CN111797422A - Data privacy protection query method and device, storage medium and electronic equipment - Google Patents

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: acquiring first data, second data and third data of basic data, and storing them in a terminal; Obtain the basic data information of the terminal; perform distributed storage of the basic data information in the cloud to obtain a distributed storage database; when the user's query instruction is obtained, extract the basic data information from the distributed storage database; store the basic data information in the terminal Match to get the target basic data. The embodiment of the present application extracts and fuses the key features of the basic data by means of tertiary storage. When operating the 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. In this way, the exposure of user privacy data to the cloud is avoided, and the security of system data and user privacy data is effectively protected in the terminal and the cloud.

Description

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

technical field

The present application relates to the field of electronic technologies, and in particular, to a data privacy protection query method, device, storage medium and electronic device.

Background technique

With the development of electronic technology, electronic devices such as smart phones are becoming more and more intelligent. Electronic devices can process data through various algorithm models, thereby providing users with various functions. For electronic devices that need to collect a large amount of data, the security of system data and the security of user privacy data are both important.

SUMMARY OF THE INVENTION

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

The embodiment of the present application provides a data privacy protection query method, which is applied to an electronic device, wherein the data privacy protection query method includes:

The first data is obtained by clustering the basic data, the second data is obtained by feature extraction on the first data, the third data is obtained by fusing a plurality of the second data, and the first data and the second data are obtained. and the third data are stored in the terminal;

acquiring basic data information of the terminal, where the basic data information is the basic data information of the second data and the third data;

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;

When the user's query instruction is acquired, extract the basic data information from the distributed storage database according to the query instruction;

The basic data information is matched on the terminal to obtain target basic data.

The embodiment of the present application also provides a data privacy protection query device, including:

The processing module is used for clustering the basic data to obtain the first data, performing feature extraction on the first data to obtain the second data, fusing a plurality of the second data to obtain the third data, and combining the first data The data, the second data and the third data are stored in the terminal;

an acquisition module for acquiring basic data information of the terminal, where the basic data information is the basic data information of the second data and the third data;

a storage module, configured 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 the distributed storage database according to the query instruction when the user's query instruction is obtained;

The matching module is used for matching the basic data information on the terminal to obtain target basic data.

The embodiment of the present application also provides a storage medium, wherein a computer program is stored in the storage medium, and when the computer program runs on the computer, the computer is caused to perform the following steps:

The first data is obtained by clustering the basic data, the second data is obtained by feature extraction on the first data, the third data is obtained by fusing a plurality of the second data, and the first data and the second data are obtained. and the third data are stored in the terminal;

acquiring basic data information of the terminal, where the basic data information is the basic data information of the second data and the third data;

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;

When the user's query instruction is acquired, extract the basic data information from the distributed storage database according to the query instruction;

The basic data information is matched on the terminal to obtain target basic data.

The embodiment of the present application also provides an electronic device, wherein the electronic device includes a processor and a memory, and a computer program is stored in the memory, and the processor is used to perform the following steps by calling the computer program stored in the memory:

The first data is obtained by clustering the basic data, the second data is obtained by feature extraction on the first data, the third data is obtained by fusing a plurality of the second data, and the first data and the second data are obtained. and the third data are stored in the terminal;

acquiring basic data information of the terminal, where the basic data information is the basic data information of the second data and the third data;

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;

When the user's query instruction is acquired, extract the basic data information from the distributed storage database according to the query instruction;

The basic data information is matched on the terminal to obtain target basic data.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

FIG. 1 is a schematic diagram of an application scenario of a data privacy protection query method provided by an embodiment of the present application.

FIG. 2 is a first schematic flowchart of a data privacy protection query method provided by an embodiment of the present application.

FIG. 3 is a schematic diagram of another application scenario of the data privacy protection query method provided by the embodiment of the present application.

FIG. 4 is a second schematic flowchart of a data privacy protection query method provided by an embodiment of the present application.

FIG. 5 is a schematic structural diagram of an apparatus for querying data privacy protection provided by an embodiment of the present application.

FIG. 6 is another schematic structural diagram of an apparatus for querying data privacy protection provided by an embodiment of the present application.

FIG. 7 is another schematic structural diagram of an apparatus for querying data privacy protection provided by an embodiment of the present application.

FIG. 8 is still another schematic structural diagram of an apparatus for querying data privacy protection provided by an embodiment of the present application.

FIG. 9 is a schematic diagram of a first structure of an electronic device provided by an embodiment of the present application.

FIG. 10 is a schematic diagram of a second structure of an electronic device provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of this application.

Referring to FIG. 1 , FIG. 1 is a schematic diagram of an application scenario of a data privacy protection query method provided by an embodiment of the present application. The data privacy protection query method is applied to electronic equipment. A panoramic perception architecture is provided in the electronic device. Panoramic perception architecture is the integration of hardware and software in electronic devices for implementing data privacy protection query methods.

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

The information perception layer is used to acquire the information of the electronic device itself and/or the information in the external environment. The information perception layer may include multiple sensors. For example, the information perception layer includes 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, an attitude sensor, a barometer, a heart rate sensor, and other sensors.

