Smart commercial display device playback safety detection method, detection equipment and storage medium

Abstract

The present invention relates to the field of device playback safety detection technology, in particular to a smart commercial display device playback safety detection method, detection device and storage medium. A series of smart commercial display device playback simulators are constructed based on a cloud-based dangerous application list, and the danger of each application is analyzed through the smart commercial display device playback simulator to obtain a first safety detection result; in a Markov decision algorithm, each permission-related basic item required for the operation of each application is calculated to execute the application permission application strategy and then transfer to the corresponding permission request list for rationality to obtain a second safety detection result; by scanning the media file list to detect and analyze whether the actual metadata of each media file in the list is tampered with by different virus metadata tampering characters, a third safety detection result is obtained. The present invention can perform multi-faceted detection and analysis on the playback security of smart commercial display devices to improve the playback security index of smart commercial display devices.

Description

Technical Field

[0001] The present invention relates to the technical field of device playback safety detection technology, and in particular to a playback safety detection method, detection equipment and storage medium for intelligent commercial display devices. Background Art

[0002] Smart commercial display devices are commercial display devices that integrate intelligent functions and are usually used in scenarios such as advertising display, information release, and interactive display. These devices combine display technology, network technology, and artificial intelligence technology to provide dynamic, interactive, and personalized information display, greatly improving the efficiency and effectiveness of information release. However, smart commercial display devices usually need to rely on running applications to display playback content, and this process must involve system permission application, file reading and calling, and application running. If smart commercial display devices have frequent system permission opening configurations, excessive application permission applications, high-risk applications, and malicious viruses tampering with file data, the smart commercial display device will cause playback privacy content leakage and core file tampering and damage, reducing the playback security of smart commercial display devices. Traditional detection methods have low accuracy and efficiency in detecting playback security of smart commercial display devices, and there are even cases where the security inspection and evaluation functions are not suitable, which cannot meet the comprehensive security performance evaluation of smart commercial display devices. Summary of the invention

[0003] The present invention overcomes the shortcomings of the prior art and provides a smart commercial display device playback safety detection method, detection equipment and storage medium.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides a method for detecting playback safety of an intelligent commercial display device, comprising the following steps:

[0006] S102: Acquire all playback system permissions required by the smart commercial display device to meet playback requirements, recursively split and calculate key playback system permissions from all playback system permissions according to the playback system gradient level, analyze the open configuration security of the key playback system permissions, and generate a system security detection result;

[0007] S104: Obtain a list of dangerous cloud applications associated with the cloud system of the smart commercial display device, build a series of smart commercial display device playback simulators based on the list of dangerous cloud applications, analyze the danger of the applications in the smart commercial display device through the smart commercial display device playback simulators, and obtain a first security detection result;

[0008] S106: Based on the first security detection result, the Markov decision algorithm is used to calculate the state transition probability of each permission-related basic item required for the operation of each application program to transfer to the corresponding permission request list after executing the application permission application strategy, and the permission request security of the application program is analyzed according to the rationality of the state transition probability to obtain a second security detection result;

[0009] S108: Obtain a media file list of the smart commercial display device, and scan the media file list to detect and analyze whether the actual metadata of each media file in the list is tampered with by different virus metadata tampering characters, thereby obtaining a third security detection result;

[0010] S110: An initial security assessment result set of the first security detection result, the second security detection result, and the third security detection result is analyzed by mapping through a Logistic mapping model to construct a security assessment optimization model to calibrate a preset security assessment tool for the intelligent commercial display device.

[0011] More specifically, the step S102 includes the following steps:

[0012] Obtain the playback requirements of the smart commercial display device, and at the same time obtain the system permission list of the smart commercial display device, search in the system permission list based on the playback requirements, and obtain all playback system permissions corresponding to the playback requirements;

[0013] Obtaining architecture design data of the playback system of the intelligent commercial display device, retrieving the playback system gradient level of the intelligent commercial display device in the big data network according to the architecture design data, introducing a trade-off algorithm to jointly calculate the information gain of each system authority in all the playback system authorities for each gradient level in the playback system gradient level, and generating a split information gain;

[0014] Constructing the root node of all playback system permissions, defining the playback system gradient level as the branch feature benchmark, taking the root node as the starting node, and splitting all playback system permissions into N subsystem permission branches through multiple split information gains;

[0015] Preset the split depth threshold, repeat the above steps to perform continuous recursive splitting on each of the system authority branches, obtain the current split depth value, and determine whether the current split depth value reaches the split depth threshold during the recursive splitting process. If so, stop the recursive splitting operation and finally output the leaf node value;

[0016] Determine the membership of each system permission in all playback system permissions to each gradient level in the playback system gradient level according to the leaf node value bureau, preset a target membership interval, and only extract the playback system permissions corresponding to the membership in the target membership interval, and mark them as key playback system permissions;

[0017] Obtain the system permission configuration of the smart commercial display device, and extract the open configuration frequency of the smart commercial display device for key playback system permissions in the preset time period through the system permission configuration. If the open configuration frequency does not exceed the preset open configuration frequency, the system-level permissions of the smart commercial display device are marked as open normal; if it exceeds, the system-level permissions of the smart commercial display device are marked as open abnormal risk, and the system security detection results are generated.

