Data privacy protection query method, device, storage medium and electronic device

By clustering, feature extraction and fusion of basic data, and distributed storage in terminals and clouds, the problem of insufficient security of system data and user privacy data in electronic devices is solved, and effective protection of data security is achieved.

CN111797422BActive Publication Date: 2024-12-03GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201910282034.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-04-09
Publication Date
2024-12-03
Estimated Expiration
2039-04-09

AI Technical Summary

Technical Problem

The prior art is difficult to ensure the security of system data and user privacy data in electronic devices at the same time, especially in the data processing process of terminals and clouds, where data leakage and insufficient security are problems.

Method used

By clustering, feature extraction and fusion of basic data, the third data is formed and stored at the terminal, and distributed storage is performed in the cloud, and multiple child nodes in the distributed storage database are used for data extraction and matching, avoiding direct Operate plain text data to ensure data security.

Benefits of technology

It effectively protects the security of terminal system data and user privacy data, avoids data leakage, and improves the security of cloud systems and the protection level of user privacy data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111797422B_ABST
    Figure CN111797422B_ABST
Patent Text Reader

Abstract

The embodiment of the present application discloses a data privacy protection query method, device, storage medium and electronic device. The data privacy protection query method includes: obtaining the first data, second data and third data of the basic data, and storing them in the terminal; obtaining the basic data information of the terminal; distributing and storing the basic data information in the cloud to obtain a distributed storage database; when obtaining the user's query instruction, extracting the basic data information in the distributed storage database; matching the basic data information in the terminal to obtain the target basic data. The embodiment of the present application extracts and fuses the key features of the basic data through a three-level storage method. When operating the data, the first data is not transmitted to the cloud, and the second and third data are extracted and transmitted to the cloud, thereby avoiding the user's privacy data from being exposed in the cloud, and effectively protecting the security of the system data and the security of the user's privacy data in the terminal and the cloud.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of electronic technology, and in particular to a data privacy protection query method, device, storage medium and electronic device. Background Art

[0002] With the advancement of electronic technology, electronic devices such as smartphones are becoming increasingly intelligent. These devices can process data using a variety of algorithms and models, providing users with a wide range of functions. For electronic devices that collect large amounts of data, the security of both system data and user privacy is crucial. Summary of the Invention

[0003] The embodiments of the present application provide a data privacy protection query method, device, storage medium and electronic device, which can balance the security of system data and the security of user privacy data in the terminal and the cloud.

[0004] An embodiment of the present application provides a data privacy protection query method, which is applied to an electronic device. The data privacy protection query method includes:

[0005] Clustering basic data to obtain first data, performing feature extraction on the first data to obtain second data, fusing multiple pieces of the second data to obtain third data, and storing the first data, the second data, and the third data in a terminal;

[0006] Acquire basic data information of the terminal, where the basic data information is basic data information of the second data and the third data;

[0007] Distributed storage of the basic data information is performed in the cloud to obtain a distributed storage database, wherein the distributed storage database includes a plurality of distributed storage sub-nodes;

[0008] When a query instruction from a user is obtained, the basic data information is extracted from the distributed storage database according to the query instruction;

[0009] The basic data information is matched at the terminal to obtain target basic data.

[0010] The present application also provides a data privacy protection query device, including:

[0011] a processing module, configured to cluster basic data to obtain first data, perform feature extraction on the first data to obtain second data, fuse multiple pieces of the second data to obtain third data, and store the first data, the second data, and the third data in a terminal;

[0012] an acquisition module, used to acquire basic data information of the terminal, wherein the basic data information is basic data information of the second data and the third data;

[0013] A storage module is used to perform distributed storage of the basic data information in the cloud to obtain a distributed storage database, wherein the distributed storage database includes multiple distributed storage sub-nodes;

[0014] An extraction module is used to extract the basic data information from the distributed storage database according to the query instruction when obtaining the user's query instruction;

[0015] The matching module is used to match the basic data information on the terminal to obtain target basic data.

[0016] An embodiment of the present application further provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed on a computer, causes the computer to perform the following steps:

[0017] Clustering basic data to obtain first data, performing feature extraction on the first data to obtain second data, fusing multiple pieces of the second data to obtain third data, and storing the first data, the second data, and the third data in a terminal;

[0018] Acquire basic data information of the terminal, where the basic data information is basic data information of the second data and the third data;

[0019] Distributed storage of the basic data information is performed in the cloud to obtain a distributed storage database, wherein the distributed storage database includes a plurality of distributed storage sub-nodes;

[0020] When a query instruction from a user is obtained, the basic data information is extracted from the distributed storage database according to the query instruction;

[0021] The basic data information is matched at the terminal to obtain target basic data.

[0022] An embodiment of the present application further provides an electronic device, wherein the electronic device includes a processor and a memory, wherein the memory stores a computer program, and the processor calls the computer program stored in the memory to perform the following steps:

[0023] Clustering basic data to obtain first data, performing feature extraction on the first data to obtain second data, fusing multiple pieces of the second data to obtain third data, and storing the first data, the second data, and the third data in a terminal;

[0024] Acquire basic data information of the terminal, where the basic data information is basic data information of the second data and the third data;

[0025] Distributed storage of the basic data information is performed in the cloud to obtain a distributed storage database, wherein the distributed storage database includes a plurality of distributed storage sub-nodes;

[0026] When a query instruction from a user is obtained, the basic data information is extracted from the distributed storage database according to the query instruction;

[0027] The basic data information is matched at the terminal to obtain target basic data. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] To more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present application. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0029] Figure 1 Schematic diagram of an application scenario of the data privacy protection query method provided in an embodiment of the present application.

[0030] Figure 2 This is a schematic diagram of the first flow chart of the data privacy protection query method provided in an embodiment of the present application.

[0031] Figure 3 A schematic diagram of another application scenario of the data privacy protection query method provided in an embodiment of the present application.

[0032] Figure 4 This is a second flow chart of the data privacy protection query method provided in an embodiment of the present application.

[0033] Figure 5 A schematic diagram of the structure of a data privacy protection query device provided in an embodiment of the present application.

[0034] Figure 6 Another structural diagram of the data privacy protection query device provided in an embodiment of the present application.

[0035] Figure 7 This is another structural diagram of the data privacy protection query device provided in an embodiment of the present application.

[0036] Figure 8 This is another structural diagram of the data privacy protection query device provided in an embodiment of the present application.

[0037] Figure 9 This is a schematic diagram of the first structure of the electronic device provided in an embodiment of the present application.

[0038] Figure 10 A second structural diagram of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0040] refer to Figure 1 , Figure 1 A schematic diagram illustrating an application scenario of the data privacy protection query method provided in an embodiment of the present application. The data privacy protection query method is applied to an electronic device. The electronic device is provided with a panoramic perception architecture. The panoramic perception architecture is an integrated hardware and software framework for implementing the data privacy protection query method in the electronic device.