Among them, the distance sensor can be used to detect the distance between the electronic device and the external object. The magnetic field sensor can be used to detect the magnetic field information of the environment in which the electronic device is located. The light sensor can be used to detect the light information of the environment where the electronic device is located. Acceleration sensors can be used to detect acceleration data of electronic devices. The fingerprint sensor can be used to collect the user's fingerprint information. Hall sensor is a magnetic field sensor made according to the Hall effect, which can be used to realize automatic control of electronic equipment. The location sensor can be used to detect the current geographic location of the electronic device. Gyroscopes can be used to detect the angular velocity of electronic devices in various directions. Inertial sensors can be used to detect motion data of electronic devices. The attitude sensor can be used to sense the attitude information of the electronic device. A barometer can be used to detect the air pressure in the environment in which the electronic device is located. The heart rate sensor may be used to detect the user's heart rate information.

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 and other processing on the data obtained by the information perception layer.

Among them, data cleaning refers to cleaning a large amount of data obtained by the information perception layer to eliminate invalid data and duplicate data. Data integration refers to integrating multiple single-dimensional data obtained by the information perception layer into a higher or more abstract dimension to comprehensively process multiple single-dimensional data. Data transformation refers to converting the data type or format of the data obtained by the information perception layer, so that the transformed data can meet the processing requirements. Data reduction refers to reducing the amount of data to the greatest extent possible on the premise of keeping the original data as much as possible.

The feature extraction layer is used to perform feature extraction on the data processed by the data processing layer to extract features included in the data. The extracted features may reflect the state of the electronic device itself, the state of the user, or the environmental state of the environment in which the electronic device is located.

Among them, the feature extraction layer can extract features or process the extracted features by filtering method, packaging method, integration method and other methods.

The filtering method refers to filtering the extracted features to remove redundant feature data. The packing method is used to filter the extracted features. The integration method refers to the integration of multiple feature extraction methods to construct a more efficient and accurate feature extraction method for feature extraction.

The scenario modeling layer is used to construct a model according to the features extracted by the feature extraction layer, and the obtained model can be used to represent the state of the electronic device, the state of the user, or the environment state, etc. 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. according to the features extracted by the feature extraction layer.

The intelligent service layer is used to provide users with intelligent services according to the model constructed by the scenario modeling layer. For example, the intelligent service layer can provide users with basic application services, can perform system intelligent optimization for electronic devices, and can also provide users with personalized intelligent services.

In addition, the panoramic perception architecture can also include multiple algorithms, each of which can be used to analyze and process data, and multiple algorithms can form an algorithm library. For example, the algorithm library may include Markov algorithm, latent Dirichlet distribution algorithm, Bayesian classification algorithm, support vector machine, K-means clustering algorithm, K-nearest neighbor algorithm, conditional random field, residual network, long Algorithms such as short-term memory networks, convolutional neural networks, and recurrent neural networks.

The embodiment of the present application provides a data privacy protection query method, and the data privacy protection query method can be applied to an electronic device. The electronic device may be a smartphone, a tablet computer, a gaming device, an AR (Augmented Reality) device, a car, a data privacy protection query device, an audio playback device, a video playback device, a notebook, a desktop computing device, a wearable device such as a watch , glasses, helmets, electronic bracelets, electronic necklaces, electronic clothing and other equipment.

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

Referring to FIG. 2 , FIG. 2 is a schematic flowchart of a first type of data privacy protection query method provided by an embodiment of the present application. The data privacy protection query method includes the following steps:

110: Cluster the basic data to obtain first data, perform feature extraction on the first data to obtain second data, fuse multiple second data to obtain third data, and combine the first data, the second data and the third data Store in the terminal.

In this step, the first data may be clustered basic data; the second data may be panoramic information features; and the third data may be fusion feature data.

The basic data may include operation information of the electronic device, configuration information of the electronic device, user information, current environment information, and the like. Specifically, the basic data may be collected through one or more sensors, and may also be collected in real time. For example, through at least one of 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, an attitude sensor, a barometer, a blood pressure sensor, a pulse sensor, a heart rate sensor, etc. One to obtain current environmental information and related information of electronic equipment. The current environment information includes the user's physical information, such as blood pressure, pulse, heart rate, and the like. The related information of the electronic device includes operation information of the electronic device, configuration information of the electronic device, user information stored in the electronic device, and the like. The user information includes the user's identity information, personal hobbies, browsing records, personal collections and other human-computer interaction information. The operation information of electronic equipment includes boot time, shutdown time, standby time, memory usage rate at each time point, main chip usage rate at each time point, current running program information, background running program information, running time of each program, each program downloads, etc. In some embodiments, the basic data may also include behavior data of the user operating the terminal, sensor data, and terminal system operation data.

After a plurality of basic data are obtained, they can be stored in the first storage module. For example, a plurality of panoramic perception information can be stored in the hard disk. Among them, multiple databases can be set, and their basic data can be stored in the corresponding databases according to the categories.

