Multi-data fusion computer virus detection method based on machine learning
Through machine learning technology, combining device performance and virus protection capabilities, adaptability recommendations are generated, which solves the problem that users find it difficult to choose suitable antivirus software, realizes multi-source data analysis and intelligent adaptation of computer virus detection performance, and improves user experience and software performance.
Patent Information
- Application Number
- CN202411163175.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-12-06
AI Technical Summary
It is difficult for computer users to choose antivirus software that is suitable for computer equipment, which makes it difficult for users to intuitively feel their virus detection capabilities when selecting antivirus software, which affects the software usage experience and cannot effectively analyze computer virus detection performance.
Using a multi-data fusion computer virus detection method based on machine learning, a virtual machine is built to perform performance evaluation and virus protection capability testing by acquiring the device performance data of computer equipment, and analyzing the performance and protection performance of virus detection software based on resource occupation data to generate Adaptation index, providing adaptability recommendations.
It realizes multi-source data analysis and intelligent adaptation of computer virus detection performance, helping users choose antivirus software suitable for the device, and improving user experience and software performance.
Smart Images

Figure CN119088689A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the computer field and relates to virus detection technology, in particular to a multi-data fusion computer virus detection method based on machine learning. Background Art
[0002] Computers, commonly known as computers, are modern electronic computing machines used for high-speed computing. They can perform numerical and logical calculations, and also have storage and memory functions. They are modern intelligent electronic devices that can run according to programs and automatically and quickly process massive amounts of data. They are composed of hardware systems and software systems. Computers without any software installed are called bare metal computers. They can be divided into five categories: supercomputers, industrial control computers, network computers, personal computers, and embedded computers. More advanced computers include biological computers, photonic computers, quantum computers, etc. The computers we commonly use are personal computers. When using personal computers, they usually download or configure corresponding security software to ensure the safe use of the computer.
[0003] Under the current technical background, computer users have insufficient knowledge of the performance of computer equipment. At the same time, computer users cannot intuitively feel the virus detection ability of the virus detection software in the computer, which makes it difficult for computer users to choose antivirus software that is compatible with the computer equipment, thus affecting the user's subsequent software usage experience. Therefore, how to analyze the computer virus detection performance based on multi-source data is the current problem;
[0004] To this end, we propose a multi-data fusion computer virus detection method based on machine learning. Summary of the invention
[0005] In view of the deficiencies in the prior art, the present invention aims to provide a multi-data fusion computer virus detection method based on machine learning.
[0006] The technical problems to be solved by the present invention are:
[0007] How to analyze computer virus detection performance based on multi-source data.
[0008] In order to achieve the above object, the present invention adopts the following technical solutions:
[0009] A multi-data fusion computer virus detection method based on machine learning, the method comprising:
[0010] Step S100, the machine body detection module obtains the equipment performance data of the computer equipment, and the equipment performance data is sent to the performance evaluation module, the environment construction module and the operation analysis module via the server;
[0011] Step S200, the performance evaluation module performs a comprehensive performance evaluation on the computer device, and obtains the computer device performance level. The computer device performance level is sent to the environment construction module via the server, and the environment construction module constructs a test virtual machine for virus detection.
[0012] Step S300, after the virtual machine to be tested is built, the operation monitoring module obtains the resource occupancy data of the virus detection and killing software, and the resource occupancy data is sent to the operation analysis module via the server;
[0013] Step S400, the operation analysis module performs a comprehensive analysis on the performance occupancy of the virus detection and killing software, and obtains the performance occupancy coefficient of the virus detection and killing software through the analysis, and the performance occupancy coefficient is sent to the application adaptation module via the server;
[0014] Step S500: The protection simulation module tests the virus protection capability of the virus detection and killing software, and obtains the protection test data of the virus detection and killing software through the test. The protection test data is sent to the protection evaluation module through the server. The protection evaluation module evaluates the virus protection performance of the virus detection and killing software, and obtains the protection evaluation value of the virus detection and killing software through the evaluation. The protection evaluation value is sent to the application adaptation module through the server.
[0015] Step S600, the application adaptation module analyzes the compatibility between the computer device and the virus detection software, and obtains a candidate list of the virus detection software. The candidate list is synchronized to the user terminal via the server, and the user terminal displays the compatibility of the virus detection software with the computer device.
[0016] Furthermore, the device performance data includes the processor cache, memory capacity, disk capacity, display cache and power supply efficiency of the computer device.
