above embodiments, it will be readily understood by those skilled in the art that the example embodiments described herein can be implemented via software or via a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or mobile hard drive) or on a network and includes several instructions for enabling a computing device (such as a personal computer, server, mobile terminal, or network device) to execute the methods according to the embodiments of the present disclosure.

[0158] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0159] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods, or program products. Therefore, various aspects of the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, microcode, etc.), or in a combination of hardware and software, collectively referred to herein as "circuits," "modules," or "systems."

[0160] Refer to the following Figure 8 800 according to this embodiment of the present disclosure will be described. Figure 8 The electronic device 800 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0161] like Figure 8 As shown, electronic device 800 is implemented as a general-purpose computing device. Components of electronic device 800 may include, but are not limited to, the aforementioned at least one processing unit 810, the aforementioned at least one storage unit 820, and a bus 830 connecting various system components (including storage unit 820 and processing unit 810).

[0162] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0163] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0164] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0165] Bus 830 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0166] The electronic device 800 can also communicate with one or more external devices (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 800, and / or any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). This communication can occur via a display unit 840 and an input / output (I / O) interface 850 connected to the display unit 840. Furthermore, the electronic device 800 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 800, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0167] Through the description of the above embodiments, it will be readily understood by those skilled in the art that the example embodiments described herein can be implemented via software or via a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or mobile hard drive) or on a network and includes several instructions for enabling a computing device (such as a personal computer, server, terminal device, or network device) to execute the methods according to the embodiments of the present disclosure.

[0168] In exemplary embodiments of the present disclosure, a computer-readable medium is also provided, on which is stored a program product capable of implementing the aforementioned methods of this specification. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to execute the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present disclosure.

[0169] In an embodiment of the present disclosure, a program product for implementing the above method is also provided. The program product may be a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0170] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0171] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0172] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0173] Program code for performing the operations of the present disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0174] Furthermore, the above-mentioned figures are merely illustrative of the processes included in the methods according to exemplary embodiments of the present disclosure and are not intended to be limiting. It is readily understood that the processes illustrated in the above-mentioned figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0175] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

Claims

1. A multi-party data processing method, characterized in that: The method is applied to a requesting party, where the requesting party forms a first sample set with first user samples of a first sample quantity, and the method includes: Based on each initial threshold, a privacy-sensitive intersection is initiated with the data party, and the intersection potential between the first sample set and the second sample set corresponding to the initial threshold is calculated; the second sample set is obtained by the data party after screening a local third sample set based on the initial threshold and the characteristic value; the third sample set includes second user samples, and each second user sample has the corresponding characteristic value; Determining a business indicator corresponding to the initial threshold based on the intersection potential and the first number of samples in the first sample set; Determining at least one target threshold value among the initial threshold values ​​based on the business indicator; The target threshold is provided to the data cube, so that the data cube divides the third sample set into at least two fourth sample sets based on the target threshold and the feature value.

2. The multi-party data processing method according to claim 1, characterized in that: The step of initiating an anonymous privacy intersection to the data party based on each of the initial thresholds and calculating the intersection potential of the first sample set and the second sample set corresponding to the initial threshold comprises: Initiating a privacy-anonymous intersection with the data party based on each of the initial thresholds, performing random rearrangement, predetermined elliptic curve mapping, and encryption processing based on the first private key on the first sample set to obtain a first encryption result; Sending the first encryption result to the data party; Obtaining a second encryption result provided by the data party, where the second encryption result is obtained by the data party performing random rearrangement, predetermined elliptic curve mapping, and encryption based on a second private key on a second sample set corresponding to the initial threshold; Randomly rearrange the second encryption result and perform encryption processing based on the first private key to obtain a third encryption result; Obtaining a fourth encryption result provided by the data party, where the fourth encryption result is obtained by the data party performing random rearrangement on the first encryption result and performing encryption processing based on the second private key; The third encryption result and the fourth encryption result are compared to obtain the intersection potential of the first sample set and the second sample set.