[0041] Among them, the panoramic perception architecture includes information perception layer, data processing layer, feature extraction layer, scenario modeling layer and intelligent service layer.

[0042] The information perception layer is used to obtain information about the electronic device itself and / or information from the external environment. The information perception layer may include multiple sensors. For example, the information perception layer may include a distance sensor, a magnetic field sensor, a light sensor, an accelerometer, a fingerprint sensor, a Hall effect sensor, a position sensor, a gyroscope, an inertial sensor, a posture sensor, a barometer, a heart rate sensor, and other sensors.

[0043] Among them, the distance sensor can be used to detect the distance between the electronic device and an external object. The magnetic field sensor can be used to detect the magnetic field information of the electronic device's environment. The light sensor can be used to detect the light information of the electronic device's environment. The acceleration sensor can be used to detect the acceleration data of the electronic device. The fingerprint sensor can be used to collect the user's fingerprint information. The Hall sensor is a magnetic field sensor made based on the Hall effect and can be used to achieve automatic control of the electronic device. The position sensor can be used to detect the current geographical location of the electronic device. The gyroscope can be used to detect the angular velocity of the electronic device in various directions. The inertial sensor can be used to detect the motion data of the electronic device. The attitude sensor can be used to sense the attitude information of the electronic device. The barometer can be used to detect the air pressure of the electronic device's environment. The heart rate sensor can be used to detect the user's heart rate information.

[0044] The data processing layer is used to process the data obtained by the information perception layer. For example, the data processing layer can perform data cleaning, data integration, data transformation, data reduction, etc. on the data obtained by the information perception layer.

[0045] Data cleaning refers to the cleaning of large amounts of data acquired by the information perception layer to eliminate invalid and duplicate data. Data integration involves integrating multiple single-dimensional data acquired by the information perception layer into a higher or more abstract dimension for comprehensive processing. Data transformation involves converting the data type or format of the data acquired by the information perception layer to meet processing requirements. Data reduction involves maximizing the reduction of data while preserving its original appearance as much as possible.

[0046] The feature extraction layer is used to extract features from the data processed by the data processing layer. The extracted features can reflect the state of the electronic device itself, the state of the user, or the environmental state of the electronic device.

[0047] Among them, the feature extraction layer can extract features or process the extracted features through methods such as filtering, packaging, and integration.

[0048] Filtering involves filtering extracted features to remove redundant feature data. Wrapping is used to filter extracted features. Integration combines multiple feature extraction methods to create a more efficient and accurate feature extraction method.

[0049] The scenario modeling layer is used to construct a model based on the features extracted by the feature extraction layer. The resulting model can be used to represent the state of the electronic device, the user, or the environment. For example, the scenario modeling layer can construct a key-value model, a pattern identification model, a graph model, an entity relationship model, an object-oriented model, etc. based on the features extracted by the feature extraction layer.

[0050] The intelligent service layer is used to provide intelligent services to users based on the models built by the scenario modeling layer. For example, the intelligent service layer can provide users with basic application services, perform intelligent system optimization for electronic devices, and provide users with personalized intelligent services.

[0051] Furthermore, the panoramic perception architecture can include multiple algorithms, each of which can be used to analyze and process data. These algorithms can form an algorithm library. For example, the algorithm library may include Markov algorithms, latent Dirichlet distribution algorithms, Bayesian classification algorithms, support vector machines, K-means clustering algorithms, K-nearest neighbor algorithms, conditional random fields, residual networks, long short-term memory networks, convolutional neural networks, and recurrent neural networks.

[0052] The present invention provides a data privacy protection query method that can be applied to electronic devices. The electronic devices may include smartphones, tablet computers, gaming devices, AR (augmented reality) devices, automobiles, data privacy protection query devices, audio and video playback devices, laptops, desktop computing devices, and wearable devices such as watches, glasses, helmets, electronic bracelets, electronic necklaces, and electronic clothing.

[0053] The data privacy protection query method provided in the embodiment of the present application can be used in the architecture of the above-mentioned panoramic perception framework, involving a panoramic perception architecture including an information perception layer, a data processing layer and a feature extraction layer.

[0054] refer to Figure 2 , Figure 2 This is a first flow chart of the data privacy protection query method provided in the embodiment of the present application. The data privacy protection query method includes the following steps:

[0055] 110 , clustering basic data to obtain first data, extracting features from the first data to obtain second data, fusing multiple pieces of second data to obtain third data, and storing the first data, the second data, and the third data in a terminal.

[0056] In this step, the first data may be the basic data after clustering; the second data may be the panoramic information features; and the third data may be the fused feature data.

[0057] Basic data may include electronic device operating information, electronic device configuration information, user information, current environment information, and more. Specifically, basic data can be collected via one or more sensors, or in real time. For example, current environment information and electronic device-related information can be acquired via at least one of a distance sensor, magnetic field sensor, light sensor, accelerometer, fingerprint sensor, Hall effect sensor, position sensor, gyroscope, inertial sensor, attitude sensor, barometer, blood pressure sensor, pulse sensor, and heart rate sensor. Current environment information includes user physical information such as blood pressure, pulse, and heart rate. Electronic device-related information includes electronic device operating information, electronic device configuration information, and user information stored within the electronic device. User information includes user identity information, personal preferences, browsing history, personal favorites, and other human-computer interaction information. Electronic device operating information includes power-on time, power-off time, standby time, memory usage at various points in time, main chip usage at various points in time, information about currently running programs, information about background running programs, the runtime of each program, and the number of downloads of each program. In some embodiments, basic data may also include user terminal operation behavior data, sensor data, and terminal system operation data.

[0058] After obtaining multiple basic data, they can be stored in the first storage module. For example, multiple panoramic perception information can be stored in a hard disk. Among them, multiple databases can be set up, and their basic data can be stored in corresponding databases according to categories.

[0059] The basic data is clustered to obtain the first data. The first data may be the clustered basic data. Basic data of the same type are aggregated together to form a data set, thereby obtaining multiple data sets of multiple categories of basic data. The basic data can be classified according to the hardware attributes of the data, such as data related to the main chip, data related to the display screen, data related to the hard disk, data related to the memory, data related to various sensors, etc. The basic data can also be classified according to the corresponding applications, such as data related to system applications and data related to installed applications; the data related to installed applications can be further classified according to specific applications, such as data related to instant messaging applications, data related to map applications, data related to shopping applications, etc. The basic data is stored in the corresponding database according to the category, which effectively isolates irrelevant data and enables the data to be stored independently. In some embodiments, obtaining the time series index corresponding to each database can also facilitate the indexing of the basic data.