[0017] Furthermore, the evaluation process of the performance evaluation module in step S200 is specifically as follows:
[0018] Get the processor cache CPU, memory capacity NC and display cache GPU of the computer device according to the formula computer device body performance value XN, the formula is as follows:
[0019] XN=CPU×a1+NC×a2+GPU×a3;
[0020] Among them, a1, a2 and a3 are weight coefficients with fixed values, the values of a1, a2 and a3 are all greater than zero and a1+a2+a3=1, a1 is the processor performance weight, a2 is the memory performance weight, and a3 is the video memory performance weight;
[0021] comparing the body performance value of the computer device with the body performance threshold;
[0022] If the machine performance value is less than or equal to the first machine performance threshold, determining that the machine performance level of the computer device is the first machine performance level;
[0023] If the machine performance value is greater than the first machine performance threshold and less than or equal to the second machine performance threshold, then determining that the machine performance level of the computer device is the third machine performance level;
[0024] If the machine performance value is greater than the second machine performance threshold, determining that the machine performance level of the computer device is the third machine performance level;
[0025] Among them, the first body performance threshold and the second body performance threshold are both greater than zero, the first body performance threshold is less than the second body performance threshold, the comprehensive performance of equipment of the first body performance level is weaker than the comprehensive performance of equipment of the second body performance level, and the comprehensive performance of equipment of the second body performance level is weaker than the comprehensive performance of equipment of the third body performance level.
[0026] Furthermore, the virtual machine construction process of the environment construction module in step S200 is specifically as follows:
[0027] Obtain the computer equipment's body performance level and select the corresponding environmental configuration parameters;
[0028] Then, the files stored in the corresponding disk of the computer device are imported into the test virtual machine, and the files are marked as regular files and private files according to the corresponding privacy file ratios, thereby obtaining the number of regular files and the number of private files in the test virtual machine, installing the virus detection software into the test virtual machine and starting it, and running the test program according to the corresponding number of parallel programs;
[0029] Among them, the proportion of privacy files = number of privacy files / (number of regular files + number of privacy files).
[0030] Furthermore, the corresponding relationship between the environmental configuration parameters and the machine performance level is as follows:
[0031] If the machine performance is at the first machine performance level, setting the environment configuration parameters of the test virtual machine to the first privacy file ratio and the first number of parallel programs;
[0032] If the machine performance is at the second machine performance level, setting the environment configuration parameters of the test virtual machine to the second privacy file ratio and the second number of parallel programs;
[0033] If the machine performance is at the third machine performance level, setting the environment configuration parameters of the test virtual machine to the third privacy file ratio and the third number of parallel programs;
[0034] Among them, the privacy file ratio is the ratio between the number of privacy files and the total number of files in the computer device, the number of parallel programs is the number of running programs in the computer device except virus detection software, the value of the first privacy file ratio is smaller than the value of the second privacy file ratio, the value of the second privacy file ratio is smaller than the value of the third privacy file ratio, the first parallel program number is smaller than the second parallel program number, and the second parallel program number is smaller than the third parallel program number.
[0035] Furthermore, the resource usage data includes real-time cache usage, real-time memory usage, real-time video memory usage and power efficiency of the virus detection and killing software.
[0036] Furthermore, the analysis process of running the analysis module in step S400 is specifically as follows:
[0037] The processor cache HC, memory capacity NC, display cache XC and power efficiency GD of the computer device are obtained, and the real-time cache occupancy SHi, real-time memory occupancy SNi, real-time video memory occupancy SXi and power efficiency YDi of the virus detection software are also obtained, where i is the number of the virus detection software;
[0038] According to the formula, the performance occupancy coefficient of computer virus detection and killing software is XZi, and the formula is as follows:
[0039]
[0040] Among them, s1, s2, s3 and s4 are proportional coefficients with fixed values, and the values of s1, s2, s3 and s4 are all greater than zero.
[0041] Furthermore, the protection test process of the protection simulation module in step S500 is specifically as follows:
[0042] Retrieve a number of test viruses and input them into the test virtual machine in sequence, and run the virus detection and killing software to execute the protection process;
[0043] If the tester uses a virus to break through the protection program of the antivirus software within the preset protection time, the protection result will be recorded as a protection failure, and the protection time of the antivirus software's protection process, the number of regular file tampering, the number of private file tampering, and the time taken to repair the tampering will be recorded;
[0044] If the test virus fails to break through the protection program of the virus detection and killing software, the protection result is recorded as successful, and the next test virus is selected for testing;
[0045] The protection results of the virus detection and killing software are counted to obtain the number of successful protection and the number of failed protection of the virus detection and killing software;
[0046] The protection test data of the virus detection software is obtained by integrating the number of successful and failed protection times of the virus detection software, the protection duration of the protection process of failed protection, the number of regular file tampering times, the number of privacy file tampering times, and the time consumed for tampering repair.
