WO2022088632A1

WO2022088632A1 - User data monitoring and analysis method, apparatus, device, and medium

Info

Publication number: WO2022088632A1
Application number: PCT/CN2021/090312
Authority: WO
Inventors: 谢展成
Original assignee: 平安科技（深圳）有限公司
Priority date: 2020-11-02
Filing date: 2021-04-27
Publication date: 2022-05-05
Also published as: CN112306835B; CN112306835A

Abstract

A third-party software-based user data monitoring and analysis method, related to data monitoring techniques, comprising: collecting a behavioral data set of a target user from third-party software (S1); reducing the dimensionality of the behavioral data set to produce a dimensionality-reduced behavioral data set (S2); utilizing a data anomaly detection model to test the dimensionality-reduced behavioral data set to produce a normal behavioral data set and an abnormal behavioral data set (S3); utilizing a collaborative filtering algorithm to execute data reconstruction on the basis of the normal behavioral data set and of the abnormal behavioral data set to produce a standard data set (S4); and executing visualization processing with respect to the standard data set to produce a visualized chart set (S5). The method solves the problem of a large amount of computer memory being consumed during a data monitoring process.

Description

User data monitoring and analysis method, device, equipment and medium

This application claims the priority of the Chinese patent application with the application number CN202011204209.1 and the title of "User Data Monitoring and Analysis Method, Apparatus, Equipment and Medium" filed with the China Patent Office on November 2, 2020, the entire contents of which are by reference Incorporated in this application.

technical field

The present application relates to the technical field of data monitoring, and in particular, to a method, device, electronic device, and computer-readable storage medium for monitoring and analyzing user data based on third-party software.

Background technique

At present, many software products or platforms will access third-party software in order to provide users with more abundant products and services. The third-party software refers to the first party and the second party. The second party refers to the problem to be solved by itself, namely the user, and the use of other software to provide services for its own users refers to the third-party software.

In order to understand the effect of the third-party software on the user, it is usually necessary to analyze the user behavior data generated by the third-party software. The inventor realizes that traditional analysis methods are mostly completed by using support vector machine (SVM) modeling, but the space consumption of SVM is mainly to store training samples and kernel matrices, because SVM uses quadratic programming to solve support vectors, while solving two The sub-planning will involve the calculation of the m-order matrix (m is the number of samples). When the number is large, the storage and calculation of the matrix will consume a lot of computer memory and the read and write speed of the computer disk.

SUMMARY OF THE INVENTION

A method for monitoring and analyzing user data based on third-party software provided by this application includes:

Collect behavioral data sets of target users from third-party software;

performing a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set;

Using a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and an abnormal behavior data set;

Using a preset collaborative filtering algorithm, perform data reconstruction according to the normal behavior data set and the abnormal behavior data set to obtain a standard data set;

Perform visualization processing on the standard data set to obtain a visual chart set, and transmit the visual chart set to a preset terminal.

The application also provides a user data monitoring and analysis device based on third-party software, the device comprising:

A behavioral data acquisition module, used to collect behavioral data sets of target users from third-party software;

A data detection module is used to perform a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set, and use a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and abnormal behavior data set;

a data reconstruction module, configured to use a preset collaborative filtering algorithm to perform data reconstruction according to the normal behavior data set and the abnormal behavior data set to obtain a standard data set;

A visualization module, configured to perform visualization processing on the standard data set to obtain a visual chart set, and transmit the visual chart set to a preset terminal.

The present application also provides an electronic device, the electronic device comprising:

a memory that stores at least one instruction; and

A processor that executes the instructions stored in the memory to achieve the following steps:

Collect behavioral data sets of target users from third-party software;

The present application also provides a computer-readable storage medium, including a storage data area and a storage program area, the storage data area stores created data, and the storage program area stores a computer program; wherein, the computer program is implemented as follows when executed by a processor step:

Collect behavioral data sets of target users from third-party software;

Description of drawings

1 is a schematic flowchart of a third-party software-based user data monitoring and analysis method provided by an embodiment of the present application;

2 is a schematic flowchart of S2 in the third-party software-based user data monitoring and analysis method provided by an embodiment of the present application;

3 is a schematic flowchart of S2 in the third-party software-based user data monitoring and analysis method provided by an embodiment of the present application;

4 is a schematic block diagram of a third-party software-based user data monitoring and analysis device provided by an embodiment of the present application;

5 is a schematic diagram of the internal structure of an electronic device for implementing a third-party software-based user data monitoring and analysis method provided by an embodiment of the present application;

The realization, functional characteristics and advantages of the purpose of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments.