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

The data format and data content of each type of first data may be different. For example, the wifi connection information in the sensor data is very limited, and no wifi information will be stored and recorded when there is no wifi signal connected; relatively speaking, for The IMU data is sent back at the frequency of Hertz every second, and it can store up to gigabytes of data a day. The feature extraction of basic data in the database is conducive to reducing redundant information and saving storage space on the one hand, and on the other hand, it can effectively extract the important meaning of the basic data. Taking audio information as an example, audio information belongs to time series information. With the increase of time, the data of audio information continues to grow, so it is necessary to perform feature extraction on the data to reduce the amount of data. Taking the audio information with dual microphone channels, 32bit bit width, and sampling frequency of 44100 as an example, the data generated in 5 minutes is about 1G. After feature extraction, the important features of each time window are obtained. At this time, the features can be in the form of vectors. For storage, 1G of data can be compressed to hundreds of kilobytes.

Data privacy protection of the same type of basic data is queried into the same database. A basic data can be stored in a database, for example, the acceleration sensor data is only stored in the acceleration sensor database. A piece of basic data can also be stored in multiple databases. For example, when a piece of basic data belongs to two categories, the basic data can be copied, and the copied basic data and the original basic data can be stored in two separate databases. In each database, the two databases correspond to the two categories to which the basic data 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.

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

A separate feature extraction is performed on the data in the separate databases to obtain the panoramic information features corresponding to each database. A feature extraction layer can be set up to perform feature extraction on the basic data in a variety of ways, and there can be different feature extraction methods corresponding to different data.

In some embodiments, the feature extraction of the basic data is performed on the database by a manual preset method, and the important features in the basic data of each category are preset. The basic data is clustered and stored in the corresponding database, and the basic data in the same database is identified with the same important features, and the preset important features corresponding to the specific data of each basic data are extracted as panoramic information features. Information features are stored a second time.

In some embodiments, feature extraction of basic data is performed on the database by means of a pre-trained machine learning model. The steps of performing feature extraction on the basic data of the databases to obtain the panoramic information features corresponding to each database may specifically include: pre-training a machine learning model to obtain a machine learning model matching the basic data; inputting the basic data into the machine learning model to obtain The model output results, and the model output results are used as panoramic information features.

A plurality of second data are fused to obtain third data. The third data may be fusion feature data. Specifically, the panorama information features can be fused using a multi-table connection method, the panoramic information features can also be fused using a time series alignment method, and the panoramic information features can also be jointly fused using a multi-table connection method and a time series alignment method. Since most of the data on the terminal is time series data, that is, the user's operation at different time points and the terminal's situation are different, and change with the change of time, so the fusion of the second data can further reduce the asymmetry between the data properties, the amount of compressed data.

The panoramic information features are fused to obtain fused feature data, and the fused feature data is stored for a third time, which can be stored in a third storage unit. Effectively perform disaster recovery backup for data through cascaded storage, which can avoid storage and transmission of plaintext data, and extract high-dimensional features from basic data through unique feature extraction steps (equivalent to encrypting basic data), effectively protect user privacy information.

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

In some embodiments, the time series index corresponding to each database can also be obtained, and the time series index corresponding to each database is also stored in the second storage module (such as a memory), so that other modules of the system can search in the database according to the time series index to the corresponding base data. The multi-source heterogeneous basic data is clustered in time series through the clustering method, 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, and reasonable access and allocation of basic data can speed up the retrieval of panoramic perception information.

120. Acquire basic data information of the terminal, where the basic data information is the basic data information of the second data and the third data.

The second data and third data of the terminal are extracted and then transmitted to the cloud, and the intelligent mobile terminal device is used as a client, and the second data and third data are uploaded to the cloud server cluster Cluster, and the TCP/IP protocol can be used to transfer the data. Encapsulated for streaming data upload to server clusters. Through the server cluster in the cloud, data at all levels can be indexed.

The basic data information of the terminal is acquired in the cloud, and the basic data information is the basic data information of the second data and the third data. The basic data information may be the second data and the third data themselves, or may be an index table of the second data and the third data. In other words, the basic data information of 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 acquired according to the basic data information.

130. Perform distributed storage on the cloud for basic data information to obtain a distributed storage database, where the distributed storage database includes a plurality of distributed storage sub-nodes.

Distributed storage is a data privacy protection query technology, which uses the disk space on each machine in the enterprise through the network, and forms a virtual storage device with these scattered storage resources, and the data is stored in all corners of the enterprise. The storage method of distributed storage can share the storage load. It not only improves the reliability, availability and access efficiency of the system, but also is easy to expand.

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

The traditional distributed storage is essentially a centralized system, which is to store data scattered on multiple independent devices, adopt a scalable system structure, use multiple storage servers to share the storage load, and use location servers to locate and store information. . The network-based distributed storage is the core technology of the blockchain. It is a distributed database established by querying the data privacy protection on the block and opening the storage space of the nodes to solve the problem of traditional distributed storage.

A node is a network node in a blockchain distributed system, and is a server, computer, phone, etc. connected through the network. For different types of blockchains, the way to become a node will be different. Taking Bitcoin as an example, participating in transactions or mining constitutes a node.