[0047] Furthermore, the assessment process of the protection assessment module in step S500 is specifically as follows:
[0048] Obtain the number of successful protections SCi and the number of failed protections DFi of the virus detection software, as well as the protection duration FTir of the protection process of failed protection, the number of regular file tamperings NGir, the number of private file tamperings YGir, and the tampering repair time XFir, where r is the test virus serial number, the upper limit of r is R, the value of R is equal to r and the number of test viruses, and the order of the protection processes of the virus detection software corresponds one by one;
[0049] According to the formula, the protection evaluation value of computer virus detection and killing software is XNi, and the formula is as follows:
[0050]
[0051] Among them, b1 and b2 are weight coefficients of fixed values, the values of b1 and b2 are both greater than zero and b1+b2=1, b1 is the success rate weight, b2 is the protection and repair weight, r1 and r2 are proportional coefficients of fixed values, 0<r1<r2.
[0052] Furthermore, the analysis process of the application adaptation module in step S600 is specifically as follows:
[0053] Obtain the machine performance level of the computer equipment, and then obtain the performance occupancy coefficient XZi and protection evaluation value XNi of the virus detection and killing software;
[0054] The device adaptation index SPi between the computer device and the virus detection software is calculated according to the formula. The specific formula is as follows:
[0055] SPi=t1 / XZi+XNi×t2;
[0056] Wherein, t1 and t2 are preference coefficients, the values of t1 and t2 are both greater than zero and t1+t2=1, when the body performance level of the computer device is the first body performance level, t1>t2, when the body performance level of the computer device is the second body performance level, t1=t2, when the body performance level of the computer device is the third body performance level, t1<t2;
[0057] Compare the device adaptation index between the computer device and the virus detection software with the device adaptation threshold;
[0058] If the device adaptation index is less than the device adaptation threshold, the virus detection and removal software is removed from the candidate list;
[0059] If the device adaptation index is greater than or equal to the device adaptation threshold, the virus detection and killing software is selected into the candidate list and the virus detection and killing software are sorted in descending order.
[0060] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:
[0061] The body detection module of the present invention obtains the equipment performance data of the computer device, and combines the equipment performance data. On the one hand, the performance evaluation module is used to perform a comprehensive performance evaluation on the body of the computer device, and the body performance level of the computer device is obtained by evaluation. On the other hand, the environment construction module is used to construct a test virtual machine for virus detection. After the test virtual machine is constructed, the operation monitoring module obtains the resource occupancy data of the virus detection and killing software, and combines the resource occupancy data to perform a comprehensive analysis on the performance occupancy of the virus detection and killing software by using the operation analysis module, and the performance occupancy coefficient of the virus detection and killing software is obtained by analysis. At the same time, the protection simulation module tests the virus protection capability of the virus detection and killing software, and the protection test data of the virus detection and killing software is obtained by the test. The protection evaluation module evaluates the virus protection performance of the virus detection and killing software in combination with the protection test data, and the protection evaluation value of the virus detection and killing software is obtained by evaluation. The application adaptation module analyzes the degree of adaptation between the computer device and the virus detection and killing software in combination with the performance occupancy coefficient and the protection evaluation value, and the candidate list of the virus detection and killing software is obtained by analysis. The present invention realizes the analysis of the computer virus detection performance and the intelligent adaptation of the computer device and the virus detection and killing software based on multi-source data. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.
[0063] Figure 1 is a flow chart of the method of the present invention;
[0064] Figure 2 is the overall system block diagram of the present invention;
[0065] Figure 3 It is a schematic diagram of the structure of the computer device in the present invention. DETAILED DESCRIPTION
[0066] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0067] Example 1: Please refer to Figure 1-Figure 2 As shown, the technical solution provided by the present invention is: a multi-data fusion computer virus detection method based on machine learning, the method is specifically as follows:
[0068] Step S100, the machine body detection module obtains the equipment performance data of the computer equipment, and the equipment performance data is sent to the performance evaluation module, the environment construction module and the operation analysis module via the server;
[0069] Step S200, the performance evaluation module performs a comprehensive performance evaluation on the computer device, and obtains the computer device performance level. The computer device performance level is sent to the environment construction module via the server, and the environment construction module constructs a test virtual machine for virus detection.
[0070] Step S300, after the virtual machine to be tested is built, the operation monitoring module obtains the resource occupancy data of the virus detection and killing software, and the resource occupancy data is sent to the operation analysis module via the server;
[0071] Step S400, the operation analysis module performs a comprehensive analysis on the performance occupancy of the virus detection and killing software, and obtains the performance occupancy coefficient of the virus detection and killing software through the analysis, and the performance occupancy coefficient is sent to the application adaptation module via the server;
[0072] Step S500: The protection simulation module tests the virus protection capability of the virus detection and killing software, and obtains the protection test data of the virus detection and killing software through the test. The protection test data is sent to the protection evaluation module through the server. The protection evaluation module evaluates the virus protection performance of the virus detection and killing software, and obtains the protection evaluation value of the virus detection and killing software through the evaluation. The protection evaluation value is sent to the application adaptation module through the server.