Detailed ways

It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

Embodiments of the present application provide a method for monitoring and analyzing user data based on third-party software. The execution subject of the third-party software-based user data monitoring and analysis method includes, but is not limited to, at least one of electronic devices that can be configured to execute the method provided by the embodiments of the present application, such as a server and a terminal. In other words, the third-party software-based user data monitoring and analysis method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.

The present application provides a method for monitoring and analyzing user data based on third-party software. Referring to FIG. 1 , it is a schematic flowchart of a method for monitoring and analyzing user data based on third-party software provided by an embodiment of the present application. The method may be performed by an apparatus, which may be implemented in software and/or hardware.

In this embodiment, the method for monitoring and analyzing user data based on third-party software includes:

S1. Collect behavior data sets of target users from third-party software.

In a preferred embodiment of the present application, the target user refers to a user of third-party software. The third-party software refers to the first party and the second party, wherein the first party refers to the target user, the second party refers to the user or platform connected to the target user, and the third-party software refers to the target user. means the software used by the First Party.

In this embodiment of the present application, the behavior data set of the target user may be acquired from third-party software through a preconfigured monitoring script. Wherein, the configuration information of the monitoring script can be deployed on an internal server, and can be quickly configured by means of hot update, without deploying a version and without performing a grayscale test.

In the embodiment of the present application, the monitoring script can be directly verified by the data reported to the data statistics system by the production end, and if a mismatch is found, it can be quickly corrected by hot update, and the user level has no perception, no affect the experience. Wherein, the configuration information includes: user visual area information, user location information, etc., which is convenient for monitoring the behavior data set generated by the user when using the third-party software. The behavior data set includes: the duration of the user browsing the third-party software, the interface related to the user browsing the third-party software, the buttons the user clicks when browsing the third-party software, etc. The third-party software generally consists of multiple interfaces, and this application implements the In an example, the specific interface and duration of the user's operation of the third-party software are obtained, and the behavior data set is obtained.

Further, in this embodiment of the present application, the acquired behavior data set is first uploaded to the redis cache, and then the behavior data set is uploaded to the database, so as to prepare for subsequent analysis and processing of the behavior data set.

In another embodiment of the present application, the behavior data set may also be stored in a blockchain node.

S2. Perform a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set.

In the preferred embodiment of the present application, since the amount of data in the acquired behavior data set is relatively large, which is not conducive to the calculation and analysis of the user behavior data by the computer, it is necessary to perform a dimensionality reduction operation on the behavior data set, To reduce the amount of data to facilitate computer calculations.

In detail, referring to FIG. 2 , in the preferred embodiment of the present application, a dimensionality reduction operation is performed on the behavior data set to obtain a dimensionality reduction behavior data set, including:

S21, performing an encoding operation on the behavior data set to obtain a user behavior vector set;

In this embodiment of the present application, the word2vec method may be used to encode the behavior data set into a user behavior vector set.

S22, using a pre-built weight set to calculate the weight behavior vector set of the user behavior vector set;

In a preferred embodiment of the present application, the weight set is a weight preset by the user according to each user behavior in the user behavior vector set.

An optional embodiment of the present application may use the following formula to calculate the weighted behavior vector set of the behavior data set:

Wherein, X _j represents the jth weight behavior vector in the weight behavior vector set, x _j represents the j th user behavior vector in the user behavior vector set, k is the data amount of the weight behavior vector set, w _j is the The jth weight in the weight set.