In a distributed storage database, there are multiple distributed storage sub-nodes. In the cloud, multiple distributed storage sub-nodes can be divided into multiple clusters according to their corresponding data categories. For example, multiple distributed storage sub-nodes can be assigned to user clusters, second-level feature clusters, and third-level feature clusters. The user cluster contains a large amount of user information. The distributed storage sub-nodes in the user cluster can correspond to the user information of each user, such as the unique identifier of the terminal and the physical address in the server for data privacy protection query of different terminal users. The secondary feature clusters and tertiary feature clusters can be retrieved and queried through user clusters.

The second-level feature clusters and the third-level feature clusters are basic data information clusters corresponding to the second data and the third data. The basic data information may be the second data and the third data themselves, or may be information that can match the second data and the third data, such as an index table corresponding to the second data and the third data. The distributed storage sub-nodes in the second-level feature cluster and the third-level feature cluster may correspond to the basic data information of each user, so as to extract the basic data information according to the distributed storage sub-nodes.

140. When the user's query instruction is acquired, extract basic data information from the distributed storage database according to the query instruction.

Obtaining the user's query instruction includes directly obtaining the user's query instruction on the cloud, and also including transmitting the query instruction to the cloud after the terminal obtains the user's query instruction. The query command contains the unique identifier of the user and the data to be queried. When the user's query instruction is obtained, according to the unique identifier of the user carried in the query instruction, the distributed storage database corresponding to the user is determined in the cloud, and the distributed database contains the distributed storage sub-system of the basic data information of the user. node.

In some embodiments, basic data information is extracted from the distributed storage database according to the query instruction, including obtaining the user's query instruction, where the query instruction carries the user's unique identifier and the data to be queried; the target distribution corresponding to the user is determined according to the unique identifier In the target distributed storage database, the distributed storage sub-nodes corresponding to the data to be queried are determined, and the basic data information is extracted according to the distributed storage sub-nodes.

It should be noted that the data to be queried may be first data, second data or third data, user information data, and so on. Corresponding to different data to be queried, there can be different query methods. For example, when the data to be queried is the first data, feature extraction is performed on the first data to be queried to obtain the second data to be queried corresponding to the first data to be queried; A distributed storage sub-node corresponding to the second data to be queried is determined in the storage database; basic data information is extracted according to the distributed storage sub-node. For another example, when the data to be queried is the second data or the third data, a distributed storage sub-node corresponding to the to-be-queried data is determined in the target distributed storage database; basic data information is extracted according to the distributed storage sub-node. For another example, when the data to be queried is user information data, etc., a distributed storage sub-node corresponding to the to-be-queried user information data is determined in the distributed storage database, and the user information data is extracted according to the distributed storage sub-node.

Those skilled in the art should know that in the process of extracting basic data information in the distributed storage database according to the query instruction, there may be various extraction methods, and the above is only an exemplary description, which should not be construed to limit the present application.

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 command is the first data, the basic data information includes relevant information that can match the first data to be queried. For example, it may include the corresponding second data, or may include the corresponding second data information about the data. When the belt query instruction is the second data, the basic data information may include the corresponding second data, or may include relevant information that can match the corresponding second data.

It should be noted that the data to be queried may be one type of data or multiple types of data, for example, may include user information data to be queried and second data. The data to be queried can be data of a certain level or data of multiple levels. For example, the second data and the third data can be queried at the same time, the first data and the second data can also be queried at the same time, etc. . In some embodiments, a query instruction of the user is obtained, and the query instruction carries the unique identifier of the user and a plurality of data to be queried. The type corresponds to the types of the data to be queried, and the corresponding query method is executed respectively. If a plurality of data to be queried belong to the same type, the query order of the plurality of data to be queried is determined, and the data to be queried is queried according to the order.

150. Match the basic data information on the terminal to obtain the target basic data.

If step 140 includes the feedback from the cloud to the user's query instruction, then step 150 includes the information connection between the cloud and the terminal. After the cloud extracts basic data information according to the data to be queried, the basic data information is matched with the data stored in the terminal to obtain the queried data required by the user.

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; when the data to be queried is the third data, the basic data information is compared with the second data of the terminal. match to obtain the target third data. When the data to be queried is the 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 according to the target second data. In some embodiments, a matching map or a retrieval table corresponding to the basic data information and the first data of the terminal is preset in the cloud. At this time, the basic data information can also be directly matched with the first data of the terminal to obtain the target first data.

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, for example, the unique identifier of the user. In order to distinguish different user terminals, the user information data can be extracted when the basic data information of the terminal is obtained, and the target data obtained by the query and the user information data of the terminal are fed back to the user when the user queries the query data. user.

Referring to FIG. 3 , FIG. 3 is a diagram of another application scenario of the data privacy protection query method provided by the embodiment of the present application. Among them, user behavior data, sensor data, . Then, after clustering a plurality of basic data, first data is obtained, and the first data is stored. The first data includes basic data such as user behavior data, sensor data, ..., system operation data, and the like.

Subsequently, the feature extraction module performs feature extraction on the first data, extracts important features of the first data as second data, and stores them. The second data includes panoramic information features such as user behavior features, sensor features, ..., system features, and the like.

The third data may be a fused panorama feature obtained by fusing the panorama information features of the second data, and the fused panorama feature is stored.

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.