[0073] Step S600, the application adaptation module analyzes the compatibility between the computer device and the virus detection software, and obtains a candidate list of the virus detection software. The candidate list is synchronized to the user terminal via the server, and the user terminal displays the compatibility of the virus detection software with the computer device.
[0074] In this embodiment, the method involves a server, which is connected to the organism detection module, the performance evaluation module, the environment construction module, the operation detection module, the operation analysis module, the protection simulation module, the protection evaluation module, the application adaptation module and the user terminal;
[0075] In this embodiment, the computer device is installed with virus detection software, and by running the virus detection software, the computer device includes a desktop computer, a laptop computer, a mobile phone, and a tablet computer;
[0076] The machine body detection module is used to obtain the equipment performance data of the computer equipment and send the equipment performance data to the server, and the server sends the equipment performance data of the computer equipment to the performance evaluation module, the environment construction module and the operation analysis module;
[0077] It should be specifically noted that the device performance data includes the processor cache, memory capacity, disk capacity, display cache and power supply efficiency of the computer device, among which the processor cache is the total cache of the central processing unit of the computer device, the memory capacity is the total memory of the computer device, the disk capacity is the total capacity of the physical drive disk in the computer device, the display cache is the total cache of the graphics processor in the computer device, and the power supply efficiency is the rated power of the host power supply in the computer device.
[0078] In this embodiment, the performance evaluation module is used to perform a comprehensive performance evaluation on the computer device. The evaluation process is as follows:
[0079] Get the processor cache CPU, memory capacity NC and display cache GPU of the computer device according to the formula computer device body performance value XN, the formula is as follows:
[0080] XN=CPU×a1+NC×a2+GPU×a3;
[0081] Among them, a1, a2 and a3 are weight coefficients with fixed values, the values of a1, a2 and a3 are all greater than zero and a1+a2+a3=1, a1 is the processor performance weight, a2 is the memory performance weight, and a3 is the video memory performance weight. In the actual working process, the value of each weight is determined according to the performance characteristics of the computer device or the performance requirements of the computer user. For example, the performance characteristics of the computer device are excellent processor performance, and the performance requirements of the computer user are memory performance, then the relationship between the weights is a2>a1>a3;
[0082] comparing the body performance value of the computer device with the body performance threshold;
[0083] If the machine performance value is less than or equal to the first machine performance threshold, determining that the machine performance level of the computer device is the first machine performance level;
[0084] If the machine performance value is greater than the first machine performance threshold and less than or equal to the second machine performance threshold, then determining that the machine performance level of the computer device is the third machine performance level;
[0085] If the machine performance value is greater than the second machine performance threshold, determining that the machine performance level of the computer device is the third machine performance level;
[0086] Among them, the first body performance threshold and the second body performance threshold are both greater than zero, the first body performance threshold is less than the second body performance threshold, the comprehensive performance of the equipment of the first body performance level is weaker than the comprehensive performance of the equipment of the second body performance level, and the comprehensive performance of the equipment of the second body performance level is weaker than the comprehensive performance of the equipment of the third body performance level;
[0087] The performance evaluation module sends the computer device's body performance level to the server, and the server sends the computer device's body performance level to the environment construction module;
[0088] The environment construction module is used to construct a test virtual machine for virus detection. The virtual machine construction process is as follows:
[0089] Obtain the computer equipment's body performance level and select the corresponding environmental configuration parameters;
[0090] The corresponding relationship between environmental configuration parameters and aircraft performance levels is as follows:
[0091] If the machine performance is at the first machine performance level, setting the environment configuration parameters of the test virtual machine to the first privacy file ratio and the first number of parallel programs;
[0092] If the machine performance is at the second machine performance level, setting the environment configuration parameters of the test virtual machine to the second privacy file ratio and the second number of parallel programs;
[0093] If the machine performance is at the third machine performance level, setting the environment configuration parameters of the test virtual machine to the third privacy file ratio and the third number of parallel programs;
[0094] The privacy file ratio is the ratio between the number of privacy files and the total number of files in the computer device, the number of parallel programs is the number of other running programs in the computer device except the virus detection software, in this embodiment, the parallel programs are all test programs, and the resource usage of each test program is consistent when running, the value of the first privacy file ratio is less than the value of the second privacy file ratio, the value of the second privacy file ratio is less than the value of the third privacy file ratio, the first parallel program number is less than the second parallel program number, and the second parallel program number is less than the third parallel program number;
[0095] Then, the files stored in the corresponding disk of the computer device are imported into the test virtual machine, and the files are marked as regular files and privacy files according to the corresponding privacy file ratio. The number of regular files and the number of privacy files of the test virtual machine are thus obtained by counting. The virus detection software is installed on the test virtual machine and started, and the test program is run according to the corresponding number of parallel programs. It can be understood that the relationship between the number of regular files and the number of privacy files is specifically: privacy file ratio = number of privacy files / (number of regular files + number of privacy files).