[0060] The data format and content of each type of primary data can vary. For example, sensor data contains very limited Wi-Fi connection information; when there's no Wi-Fi signal, no Wi-Fi information is stored. In contrast, IMU data is transmitted back at a frequency of one hertz per second, allowing for up to several gigabytes of data to be stored daily. Feature extraction of basic database data helps reduce redundant information and save storage space while also effectively extracting important insights from the data. For example, audio data is time-series information, and as time passes, the volume of audio data continues to grow. Therefore, feature extraction is necessary to reduce the data volume. For example, with dual microphone channels, a 32-bit bit width, and a sampling frequency of 44100, five minutes of audio data generates approximately one gigabyte of data. Feature extraction yields the key features for each time window, which can be stored as vectors. This allows one gigabyte of data to be compressed to a few hundred kilobytes.

[0061] The same type of basic data is queried in the same database with data privacy protection. One basic data item can be stored in one database. For example, accelerometer data is only stored in the accelerometer database. One basic data item can also be stored in multiple databases. For example, when a basic data item belongs to two categories, the basic data item can be copied and the copied basic data and the original basic data can be stored in two databases respectively. The two databases correspond to the two categories to which the basic data item belongs. It should be noted that the database can store not only the currently acquired panoramic perception information, but also the previously stored panoramic perception information.

[0062] Feature extraction is performed on the first data to obtain second data, which may be panoramic information features. Feature extraction is performed on the basic data of the database to obtain panoramic information features corresponding to each database, and the panoramic information features are stored a second time. The second data does not need to contain a large amount of original basic data, but only needs to contain the corresponding panoramic information features. Feature extraction is performed on the first data to effectively extract the important features of the first data, reduce the redundant information of the original basic data, and save storage space. Compared with the original basic data and the first data, the amount of second data is greatly reduced. It should be noted that feature extraction of the first data of the database and storage of the extracted second data can also avoid directly storing the original data format, strictly control information security, and protect user privacy. By extracting features from the basic data of the database, the source data can be desensitized, and user data desensitized by the feature layer can be effectively recorded, reducing data redundancy and facilitating subsequent use.

[0063] Perform separate feature extraction on the data in each database to obtain the panoramic information features corresponding to each database. Feature extraction layers can be set up to extract features from the basic data in multiple ways, and different feature extraction methods can be used for different data.

[0064] In some embodiments, a manually pre-defined method is used to extract features from the basic data in the database, pre-setting important features for each category of basic data. The basic data is clustered and stored in corresponding databases. The basic data in the same database are then identified for the same important features. The pre-defined important features are extracted and mapped to specific data items of each basic data item as panoramic information features, which are then stored a second time.

[0065] In some embodiments, a method of pre-training a machine learning model is used to extract features from the basic data of the database. The steps of extracting features from the basic data of the database to obtain the panoramic information features corresponding to each database may specifically include: pre-training the machine learning model to obtain a machine learning model that matches the basic data; inputting the basic data into the machine learning model, obtaining the model output, and using the model output as the panoramic information features.

[0066] The plurality of second data are fused to obtain third data. The third data may be fused feature data. Specifically, the panoramic information features may be fused using a multi-table join method, or a time series alignment method, or a combination of multi-table join and time series alignment. Since most of the data on the terminal is time series data, that is, the user's operations and terminal scenarios at different time points are different and change over time, fusing the second data can further reduce the asymmetry between the data and compress the data volume.

[0067] The panoramic information features are fused to obtain fused feature data, which is then stored a third time in a third storage unit. This cascaded storage method effectively provides disaster recovery backup for data, avoiding the storage and transmission of plaintext data. A unique feature extraction step extracts high-dimensional features from the basic data (equivalent to encrypting the basic data), effectively protecting user privacy information.

[0068] The first data, the second data, and the third data are stored in the terminal, and the storage method can be a triggered data return method, that is, the data return method can be a triggered return method. For example, for the network module, when the WIFI function is turned on, it searches for nearby available networks. At this time, the data detected by the network module is transmitted to the system. When the system collects basic data, it monitors and collects system notification messages.

[0069] In some embodiments, the time series index corresponding to each database can also be obtained, and the time series index corresponding to each database can also be stored in a second storage module (such as a memory) so that other modules of the system can find the corresponding basic data in the database according to the time series index. The multi-source heterogeneous basic data are clustered in time series by clustering, which effectively compresses the original basic data, reduces the redundant information of the basic data, and realizes the real-time indexing and access of the basic data. The computing resources and storage resources of electronic devices are limited. Reasonable access and allocation of basic data can speed up the retrieval of panoramic perception information.

[0070] 120. Obtain basic data information of the terminal, where the basic data information is basic data information of the second data and the third data.

[0071] After extracting the second and third data from the terminal, they are transmitted to the cloud. Using the smart mobile terminal device as a client, the second and third data are uploaded to the cloud server cluster. The data can be encapsulated using the TCP / IP protocol and uploaded to the server cluster as streaming data. Through the cloud server cluster, data at all levels can be indexed.

[0072] Obtain basic data information of the terminal in the cloud. The basic data information is basic data information of the second data and the third data. The basic data information can be the second data and the third data themselves, or an index table of the second data and the third data. In other words, the basic data information in the cloud corresponds to the second data and the third data of the terminal, and the second data and the third data of the terminal can be obtained based on the basic data information.

[0073] 130 , performing distributed storage on the cloud for basic data information to obtain a distributed storage database, wherein the distributed storage database includes a plurality of distributed storage sub-nodes.

[0074] Distributed storage is a data privacy-preserving query technology that utilizes the disk space on every machine in an enterprise over a network, combining these dispersed storage resources into a virtual storage device. Data is stored in various locations throughout the enterprise. Distributed storage can share the storage load, improving system reliability, availability, and access efficiency while also facilitating scalability.

[0075] Distributed storage technology may include storing files multiple times on multiple machines, which will disperse the burden and risk of data privacy protection queries. The more copies of a file there are, the less likely it is to be lost. However, the more copies there are, the more places they can be stolen, so an encryption system is needed for sensitive data or environments. In some embodiments, the data distributedly stored in the cloud is basic data information, which does not include the original basic data, nor does it include the first data obtained by clustering the original data. It may include the second data obtained by feature extraction of the first data, and may include the third data obtained by fusing the second data. The basic data information is distributedly stored in the cloud to obtain a distributed storage database. Since the storage and processing of the original basic data are not involved in the cloud, the distributed storage method can ensure a high level of security while ensuring performance.

[0076] Traditional distributed storage is essentially a centralized system that stores data across multiple independent devices, employing a scalable system architecture, utilizing multiple storage servers to share the storage load, and using location servers to locate stored information. Network-based distributed storage, a core technology of blockchain, addresses the challenges of traditional distributed storage by integrating privacy-preserving data queries into blocks and establishing a distributed database through the storage space of open nodes.

