Self-data monitoring method and system based on privacy recommendation system of pri reco platform

Abstract

The application provides a self-data monitoring method and system based on a PriReCo platform privacy recommendation system, comprising the following steps: S1: adding a random value in an APP terminal feature set to perform intersection operation on the mixed set, and checking whether the random value exists in a PSI privacy intersection operation result; S2: performing privacy intersection operation after deleting part of feature items, and verifying whether the server stores privacy data of the user according to whether the server recommends a commodity of the deleted feature. Through improvement of the APP, the user can clearly see that the privacy of the user is indeed not stored by the platform, and the platform only recommends a commodity meeting a feature value for the user according to a calculation result when the user initiatively initiates PSI privacy calculation operation, so that the user is more at ease with the related service.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of privacy data monitoring, in particular to a self data monitoring method and system based on a PriReCo platform privacy recommendation system. BACKGROUND

[0002] The private set intersection (PSI) technology is to obtain the intersection part of all data of both parties without leaking the real data of both parties, thereby avoiding the leakage of non-intersection part data.

[0003] The Sacre platform launches a PriReCo subsystem, which can recommend some interested goods or services to users while protecting the privacy of user data. The user portrait data is completely saved on the local APP, and the server has no right to obtain these user privacy data and does not record the corresponding product viewing and browsing records of the user. Only when the user actively requests the PIS private set intersection, the server will recommend suitable products or services to the user according to the operation result. The purpose of recommending suitable goods to the user while protecting the privacy of user data is achieved.

[0004] However, the current recommendation method still has a certain privacy data problem, because all the data features are a large set abstracted by the platform according to all the goods, that is, the server masters the data set of all the features of the goods. When the user issues a private intersection service, the feature data set of the user is only a part of the large feature data set, and the server can still obtain all the privacy data of the user, that is, the user leaks the privacy data of the feature set in the use process. We need to solve the above-mentioned privacy data leakage problem. SUMMARY

[0005] In view of the defects in the prior art, the purpose of the present application is to provide a self data monitoring method and system based on a PriReCo platform privacy recommendation system.

[0006] According to the self data monitoring method based on the PriReCo platform privacy recommendation system provided by the present application, the method comprises the following steps:

[0007] Step S1: adding a random value in the feature set on the APP side to confuse the set for intersection, and checking whether the random value exists in the PSI private intersection operation result;

[0008] Step S2: deleting part of the feature items and then performing private intersection, and verifying whether the server stores the privacy data of the user according to whether the server recommends the goods of the deleted features.

[0009] Preferably, the step S1 comprises the following sub-steps:

[0010] Step S1.1: randomly generating a confused item data feature;

[0011] Step S1.2: fusing the randomly generated data feature into user portrait privacy data by the PSI privacy intersection service of the APP side;

[0012] Step S1.3: performing a privacy intersection operation on the fused data and the PriReCo platform server;

[0013] Step S1.4: checking the calculation result after the privacy intersection, checking whether the randomly generated data feature in step S1.1 exists, if it exists, it indicates that the server has cheating behavior, generating an alarm information and reminding the user.

[0014] Preferably, the step S2 comprises the following sub-steps:

[0015] Step S2.1: deleting part of the user personal portrait data feature set by the PSI privacy intersection service of the APP side;

[0016] Step S2.2: performing a privacy intersection operation on the deleted data and the server;

[0017] Step S2.3: checking the platform system recommendation result set, verifying whether the server saves the user's privacy data.

[0018] Preferably, the data feature is a data feature that does not exist in the PriReCo platform.

[0019] Preferably, in the step S2.3, if the goods of the deleted feature set are received, it is determined that the server saves the PSI privacy operation result every time, and a Warning information is generated and the user is prompted.

[0020] According to the self-data monitoring system of the PriReCo platform privacy recommendation system provided by the application, the following modules are included:

[0021] Module M1: adding a random value in the APP side feature set to confuse the set for intersection, checking whether the random value exists in the PSI privacy intersection operation result;

[0022] Module M2: deleting part of the feature items and then performing a privacy intersection, checking whether the server recommends the goods of the deleted features, verifying whether the server stores the user's privacy data.

[0023] Preferably, the module M1 comprises the following sub-modules:

[0024] Module M1.1: randomly generating a confused item data feature;

[0025] Module M1.2: the randomly generated data features are fused into the user portrait privacy data by the APP-side PSI privacy intersection service;

[0026] Module M1.3: the fused data is subjected to a privacy intersection operation with the PriReCo platform server;

[0027] Module M1.4: the calculation result after the privacy intersection is viewed to check whether the randomly generated data features exist, and if so, it indicates that the server has cheating behavior, and an alarm information is generated and the user is reminded.