[0096] After the virtual machine to be tested is built, the operation monitoring module is used to obtain resource occupancy data of the virus detection and killing software, and send the resource occupancy data to the server, and the server sends the resource occupancy data of the virus detection and killing software to the operation analysis module, and the resource occupancy data includes the real-time cache occupancy, real-time memory occupancy, real-time video memory occupancy and power efficiency of the virus detection and killing software;
[0097] In this embodiment, the operation analysis module is used to comprehensively analyze the performance occupancy of the virus detection and killing software. The specific analysis process is as follows:
[0098] The processor cache HC, memory capacity NC, display cache XC and power efficiency GD of the computer device are obtained, and the real-time cache occupancy SHi, real-time memory occupancy SNi, real-time video memory occupancy SXi and power efficiency YDi of the virus detection software are also obtained, where i is the number of the virus detection software;
[0099] According to the formula, the performance occupancy coefficient of computer virus detection and killing software is XZi, and the formula is as follows:
[0100]
[0101] Among them, s1, s2, s3 and s4 are proportional coefficients of fixed values, and the values of s1, s2, s3 and s4 are all greater than zero. It can be understood that the proportional coefficients are used to adjust the values of various indicators to the same order of magnitude;
[0102] The operation analysis module sends the performance occupancy coefficient of the virus detection and killing software to the server, and the server sends the performance occupancy coefficient of the virus detection and killing software to the application adaptation module.
[0103] In this embodiment, the protection simulation module is used to test the virus protection capability of the virus detection and killing software. The protection test process is as follows:
[0104] Retrieve a number of test viruses and input them into the test virtual machine in sequence, and run the virus detection and killing software to execute the protection process;
[0105] If the tester uses a virus to break through the protection program of the antivirus software within the preset protection time, the protection result will be recorded as a protection failure, and the protection time of the antivirus software's protection process, the number of regular file tampering, the number of private file tampering, and the time taken to repair the tampering will be recorded;
[0106] If the test virus fails to break through the protection program of the virus detection and killing software, the protection result is recorded as successful, and the next test virus is selected for testing;
[0107] The protection results of the virus detection and killing software are counted to obtain the number of successful protection and the number of failed protection of the virus detection and killing software;
[0108] The protection test data of the virus detection and killing software is obtained by integrating the number of successful and failed protections of the virus detection and killing software, the protection duration of the protection process of the failed protection, the number of regular file tamperings, the number of private file tamperings, and the time taken to repair the tamperings;
[0109] The protection simulation module sends the protection test data of the virus detection and killing software to the server, and the server sends the protection test data of the virus detection and killing software to the protection assessment module;
[0110] The protection assessment module is used to assess the virus protection performance of the virus detection and killing software. The assessment process is as follows:
[0111] Obtain the number of successful protections SCi and the number of failed protections DFi of the virus detection software, as well as the protection duration FTir of the protection process of failed protection, the number of regular file tamperings NGir, the number of private file tamperings YGir, and the tampering repair time XFir, where r is the test virus serial number, the upper limit of r is R, the value of R is equal to r and the number of test viruses, and the order of the protection processes of the virus detection software corresponds one by one;
[0112] According to the formula, the protection evaluation value of computer virus detection and killing software is XNi, and the formula is as follows:
[0113]
[0114] Among them, b1 and b2 are weight coefficients of fixed values, the values of b1 and b2 are both greater than zero and b1+b2=1, b1 is the success rate weight, b2 is the protection and repair weight, r1 and r2 are proportional coefficients of fixed values, 0<r1<r2. It can be understood that the more successful times of virus detection and killing software, the longer the protection time, the fewer the number of regular file tampering and privacy file tampering, the shorter the tampering repair time, and the stronger the protection evaluation of the virus detection and killing software;
[0115] The protection evaluation module sends the protection evaluation value of the virus detection and killing software to the server, and the server sends the protection evaluation value of the virus detection and killing software to the application adaptation module.