[0077] A node is a network node in a blockchain distributed system, which is a server, computer, phone, etc. connected through a network. The way to become a node will also be different for blockchains of different natures.

[0078] A distributed storage database contains multiple distributed storage subnodes. In the cloud, these subnodes can be divided into clusters based on their corresponding data categories. For example, these subnodes can be grouped into user clusters, secondary feature clusters, and tertiary feature clusters. User clusters contain a large amount of user information, and the distributed storage subnodes in these clusters can correspond to individual user information, such as the unique identifier of the terminal and the physical address of the server for privacy-preserving queries on user data across different terminals. Secondary and tertiary feature clusters can be retrieved and queried using user clusters.

[0079] Secondary and tertiary feature clusters are clusters of basic data information corresponding to the second and third data. The basic data information can be the second and third data themselves, or information that can be used to match the second and third data, such as an index table corresponding to the second and third data. The distributed storage subnodes in the secondary and tertiary feature clusters can correspond to the basic data information of each user, allowing the basic data information to be extracted based on the distributed storage subnodes.

[0080] 140. When a query instruction from a user is obtained, basic data information is extracted from a distributed storage database according to the query instruction.

[0081] Obtaining a user's query command includes directly obtaining the user's query command in the cloud, or transmitting the query command to the cloud after the terminal obtains the user's query command. The query command carries the user's unique identifier and the data to be queried. When the user's query command is obtained, the cloud determines the corresponding distributed storage database for the user based on the user's unique identifier carried in the query command. This distributed database contains a distributed storage subnode that contains the user's basic data information.

[0082] In some embodiments, basic data information is extracted from a distributed storage database according to a query instruction, including: obtaining a user's query instruction, the query instruction carrying the user's unique identifier and the data to be queried; determining a target distributed storage database corresponding to the user based on the unique identifier; determining a distributed storage sub-node corresponding to the data to be queried in the target distributed storage database, and extracting basic data information based on the distributed storage sub-node.

[0083] It should be noted that the data to be queried can be the first data, the second data or the third data, or the user information data, etc. Different query methods may be used for different data to be queried. For example, when the data to be queried is the first data, the first data to be queried is feature extracted to obtain the second data to be queried corresponding to the first data to be queried; based on the second data to be queried, the distributed storage sub-node corresponding to the second data to be queried is determined in the target distributed storage database; and the basic data information is extracted based on the distributed storage sub-node. For another example, when the data to be queried is the second data or the third data, the distributed storage sub-node corresponding to the data to be queried is determined in the target distributed storage database; and the basic data information is extracted based on the distributed storage sub-node. For another example, when the data to be queried is user information data, etc., the distributed storage sub-node corresponding to the user information data to be queried is determined in the distributed storage database, and the user information data is extracted based on the distributed storage sub-node.

[0084] Those skilled in the art should know that in the process of extracting basic data information from a distributed storage database according to a query instruction, there may be multiple extraction methods. The above description is merely an exemplary description and should not constitute a limitation to this application.

[0085] The extracted basic data information corresponding to the user's query instruction may include the data to be queried itself, or may include relevant information that can match the data to be queried. For example, when the query instruction is first data, the basic data information includes relevant information that can match the first data to be queried. For example, it may include corresponding second data, or may include relevant information that can match the corresponding second data. When the query instruction is second data, the basic data information may include corresponding second data, or may include relevant information that can match the corresponding second data.

[0086] It should be noted that the data to be queried can be one type of data or multiple types of data. For example, it can include user information data to be queried and second data. The data to be queried can be data of a certain level or multiple levels of data. For example, the second data and the third data can be queried at the same time, or the first data and the second data can be queried at the same time, and so on. In some embodiments, a query instruction of the user is obtained, and the query instruction carries the user's unique identifier and multiple data to be queried. After determining the target distributed storage database corresponding to the user based on the unique identifier, the types of the multiple data to be queried are determined, and corresponding query methods are executed respectively corresponding to the types of the multiple data to be queried. If the multiple data to be queried belong to the same type, the query order of the multiple data to be queried is determined, and the data to be queried is queried in order.

[0087] 150, matching the basic data information on the terminal to obtain target basic data.

[0088] If step 140 includes the cloud's feedback on the user's query command, then step 150 includes the information connection between the cloud and the terminal. After the cloud extracts basic data information based on the data to be queried, the basic data information is matched with the data stored in the terminal to obtain the data to be queried required by the user.

[0089] When the data to be queried is second data, the basic data information is matched with the second data of the terminal to obtain the target second data; when the data to be queried is third data, the basic data information is matched with the second data of the terminal to obtain the target third data. When the data to be queried is first data, the basic data information can be matched with the second data of the terminal to obtain the target second data, and the target first data can be searched in the terminal based on the target second data. In some embodiments, a matching mapping or retrieval table corresponding to the basic data information and the first data of the terminal is pre-set in the cloud. In this case, the basic data information can also be directly matched with the first data of the terminal to obtain the target first data.

[0090] It should be noted that in order to identify different terminals in the cloud, the cloud itself may store user information data or related data corresponding to the user information data, such as a unique user identifier. To distinguish different user terminals, the user information data can be extracted when the terminal's basic data information is obtained. When the user queries the target data, the target data obtained from the query and the terminal's user information data are fed back to the user together.

[0091] refer to Figure 3 , Figure 3This diagram illustrates another application scenario for the data privacy protection query method provided in an embodiment of the present application. The basic data may be sourced from user behavior data, sensor data, and system operation data. Specifically, the basic data may be acquired through sensors, etc. Subsequently, the multiple basic data are clustered to obtain first data, which is then stored. The first data includes basic data such as user behavior data, sensor data, and system operation data.

[0092] Subsequently, the feature extraction module extracts features from the first data, extracts important features of the first data as second data, and stores the second data. The second data includes panoramic information features such as user behavior features, sensor features, ..., and system features.

[0093] The third data may be a fused panoramic feature obtained by fusing the panoramic information feature of the second data, and the fused panoramic feature is stored.

[0094] It should be noted that the first data, the second data and the third data are all stored in the terminal to ensure that the original data will not be lost.

[0095] After obtaining the third data, the second and third data can be uploaded to the cloud and provided to the server for data analysis. Alternatively, the second and third data can be transmitted to the application service layer or data processing layer for calculation. In addition, the second and third data can be redundantly backed up to increase data redundancy and effectively prevent data loss.