For example, one of the application examples of this application encodes behavior data sets including the duration of the user browsing the third-party software, the interface related to the user's browsing of the third-party software, etc., respectively, and the duration of the user's browsing the third-party software is x ₁ . The software interface is the user behavior vector set of x ₂ , and the corresponding calculation is performed through the weight set to obtain the weight behavior vector set including the weight behavior vector sets X ₁ and X ₂ . S23. Perform dimensionality reduction processing on the weight behavior vector set to obtain the dimensionality reduction behavior data set.

An optional embodiment of the present application may use the following formula to perform dimensionality reduction processing on the weight behavior vector set:

Q _i =(X _i -X _i W _j W _j ^T )(X _i -X _i W _j W _j ^T ) ^T

Wherein, Q _i represents the ith dimension reduction behavior data in the dimensionality reduction behavior data set, X _i represents the ith weight behavior vector in the weight behavior vector set, and W _j represents the weight matrix obtained from the weight set. The jth row vector, W _j ^T represents the transpose of W _j .

In another optional embodiment of the present application, a PCA algorithm may also be used to perform dimensionality reduction processing on the weight behavior vector set to obtain a dimensionality reduction behavior data set.

S3, using a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and an abnormal behavior data set.

In a preferred embodiment of the present application, there are many abnormal data related to user behavior in the dimensionality reduction behavior data set. For example, the time when a user browses third-party software is generally considered to be normal data for several minutes to several hours. Hours or even twenty hours of browsing time are considered abnormal data. Therefore, the embodiment of the present application needs to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and an abnormal behavior data set.

In a preferred embodiment of the present application, a support vector data description (SVDD for short) can be used to construct a data anomaly detection model. The SVDD is a data description method that can describe the target dataset hyperspherically and can be used for heterogeneous point detection or classification. In detail, referring to FIG. 3 , the S3 includes:

S31. Construct a hypersphere according to the dimensionality reduction behavior data set;

In an optional embodiment, the hypersphere is constructed using the following formula:

C-α _i -γ _i =0

where α _i represents the first Lagrangian multiplier of the hypersphere, o represents the center of the hypersphere, C represents the penalty factor, q _i represents the dimensionality reduction behavior data set, and γ _i represents the relaxation variable .

S32, calculating the radius of the hypersphere;

In an optional embodiment, the radius of the hypersphere is calculated using the following formula:

Wherein, R represents the radius of the hypersphere, α _j represents the second Lagrangian multiplier of the hypersphere, Q _i , Q _j represent any two dimensionality reduction behavior data in the dimensionality reduction behavior data set, K ( ) represents a Gaussian kernel function.

S33, calculate the distance from the data in the dimensionality reduction behavior data set to the center of the hypersphere;

In an optional embodiment, the following formula is used to calculate the distance from the data in the dimensionality reduction behavior data set to the center of the hypersphere:

Wherein, D represents the distance from the data in the dimensionality reduction behavior data set to the center of the hypersphere, and || represents the norm calculation.

S34, summarizing the data whose distance is less than the radius to obtain the normal behavior data set;

In this embodiment of the present application, the distance from the data in the dimensionality reduction behavior data set to the center of the hypersphere is compared with the radius of the hypersphere, and if the distance is smaller than the radius of the hypersphere, the data is considered to be is normal data, and the data whose distance is smaller than the radius is aggregated by using SQL technology to obtain the normal behavior data set.

S35. Summarize the data whose distance is greater than or equal to the radius to obtain the abnormal behavior data set.

Further, in the embodiment of the present application, if the distance is greater than or equal to the radius of the hypersphere, the data is considered to be abnormal data, and SQL technology is used to summarize the data whose distance is greater than or equal to the radius to obtain: The abnormal behavior dataset.

S4. Using a preset collaborative filtering algorithm, perform data reconstruction according to the normal behavior data set and the abnormal behavior data set to obtain a standard data set.