[0018] More specifically, the step S104 includes the following steps:

[0019] Obtain a list of dangerous cloud applications associated with the cloud system of the smart commercial display device, and extract source file information and permission information of each dangerous application through the list of dangerous cloud applications;

[0020] Based on the big data network, a playback logic knowledge graph is obtained, and the architecture design data of the intelligent commercial display device playback system is identified in the playback logic knowledge graph to obtain the preset playback logic of the intelligent commercial display device playback system;

[0021] Establish an initial rule engine according to the preset playback logic, inject the architecture design data of the intelligent commercial display device playback system into the initial rule engine for dynamic logic loading training, and generate a series of intelligent commercial display device playback simulators;

[0022] The source file information and permission information of each dangerous application are run and parsed through a series of intelligent commercial display device playback simulators. During the simulation process, the security control data output by each dangerous application within a preset time period is read to obtain the security control data of each dangerous application for the intelligent commercial display device playback system simulator;

[0023] The actual security control data of each application in the smart commercial display device within a preset time period is obtained through the application monitoring log, and a security control data warehouse for dangerous applications in the cloud is constructed according to the security control data set of each dangerous application by the smart commercial display device playback system simulator;

[0024] Import the actual security control data of each application within a preset time period into the security control data warehouse for traversal matching, and calculate the degree of consistency between the security control data of each dangerous application and the security control data of the intelligent commercial display device playback system simulator for each dangerous application one by one;

[0025] If the degree of match is not greater than the preset degree of match, the application corresponding to the actual security control data will be listed as a normal application; if the degree of match is greater than the preset degree of match, the application corresponding to the actual security control data will be listed as a risky application, generating a first security detection result.

[0026] More specifically, the step S106 includes the following steps:

[0027] Based on the first security detection result, a permission request list of each application of the smart commercial display device and an application permission application strategy of the smart commercial display device playback system are obtained, and functional information of each application is obtained at the same time, and several basic permission-related items required for the operation of each application are retrieved from the big data network according to the functional information;

[0028] A Markov decision algorithm is introduced, in which the probability of each permission-related basic item necessary for the operation of each application program transferring to the state corresponding to the permission request list after executing the application permission application strategy is calculated, and several sub-state transition probabilities of each application program are obtained;

[0029] Based on the big data network retrieval, a number of requested permissions that must be applied for when executing the application permission application strategy for each permission-related basic item are obtained, which are defined as accurate requested permissions, and abnormal state transition probabilities are preset according to the accurate requested permissions;

[0030] Extract applications that have at least one or more sub-state transition probabilities greater than the abnormal state transition probability and mark them as suspicious applications, and obtain the reward value of transferring each permission-related basic item required for the operation of the suspicious application to the corresponding permission request list to obtain several actual reward functions;

[0031] Use the entropy weight method to calculate the risk weight value of each requested permission in the permission request list corresponding to the suspicious application relative to the intelligent commercial display device playback system, and preset a risk reward function for each requested permission based on the risk weight value;

[0032] If the permission request list corresponding to the suspicious application does not contain a requested permission whose actual reward function is greater than the risk reward function, the status of the permission request list of the suspicious application is marked as a normal permission request behavior;

[0033] If at least one requested permission whose actual reward function is greater than the risk reward function appears in the permission request list corresponding to the suspicious application, the status of the permission request list applied by the suspicious application is marked as abnormal permission application behavior, and a second security detection result is generated.

[0034] More specifically, the step S108 includes the following steps:

[0035] Obtain a media file list of the smart commercial display device, and perform a global scan on the media file list based on the second security detection result by using a file scanning module of the detection device to obtain a standard file type and a corresponding standard file format of each media file;

[0036] Searching in a big data network according to the standard file type and the standard file format to obtain multiple types of malicious viruses associated with each media file in the list of tamperable media files;

[0037] Construct an inverted index map, obtain the metadata tampering characters of various malicious viruses that tamper with media files under different protection levels and different file formats based on the big data network, and write them into the inverted index map to obtain an inverted index map of malicious viruses-metadata tampering characters;

[0038] Obtain the current protection level of the playback system of the intelligent commercial display device, import the current protection level into the malicious virus-metadata tampering character inverted index map for inverted indexing, obtain the metadata tampering characters of the media files tampered by various malicious virus types under the current protection level and standard file format conditions, and define them as suspected metadata tampering characters;

[0039] Obtaining an original metadata package for each media file, constructing an original metadata model graph corresponding to each media file according to the original metadata package, and performing character tampering on the original metadata model graph based on the suspected metadata tampering character to obtain the tampered original metadata model graph of each media file;

[0040] Obtain the current metadata model graph of each media file, and calculate the degree of overlap after aligning the current metadata model graph of each media file with the corresponding tampered original metadata model graph one by one. If the degree of overlap is lower than a preset degree of overlap, mark the media file of the current metadata model graph corresponding to the degree of overlap as a safe file;

[0041] If the overlap degree is higher than a preset overlap degree, the media file of the current metadata model graph corresponding to the overlap degree is marked as a dangerous tampered file, and a third security detection result is generated.