[0116] The application adaptation module is used to analyze the degree of adaptation between the computer device and the virus detection and killing software. The specific analysis process is as follows:
[0117] Obtain the machine performance level of the computer equipment, and then obtain the performance occupancy coefficient XZi and protection evaluation value XNi of the virus detection and killing software;
[0118] The device adaptation index SPi between the computer device and the virus detection software is calculated according to the formula. The specific formula is as follows:
[0119] SPi=t1 / XZi+XNi×t2;
[0120] Wherein, t1 and t2 are preference coefficients, the values of t1 and t2 are both greater than zero and t1+t2=1, when the body performance level of the computer device is the first body performance level, t1>t2, when the body performance level of the computer device is the second body performance level, t1=t2, when the body performance level of the computer device is the third body performance level, t1<t2;
[0121] Compare the device adaptation index between the computer device and the virus detection software with the device adaptation threshold;
[0122] If the device adaptation index is less than the device adaptation threshold, the virus detection and removal software is removed from the candidate list;
[0123] If the device adaptation index is greater than or equal to the device adaptation threshold, the virus detection software is selected into the candidate list and the virus detection software is sorted in descending order;
[0124] The application adaptation module synchronizes the candidate list to the user terminal via the server, and the user terminal displays the compatibility of the virus detection software and the computer device based on the candidate list through the display;
[0125] Example 2: Figure 3As shown, the present invention also provides a structural schematic diagram of a computer device, which may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor can call the logic instructions in the memory to execute a multi-data fusion computer virus detection method based on machine learning, the method comprising: a body detection module obtains the device performance data of the computer device, and the device performance data is sent to a performance evaluation module, an environment construction module, and an operation analysis module via a server; the performance evaluation module performs a comprehensive performance evaluation on the body of the computer device, and obtains the body performance level of the computer device, and the body performance level is sent to the environment construction module via a server, and the environment construction module constructs a test virtual machine for virus detection; after the test virtual machine is constructed, the operation monitoring module obtains the resource occupancy data of the virus detection software, and the resource occupancy data is sent to the operation analysis module via a server; the operation analysis ... performance of the virus detection software is analyzed by the operation analysis module. A comprehensive analysis is conducted on the occupancy situation to obtain the performance occupancy coefficient of the virus detection software, which is sent to the application adaptation module via the server; the protection simulation module tests the virus protection capability of the virus detection software, and obtains the protection test data of the virus detection software. The protection test data is sent to the protection assessment module via the server. The protection assessment module assesses the virus protection performance of the virus detection software, and obtains the protection assessment value of the virus detection software. The protection assessment value is sent to the application adaptation module via the server; the application adaptation module analyzes the degree of compatibility between the computer device and the virus detection software, and obtains a candidate list of the virus detection software. The candidate list is synchronized to the user terminal via the server, and the user terminal displays the compatibility of the virus detection software and the computer device.
[0126] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.
[0127] Embodiment 3: The present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the multi-data fusion computer virus detection method based on machine learning provided by the above methods, and the method includes: a body detection module obtains device performance data of a computer device, and the device performance data is sent to a performance evaluation module, an environment construction module and an operation analysis module via a server; the performance evaluation module performs a comprehensive performance evaluation on the body of the computer device, and obtains the body performance level of the computer device by evaluation, and the body performance level is sent to the environment construction module via a server, and the environment construction module constructs a test virtual machine for virus detection; after the test virtual machine is constructed, the operation monitoring module obtains the resource occupancy of the virus detection software The data and resource occupancy data are sent to the operation analysis module via the server; the operation analysis module conducts a comprehensive analysis on the performance occupancy of the virus detection and killing software, and obtains the performance occupancy coefficient of the virus detection and killing software through the analysis, and the performance occupancy coefficient is sent to the application adaptation module via the server; the protection simulation module tests the virus protection capability of the virus detection and killing software, and obtains the protection test data of the virus detection and killing software through the test, and the protection test data is sent to the protection assessment module via the server, and the protection assessment module assesses the virus protection performance of the virus detection and killing software, and obtains the protection assessment value of the virus detection and killing software through the assessment, and the protection assessment value is sent to the application adaptation module via the server; the application adaptation module analyzes the degree of compatibility between the computer device and the virus detection and killing software, and obtains the candidate list of the virus detection and killing software through the analysis, and the candidate list is synchronized to the user terminal via the server, and the user terminal displays the compatibility of the virus detection and killing software with the computer device.
[0128] Embodiment 4: The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned multi-data fusion computer virus detection method based on machine learning, the method comprising: a body detection module obtains device performance data of a computer device, and the device performance data is sent to a performance evaluation module, an environment construction module and an operation analysis module via a server; the performance evaluation module performs a comprehensive performance evaluation on the body of the computer device, and obtains the body performance level of the computer device, and the body performance level is sent to the environment construction module via a server, and the environment construction module constructs a test virtual machine for virus detection; after the test virtual machine is constructed, the operation monitoring module obtains resource occupancy data of the virus detection software, and the resource occupancy data is sent to the operation analysis module via the server. Module; the operation analysis module conducts a comprehensive analysis on the performance occupancy of the virus detection and killing software, and obtains the performance occupancy coefficient of the virus detection and killing software through the analysis, and the performance occupancy coefficient is sent to the application adaptation module through the server; the protection simulation module tests the virus protection capability of the virus detection and killing software, and obtains the protection test data of the virus detection and killing software through the test, and the protection test data is sent to the protection assessment module through the server, and the protection assessment module assesses the virus protection performance of the virus detection and killing software, and obtains the protection assessment value of the virus detection and killing software through the assessment, and the protection assessment value is sent to the application adaptation module through the server; the application adaptation module analyzes the degree of compatibility between the computer device and the virus detection and killing software, and obtains the candidate list of the virus detection and killing software through the analysis, and the candidate list is synchronized to the user terminal through the server, and the user terminal displays the compatibility of the virus detection and killing software with the computer device.