[0028] Preferably, the module M2 comprises the following sub-steps:

[0029] Module M2.1: part of the user personal portrait data features set is deleted by the APP-side PSI privacy intersection service;

[0030] Module M2.2: the pruned data is subjected to a privacy intersection operation with the server;

[0031] Module M2.3: the platform system recommendation result set is viewed to verify whether the server saves the user's privacy data.

[0032] Preferably, the data features are data features that do not exist in the PriReCo platform.

[0033] Preferably, in the module M2.3, if the goods of the deleted feature set are received, it is determined that the server saves the PSI privacy operation result every time, a Warning information is generated and the user is prompted.

[0034] Compared with the prior art, the present application has the following beneficial effects:

[0035] 1. By improving the APP, the user can clearly see that his privacy is indeed not stored by the platform, and only when the user initiates the PSI privacy calculation operation, the platform will recommend goods meeting the feature value according to the calculation result, so that the user is more at ease with the related service.

[0036] 2. By verifying whether the user side and the server are really performing the privacy set intersection operation, the server simply obtaining the user privacy data for recommendation service is excluded.

[0037] 3. The present application can verify from the side whether the PriReCo platform truly uses the PSI privacy calculation service and whether the user's task privacy data is recorded, so that the user is more at ease with the PriReCo platform. BRIEF DESCRIPTION OF DRAWINGS

[0038] Other features, objects, and advantages of the application will become apparent from the following detailed description of non-limiting embodiments, when read in connection with the following accompanying drawings:

[0039] Figure 1 The figure of the self-data monitoring system architecture in the embodiment of the application. DETAILED DESCRIPTION

[0040] The application will be described in detail below with specific embodiments. The following embodiments will help those skilled in the art to further understand the application, but do not limit the application in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the application. These are within the scope of protection of the application.

[0041] The application discloses a self-data monitoring method based on a PriReCo platform privacy recommendation system, referring to Figure 1 , comprising the following steps:

[0042] Step S1: adding random values in the APP end feature set to perform intersection operation on the mixed set, and checking whether the random values exist in the PSI privacy intersection operation result.

[0043] This step is mainly used to verify whether the user end and the server are really performing the privacy set intersection operation, and to exclude the server from simply obtaining user privacy data to provide recommendation services.

[0044] Specifically, the following sub-steps are included:

[0045] Step S1.1: randomly generating some mixed item data features; these data features are data features that do not exist in the PriReCo platform, such as time ABR and some data unrelated to goods.

[0046] Step S1.2: fusing the randomly generated data features into the user portrait privacy data by the PSI privacy intersection service of the APP end;

[0047] Step S1.3: performing privacy intersection operation on the fused data and the PriReCo platform server;

[0048] Step S1.4: checking the calculation result after the privacy intersection, checking whether the data features randomly generated in step S1.1 exist, if they exist, it means that the server has cheating behavior, generating an alarm information and reminding the user.

[0049] Step S2: deleting part of the feature items and then performing privacy intersection, verifying whether the server stores the user's privacy data according to whether the server will recommend the goods of the deleted features.

[0050] Further, step S2 includes the following sub-steps:

[0051] Step S2.1: deleting part of the user personal portrait data feature set by the PSI privacy intersection service of the APP end;

[0052] Step S2.2: performing a privacy intersection operation on the pruned data and the server;

[0053] Step S2.3: checking the platform system recommendation result set to verify whether the server saves the user's privacy data. If the goods of the deleted feature set are received, it means that the server will save the PSI privacy operation result every time, to facilitate the recommendation of related goods for the user. At this time, a Warning information is generated for the user, prompting that the user's information may be leaked.

[0054] The monitoring method mainly solves the problem of user's distrust of the privacy intersection operation service provided by the PriReCo platform. During the use of the APP, the user is always worried that his / her query and browsing records will be recorded by the server, and in addition, the user is also worried that the platform does not truly perform the PSI operation, but only takes the user portrait data to the user according to the user portrait feature value to recommend related goods to the user.

[0055] The monitoring method mainly solves the user's doubts, and also indirectly shows that the PriReCo platform truly uses the PSI privacy calculation service and does not record the user's task privacy data, to provide the best privacy recommendation service for the user.

[0056] The application also discloses a self-data monitoring system based on a PriReCo platform privacy recommendation system, comprising the following modules:

[0057] Module M1: adding random values in the feature set of the APP end to confuse the set for intersection, and checking whether the random values exist in the PSI privacy intersection operation result;

[0058] Further, module M1 includes the following sub-modules:

[0059] Module M1.1: randomly generating some confused item data features, wherein the data features are data features that do not exist in the PriReCo platform.