[0042] More specifically, the step S110 includes the following steps:

[0043] Obtaining a preset security assessment tool of the smart commercial display device and a preset security assessment mechanism stored in the preset security assessment tool, and evaluating the first security detection result, the second security detection result, and the third security detection result one by one through the preset security assessment tool to obtain an initial security assessment result set;

[0044] Extracting a security assessment criterion of a preset security assessment mechanism, and obtaining a critical assessment peak range of the preset security assessment mechanism for the first security detection result, the second security detection result, and the third security detection result based on the security assessment criterion;

[0045] A Logistic mapping model is introduced, and a series of chaotic sequences are generated by performing chaotic mapping on the first safety detection result, the second safety detection result, and the third safety detection result through the Logistic mapping model, and the series of chaotic sequences are mapped to the corresponding critical assessment peak range to obtain a target safety assessment solution set;

[0046] Preset M groups of initial safety assessment populations according to the initial safety assessment result set, calculate the fitness of each target safety assessment individual in each group of initial safety assessment populations based on the safety assessment criteria, extract the target safety assessment individual corresponding to the maximum fitness, and generate a series of optimal sub-individual chaotic sequences by chaotic mapping in the Logistic mapping model;

[0047] Through a series of optimal sub-individual chaotic sequences, a chaotic search is performed on the target safety assessment solution set in a Logistic mapping model, and the target safety assessment solution of each target safety assessment individual is continuously updated and iterated until the fitness reaches a preset fitness, thereby obtaining the optimal target safety assessment solution of each target safety assessment individual in each group of initial safety assessment populations;

[0048] Extract the optimal target safety assessment solution corresponding to the target safety assessment individuals in each group of initial safety assessment populations that respond to the first safety detection result, the second safety detection result, and the third safety detection result, and integrate and reconstruct them to construct a safety assessment optimization model;

[0049] The security assessment optimization model is applied to a preset security assessment tool for adjustment, optimization and re-evaluation, and a new security assessment result set is output. A comprehensive playback security assessment report is generated in the detection device based on the new security assessment result set and uploaded to the operation and maintenance terminal of the smart commercial display device.

[0050] A second aspect of the present invention provides a smart commercial display device playback safety detection device, which is applied to any of the smart commercial display device playback safety detection methods, and specifically includes:

[0051] A system permission configuration detection module, the system permission configuration detection module is used to detect whether the open configuration frequency of the key playback system permission in a preset time period exceeds a preset open configuration frequency;

[0052] A playback simulator training module, which is used for dynamic logic loading and training of a series of intelligent commercial display device playback simulators;

[0053] A file scanning module, the file scanning module is used to globally scan all media files in the media file list of the intelligent commercial display device;

[0054] An assessment report generation module, the assessment report generation module is used to generate a playback safety assessment report according to a new safety assessment result set;

[0055] The data processing module includes a memory and a processor. The processor analyzes and processes the data obtained by each module, and the memory can store the data of each module.

[0056] A third aspect of the present invention provides a computer-readable storage medium, which stores a computer detection program. When the computer detection program is executed by at least one processor, it can implement any one of the smart commercial display device playback safety detection methods.

[0057] The present invention solves the technical defects existing in the background technology, and the beneficial technical effects of the present invention are:

[0058] By analyzing the open configuration security of the key playback system permissions of the smart commercial display device, a system security detection result is generated; a series of smart commercial display device playback simulators are built based on the cloud dangerous application list, and the danger of each application in the smart commercial display device is analyzed through the smart commercial display device playback simulator to obtain the first security detection result; in the Markov decision algorithm, each permission-related basic item required for the operation of each application is calculated to execute the application permission application strategy and then transfer to the corresponding permission request list for rationality detection and analysis of the application permission request security to obtain the second security detection result; obtain the media file list of the smart commercial display device, and scan the media file list to detect and analyze whether the actual metadata of each media file in the list is tampered with by different virus metadata tampering characters to obtain the third security detection result; the initial security assessment result set of the first security detection result, the second security detection result and the third security detection result is mapped and analyzed by the Logistic mapping model to build a security assessment optimization model to adjust the preset security assessment tool of the smart commercial display device. The present invention can perform multi-faceted detection and analysis on the playback security of the smart commercial display device to improve the playback security factor and playback stability of the smart commercial display device. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0060] Figure 1 A first method flow chart of a method for detecting playback safety of an intelligent commercial display device is shown;