[0129] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0130] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A multi-data fusion computer virus detection method based on machine learning, characterized in that: Methods include: Step S100, the machine body detection module obtains the equipment performance data of the computer equipment, and the equipment performance data is sent to the performance evaluation module, the environment construction module and the operation analysis module via the server; Step S200, the performance evaluation module performs a comprehensive performance evaluation on the computer device, and obtains the computer device performance level. The computer device performance level is sent to the environment construction module via the server, and the environment construction module constructs a test virtual machine for virus detection. Step S300, after the virtual machine to be tested is built, the operation monitoring module obtains the resource occupancy data of the virus detection and killing software, and the resource occupancy data is sent to the operation analysis module via the server; Step S400, the operation analysis module performs a comprehensive analysis on the performance occupancy of the virus detection and killing software, and obtains the performance occupancy coefficient of the virus detection and killing software through the analysis, and the performance occupancy coefficient is sent to the application adaptation module via the server; Step S500: The protection simulation module tests the virus protection capability of the virus detection and killing software, and obtains the protection test data of the virus detection and killing software through the test. The protection test data is sent to the protection evaluation module through the server. The protection evaluation module evaluates the virus protection performance of the virus detection and killing software, and obtains the protection evaluation value of the virus detection and killing software through the evaluation. The protection evaluation value is sent to the application adaptation module through the server. Step S600, the application adaptation module analyzes the compatibility between the computer device and the virus detection software, and obtains a candidate list of the virus detection software. The candidate list is synchronized to the user terminal via the server, and the user terminal displays the compatibility of the virus detection software with the computer device.
2. The multi-data fusion computer virus detection method based on machine learning according to claim 1 is characterized in that: Device performance data includes the computer device's processor cache, memory capacity, disk capacity, display cache, and power supply efficiency.
3. The multi-data fusion computer virus detection method based on machine learning according to claim 2 is characterized in that: The evaluation process of the performance evaluation module in step S200 is specifically as follows: Get the processor cache CPU, memory capacity NC and display cache GPU of the computer device according to the formula computer device body performance value XN, the formula is as follows: XN=CPU×a1+NC×a2+GPU×a3; Among them, a1, a2 and a3 are weight coefficients with fixed values, the values of a1, a2 and a3 are all greater than zero and a1+a2+a3=1, a1 is the processor performance weight, a2 is the memory performance weight, and a3 is the video memory performance weight; comparing the body performance value of the computer device with the body performance threshold; If the machine performance value is less than or equal to the first machine performance threshold, determining that the machine performance level of the computer device is the first machine performance level; If the machine performance value is greater than the first machine performance threshold and less than or equal to the second machine performance threshold, then determining that the machine performance level of the computer device is the third machine performance level; If the machine performance value is greater than the second machine performance threshold, determining that the machine performance level of the computer device is the third machine performance level; Among them, the first body performance threshold and the second body performance threshold are both greater than zero, the first body performance threshold is less than the second body performance threshold, the comprehensive performance of equipment of the first body performance level is weaker than the comprehensive performance of equipment of the second body performance level, and the comprehensive performance of equipment of the second body performance level is weaker than the comprehensive performance of equipment of the third body performance level.
4. The multi-data fusion computer virus detection method based on machine learning according to claim 3 is characterized in that: The virtual machine construction process of the environment construction module in step S200 is specifically as follows: Obtain the computer equipment's body performance level and select the corresponding environmental configuration parameters; Then, the files stored in the corresponding disk of the computer device are imported into the test virtual machine, and the files are marked as regular files and private files according to the corresponding privacy file ratios, thereby obtaining the number of regular files and the number of private files in the test virtual machine, installing the virus detection software into the test virtual machine and starting it, and running the test program according to the corresponding number of parallel programs; Among them, the proportion of privacy files = number of privacy files / (number of regular files + number of privacy files).