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

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 set on the cloud, and a user master is also set on the cloud, and the user master records a large number of User information is convenient for subsequent indexing of user information, and the user master can retrieve and query the secondary feature master and the tertiary feature master. The master can be a 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 processing server, so as to facilitate the storage, processing and distribution of the input data distribution server. Each master is responsible for maintaining the index table, but does not really store the actual data. The advantage of its design is to use the distributed storage method to store and maintain Nanjing information. The advantages of distributed storage are that it supports high-performance read and write, multi-copy consistency, easy disaster recovery and backup of data, elastic expansion of server nodes, and standardization of storage systems.

When the panorama perception modeling layer of the server needs to use secondary features and tertiary features, by sending a request to the user master, the secondary feature data corresponding to the user can be obtained from the sub-nodes (nodes) of the distributed database or Tertiary feature data.

In some embodiments, the indexing method for indexing the first data, the second data or the third data, etc. may be the CG-Index method. The basic idea is that each node is responsible for maintaining a local B+ tree and maintaining a The global CG-index index table, by accessing the CG-index index table, can determine which nodes need to query the local index, which can support high-performance random read and write. On the other hand, CG-index regards the index as another form of data and stores the table, and internally uses the complementary check table instead of the ordinary table to achieve index fault tolerance and recovery, reducing the storage cost of the index.

Referring to FIG. 4 , FIG. 4 is a schematic flowchart of a second type of data privacy protection query method provided by an embodiment of the present application. The data privacy protection query method includes the following steps:

210. Cluster the basic data to obtain first data, perform feature extraction on the first data to obtain second data, fuse multiple second data to obtain third data, and combine the first data, the second data and the third data Store in the terminal.

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

The first-level storage module: stores the first data as the data in the first-level storage database. It is worth noting that because 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.

Secondary storage module: High-dimensional features in the independent database of the first data are extracted from the secondary storage, which effectively reduces data redundancy and desensitizes the source data.

Three-level storage module: It mainly fuses the second data of independent features. Specifically, it performs table join operation on the database of secondary storage, merges data dimensions with the same time series, and fuses panoramic features.

220. Set unique identifiers for different terminals to distinguish different terminals.

The secondary storage and tertiary storage information of the terminal is transmitted to the cloud, and the device information of the user is marked to distinguish the user from other users. Different users store different data in the cloud. By setting a unique identifier for the terminal, different terminals can be distinguished. When extracting and matching data, the part corresponding to the user can be accurately found.

230. Acquire basic data information of the terminal, where the basic data information is the basic data information of the second data and the third data.

The basic data information of the terminal is acquired in the cloud, and the basic data information is the basic data information of the second data and the third data. The basic data information may be the second data and the third data themselves, or may be an index table of the second data and the third data. In other words, the basic data information of 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 acquired according to the basic data information.

240. Perform distributed storage on the cloud for basic data information to obtain a distributed storage database, where the distributed storage database includes a plurality of distributed storage sub-nodes.

In a distributed storage database, there are multiple distributed storage sub-nodes. In the cloud, multiple distributed storage sub-nodes can be divided into multiple clusters according to their corresponding data categories. For example, multiple distributed storage sub-nodes can be assigned to user clusters, second-level feature clusters, and third-level feature clusters. The user cluster contains a large amount of user information. The distributed storage sub-nodes in the user cluster can correspond to the user information of each user, such as the unique identifier of the terminal and the physical address in the server for data privacy protection query of different terminal users. The secondary feature clusters and tertiary feature clusters can be retrieved and queried through user clusters.

The second-level feature clusters and the third-level feature clusters are basic data information clusters corresponding to the second data and the third data. The basic data information may be the second data and the third data themselves, or may be information that can match the second data and the third data, such as an index table corresponding to the second data and the third data. The distributed storage sub-nodes in the second-level feature cluster and the third-level feature cluster may correspond to the basic data information of each user, so as to extract the basic data information according to the distributed storage sub-nodes.

250. Obtain a query instruction of the user, where the query instruction carries the unique identifier of the user and the data to be queried.

Obtaining the user's query instruction includes directly obtaining the user's query instruction on the cloud, and also including transmitting the query instruction to the cloud after the terminal obtains the user's query instruction. The query command contains the unique identifier of the user and the data to be queried.

260. Determine a target distributed storage database corresponding to the user according to the unique identifier.

When the user's query instruction is obtained, according to the unique identifier of the user carried in the query instruction, the distributed storage database corresponding to the user is determined in the cloud, and the distributed database contains the distributed storage sub-system of the basic data information of the user. node.

270. Determine whether the data to be queried is the first data.

It should be noted that the data to be queried may be first data, second data or third data, user information data, and so on. Corresponding to different data to be queried, there can be different query methods. Since the first data involves the underlying original data, in order to protect user privacy, the first data is not transmitted to the cloud. Determining whether the query data is the first data is helpful for responding to the query instruction according to different situations.

Those skilled in the art should know that in the process of extracting basic data information in the distributed storage database according to the query instruction, there may be various extraction methods, and the above is only an exemplary description, which should not be construed to limit the present application.