[0061] Figure 2A second method flow chart of a method for detecting playback safety of an intelligent commercial display device is shown;

[0062] Figure 3 A device schematic diagram of a smart commercial display device playback safety detection device is shown. DETAILED DESCRIPTION

[0063] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0065] The first aspect of the present invention provides a method for detecting the playback safety of an intelligent commercial display device. Figure 1 As shown, the following steps are included:

[0066] S102: Acquire all playback system permissions required by the smart commercial display device to meet playback requirements, recursively split and calculate key playback system permissions from all playback system permissions according to the playback system gradient level, analyze the open configuration security of the key playback system permissions, and generate a system security detection result;

[0067] S104: Obtain a list of dangerous cloud applications associated with the cloud system of the smart commercial display device, build a series of smart commercial display device playback simulators based on the list of dangerous cloud applications, analyze the danger of the applications in the smart commercial display device through the smart commercial display device playback simulators, and obtain a first security detection result;

[0068] S106: Based on the first security detection result, the Markov decision algorithm is used to calculate the state transition probability of each permission-related basic item required for the operation of each application program to transfer to the corresponding permission request list after executing the application permission application strategy, and the permission request security of the application program is analyzed according to the rationality of the state transition probability to obtain a second security detection result;

[0069] S108: Obtain a media file list of the smart commercial display device, and scan the media file list to detect and analyze whether the actual metadata of each media file in the list is tampered with by different virus metadata tampering characters, thereby obtaining a third security detection result;

[0070] S110: An initial security assessment result set of the first security detection result, the second security detection result, and the third security detection result is analyzed by mapping through a Logistic mapping model to construct a security assessment optimization model to calibrate a preset security assessment tool for the intelligent commercial display device.

[0071] More specifically, the step S102 is as follows: Figure 2 As shown, the specific steps include:

[0072] S202: Acquire the playback requirements of the smart commercial display device, and simultaneously acquire the system permission list of the smart commercial display device, and search the system permission list based on the playback requirements to obtain all playback system permissions corresponding to the playback requirements;

[0073] S204: Acquire architecture design data of the playback system of the intelligent commercial display device, retrieve and acquire the playback system gradient level of the intelligent commercial display device in the big data network according to the architecture design data, introduce a trade-off algorithm to jointly calculate the information gain of each system authority in all the playback system authorities for each gradient level in the playback system gradient level, and generate a split information gain;

[0074] S206: constructing a root node of all playback system permissions, defining the playback system gradient level as a branch feature benchmark, and using the root node as a starting node to split all playback system permissions into N subsystem permission branches through multiple split information gains;

[0075] S208: Preset a split depth threshold, repeat the above steps to perform continuous recursive splitting on each of the system authority branches, obtain a current split depth value, and determine whether the current split depth value reaches the split depth threshold during the recursive splitting process. If so, stop the recursive splitting operation and finally output the leaf node value;

[0076] S210: determining the membership of each system permission in all the playback system permissions to each gradient level in the playback system gradient level according to the leaf node value bureau, presetting a target membership interval, and only extracting the playback system permissions corresponding to the membership in the target membership interval, and marking them as key playback system permissions;

[0077] S212: Obtain the system permission configuration of the smart commercial display device, and extract the open configuration frequency of the smart commercial display device for key playback system permissions in a preset time period through the system permission configuration. If the open configuration frequency does not exceed the preset open configuration frequency, the system-level permission of the smart commercial display device is marked as open normal; if it exceeds, the system-level permission of the smart commercial display device is marked as open abnormal risk, and a system security detection result is generated.

[0078] It should be noted that when playing applications on smart commercial display devices, it is usually necessary to apply for and set some system-level permissions of the playback system. For example, when a video application plays and records videos, it may be necessary to apply for access to the system camera. The playback system usually adaptively opens the system-level permissions, but the excessive opening of system-level permissions may cause some dangerous applications to arbitrarily obtain and access the core files and privacy content of the smart commercial display device, thereby making the smart commercial display device playback system vulnerable to malicious attacks and playback failures, etc., reducing the playback security quality. This method can recursively split all playback system permissions according to the gradient level of the smart commercial display device playback system. Since there are multiple system permissions in the system permission list of the device, some of the system permissions are key permissions to ensure the safety of the system operation. Therefore, through recursive splitting, all system permissions in the system permission list can be quickly identified and classified at the system gradient level, so that the key system permissions can be quickly distinguished. The output leaf node value is the importance classification result of each system permission after classification according to the gradient level, so that the key playback system permissions can be obtained. And the open configuration frequency of key system permissions is detected and analyzed to identify which key playback system permissions may pose a threat to device security. In order to ensure the security of device playback, the frequency of open configuration should be as low as possible. Therefore, if the frequency of open configuration of key playback system permissions does not exceed the preset frequency of open configuration, it means that the system permission open state of the smart commercial display device playback system has high security, and the system-level permissions of the smart commercial display device can be marked as open normal. Otherwise, it means that the security is low and it should be marked as open abnormal risk. This method can quickly and accurately determine the key systems in the system permissions and analyze and detect whether their external open settings have a certain degree of security, reducing the potential security risks of system permission application and setting in the smart commercial display device playback system, and ensuring the security and stability of the device at the system level.