5. The multi-data fusion computer virus detection method based on machine learning according to claim 4 is characterized in that: The corresponding relationship between environmental configuration parameters and aircraft performance levels is as follows: If the machine performance is at the first machine performance level, setting the environment configuration parameters of the test virtual machine to the first privacy file ratio and the first number of parallel programs; If the machine performance is at the second machine performance level, setting the environment configuration parameters of the test virtual machine to the second privacy file ratio and the second number of parallel programs; If the machine performance is at the third machine performance level, setting the environment configuration parameters of the test virtual machine to the third privacy file ratio and the third number of parallel programs; Among them, the privacy file ratio is the ratio between the number of privacy files and the total number of files in the computer device, the number of parallel programs is the number of running programs in the computer device except virus detection software, the value of the first privacy file ratio is smaller than the value of the second privacy file ratio, the value of the second privacy file ratio is smaller than the value of the third privacy file ratio, the first parallel program number is smaller than the second parallel program number, and the second parallel program number is smaller than the third parallel program number.
6. The multi-data fusion computer virus detection method based on machine learning according to claim 4 is characterized in that: Resource usage data includes the real-time cache usage, real-time memory usage, real-time video memory usage and power efficiency of the virus detection software.
7. The multi-data fusion computer virus detection method based on machine learning according to claim 6 is characterized in that: The analysis process of running the analysis module in step S400 is specifically as follows: The processor cache HC, memory capacity NC, display cache XC and power efficiency GD of the computer device are obtained, and the real-time cache occupancy SHi, real-time memory occupancy SNi, real-time video memory occupancy SXi and power efficiency YDi of the virus detection software are also obtained, where i is the number of the virus detection software; According to the formula, the performance occupancy coefficient of computer virus detection and killing software is XZi, and the formula is as follows: Among them, s1, s2, s3 and s4 are proportional coefficients with fixed values, and the values of s1, s2, s3 and s4 are all greater than zero.
8. The multi-data fusion computer virus detection method based on machine learning according to claim 7 is characterized in that: The protection test process of the protection simulation module in step S500 is specifically as follows: Retrieve a number of test viruses and input them into the test virtual machine in sequence, and run the virus detection and killing software to execute the protection process; If the tester uses a virus to break through the protection program of the antivirus software within the preset protection time, the protection result will be recorded as a protection failure, and the protection time of the antivirus software's protection process, the number of regular file tampering, the number of private file tampering, and the time taken to repair the tampering will be recorded; If the test virus fails to break through the protection program of the virus detection and killing software, the protection result is recorded as successful, and the next test virus is selected for testing; The protection results of the virus detection and killing software are counted to obtain the number of successful protection and the number of failed protection of the virus detection and killing software; The protection test data of the virus detection software is obtained by integrating the number of successful and failed protection times of the virus detection software, the protection duration of the protection process of failed protection, the number of regular file tampering times, the number of privacy file tampering times, and the time consumed for tampering repair.
9. The multi-data fusion computer virus detection method based on machine learning according to claim 8 is characterized in that: The assessment process of the protection assessment module in step S500 is specifically as follows: Obtain the number of successful protections SCi and the number of failed protections DFi of the virus detection software, as well as the protection duration FTir of the protection process of failed protection, the number of regular file tamperings NGir, the number of private file tamperings YGir, and the tampering repair time XFir, where r is the test virus serial number, the upper limit of r is R, the value of R is equal to r and the number of test viruses, and the order of the protection processes of the virus detection software corresponds one by one; According to the formula, the protection evaluation value of computer virus detection and killing software is XNi, and the formula is as follows: Among them, b1 and b2 are weight coefficients of fixed values, the values of b1 and b2 are both greater than zero and b1+b2=1, b1 is the success rate weight, b2 is the protection and repair weight, r1 and r2 are proportional coefficients of fixed values, 0<r1<r2.
10. The multi-data fusion computer virus detection method based on machine learning according to claim 9 is characterized in that: The analysis process of the application adaptation module in step S600 is specifically as follows: Obtain the machine performance level of the computer equipment, and then obtain the performance occupancy coefficient XZi and protection evaluation value XNi of the virus detection and killing software; The device adaptation index SPi between the computer device and the virus detection software is calculated according to the formula. The specific formula is as follows: SPi=t1 / XZi+XNi×t2; Wherein, t1 and t2 are preference coefficients, the values of t1 and t2 are both greater than zero and t1+t2=1, when the body performance level of the computer device is the first body performance level, t1>t2, when the body performance level of the computer device is the second body performance level, t1=t2, when the body performance level of the computer device is the third body performance level, t1<t2; Compare the device adaptation index between the computer device and the virus detection software with the device adaptation threshold; If the device adaptation index is less than the device adaptation threshold, the virus detection and removal software is removed from the candidate list; If the device adaptation index is greater than or equal to the device adaptation threshold, the virus detection and killing software is selected into the candidate list and the virus detection and killing software are sorted in descending order.