3. The multi-party data processing method according to claim 1, characterized in that: The first sample set includes a positive sample subset and a negative sample subset, and the initiating an anonymous privacy intersection to the data party based on each initial threshold, and calculating the intersection potential of the first sample set and a second sample set corresponding to the initial threshold, includes: Initiate two anonymous privacy intersections to the data party based on each of the initial thresholds, and respectively calculate the positive sample intersection potential of the positive sample subset and the second sample set corresponding to the initial threshold, and calculate the negative sample intersection potential of the negative sample subset and the second sample set corresponding to the initial threshold; The first number of samples includes the number of positive samples and the number of negative samples, and determining the business indicator corresponding to the initial threshold based on the intersection potential and the first number of samples in the first sample set includes: A business indicator corresponding to the initial threshold is determined based on the positive sample intersection potential, the negative sample intersection potential, the number of positive samples in the first sample set, and the number of negative samples in the first sample set.

4. The multi-party data processing method according to claim 1, characterized in that: The number of second samples of the second user sample in the third sample set is greater than the number of the first samples, and before initiating an anonymous privacy intersection to the data party based on each of the initial thresholds and calculating the positive sample intersection potential and the negative sample intersection potential of the second sample set corresponding to the first sample set and the initial threshold, the method further includes: Obtaining the second sample quantity provided by the data provider; Aligning the first sample set and the second sample set by sample quantity based on the second sample quantity.

5. The multi-party data processing method according to claim 1, characterized in that: Before initiating an anonymous privacy intersection to the data party based on each of the initial thresholds and calculating the positive sample intersection potential and the negative sample intersection potential of the first sample set and the second sample set corresponding to the initial threshold, the method further includes: Obtaining the characteristic value range provided by the data provider; Determining at least one of the initial thresholds based on the feature value range; The initial threshold is provided to the data entity.

6. The multi-party data processing method according to claim 1, characterized in that: The business indicator includes at least one of hit rate, accuracy rate, and improvement rate.

7. The multi-party data processing method according to claim 1, characterized in that: The data cubes include at least two; wherein, each of the data cubes corresponds to the same feature type; or, the feature type corresponding to at least one of the data cubes is different from the feature type corresponding to the other data cubes.

8. A multi-party joint recommendation method, characterized in that: The method is applied to a requesting party, and includes: Initiating an anonymous query to the data party for the user to be recommended, and determining a priority level corresponding to the user to be recommended; each priority level corresponds to a fourth sample set divided by the data party based on the target threshold and the characteristic value after providing the target threshold to the data party in the multi-party data processing method according to any one of claims 1 to 7; The recommendation is performed on the user to be recommended based on the priority.

9. An electronic device, characterized in that: The electronic device serves as a requester, and the requester forms a first sample set with first user samples of a first sample quantity. The electronic device includes: a privacy intersection module, configured to initiate a private intersection with the data provider based on each initial threshold, and calculate the intersection potential between the first sample set and a second sample set corresponding to the initial threshold; the second sample set is obtained by the data provider after screening a local third sample set based on the initial threshold and the characteristic value; the third sample set includes second user samples, and each second user sample has the corresponding characteristic value; an indicator calculation module, configured to determine a business indicator corresponding to the initial threshold based on the intersection potential and the number of first samples in the first sample set; A threshold determination module, configured to determine at least one target threshold from the initial thresholds based on the business indicator; The data sending module is configured to provide the target threshold to the data source, so that the data source divides the third sample set into at least two fourth sample sets based on the target threshold and the characteristic value.

10. An electronic device, characterized in that: The electronic device serves as a requesting party, and the electronic device includes: a query module configured to initiate an anonymous query to a data entity for a user to be recommended, and determine a priority level corresponding to the user to be recommended; a fourth sample set divided by the data entity based on the target threshold and the characteristic value after the electronic device according to claim 9 provides the target threshold to the data entity for each priority level; A delivery module is used to deliver to the user to be recommended based on the priority.

11. An electronic device, characterized in that: include: processor; a memory for storing a computer program for the processor; The processor is configured to execute the multi-party data processing method according to any one of claims 1 to 7, or the multi-party joint recommendation method according to claim 8, by executing the computer program.

12. A computer-readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the multi-party data processing method according to any one of claims 1 to 7 or the multi-party joint recommendation method according to claim 8 is implemented.

Images