[0096] In some embodiments, features are extracted from the second data and the third data and transmitted to the cloud, where corresponding secondary feature masters and tertiary feature masters are respectively provided. A user master is also provided in the cloud. The user master records a large amount of user information to facilitate subsequent indexing of the user information. The secondary feature master and the tertiary feature master can be retrieved and queried through the user master. The master can be a single server or a server cluster. Its main responsibility is to maintain the physical address table and logical address table of the storage server cluster and the processing server, so as to facilitate the storage and processing distribution of the input data allocation server. Each master is responsible for maintaining the index table, but may not actually store the actual data. The advantage of its design is that it uses a distributed storage method to store and maintain Nanjing information. The advantage of distributed storage is that it supports high-performance reading and writing, multi-copy consistency, facilitates disaster recovery and backup of data, elastic expansion of server nodes, and standardization of storage systems.

[0097] When the server's panoramic perception modeling layer needs to use secondary features and tertiary features, by sending a request to the user master, the secondary feature data or tertiary feature data corresponding to the user can be obtained from the child node of the distributed database.

[0098] In some embodiments, the indexing method for indexing the first data, the second data, or the third data can be a CG-Index method. The basic idea is that each node is responsible for maintaining a local B+ tree and a global CG-index index table. By accessing the CG-index index table, it can be determined which nodes need to query the local index, which can support high-performance random reading and writing. CG-index treats the index as another form of data and stores it in a table. It uses a complementary checksum table instead of an ordinary table to achieve index fault tolerance and recovery, reducing the storage overhead of the index.

[0099] refer to Figure 4 , Figure 4 This is a second flow chart of the data privacy protection query method provided in the embodiment of the present application. The data privacy protection query method includes the following steps:

[0100] 210. Cluster the basic data to obtain first data, extract features from the first data to obtain second data, fuse multiple second data to obtain third data, and store the first data, second data, and third data in the terminal.

[0101] The basic data includes but is not limited to user behavior data, sensor data, system operation data, etc., and the terminal stores first data, second data, and third data of the basic data.

[0102] The primary storage module stores the first data as data in the primary storage database. It is worth noting that since the database involves user core data and user privacy data, it is only stored and backed up locally on the terminal and will not be uploaded to the server.

[0103] Secondary storage module: The secondary storage extracts high-dimensional features from the primary data independent database, effectively reducing data redundancy and desensitizing the source data.

[0104] The tertiary storage module mainly integrates the second data with independent features. Specifically, it performs table join operations on the secondary storage database, merges data dimensions with the same time series, and integrates panoramic features.

[0105] 220. Set unique identifiers for different terminals to distinguish them.

[0106] The terminal's secondary and tertiary storage information is transferred to the cloud, and the user's device information is tagged to distinguish them from other users. Different users store different data in the cloud. By setting a unique identifier for each terminal, different terminals can be distinguished, allowing the user's corresponding data to be accurately found when extracting and matching data.

[0107] 230. Obtain basic data information of the terminal, where the basic data information is basic data information of the second data and the third data.

[0108] Obtain basic data information of the terminal in the cloud. The basic data information is basic data information of the second data and the third data. The basic data information can be the second data and the third data themselves, or an index table of the second data and the third data. In other words, the basic data information in the cloud corresponds to the second data and the third data of the terminal, and the second data and the third data of the terminal can be obtained based on the basic data information.

[0109] 240. Distributed storage is performed on the basic data information in the cloud to obtain a distributed storage database, which includes multiple distributed storage sub-nodes.

[0110] A distributed storage database contains multiple distributed storage subnodes. In the cloud, these subnodes can be divided into clusters based on their corresponding data categories. For example, these subnodes can be grouped into user clusters, secondary feature clusters, and tertiary feature clusters. User clusters contain a large amount of user information, and the distributed storage subnodes in these clusters can correspond to individual user information, such as the unique identifier of the terminal and the physical address of the server for privacy-preserving queries on user data across different terminals. Secondary and tertiary feature clusters can be retrieved and queried using user clusters.

[0111] Secondary and tertiary feature clusters are clusters of basic data information corresponding to the second and third data. The basic data information can be the second and third data themselves, or information that can be used to match the second and third data, such as an index table corresponding to the second and third data. The distributed storage subnodes in the secondary and tertiary feature clusters can correspond to the basic data information of each user, allowing the basic data information to be extracted based on the distributed storage subnodes.

[0112] 250. Obtain the user's query instruction, where the query instruction carries the user's unique identifier and the data to be queried.

[0113] Obtaining the user's query instruction includes directly obtaining the user's query instruction in the cloud, and also includes transmitting the query instruction to the cloud after the terminal obtains the user's query instruction. The query instruction carries the user's unique identifier and the data to be queried.

[0114] 260. Determine the target distributed storage database corresponding to the user based on the unique identifier.

[0115] When a user's query instruction is obtained, the distributed storage database corresponding to the user is determined in the cloud according to the user's unique identifier carried in the query instruction. The distributed database contains a distributed storage sub-node containing the user's basic data information.

[0116] 270. Determine whether the data to be queried is the first data.

[0117] It should be noted that the data to be queried can be first data, second data, third data, user information data, and so on. Different query methods can be used for different types of data to be queried. Because the first data involves the underlying raw data, to protect user privacy, the first data is not transmitted to the cloud. Determining whether the queried data is first data helps to respond to the query instruction according to different situations.

[0118] Those skilled in the art should know that in the process of extracting basic data information from a distributed storage database according to a query instruction, there may be multiple extraction methods. The above description is merely an exemplary description and should not constitute a limitation to this application.

[0119] The data to be queried can be one type of data or multiple types of data. For example, it can include user information data to be queried and the second data. The data to be queried can be data of a certain level or multiple levels of data. For example, the second data and the third data can be queried at the same time, or the first data and the second data can be queried at the same time, and so on. In some embodiments, the user's query instruction is obtained, and the query instruction carries the user's unique identifier and multiple data to be queried. After determining the target distributed storage database corresponding to the user based on the unique identifier, the types of the multiple data to be queried are determined, and corresponding query methods are executed respectively corresponding to the types of the multiple data to be queried. If the multiple data to be queried belong to the same type, the query order of the multiple data to be queried is determined, and the query data to be queried is judged to be the first data in order. When it is judged that the data to be queried is the first data, the query steps corresponding to the first data are executed in order; when it is judged that the data to be queried is not the first data, the query steps corresponding to when the data to be queried is not the first data are executed in order.

[0120] 281. If not, determine the distributed storage sub-node corresponding to the data to be queried in the target distributed storage database.

[0121] 282. Match the basic data information with the data stored in the terminal to obtain the target data.

[0122] When the data to be queried is second data or third data, a distributed storage subnode corresponding to the second data or third data is determined in the target distributed storage database; and basic data information is extracted from the distributed storage subnode. For another example, when the data to be queried is user information data, a distributed storage subnode corresponding to the user information data to be queried is determined in the distributed storage database, and the user information data is extracted from the distributed storage subnode.

[0123] 291. If yes, perform feature extraction on the first data to be queried to obtain second data to be queried corresponding to the first data to be queried.