In a preferred embodiment of the present application, the S4 includes: calculating the distance between each normal data in the normal behavior data set and each abnormal data in the abnormal behavior data set to obtain a distance value set; Each distance value in the distance value set is compared with a preset threshold value, normal data and abnormal data corresponding to the distance value set not greater than the threshold value are selected, and the selected normal data and abnormal data are aggregated to obtain a standard data set.

In an optional embodiment, the following formula is used to calculate the distance between the normal behavior data set and the abnormal behavior data set:

Wherein, dist(x,y) represents the distance between the normal behavior data set and the abnormal behavior data set, xi represents the data points in the normal behavior data set, yi represents the data points in the abnormal behavior data set, and n represents The data volume of the normal behavior data set or the abnormal behavior data set.

For example, the preset threshold is 10, and if the distance between a normal data A and an abnormal data B is 5, both the normal data A and the abnormal data B can be divided into the standard data set.

S5. Visualize the standard data set to obtain a visual chart set, and return the visual chart set to a preset terminal.

The visualization refers to transforming the unclear and unorganized data into a clear and intuitive chart form through certain technical means, which is convenient for analysis and viewing of the data. There are forms, and it is impossible to intuitively analyze the changes of users' browsing time. If these data are converted into line graphs, you can intuitively see the changes of users' browsing time; the number of times users click software buttons when browsing third-party software is also in the form of numbers. There are standard data sets. If you convert these data into column charts, you can intuitively see the number of button clicks in the software, and you can also intuitively see which buttons are most popular among users and which buttons are not.

Further, in a preferred embodiment of the present application, the jfreeChart icon drawing class library is invoked through java technology to process the standard data set, and a column chart set of clearly visible user behavior data is generated.

JFreeChart is an open chart drawing class library on the JAVA platform. It can draw data into pie charts, bar charts, scatter charts, time series charts, Gantt charts, line charts and other charts, and can generate PNG and JPEG formats. The output can also be associated with PDF and EXCEL.

This embodiment of the present application collects behavior data sets of target users from third-party software, and performs dimensionality reduction operations, data anomaly detection, and data reconstruction on the behavior data sets, thereby reducing the data dimensions of the behavior data sets, and converting the behavior data After the set is divided into a normal behavior data set and an abnormal behavior data set, data reconstruction is performed to obtain a standard data set. Compared with traditional analysis methods such as support vector machines, the dimensionality reduction operation in the embodiment of the present application can effectively reduce the data dimension and avoid Waste of storage and computing resources, while improving data through data anomaly detection and data reconstruction, and improving the accuracy of data monitoring, so the third-party software-based user data monitoring and analysis method, device and computer-readable storage medium proposed in this application, It can solve the problem of consuming a lot of computer memory in the process of data monitoring.

As shown in FIG. 4 , it is a schematic block diagram of the user data monitoring and analysis device based on the third-party software of the present application.

The apparatus 100 for monitoring and analyzing user data based on third-party software described in this application may be installed in an electronic device. According to the realized functions, the third-party software-based user data monitoring and analysis device may include a behavior data acquisition module 101 , a data detection module 102 , a data reconstruction module 103 and a visualization module 104 . The modules described in the present invention can also be called units, which refer to a series of computer program segments that can be executed by the electronic device processor and can perform fixed functions, and are stored in the memory of the electronic device.

In this embodiment, the functions of each module/unit are as follows:

The behavior data acquisition module 101 is used to collect the behavior data set of the target user from third-party software;

The data detection module 102 is configured to perform a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set, and use a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and anomalous behavior datasets;

The data reconstruction module 103 is configured to use a preset collaborative filtering algorithm to perform data reconstruction according to the normal behavior data set and the abnormal behavior data set to obtain a standard data set;

The visualization module 104 is configured to perform visualization processing on the standard data set to obtain a visual chart set, and transmit the visual chart set to a preset terminal;

In detail, the specific implementations of each module of the apparatus for extracting and generating text content in the image are as follows:

The behavior data acquisition module 101 is used to collect behavior data sets of target users from third-party software.