The data to be queried may be one type of data or multiple types of data, for example, may include user information data to be queried and second data. The data to be queried can be data of a certain level or data of multiple levels. For example, the second data and the third data can be queried at the same time, the first data and the second data can also be queried at the same time, etc. . In some embodiments, a query instruction of the user is obtained, and the query instruction carries the unique identifier of the user and a plurality of data to be queried. The type corresponds to the types of multiple data to be queried, and the corresponding query method is executed respectively. If multiple data to be queried belong to the same type, determine the query order of the multiple data to be queried, and judge whether the data to be queried is the first data according to the order. When it is judged that the data to be queried is the first data, execute in order The query step corresponding to the first data; when it is determined that the data to be queried is not the first data, the corresponding query steps when the data to be queried is not the first data are executed in sequence.

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

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

When the data to be queried is the second data or the third data, the distributed storage sub-node corresponding to the second data or the third data is determined in the target distributed storage database; the basic data information is extracted according to the distributed storage sub-node. For another example, when the data to be queried is user information data, etc., a distributed storage sub-node corresponding to the to-be-queried user information data is determined in the distributed storage database, and the user information data is extracted according to the distributed storage sub-node.

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.

Since the first data and the panoramic information features corresponding to the first data are not stored in the cloud, 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 to be queried can be obtained. The data is queried, and the corresponding first data is found according to the second data.

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

It should be noted that the third data to be queried can also be obtained by merging the panoramic features of the second data to be queried. The distributed storage sub-node corresponding to the data extracts basic data information according to the distributed storage sub-node.

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

294. Search the terminal for the target first data according to the target second data.

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; when the data to be queried is the third data, the basic data information is compared with the second data of the terminal. match to obtain the target third data. When the data to be queried is the 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 according to the target second data. In some embodiments, a matching map or a retrieval table corresponding to the basic data information and the first data of the terminal is preset in the cloud. At this time, the basic data information can also be directly matched with the first data of the terminal to obtain the target first data.

In some embodiments, the data privacy protection query method may specifically include: first obtaining information of 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 devices display content information, download information on electronic devices, etc.), and then process the information of electronic devices (such as classification, etc.) through the data processing layer, and then extract the first information from the information processed by the data processing layer through the feature extraction layer. The second data and the third data (for details of the second data and the third data, please refer to the description of the above embodiment), and after the second data and the third data are processed, the target model parameters are uploaded to the server for storage through the storage module. The server does not receive the first data based on the protection data. When it wants to query the first data, it can correspond to the first data by querying the related data of the second data and the third data in the server, so as to avoid clear text data. to operate.

It can be seen from the above that, in the data privacy protection query method provided by the embodiments of the present application, first data is clustered to obtain first data, feature extraction is performed on the first data to obtain second data, and multiple second data is fused to obtain first data. Three data, the first data, the second data and the third data are stored in the terminal; then the basic data information of the terminal is obtained, and the basic data information is the basic data information of the second data and the third data; then the basic data information is stored in the terminal. The cloud performs distributed storage to obtain a distributed storage database. The distributed storage database contains multiple distributed storage sub-nodes; then when the user's query command is obtained, the basic data information is extracted from the distributed storage database according to the query command. ; Finally, the basic data information is matched on 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, the direct operation of the plaintext data is avoided, which effectively protects the security of the terminal system data and the security of user privacy data. The first data is not transmitted to the cloud, and the second data and the third data are extracted and transmitted to the cloud, thereby avoiding the exposure of user privacy data to the cloud, and further protecting the security of cloud system data and user privacy data.

Referring to FIG. 5 , FIG. 5 is a schematic structural diagram of an apparatus for querying data privacy protection provided by an embodiment of the present application. The data privacy protection query apparatus 300 may be integrated into an electronic device, and the data privacy protection query apparatus 300 includes a processing module 301 , an acquisition module 302 , a storage module 303 , an extraction module 304 and a matching module 305 .

The processing module 301 is configured to cluster basic data to obtain first data, perform feature extraction on the first data to obtain second data, fuse multiple second data to obtain third data, and combine the first data and the second data and the third data are stored in the terminal;

an acquisition module 302, configured to acquire basic data information of the terminal, where the basic data information is the basic data information of the second data and the third data;

The storage module 303 is used for distributed storage of basic data information in the cloud to obtain a distributed storage database, and the distributed storage database includes a plurality of distributed storage sub-nodes;

The extraction module 304 is configured to extract basic data information from the distributed storage database according to the query instruction when the user's query instruction is obtained;

The matching module 305 is configured to match the basic data information on the terminal to obtain the target basic data.

Please refer to FIG. 6 together. FIG. 6 is another schematic structural diagram of a data privacy protection query apparatus provided by 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, and the processing module 301 may include a first storage unit 3011 , a second storage unit 3012 and a third storage unit 3013 .

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

The second storage unit 3012 is used to perform feature extraction of basic data on the database, obtain the panoramic information feature corresponding to each database, and use the panoramic information feature as the second data to store the second data for the second time;

In some embodiments, the second storage unit is also used to:

Pre-training the machine learning model to obtain a machine learning model matching the first data;

Input the first data into the machine learning model, obtain the output result of the model, and use the output result of the model as the second data.

The third storage unit 3013 is configured to fuse the features of the panoramic information to obtain fused feature data, and use the fused feature data as third data for third storage.

In some embodiments, the third storage unit 3013 may be specifically configured 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 the third time.