[0124] Since the first data and the panoramic information features corresponding to the first data are not stored in the cloud, the features of the first data to be queried can be extracted first to obtain the second data to be queried corresponding to the first data to be queried, and the second data can be queried to find the corresponding first data based on the second data.

[0125] 292. According to the second data to be queried, determine a distributed storage sub-node corresponding to the second data to be queried in the target distributed storage database, and extract basic data information according to the distributed storage sub-node.

[0126] It should be noted that the third data to be queried can also be obtained by fusing panoramic features based on the second data to be queried. In step 292, based on the third data to be queried, the distributed storage sub-node corresponding to the third-level data to be queried is determined in the target distributed storage database, and basic data information is extracted based on the distributed storage sub-node.

[0127] 293. Match the basic data information with the second data of the terminal to obtain target second data.

[0128] 294. Search for the target first data in the terminal according to the target second data.

[0129] When the data to be queried is second data, the basic data information is matched with the second data of the terminal to obtain the target second data; when the data to be queried is third data, the basic data information is matched with the second data of the terminal to obtain the target third data. When the data to be queried is first data, the basic data information can be matched with the second data of the terminal to obtain the target second data, and the target first data can be searched in the terminal based on the target second data. In some embodiments, a matching mapping or retrieval table corresponding to the basic data information and the first data of the terminal is pre-set in the cloud. In this case, the basic data information can also be directly matched with the first data of the terminal to obtain the target first data.

[0130] In some embodiments, the data privacy protection query method may specifically include: first, obtaining information about the user's electronic device through the information perception layer (specifically including electronic device operation information, user behavior information, information obtained by various sensors, electronic device status information, electronic device display content information, electronic device download information, etc.), and then processing the information of the electronic device through the data processing layer (such as classification, etc.), and then extracting the second data and the third data from the information processed by the data processing layer through the feature extraction layer (the second data and the third data can be specifically referred to the description of the above embodiment), and then processing the second data and the third data, uploading the target model parameters to the server for storage through the storage module. The server does not receive the first data based on the protection data. When you want to query the first data, you can query the relevant data of the second data and the third data in the server and then correspond to the first data, thereby avoiding operations on plaintext data.

[0131] As can be seen from the above, the data privacy protection query method provided by the embodiment of the present application first clusters the basic data to obtain the first data, extracts the features of the first data to obtain the second data, fuses the multiple second data to obtain the third data, and stores the first data, the second data and the third data in the terminal; then obtains the basic data information of the terminal, which is the basic data information of the second data and the third data; then distributes the basic data information in the cloud to obtain a distributed storage database, which contains multiple distributed storage sub-nodes; then, when the user's query instruction is obtained, the basic data information is extracted from the distributed storage database according to the query instruction; finally, the basic data information is matched in the terminal to obtain the target basic data. Through the three-level storage method, the key features of the basic data are extracted and fused, and when operating the data, direct operations on the plaintext data are avoided, which effectively protects the security of the terminal system data and the security of the user's privacy data. The first data is not transmitted to the cloud, and the second and third data are extracted and transmitted to the cloud, thereby avoiding the exposure of the user's privacy data to the cloud, further protecting the security of the cloud system data and the security of the user's privacy data.

[0132] refer to Figure 5 , Figure 5 Schematic diagram of the structure of the data privacy protection query device provided in an embodiment of the present application. The data privacy protection query device 300 can be integrated into an electronic device and includes a processing module 301, an acquisition module 302, a storage module 303, an extraction module 304, and a matching module 305.

[0133] Processing module 301, configured to cluster basic data to obtain first data, extract features from the first data to obtain second data, fuse multiple pieces of second data to obtain third data, and store the first data, second data, and third data in a terminal;

[0134] An acquisition module 302 is configured to acquire basic data information of the terminal, where the basic data information is basic data information of the second data and the third data;

[0135] The storage module 303 is used to perform distributed storage of basic data information in the cloud to obtain a distributed storage database, which includes multiple distributed storage sub-nodes;

[0136] The extraction module 304 is used to extract basic data information from the distributed storage database according to the query instruction when obtaining the user's query instruction;

[0137] The matching module 305 is used to match the basic data information at the terminal to obtain target basic data.

[0138] Please also refer to Figure 6 , Figure 6 Another structural diagram of the data privacy protection query device provided in an embodiment of the present application. In some embodiments, the first data, the second data, and the third data in the processing module 301 are stored in the terminal. The processing module 301 may include a first storage unit 3011, a second storage unit 3012, and a third storage unit 3013.

[0139] The first storage unit 3011 is used to cluster the basic data to obtain first data, and to store the first data for the first time in a corresponding database;

[0140] The second storage unit 3012 is used to extract features of basic data from the database to obtain panoramic information features corresponding to each database, use the panoramic information features as second data, and store the second data for a second time;

[0141] In some embodiments, the second storage unit is further configured to:

[0142] Pre-training a machine learning model to obtain a machine learning model that matches the first data;

[0143] The first data is input into the machine learning model, the model output result is obtained, and the model output result is used as the second data.

[0144] The third storage unit 3013 is used to fuse the panoramic information features to obtain fused feature data, and store the fused feature data as third data for a third time.

[0145] In some embodiments, the third storage unit 3013 can be specifically used to fuse multiple second data in a multi-table connection and / or time sequence alignment manner to obtain third data, and store the third data for a third time.

[0146] Please also refer to Figure 7 , Figure 7 This is another structural diagram of the data privacy protection query device provided by an embodiment of the present application. In some embodiments, the extraction module 304 may include a query unit 3041 , a determination unit 3042 , and an extraction unit 3043 .

[0147] The query unit 3041 is used to obtain the user's query instruction, which carries the user's unique identifier and the data to be queried;

[0148] The determining unit 3042 is configured to determine the target distributed storage database corresponding to the user according to the unique identifier;

[0149] The extraction unit 3043 is used to determine the distributed storage sub-node corresponding to the data to be queried in the target distributed storage database, and extract basic data information according to the distributed storage sub-node.

[0150] When the data to be queried is the first data, the steps performed by the extraction unit 3043 include: performing feature extraction on the first data to be queried to obtain the second data to be queried corresponding to the first data to be queried; and determining, based on the second data to be queried, a distributed storage sub-node corresponding to the second data to be queried in the target distributed storage database.

[0151] In some embodiments, the extraction module 304 may further include an acquisition unit 3044 for acquiring a data level of the data to be queried, where the data level includes at least first data, second data, and third data.

[0152] Please also refer to Figure 8 , Figure 8 Another structural diagram of the data privacy protection query device provided in an embodiment of the present application. In some embodiments, the matching module 305 may include a first matching unit 3051 , a second matching unit 3052 , and a third matching unit 3053 .