[0079] More specifically, the step S104 includes the following steps:

[0080] Obtain a list of dangerous cloud applications associated with the cloud system of the smart commercial display device, and extract source file information and permission information of each dangerous application through the list of dangerous cloud applications;

[0081] Based on the big data network, a playback logic knowledge graph is obtained, and the architecture design data of the intelligent commercial display device playback system is identified in the playback logic knowledge graph to obtain the preset playback logic of the intelligent commercial display device playback system;

[0082] Establish an initial rule engine according to the preset playback logic, inject the architecture design data of the intelligent commercial display device playback system into the initial rule engine for dynamic logic loading training, and generate a series of intelligent commercial display device playback simulators;

[0083] The source file information and permission information of each dangerous application are run and parsed through a series of intelligent commercial display device playback simulators. During the simulation process, the security control data output by each dangerous application within a preset time period is read to obtain the security control data of each dangerous application for the intelligent commercial display device playback system simulator;

[0084] The actual security control data of each application in the smart commercial display device within a preset time period is obtained through the application monitoring log, and a security control data warehouse for dangerous applications in the cloud is constructed according to the security control data set of each dangerous application by the smart commercial display device playback system simulator;

[0085] Import the actual security control data of each application within a preset time period into the security control data warehouse for traversal matching, and calculate the degree of consistency between the security control data of each dangerous application and the security control data of the intelligent commercial display device playback system simulator for each dangerous application one by one;

[0086] If the degree of match is not greater than the preset degree of match, the application corresponding to the actual security control data will be listed as a normal application; if the degree of match is greater than the preset degree of match, the application corresponding to the actual security control data will be listed as a risky application, generating a first security detection result.

[0087] It should be noted that the source file information includes executable file information, configuration file information, resource file information and resource dependencies; the permission information includes license key information, system resource access permission information and startup script information. Detecting the danger of applications is one of the key factors to ensure the playback safety of smart commercial display devices. The traditional way to detect the danger of applications is usually to use a security detection program to run virus monitoring on them one by one. This method has low security detection efficiency and is prone to false detection and missed detection, and has not significantly improved the detection of application danger. By transferring each application on the smart commercial display device to the cloud-based dangerous application database and analyzing and comparing it with all the dangerous applications stored one by one, it is possible to efficiently and accurately identify the applications that may be risky on the smart commercial display device, greatly improving the safety of application use. This method constructs an initial rule engine through the preset playback logic of the smart commercial display device playback system and performs dynamic logic loading training to generate a series of smart commercial display device playback simulators. The construction of the rule engine can flexibly and efficiently define and execute rules to further process complex playback task logic, accurately automate the decision-making process, improve the playback system's simulation execution of dangerous applications The rate and accuracy of the speed and accuracy of the execution of dangerous applications ensure the reliability of application comparison. A security control data warehouse for dangerous applications in the cloud is established through the security control data simulated and output by dangerous applications in a series of smart commercial display device playback simulators, and a degree of fit calculation and comparative analysis is performed in the security control data warehouse based on the actual security control data of each application in the smart commercial display device. If the degree of fit is not greater than the preset degree of fit, it means that the application has failed to match the corresponding dangerous application, so the application is listed as a normal application. Otherwise, it means that the application has matched the corresponding dangerous application in the dangerous application database, so the application has a high risk and is therefore listed as a risky application. This method can quickly compare and analyze the applications of smart commercial display devices with the list of dangerous applications in the cloud, effectively discover and mark high-risk applications that may exist on the device, and greatly improve the detection quality and efficiency compared to traditional detection methods, ensuring the security of smart commercial display devices.