In the embodiment of the present application, the monitoring script can be directly verified by the data reported to the data statistics system by the production end, and if a mismatch is found, it can be quickly corrected by hot update, and the user level has no perception, no affect the experience. Wherein, the configuration information includes: user visual area information, user location information, etc., which is convenient for monitoring the behavior data set generated by the user when using the third-party software. The behavior data set includes: the duration of the user browsing the third-party software, the interface related to the user browsing the third-party software, the buttons clicked by the user when browsing the third-party software, and the like.

The data detection module 102 is configured to perform a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set, and use a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and Anomalous behavior dataset.

Specifically, in a preferred embodiment of the present application, performing a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set includes: performing an encoding operation on the behavior data set to obtain a user behavior vector set; using The pre-built weight set is calculated to obtain the weight behavior vector set of the user behavior vector set; the dimension reduction process is performed on the weight behavior vector set to obtain the dimension reduction behavior data set.

For example, one of the application examples of this application encodes behavior data sets including the duration of the user browsing the third-party software, the interface related to the user's browsing of the third-party software, etc., respectively, and the duration of the user's browsing the third-party software is x ₁ . The software-related interface is the user behavior vector set of x ₂ , and the corresponding calculation is performed through the weight set to obtain the weight behavior vector set including the weight behavior vector sets X ₁ and X ₂ .

Q _i =(X _i -X _i W _j W _j ^T )(X _i -X _i W _j W _j ^T ) ^T

In a preferred embodiment of the present application, a support vector data description (SVDD for short) can be used to construct a data anomaly detection model. The SVDD is a data description method that can describe the target dataset hyperspherically and can be used for heterogeneous point detection or classification. In detail, using a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and an abnormal behavior data set includes: constructing a hypersphere according to the dimensionality reduction behavior data set; Calculate the distance from the data in the dimensionality reduction behavior dataset to the center of the hypersphere; summarize the data whose distance is less than the radius to obtain the normal behavior dataset; summarize the distance greater than or data equal to the radius to obtain the abnormal behavior data set.

C-α _i -γ _i =0

The data reconstruction module 103 is configured to use a preset collaborative filtering algorithm to perform data reconstruction according to the normal behavior data set and the abnormal behavior data set to obtain a standard data set.

In a preferred embodiment of the present application, using a preset collaborative filtering algorithm to perform data reconstruction according to the normal behavior data set and the abnormal behavior data set to obtain a standard data set includes: calculating the normal behavior data The distance between each normal data in the set and each abnormal data in the abnormal behavior data set, to obtain a distance value set; compare each distance value in the distance value set with a preset threshold, and select not greater than the threshold The normal data and abnormal data corresponding to the distance value set are collected, and the selected normal data and abnormal data are aggregated to obtain a standard data set.

The visualization module 104 is configured to perform visualization processing on the standard data set to obtain a visual chart set, and transmit the visual chart set to a preset terminal.

As shown in FIG. 5 , it is a schematic structural diagram of an electronic device implementing a third-party software-based user data monitoring and analysis method in the present application.

The electronic device 1 may include a processor 10, a memory 11 and a bus, and may also include a computer program stored in the memory 11 and running on the processor 10, such as user data monitoring and analysis based on third-party software Procedure 12.

Wherein, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, CD etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1 , such as a mobile hard disk of the electronic device 1 . In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a pluggable mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital) equipped on the electronic device 1. , SD) card, flash memory card (Flash Card), etc. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various data installed in the electronic device 1, such as the code of the user data monitoring and analysis program 12 based on third-party software, etc., but also can be used to temporarily store the output that has been output or will be output. The data.

In some embodiments, the processor 10 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one or more integrated circuits. Central Processing Unit (CPU), microprocessor, digital processing chip, graphics processor and combination of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, by running or executing the program or module (for example, executing the program) stored in the memory 11. User data monitoring and analysis programs based on third-party software, etc.), and call the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

The bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (Extended industry standard architecture, EISA for short) bus or the like. The bus can be divided into address bus, data bus, control bus and so on. The bus is configured to implement connection communication between the memory 11 and at least one processor 10 and the like.