Please also refer to FIG. 7. FIG. 7 is another schematic structural diagram of a data privacy protection query apparatus 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 .

The query unit 3041 is used to obtain the query instruction of the user, and the query instruction carries the unique identifier of the user and the data to be queried;

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

The extraction unit 3043 is configured to determine the distributed storage sub-nodes corresponding to the data to be queried in the target distributed storage database, and extract basic data information according to the distributed storage sub-nodes.

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 second data to be queried corresponding to the first data to be queried; data, and determine a distributed storage sub-node corresponding to the second data to be queried in the target distributed storage database.

In some embodiments, the extracting module 304 may further include an obtaining unit 3044, configured to obtain a data level of the data to be queried, where the data level at least includes the first data, the second data and the third data.

Please also refer to FIG. 8. FIG. 8 is still another schematic structural diagram of a data privacy protection query apparatus provided by 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 .

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

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

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

In some embodiments, the apparatus may further include a backup module and a transmission module. The backup module is used for real-time backup of the fusion feature data on the terminal. The transmission module is used to transmit the fusion feature data to the application service layer or the data processing layer, so that the application service layer or the data processing layer can perform calculation by using the fusion information characteristic.

It can be seen from the above that the embodiment of the present application provides a data privacy protection query device. First, the processing module 301 performs clustering on basic data to obtain first data, performs feature extraction on the first data to obtain second data, and combines multiple second data. The data is fused to obtain the third data, and the first data, the second data and the third data are stored in the terminal; then the acquisition module 302 acquires the basic data information of the terminal, and the basic data information is the basic data 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, and the distributed storage database contains a plurality of distributed storage sub-nodes; then the extraction module 304 obtains the user's query instruction when , extract the basic data information in the distributed storage database according to the query instruction; finally, the matching module 305 matches the basic data information on 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, the direct operation of the plaintext data is avoided, which effectively protects the security of the terminal system data and the security of user privacy data. The first data is not transmitted to the cloud, and the second data and the third data are extracted and transmitted to the cloud, thereby avoiding the exposure of user privacy data to the cloud, and further protecting the security of cloud system data and user privacy data.

The embodiments of the present application also provide an electronic device. The electronic device may be a smartphone, a tablet computer, a gaming device, an AR (Augmented Reality) device, a car, a data privacy protection query device, an audio playback device, a video playback device, a notebook, a desktop computing device, a wearable device such as a watch , glasses, helmets, electronic bracelets, electronic necklaces, electronic clothing and other equipment.

Referring to FIG. 9 , FIG. 9 is a first structural schematic diagram of an electronic device 900 provided by 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 .

The processor 901 is the control center of the electronic device 900, uses various interfaces and lines to connect various parts of the entire electronic device, executes the electronic device by running or calling the computer program stored in the memory 902, and calling the data stored in the memory 902. Various functions of the device and processing data, so as to carry out the overall monitoring of the electronic device.

In this embodiment, the processor 901 in the electronic device 900 loads the instructions corresponding to the processes of one or more computer programs into the memory 902 according to the following steps, and is executed by the processor 901 and stored in the memory 902 A computer program in , which implements various functions:

The first data is obtained by clustering the basic data, the second data is obtained by feature extraction on the first data, the third data is obtained by fusing a plurality of second data, and the first data, the second data and the third data are stored in the terminal. to store;

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

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

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

The basic data information is matched on the terminal to obtain the target basic data.

In some embodiments, when performing feature extraction on the first data to obtain the second data, the processor 901 performs the following steps:

Pre-training the machine learning model to obtain a machine learning model matching the first data;

Input the first data into the machine learning model, obtain the output result of the model, and use the output result of the model as the second data.

In some embodiments, when a plurality of second data are fused to obtain third data, the processor 901 performs the following steps:

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

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

Obtain the user's query instruction, where the query instruction carries the user's unique identifier and the 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 basic data information is extracted according to the distributed storage sub-node.

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

The data level of the data to be queried is acquired, and the data level includes the first data, the second data and the third data.

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

Determine the distributed storage sub-node corresponding to the data to be queried in the target distributed storage database;

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;

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

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

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;

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.

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

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.

In some embodiments, referring to FIG. 10 , FIG. 10 is a schematic diagram of a second structure of an electronic device 900 according to an embodiment of the present application.

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 , respectively.

The display screen 903 may be used to display information input by or provided to the user and various graphical user interfaces of the electronic device, which may be composed of images, text, icons, videos, and any combination thereof.

The control circuit 904 is electrically connected to the display screen 903 for controlling the display screen 903 to display information.

The input unit 905 may be used to receive input numbers, character information, or user characteristic information (eg, fingerprints), and generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control. The input unit 905 may include a fingerprint identification module.

The sensor 906 is used to collect the information of the electronic device itself or the user's information or the external environment information. For example, the 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.

Power supply 907 is used to power various components of electronic device 900 . In some embodiments, the power supply 907 may be logically connected to the processor 901 through a power management system, so as to implement functions such as managing charging, discharging, and power consumption through the power management system.

Although not shown in FIG. 10 , the electronic device 900 may further include a camera, a Bluetooth module, and the like, which will not be repeated here.