[0088] More specifically, the step S106 includes the following steps:

[0089] Based on the first security detection result, a permission request list of each application of the smart commercial display device and an application permission application strategy of the smart commercial display device playback system are obtained, and functional information of each application is obtained at the same time, and several basic permission-related items required for the operation of each application are retrieved from the big data network according to the functional information;

[0090] A Markov decision algorithm is introduced, in which the probability of each permission-related basic item necessary for the operation of each application program transferring to the state corresponding to the permission request list after executing the application permission application strategy is calculated, and several sub-state transition probabilities of each application program are obtained;

[0091] Based on the big data network retrieval, a number of requested permissions that must be applied for when executing the application permission application strategy for each permission-related basic item are obtained, which are defined as accurate requested permissions, and abnormal state transition probabilities are preset according to the accurate requested permissions;

[0092] Extract applications that have at least one or more sub-state transition probabilities greater than the abnormal state transition probability and mark them as suspicious applications, and obtain the reward value of transferring each permission-related basic item required for the operation of the suspicious application to the corresponding permission request list to obtain several actual reward functions;

[0093] Use the entropy weight method to calculate the risk weight value of each requested permission in the permission request list corresponding to the suspicious application relative to the intelligent commercial display device playback system, and preset a risk reward function for each requested permission based on the risk weight value;

[0094] If the permission request list corresponding to the suspicious application does not contain a requested permission whose actual reward function is greater than the risk reward function, the status of the permission request list of the suspicious application is marked as a normal permission request behavior;

[0095] If at least one requested permission whose actual reward function is greater than the risk reward function appears in the permission request list corresponding to the suspicious application, the status of the permission request list applied by the suspicious application is marked as abnormal permission application behavior, and a second security detection result is generated.

[0096] It should be noted that application permission application analysis is also an important indicator for detecting the playback security of smart commercial display devices. When running certain applications, smart commercial display devices may have unreasonable excessive permission applications. When the application is at high risk, its excessive permission application behavior will cause the privacy content and important files of the smart commercial display device to be stolen or destroyed, resulting in the inability of the smart commercial display device to run and play the application, affecting the playback performance of the smart commercial display device. Therefore, this method can analyze the rationality of the permission request behavior of the applications installed on the smart commercial display device, thereby detecting whether there is excessive permission application to ensure the security of the device. Among them, the permission-associated basic items include access to contacts, locations, cameras, microphones, recordings, and address books; the Markov decision algorithm can be used to model a mathematical framework for applications to make decisions at different state points and analyze state transition probabilities. When an application applies for permission, it is necessary to analyze its permission-associated basic items after executing the application permission application strategy to generate the required permission request instructions. Therefore, the Markov decision algorithm is used to calculate the state transition probability of each application's permission-associated basic items after executing the application permission application strategy and transferring to the corresponding permission request list. The rationality of the permission request for the smart commercial display device application can be analyzed. When there is at least one or more sub-state transition probabilities greater than the abnormal state transition probability, the application will be deemed to be reasonable. If there is an application corresponding to the rate, it means that the smart commercial display device has an application that excessively applies for permissions, and this application is suspicious and unreasonable; the actual reward function represents the actual safety factor of the permissions excessively applied for by the application relative to the smart commercial display device playback system, and the risk-reward function represents the preset risk factor of each requested permission in the permission request list of the application relative to the smart commercial display device playback system. If the permission request list corresponding to the suspicious application does not contain a requested permission with an actual reward function greater than the risk-reward function, it means that the permissions excessively applied for by the suspicious application do not include risky permissions, and it can be marked as normal permission application behavior. Otherwise, it means that it contains risky permissions and is marked as abnormal permission application behavior.

[0097] To sum up, this method can analyze and detect the security and rationality of the permission application behavior of existing applications on smart commercial display devices, which helps to identify possible permission abuse problems in the process of playing applications on smart commercial display devices, and prevent applications from excessively applying for high-risk permissions, which may cause the privacy content and important files of smart commercial display devices to be stolen or destroyed, thereby further improving the security and privacy protection level of smart commercial display devices with high reliability.

[0098] More specifically, the step S108 includes the following steps:

[0099] Obtain a media file list of the smart commercial display device, and perform a global scan on the media file list based on the second security detection result by using a file scanning function of the smart commercial display device to obtain a standard file type and a corresponding standard file format of each media file;

[0100] Searching in a big data network according to the standard file type and the standard file format to obtain multiple types of malicious viruses associated with each media file in the list of tamperable media files;

[0101] Construct an inverted index map, obtain the metadata tampering characters of various malicious viruses that tamper with media files under different protection levels and different file formats based on the big data network, and write them into the inverted index map to obtain an inverted index map of malicious viruses-metadata tampering characters;

[0102] Obtain the current protection level of the playback system of the intelligent commercial display device, import the current protection level into the malicious virus-metadata tampering character inverted index map for inverted indexing, obtain the metadata tampering characters of the media files tampered by various malicious virus types under the current protection level and standard file format conditions, and define them as suspected metadata tampering characters;

[0103] Obtaining an original metadata package for each media file, constructing an original metadata model graph corresponding to each media file according to the original metadata package, and performing character tampering on the original metadata model graph based on the suspected metadata tampering character to obtain the tampered original metadata model graph of each media file;

[0104] Obtain the current metadata model graph of each media file, and calculate the degree of overlap after aligning the current metadata model graph of each media file with the corresponding tampered original metadata model graph one by one. If the degree of overlap is lower than a preset degree of overlap, mark the media file of the current metadata model graph corresponding to the degree of overlap as a safe file;

[0105] If the overlap degree is higher than a preset overlap degree, the media file of the current metadata model graph corresponding to the overlap degree is marked as a dangerous tampered file, and a third security detection result is generated.