FIG. 5 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 5 does not constitute a limitation on the electronic device 1, and may include fewer or more components than those shown in the drawings. components, or a combination of certain components, or a different arrangement of components.

For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) for powering the various components, preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that the power management The device implements functions such as charge management, discharge management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components. The electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

Further, the electronic device 1 may also include a network interface, optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.

Optionally, the electronic device 1 may further include a user interface, and the user interface may be a display (Display), an input unit (eg, a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like. The display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.

It should be understood that the embodiments are only used for illustration, and are not limited by this structure in the scope of the patent application.

The third-party software-based user data monitoring and analysis program 12 stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, and when running in the processor 10, can achieve:

Collect behavioral data sets of target users from third-party software;

Further, if the modules/units integrated by the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium, and the computer-readable storage medium , which can be non-volatile or volatile. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) .

Further, the computer usable storage medium may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function, and the like; using the created data, etc.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division manners in actual implementation.

The modules described as separate components may or may not be physically separated, and components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.

It will be apparent to those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, but that the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

Accordingly, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the application is to be defined by the appended claims rather than the foregoing description, which is therefore intended to fall within the scope of the claims. All changes within the meaning and scope of the equivalents of , are included in this application. Any accompanying reference signs in the claims should not be construed as limiting the involved claims.

The blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

Furthermore, it is clear that the word "comprising" does not exclude other units or steps and the singular does not exclude the plural. Several units or means recited in the system claims can also be realized by one unit or means by means of software or hardware. Second-class terms are used to denote names and do not denote any particular order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application rather than limitations. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present application can be Modifications or equivalent substitutions can be made without departing from the spirit and scope of the technical solutions of the present application.

Claims

A method for monitoring and analyzing user data based on third-party software, wherein the method comprises:

Collect behavioral data sets of target users from third-party software;

performing a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set;

Using a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and an abnormal behavior data set;

Using a preset collaborative filtering algorithm, perform data reconstruction according to the normal behavior data set and the abnormal behavior data set to obtain a standard data set;

Perform visualization processing on the standard data set to obtain a visual chart set, and transmit the visual chart set to a preset terminal.
The method for monitoring and analyzing user data based on third-party software according to claim 1, wherein the behavior data set includes the duration of the user browsing the third-party software, the interface related to the user browsing the third-party software, the user browsing the button to click when describing third-party software.
The method for monitoring and analyzing user data based on third-party software according to claim 1, wherein, performing a dimension reduction operation on the behavior data set to obtain a dimension reduction behavior data set, comprising:

Perform an encoding operation on the behavior data set to obtain a user behavior vector set;

Using the pre-built weight set, calculate the weight behavior vector set of the user behavior vector set;

Perform dimensionality reduction processing on the weight behavior vector set to obtain the dimensionality reduction behavior data set.
The method for monitoring and analyzing user data based on third-party software according to claim 3, wherein the performing dimensionality reduction processing on the weight behavior vector set to obtain the dimensionality reduction behavior data set, comprising:

The dimensionality reduction process is performed on the weight behavior vector set using the following formula:

Q i =(X i -X i W j W j T )(X i -X i W j W j T ) T

Wherein, Q i represents the ith dimension reduction behavior data in the dimensionality reduction behavior data set, X i represents the ith weight behavior vector in the weight behavior vector set, and W j represents the weight matrix obtained from the weight set. The jth row vector, W j T represents the transpose of W j .
The method for monitoring and analyzing user data based on third-party software according to claim 1, wherein the dimensionality reduction behavior data set is detected by using a pre-built data abnormality detection model to obtain a normal behavior data set and an abnormal behavior data set ,include:

Construct a hypersphere according to the dimensionality reduction behavior data set, and calculate the radius of the hypersphere;

Calculate the distance from the data in the dimensionality reduction behavior data set to the center of the hypersphere;

Summarize the data whose distance is less than the radius to obtain the normal behavior data set;