[0060] Module M1.2: fusing the randomly generated data features into the user portrait privacy data by the PSI privacy intersection service of the APP end;

[0061] Module M1.3: performing a privacy intersection operation on the fused data and the PriReCo platform server;

[0062] Module M1.4: Check the calculation result after privacy intersection, check whether there is randomly generated data feature, if there is, it means that the server has cheating behavior, generate alarm information and remind the user.

[0063] Module M2: After deleting part of the feature items, privacy intersection is performed again to check whether the server recommends the goods of the deleted features, and to verify whether the server stores the user's privacy data.

[0064] Further, module M2 includes the following sub-steps:

[0065] Module M2.1: Delete part of the user's personal portrait data feature set through the PSI privacy intersection service of the APP end;

[0066] Module M2.2: Perform privacy intersection operation on the pruned data and the server;

[0067] Module M2.3: Check the platform system recommendation result set to verify whether the server saves the user's privacy data. If the goods of the deleted feature set are received, it is determined that the server saves the PSI privacy operation result every time, generates a warning information and prompts the user.

[0068] Those skilled in the art know that, in addition to implementing the system provided by the present application and each device, module and unit thereof in the form of pure computer readable program code, the system provided by the present application and each device, module and unit thereof can also be implemented in the form of logic gate, switch, special integrated circuit, programmable logic controller and embedded microcontroller to achieve the same function by logically programming the method steps. Therefore, the system provided by the present application and each device, module and unit thereof can be considered as a hardware component, and the devices, modules and units included therein for achieving various functions can also be considered as structures within the hardware component; the devices, modules and units for achieving various functions can also be considered as both software modules for implementing the method and structures within the hardware component.

[0069] The specific embodiments of the present application are described above. It should be understood that the present application is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essential content of the present application. In the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A method for monitoring the self-data of a privacy-recommending system, characterized in that, include: Step S1: Add random values ​​to the feature set on the APP side, perform intersection with the obfuscated set, and check whether random values ​​exist in the PSI privacy intersection operation result; Step S1 includes the following sub-steps: Step S1.1: Randomly generate features for obfuscated project data; Step S1.2: Integrate the randomly generated data features into the user profile privacy data using the PSI privacy intersection service on the APP side; Step S1.3: Perform privacy intersection calculation with the merged data and the server; Step S1.4: Check the calculation results after privacy intersection and see if the data features randomly generated in step S1.1 exist. If they do, it means that the server has cheated. Generate an alarm message and remind the user. Step S2: After deleting some feature items, perform privacy intersection again. Verify whether the server stores user privacy data by determining whether the server recommends products with deleted features. Step S2 includes the following sub-steps: Step S2.1: Delete part of the user's personal profile data feature set through the PSI privacy intersection service on the APP; Step S2.2: Perform a privacy intersection operation between the pruned data and the server; Step S2.3: Check the platform system's recommendation result set to verify whether the server has stored the user's private data.

2. The self-data monitoring method for a privacy recommendation system according to claim 1, characterized in that: In step S2.3, if a product with a deleted feature set is received, it is determined that the server saves the PSI privacy calculation result each time, generates a warning message and notifies the user.

3. A self-data monitoring system for a privacy recommendation system, characterized in that: Includes the following modules: Module M1: Adds random values ​​to the feature set on the APP side, performs intersection with the obfuscated set, and checks whether random values ​​exist in the PSI privacy intersection result; Module M1 includes the following sub-modules: Module M1.1: Randomly generates obfuscated project data features; Module M1.2: Integrates randomly generated data features from the PSI privacy intersection service on the APP into the user profile privacy data; Module M1.3: Performs privacy-preserving intersection calculations on the merged data and the server data; Module M1.4: View the calculation results after privacy intersection, check if there are randomly generated data features. If so, it indicates that the server has cheated, generate alarm information and remind the user. Module M2: After deleting some feature items, perform privacy intersection to check if the server recommends products with deleted features and verify whether the server stores user privacy data; Module M2 includes the following sub-steps: Module M2.1: Deletes part of the user's personal profile data feature set through the PSI privacy intersection service on the APP; Module M2.2: Performs privacy intersection calculations between the pruned data and the server; Module M2.3: View the platform system's recommendation result set and verify whether the server has stored the user's private data.

4. The self-data monitoring system of the privacy recommendation system according to claim 3, characterized in that: In module M2.3, if a product with a deleted feature set is received, it is determined that the server saves the PSI privacy calculation result each time, generates a warning message and notifies the user.

Images