[0106] It should be noted that if the smart commercial display device fails to perform security checks on the stored files regularly, some key files may be invaded and tampered by different kinds of malicious viruses, which will cause the application to be unable to run these key files, resulting in the phenomenon that the smart commercial display device cannot play the content of this application, reducing the file security management index and playback quality of the smart commercial display device. This method can realize a global scan of all media files stored in the smart commercial display device, and analyze and check whether the metadata of these media files has been tampered with, damaged, missing, or suspiciously modified by different malicious viruses, to ensure that there are no malicious files or potential threats. Among them, the inverted index map is a visual diagram used to display the inverted index structure in information retrieval systems and search engines, which can accelerate the retrieval of keywords in a large number of documents for quick query and retrieval. Compared with traditional document indexing methods, inverted indexes are particularly suitable for the retrieval of file texts, which can significantly improve query efficiency. By constructing an inverted index map, it is possible to quickly query the suspected metadata tampering characters of various malicious viruses that tamper with media files under the current protection level and standard file format conditions, and construct the original metadata model diagram of each media file after tampering based on the queried suspected metadata tampering characters. Finally, by comparing the overlap between the current metadata model diagram of each media file and the original metadata model diagram, it is possible to quickly detect the media files tampered with by malicious viruses. If the overlap is lower than the preset overlap, it means that the metadata of the current media file and the tampered metadata do not have similarity, so it is determined that the media file mark has not been tampered with by malicious viruses and can be regarded as a safe file; if it is higher than the preset overlap, it means that the two are highly similar, so it is determined that the media file mark has been maliciously tampered with by malicious viruses and is regarded as a dangerous tampered file. This method can realize the comprehensive scanning and detection function of media files, and can effectively ensure that there are no malicious files or potential threats in the media files of smart commercial display devices, thereby improving the playback security of smart commercial display devices.

[0107] More specifically, the step S110 includes the following steps:

[0108] Obtaining a preset security assessment tool of the smart commercial display device and a preset security assessment mechanism stored in the preset security assessment tool, and evaluating the first security detection result, the second security detection result, and the third security detection result one by one through the preset security assessment tool to obtain an initial security assessment result set;

[0109] Extracting a security assessment criterion of a preset security assessment mechanism, and obtaining a critical assessment peak range of the preset security assessment mechanism for the first security detection result, the second security detection result, and the third security detection result based on the security assessment criterion;

[0110] A Logistic mapping model is introduced, and a series of chaotic sequences are generated by performing chaotic mapping on the first safety detection result, the second safety detection result, and the third safety detection result through the Logistic mapping model, and the series of chaotic sequences are mapped to the corresponding critical assessment peak range to obtain a target safety assessment solution set;

[0111] Preset M groups of initial safety assessment populations according to the initial safety assessment result set, calculate the fitness of each target safety assessment individual in each group of initial safety assessment populations based on the safety assessment criteria, extract the target safety assessment individual corresponding to the maximum fitness, and generate a series of optimal sub-individual chaotic sequences by chaotic mapping in the Logistic mapping model;

[0112] Through a series of optimal sub-individual chaotic sequences, a chaotic search is performed on the target safety assessment solution set in a Logistic mapping model, and the target safety assessment solution of each target safety assessment individual is continuously updated and iterated until the fitness reaches a preset fitness, thereby obtaining the optimal target safety assessment solution of each target safety assessment individual in each group of initial safety assessment populations;

[0113] Extract the optimal target safety assessment solution corresponding to the target safety assessment individuals in each group of initial safety assessment populations that respond to the first safety detection result, the second safety detection result, and the third safety detection result, and integrate and reconstruct them to construct a safety assessment optimization model;

[0114] The security assessment optimization model is applied to a preset security assessment tool for adjustment, optimization and re-evaluation, and a new security assessment result set is output. A comprehensive playback security assessment report is generated in the detection device based on the new security assessment result set and uploaded to the operation and maintenance terminal of the smart commercial display device.