[0153] The first matching unit 3051 is configured to, when the data to be queried is the first data, match the target basic data with the second data of the terminal to obtain the target second data; and search the terminal for the target first data according to the target second data.

[0154] The second matching unit 3052 is configured to match the basic data information with the second data of the terminal to obtain target second data when the data to be queried is the second data.

[0155] The third matching unit 3053 is configured to match the basic data information with the second data of the terminal to obtain target third data when the data to be queried is third data.

[0156] In some embodiments, the apparatus may further include a backup module and a transmission module. The backup module is configured to back up the fused feature data in real time on the terminal. The transmission module is configured to transmit the fused feature data to the application service layer or the data processing layer so that the application service layer or the data processing layer can use the fused information features for calculation.

[0157] As can be seen from the above, the embodiment of the present application provides a data privacy protection query device. First, the processing module 301 clusters the basic data to obtain the first data, extracts features from the first data to obtain the second data, fuses multiple second data to obtain the third data, and stores the first data, second data and third data in the terminal; then the acquisition module 302 obtains the basic data information of the terminal, and the basic data information is the basic data information of the second data and the third data; then the storage module 303 performs distributed storage of the basic data information in the cloud to obtain a distributed storage database, which contains multiple distributed storage sub-nodes; then the extraction module 304 extracts the basic data information in the distributed storage database according to the query instruction when the user's query instruction is obtained; finally, the matching module 305 matches the basic data information in the terminal to obtain the target basic data. Through the three-level storage method, the key features of the basic data are extracted and fused. When operating the data, direct operations on the plaintext data are avoided, which effectively protects the security of the terminal system data and the security of the user's privacy data. The first data is not transmitted to the cloud, and the second data and the third data are extracted and then transmitted to the cloud, thereby preventing the user's privacy data from being exposed in the cloud, and further protecting the security of the cloud system data and the security of the user's privacy data.

[0158] The present application also provides an electronic device. The electronic device may be a smartphone, a tablet computer, a gaming device, an AR (augmented reality) device, an automobile, a data privacy protection query device, an audio player, a video player, a notebook, a desktop computing device, or a wearable device such as a watch, glasses, a helmet, an electronic bracelet, an electronic necklace, or electronic clothing.

[0159] refer to Figure 9 , Figure 9 This is a schematic diagram of a first structure of an electronic device 900 provided in an embodiment of the present application. The electronic device 900 includes a processor 901 and a memory 902. The processor 901 is electrically connected to the memory 902.

[0160] The processor 901 is the control center of the electronic device 900. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or calling computer programs stored in the memory 902 and calling data stored in the memory 902, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole.

[0161] In this embodiment, the processor 901 in the electronic device 900 loads instructions corresponding to one or more computer program processes into the memory 902 according to the following steps, and the processor 901 runs the computer program stored in the memory 902 to implement various functions:

[0162] Clustering basic data to obtain first data, performing feature extraction on the first data to obtain second data, fusing multiple second data to obtain third data, and storing the first data, the second data, and the third data in a terminal;

[0163] Obtaining basic data information of the terminal, where the basic data information is basic data information of the second data and the third data;

[0164] Distributed storage of basic data information in the cloud to obtain a distributed storage database, which includes multiple distributed storage sub-nodes;

[0165] When a user's query instruction is obtained, basic data information is extracted from the distributed storage database according to the query instruction;

[0166] Match the basic data information on the terminal to obtain the target basic data.

[0167] In some embodiments, when extracting features from the first data to obtain the second data, the processor 901 performs the following steps:

[0168] Pre-training a machine learning model to obtain a machine learning model that matches the first data;

[0169] The first data is input into the machine learning model, the model output result is obtained, and the model output result is used as the second data.

[0170] In some embodiments, when fusing multiple second data to obtain third data, the processor 901 performs the following steps:

[0171] The plurality of second data are fused in a manner of multi-table connection and / or time series alignment to obtain third data.

[0172] In some embodiments, when a query instruction from a user is obtained and basic data information is extracted from a distributed storage database according to the query instruction, the processor 901 performs the following steps:

[0173] Obtain the user's query instruction, which carries the user's unique identifier and the data to be queried;

[0174] Determine the target distributed storage database corresponding to the user based on the unique identifier;

[0175] A distributed storage sub-node corresponding to the data to be queried is determined in the target distributed storage database, and basic data information is extracted according to the distributed storage sub-node.

[0176] In some embodiments, before determining the distributed storage sub-node corresponding to the data to be queried in the target distributed storage database, the processor 901 performs the following steps:

[0177] The data level of the data to be queried is obtained, where the data level includes first data, second data, and third data.

[0178] In some embodiments, when the data to be queried is the second data or the third data, the processor 901 performs the following steps:

[0179] Determine the distributed storage subnode corresponding to the data to be queried in the target distributed storage database;

[0180] When the data to be queried is the second data, the basic data information is matched with the second data of the terminal to obtain the target second data;

[0181] When the data to be queried is third data, the basic data information is matched with the second data of the terminal to obtain target third data.

[0182] In some embodiments, when the data to be queried is first data, the processor 901 performs the following steps:

[0183] Extracting features of the first data to be queried to obtain second data to be queried corresponding to the first data to be queried;

[0184] According to the second data to be queried, a distributed storage sub-node corresponding to the second data to be queried is determined in the target distributed storage database.

[0185] In some embodiments, when the data to be queried is first data, when the basic data information is matched on the terminal to obtain target basic data, the processor 901 performs the following steps:

[0186] Matching the target basic data with the second data of the terminal to obtain the target second data;

[0187] The target first data is searched for in the terminal according to the target second data.

[0188] In some embodiments, reference Figure 10 , Figure 10 This is a second structural diagram of the electronic device 900 provided in an embodiment of the present application.

[0189] The electronic device 900 further includes a display screen 903, a control circuit 904, an input unit 905, a sensor 906, and a power supply 907. The processor 901 is electrically connected to the display screen 903, the control circuit 904, the input unit 905, the sensor 906, and the power supply 907.

[0190] The display screen 903 may be used to display information input by a user or information provided to a user, as well as various graphical user interfaces of the electronic device. These graphical user interfaces may be composed of images, texts, icons, videos, and any combination thereof.

[0191] The control circuit 904 is electrically connected to the display screen 903 and is used to control the display screen 903 to display information.

[0192] The input unit 905 may be configured to receive input numbers, characters, or user characteristics (e.g., fingerprints), and generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. The input unit 905 may include a fingerprint recognition module.

[0193] Sensor 906 is used to collect information about the electronic device itself, the user, or the external environment. For example, sensor 906 may include a distance sensor, a magnetic field sensor, a light sensor, an acceleration sensor, a fingerprint sensor, a Hall sensor, a position sensor, a gyroscope, an inertial sensor, a posture sensor, a barometer, a heart rate sensor, and the like.