Summarize the data whose distance is greater than or equal to the radius to obtain the abnormal behavior data set.
The method for monitoring and analyzing user data based on third-party software according to claim 5, wherein the calculating the radius of the hypersphere comprises:

The radius of the hypersphere is calculated using the following formula:

Wherein, R represents the radius of the hypersphere, α i represents the first Lagrangian multiplier of the hypersphere, α j represents the second Lagrangian multiplier of the hypersphere, Q i , Q j represents any two dimensionality reduction behavior data in the dimensionality reduction behavior data set, and K() represents a Gaussian kernel function.
The method for monitoring and analyzing user data based on third-party software according to any one of claims 1 to 6, wherein the use of a preset collaborative filtering algorithm is based on the normal behavior data set and the abnormal behavior data set Perform data reconstruction to get a standard dataset, including:

Calculate the distance between each normal data in the normal behavior data set and each abnormal data in the abnormal behavior data set to obtain a distance value set;

Compare each distance value in the distance value set with a preset threshold value, select normal data and abnormal data corresponding to the distance value set not greater than the threshold value, and summarize the selected normal data and abnormal data to obtain a standard data set .
A device for monitoring and analyzing user data based on third-party software, wherein the device includes:

A behavioral data acquisition module, used to collect behavioral data sets of target users from third-party software;

A data detection module is used to perform a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set, and use a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and abnormal behavior data set;

a data reconstruction module, configured to use a preset collaborative filtering algorithm to perform data reconstruction according to the normal behavior data set and the abnormal behavior data set to obtain a standard data set;

A visualization module, configured to perform visualization processing on the standard data set to obtain a visual chart set, and transmit the visual chart set to a preset terminal.
An electronic device, wherein the electronic device comprises:

at least one processor; and,

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of:

Collect behavioral data sets of target users from third-party software;

performing a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set;

Using a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and an abnormal behavior data set;

Using a preset collaborative filtering algorithm, perform data reconstruction according to the normal behavior data set and the abnormal behavior data set to obtain a standard data set;

Perform visualization processing on the standard data set to obtain a visual chart set, and transmit the visual chart set to a preset terminal.
The electronic device according to claim 9, wherein the behavior data set includes the duration of the user browsing the third-party software, the interface related to the user browsing the third-party software, and the buttons clicked by the user when browsing the third-party software .
The electronic device according to claim 9, wherein, performing a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set, comprising:

Perform an encoding operation on the behavior data set to obtain a user behavior vector set;

Using the pre-built weight set, calculate the weight behavior vector set of the user behavior vector set;

Perform dimensionality reduction processing on the weight behavior vector set to obtain the dimensionality reduction behavior data set.
The electronic device according to claim 11, wherein the performing a dimensionality reduction process on the weight behavior vector set to obtain the dimensionality reduction behavior data set, comprising:

The dimensionality reduction process is performed on the weight behavior vector set using the following formula:

Q i =(X i -X i W j W j T )(X i -X i W j W j T ) T

Wherein, Q i represents the ith dimension reduction behavior data in the dimensionality reduction behavior data set, X i represents the ith weight behavior vector in the weight behavior vector set, and W j represents the weight matrix obtained from the weight set. The jth row vector, W j T represents the transpose of W j .
The electronic device according to claim 9, wherein, using a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and an abnormal behavior data set, comprising:

Construct a hypersphere according to the dimensionality reduction behavior data set, and calculate the radius of the hypersphere;

Calculate the distance from the data in the dimensionality reduction behavior data set to the center of the hypersphere;

Summarize the data whose distance is less than the radius to obtain the normal behavior data set;

Summarize the data whose distance is greater than or equal to the radius to obtain the abnormal behavior data set.
The electronic device of claim 13, wherein the calculating the radius of the hypersphere comprises:

The radius of the hypersphere is calculated using the following formula:

Wherein, R represents the radius of the hypersphere, α i represents the first Lagrangian multiplier of the hypersphere, α j represents the second Lagrangian multiplier of the hypersphere, Q i , Q j represents any two dimensionality reduction behavior data in the dimensionality reduction behavior data set, and K() represents a Gaussian kernel function.
The electronic device according to any one of claims 9 to 14, wherein, by using a preset collaborative filtering algorithm, data reconstruction is performed according to the normal behavior data set and the abnormal behavior data set to obtain standard data set, including:

Calculate the distance between each normal data in the normal behavior data set and each abnormal data in the abnormal behavior data set to obtain a distance value set;

Compare each distance value in the distance value set with a preset threshold value, select normal data and abnormal data corresponding to the distance value set not greater than the threshold value, and summarize the selected normal data and abnormal data to obtain a standard data set .
A computer-readable storage medium, comprising a storage data area and a storage program area, the storage data area stores data created, and the storage program area stores a computer program; wherein, the computer program is executed by a processor The following steps are implemented:

Collect behavioral data sets of target users from third-party software;

performing a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set;

Using a pre-built data anomaly detection model to detect the dimensionality reduction behavior data set to obtain a normal behavior data set and an abnormal behavior data set;

Using a preset collaborative filtering algorithm, perform data reconstruction according to the normal behavior data set and the abnormal behavior data set to obtain a standard data set;

Perform visualization processing on the standard data set to obtain a visual chart set, and transmit the visual chart set to a preset terminal.
The computer-readable storage medium of claim 16 , wherein the behavior data set includes the duration of the user browsing the third-party software, the time the user browses the third-party software related interface, the time when the user browses the third-party software button to click.
The computer-readable storage medium of claim 16, wherein the performing a dimensionality reduction operation on the behavior data set to obtain a dimensionality reduction behavior data set, comprising:

Perform an encoding operation on the behavior data set to obtain a user behavior vector set;

Using the pre-built weight set, calculate the weight behavior vector set of the user behavior vector set;

Perform dimensionality reduction processing on the weight behavior vector set to obtain the dimensionality reduction behavior data set.
The computer-readable storage medium according to claim 18, wherein the performing dimensionality reduction processing on the weight behavior vector set to obtain the dimensionality reduction behavior data set comprises:

The dimensionality reduction process is performed on the weight behavior vector set using the following formula:

Q i =(X i -X i W j W j T )(X i -X i W j W j T ) T

Wherein, Q i represents the ith dimension reduction behavior data in the dimensionality reduction behavior data set, X i represents the ith weight behavior vector in the weight behavior vector set, and W j represents the weight matrix obtained from the weight set. The jth row vector, W j T represents the transpose of W j .
The computer-readable storage medium according to claim 16 , wherein, detecting the dimensionality reduction behavior data set by using a pre-built data abnormality detection model to obtain a normal behavior data set and an abnormal behavior data set, comprising:

Construct a hypersphere according to the dimensionality reduction behavior data set, and calculate the radius of the hypersphere;

Calculate the distance from the data in the dimensionality reduction behavior data set to the center of the hypersphere;

Summarize the data whose distance is less than the radius to obtain the normal behavior data set;

Summarize the data whose distance is greater than or equal to the radius to obtain the abnormal behavior data set.
The computer-readable storage medium of claim 20, wherein the calculating the radius of the hypersphere comprises:

The radius of the hypersphere is calculated using the following formula:

Wherein, R represents the radius of the hypersphere, α i represents the first Lagrangian multiplier of the hypersphere, α j represents the second Lagrangian multiplier of the hypersphere, Q i , Q j represents any two dimensionality reduction behavior data in the dimensionality reduction behavior data set, and K() represents a Gaussian kernel function.
The computer-readable storage medium according to any one of claims 16 to 21, wherein the data reconstruction is performed according to the normal behavior data set and the abnormal behavior data set by using a preset collaborative filtering algorithm, Get a standard dataset, including:

Calculate the distance between each normal data in the normal behavior data set and each abnormal data in the abnormal behavior data set to obtain a distance value set;

Compare each distance value in the distance value set with a preset threshold value, select normal data and abnormal data corresponding to the distance value set not greater than the threshold value, and summarize the selected normal data and abnormal data to obtain a standard data set .