It can be seen from the above that the embodiment of the present application provides an electronic device, and the processor in the electronic device performs the following steps: first, the basic data is clustered to obtain the first data, the first data is subjected to feature extraction to obtain the second data, and the A plurality of second data are fused to obtain third data, and the first data, the second data and the third data are stored in the terminal; then basic data information of the terminal is obtained, and the basic data information is the basis of the second data and the third data data information; then perform distributed storage of 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, according to the query instruction The basic data information is extracted from the distributed storage database; finally, the basic data information is matched on 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, the direct operation of the plaintext data is avoided, which effectively protects the security of the terminal system data and the security of user privacy data. The first data is not transmitted to the cloud, and the second data and the third data are extracted and transmitted to the cloud, thereby avoiding the exposure of user privacy data to the cloud, and further protecting the security of cloud system data and user privacy data.

An embodiment of the present application further provides a storage medium, where a computer program is stored in the storage medium, and when the computer program runs on the computer, the computer executes the data privacy protection query method of any of the foregoing embodiments.

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

The first data is obtained by clustering the basic data, the second data is obtained by feature extraction on the first data, the third data is obtained by fusing a plurality of second data, and the first data, the second data and the third data are stored in the terminal. to store;

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

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

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

The basic data information is matched on the terminal to obtain the target basic data.

It should be noted that those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, The storage medium may include, but is not limited to, a read only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and the like.

The data privacy protection query method, device, storage medium, and electronic device provided by the embodiments of the present application are described in detail above. The principles and implementations of the present application are described herein using specific examples, and the descriptions of the above embodiments are only used to help understand the methods and core ideas of the present application; meanwhile, for those skilled in the art, according to the Thoughts, there will be changes in the specific implementation and application scope. In conclusion, the content of this specification should not be construed as a limitation on the application.

Claims (13)

1. A data privacy protection query method, wherein the data privacy protection query method comprises: The first data is obtained by clustering the basic data, the second data is obtained by feature extraction on the first data, the third data is obtained by fusing a plurality of the second data, and the first data and the second data are obtained. and the third data are stored in the terminal; acquiring basic data information of the terminal, where the basic data information is the basic data information of the second data and the third data; 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; When the user's query instruction is acquired, extract the basic data information from the distributed storage database according to the query instruction; The basic data information is matched on the terminal to obtain target basic data. 2. The data privacy protection query method according to claim 1, wherein, before the acquiring the basic data information of the terminal, further comprising: Unique identifiers are set for different terminals to distinguish different terminals. 3. The data privacy protection query method according to claim 2, wherein, when the user's query instruction is obtained, extracting the basic data information in a distributed storage database according to the query instruction, comprising: Obtain a query instruction of the user, where the query instruction carries the unique identifier of the user and the 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 the distributed storage sub-node corresponding to the data to be queried is determined in the target distributed storage database, the method further comprises: The data level of the data to be queried is acquired, where the data level includes first data, second data and third data. 5. The data privacy protection query method according to claim 4, wherein the determining the distributed storage sub-node corresponding to the data to be queried in the target distributed storage database comprises: When the data to be queried is the second data or the third data, determining a distributed storage sub-node corresponding to the data to be queried in the target distributed storage database; The matching of the basic data information on the terminal to obtain the target basic data includes: 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; When the data to be queried is the third data, the basic data information is matched with the second data of the terminal to obtain the target third data. 6. The data privacy protection query method according to claim 4, wherein the determining the distributed storage sub-node corresponding to the query instruction in the target distributed storage database comprises: When the data to be queried is the 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 of the basic data information at the terminal to obtain the target basic data comprises: 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 includes at least behavior data, sensor data and terminal system operation data of the user operating the terminal. 9 . 9. The data privacy protection query method according to claim 1, wherein the feature extraction of the first data to obtain the second data comprises: Pre-training a machine learning model to obtain a machine learning model matching the first data; Inputting the first data into the machine learning model, obtaining an output result of the model, and using the output result of the model as the second data. 10. The data privacy protection query method according to claim 1, wherein the obtaining third data by fusing a plurality of the second data comprises: A plurality of the second data are fused in the manner of multi-table connection and/or time series alignment to obtain third data. 11. A data privacy protection query device, wherein the data privacy protection query device comprises: The processing module is used for clustering the basic data to obtain the first data, performing feature extraction on the first data to obtain the second data, fusing a plurality of the second data to obtain the third data, and combining the first data The data, the second data and the third data are stored in the terminal; an acquisition module, configured to acquire basic data information of the terminal, where the basic data information is the basic data information of the second data and the third data; a storage module, configured 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 the distributed storage database according to the query instruction when the user's query instruction is obtained; The matching module is used for matching the basic data information on the terminal to obtain target basic data. 12. A storage medium having a computer program stored thereon, wherein when the computer program is run on a computer, the computer is made to execute the data privacy protection query according to any one of claims 1 to 10 method. 13. An electronic device, characterized in that the electronic device comprises a processor and a memory, and a computer program is stored in the memory, and the processor is used to execute the computer program by invoking the computer program stored in the memory. Claims The data privacy protection query method according to any one of claims 1 to 10.

Images