[0194] The power supply 907 is used to supply power to various components of the electronic device 900. In some embodiments, the power supply 907 can be logically connected to the processor 901 through a power management system, thereby managing charging, discharging, and power consumption through the power management system.

[0195] although Figure 10 Not shown, the electronic device 900 may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0196] As can be seen from the above, an embodiment of the present application provides an electronic device, in which a processor in the electronic device performs the following steps: first, clustering basic data to obtain first data, extracting features from the first data to obtain second data, fusing multiple second data to obtain third data, and storing the first data, second data, and third data in a terminal; then obtaining basic data information of the terminal, which is basic data information of the second data and the third data; then distributing the basic data information in the cloud to obtain a distributed storage database, which includes multiple distributed storage sub-nodes; then, when a user's query instruction is obtained, extracting basic data information from the distributed storage database according to the query instruction; finally, matching the basic data information in the terminal to obtain target basic data. Through the three-level storage method, the key features of the basic data are extracted and fused, and when operating the data, direct operations on plaintext data are avoided, effectively protecting the security of terminal system data and the security of user privacy data. The first data is not transmitted to the cloud, and the second and third data are transmitted to the cloud after extraction, thereby avoiding the exposure of user privacy data to the cloud, further protecting the security of cloud system data and the security of user privacy data.

[0197] An embodiment of the present application further provides a storage medium, in which a computer program is stored. When the computer program runs on a computer, the computer executes the data privacy protection query method of any of the above embodiments.

[0198] For example, in some embodiments, when the computer program is run on a computer, the computer performs the following steps:

[0199] Clustering basic data to obtain first data, performing feature extraction on the first data to obtain second data, fusing multiple second data to obtain third data, and storing the first data, the second data, and the third data in a terminal;

[0200] Obtaining basic data information of the terminal, where the basic data information is basic data information of the second data and the third data;

[0201] Distributed storage of basic data information in the cloud to obtain a distributed storage database, which includes multiple distributed storage sub-nodes;

[0202] When a user's query instruction is obtained, basic data information is extracted from the distributed storage database according to the query instruction;

[0203] Match the basic data information on the terminal to obtain the target basic data.

[0204] It should be noted that, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, which may include but is not limited to: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0205] The above is a detailed introduction to the data privacy protection query method, device, storage medium, and electronic device provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core ideas of the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A data privacy protection query method, wherein: The data privacy protection query method comprises: Perform category clustering and time series clustering on basic data to obtain first data and time series indexes, perform feature extraction on the first data to obtain second data, fuse multiple pieces of the second data based on a multi-table connection method and / or a time series alignment method to obtain third data, store the first data, time series indexes, second data, and third data based on the categories obtained by clustering in the terminal, and each category corresponds to a database; Acquire basic data information of the terminal, where the basic data information is the second data and the third data or an index table of the second data and the third data; Distributed storage is performed on the basic data information in the cloud to obtain a distributed storage database, wherein the distributed storage database includes a plurality of distributed storage sub-nodes; When a query instruction from a user is obtained, the basic data information is extracted from a distributed storage database according to the query instruction; The basic data information is matched in the terminal data based on the time series index to obtain target basic data, wherein the terminal data includes the first data, the second data and the third data.

2. The data privacy protection query method according to claim 1, wherein: Before obtaining the basic data information of the terminal, the method further includes: Unique identifiers are set for different terminals to distinguish different terminals.

3. The data privacy protection query method according to claim 2, wherein: When a query instruction from a user is obtained, extracting the basic data information from a distributed storage database according to the query instruction includes: Obtaining a query instruction from a user, wherein the query instruction carries a unique identifier of the user and data to be queried; Determine the target distributed storage database corresponding to the user according to the unique identifier; A distributed storage sub-node corresponding to the data to be queried is determined in the target distributed storage database, and the basic data information is extracted according to the distributed storage sub-node.

4. The data privacy protection query method according to claim 3, wherein: Before determining the distributed storage subnode corresponding to the to-be-queried data in the target distributed storage database, the method further includes: The data level of the data to be queried is obtained, where the data level includes first data, second data, and third data.

5. The data privacy protection query method according to claim 4, wherein: Determining the distributed storage sub-node corresponding to the to-be-queried data in the target distributed storage database includes: When the data to be queried is the second data or the third data, determining a distributed storage subnode corresponding to the data to be queried in the target distributed storage database; The matching the basic data information with the terminal data based on the time series index to obtain the target basic data includes: When the data to be queried is second data, matching the basic data information with the second data of the terminal to obtain target second data; When the data to be queried is third data, the basic data information is matched with the third data of the terminal to obtain target third data.

6. The data privacy protection query method according to claim 4, wherein: Determining the distributed storage sub-node corresponding to the query instruction in the target distributed storage database includes: When the data to be queried is first data, feature extraction is performed on the first data to be queried to obtain second data to be queried corresponding to the first data to be queried; According to the second data to be queried, a distributed storage sub-node corresponding to the second data to be queried is determined in the target distributed storage database.

7. The data privacy protection query method according to claim 6, wherein: The matching the basic data information with the terminal data based on the time series index to obtain the target basic data includes: Matching the target basic data with the second data of the terminal to obtain the target second data; The target first data is searched in the terminal according to the target second data.

8. The data privacy protection query method according to claim 1, wherein: The basic data at least includes behavior data of the user operating the terminal, sensor data and terminal system operation data.

9. The data privacy protection query method according to claim 1, wherein: The extracting features from the first data to obtain second data includes: Pre-training a machine learning model to obtain a machine learning model that matches the first data; The first data is input into the machine learning model, the model output result is obtained, and the model output result is used as the second data.

10. A data privacy protection query device, wherein: The data privacy protection query device comprises: a processing module, configured to cluster basic data to obtain first data, extract features from the first data to obtain second data, fuse multiple pieces of the second data to obtain third data, and store the first data, the second data, and the third data in a terminal; An acquisition module, used to acquire basic data information of the terminal, wherein the basic data information is basic data information of the second data and the third data; A storage module is used to perform distributed storage of the basic data information in the cloud to obtain a distributed storage database, wherein the distributed storage database includes a plurality of distributed storage sub-nodes; An extraction module, configured to extract the basic data information from a distributed storage database according to a query instruction received from a user; A matching module is used to match the basic data information in the terminal data based on the time series index to obtain target basic data, wherein the terminal data includes the first data, the second data and the third data.

11. A storage medium having a computer program stored thereon, characterized in that: When the computer program runs on a computer, the computer is enabled to execute the data privacy protection query method according to any one of claims 1 to 9.

12. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein a computer program is stored in the memory, and the processor is used to execute the data privacy protection query method according to any one of claims 1 to 9 by calling the computer program stored in the memory.