[0115] It should be noted that existing intelligent commercial display devices usually have an evaluation model for evaluating their own playback security to ensure regular evaluation of playback security, that is, a preset security evaluation tool. However, since the preset security evaluation tool is not adapted to the security evaluation mechanism or logic of the first security detection result, the second security detection result, and the third security detection result obtained above, if the evaluation is performed through the preset security evaluation tool, the evaluation results may be inaccurate and have serious errors, which reduces the security summary evaluation performance of the intelligent commercial display device. Therefore, this method uses the Logistic mapping model to analyze and calculate the results of the preset security evaluation tool to evaluate the first security detection result, the second security detection result, and the third security detection result, so as to construct an optimization model that can optimize the evaluation results of the preset security evaluation tool to adjust and optimize the preset security evaluation tool, thereby providing a comprehensive playback security evaluation report for formulating a reasonable equipment operation and maintenance strategy, and further improving the safety index and reliability of the equipment playback. Among them, the critical evaluation peak range refers to the evaluation solution range formed by the maximum critical evaluation peak and the minimum evaluation critical peak, which is used to limit the search range of a series of chaotic sequences to find the optimal solution and improve the accuracy of the optimal solution. Among them, the Chinese name of the Logistic mapping model is the logarithmic mapping model, which can describe a simple mathematical model of population growth under a chaotic system. Through the chaotic mapping of the Logistic mapping model, the optimal solution search for fitness update iteration can be performed on each set of security assessment results of the preset security assessment tool for the first security detection result, the second security detection result, and the third security detection result, so that the assessment results of the preset security assessment tool can be adaptively adjusted and optimized globally, greatly improving the assessment effect and accuracy of the existing preset security assessment tool for all the above security detection results, without the need to re-replace the steps of the smart commercial display device assessment tool, reducing the cost of device playback security assessment. This method can optimize the assessment results of the assessment tool and ensure the safety and reliability of the smart commercial display device.

[0116] In addition, the intelligent commercial display device playback safety detection method further includes the following steps:

[0117] Obtain the cloud virus protection program currently enabled by the smart commercial display device and the virus detection and killing protocol of the cloud virus protection program, and obtain several types of viruses that can invade the smart commercial display device through the big data network, which are defined as the types of viruses that can invade;

[0118] A fuzzy C-means algorithm is introduced to perform fuzzy clustering calculation on the virus detection and killing protocol and several types of intrusive viruses and continuously iterate and update, and finally the detectable and undetectable parts of the cloud virus protection program for several types of intrusive viruses are obtained;

[0119] Obtain a cloud virus database that the intelligent commercial display device needs to protect, plan the intrusive virus protection range of the cloud virus protection program in the cloud virus database according to the detectable and undetectable parts, and extract the virus data storage volume of the intrusive virus protection range, which is defined as the sub-virus data storage volume;

[0120] Obtain the virus data storage capacity of the cloud virus database, which is defined as the main virus data storage capacity, introduce a hash algorithm to calculate the hash function between the sub-virus data storage capacity and the main virus data storage capacity, and determine the virus protection level of the cloud virus protection program according to the hash function;

[0121] If the virus protection level is lower than the preset protection level, a number of optimized patch solutions adapted to the cloud virus protection program and the historical virus detection rate of each optimized patch solution are obtained based on the big data network;

[0122] The optimized patch solutions are arranged in descending order based on the historical virus detection rates, and the optimized patch solution corresponding to the maximum historical virus detection rate is extracted as the virus detection optimization solution for the current cloud virus protection program and uploaded to the operation and maintenance terminal of the intelligent commercial display device.

[0123] It should be noted that, in order to prevent the intrusion of malicious viruses, existing smart commercial display devices are usually equipped with a cloud virus protection program in the cloud for regular detection and killing of possible and intrusive malicious viruses. Although some cloud virus protection programs can identify the types of viruses that exist, they are unable to provide corresponding protection. The reason may be that there is no adapted killing optimization plan to execute, which makes the cloud virus protection program's killing performance for different smart commercial display devices uneven, increasing the risk of virus tampering and file damage when using this cloud virus protection program. Therefore, this method can determine the virus protection level of the cloud virus protection program for the killable part and the unkillable part of the intrusive virus types in the current smart commercial display device, and obtain the optimization patch that can be adapted to the cloud virus protection program according to the virus protection level to further supplement the killing plan for the unkillable virus part, so as to improve the protection performance and protection safety index of the cloud virus protection program for the cloud virus protection program of the smart commercial display device, avoid the invasion of malicious viruses, reduce the probability and frequency of malicious virus invasion, and have a high degree of protection reliability.

[0124] In addition, the intelligent commercial display device playback safety detection method further includes the following steps:

[0125] Obtain a list of permission requests of the smart commercial display device at a preset time sequence, and simultaneously obtain application information running and playing in the preset time sequence of the smart commercial display device playback system;

[0126] Analyzing the permission request list according to the application information to extract a number of key system permissions, marking a request timestamp of each key system permission through the permission request list, and arranging the key system permissions in time sequence based on the request timestamp to obtain a key system permission queue;

[0127] Obtain the monitoring and killing cycle of the cloud virus protection program on the permission request list at a preset time sequence, assign a same maximum process deadline time slice to each key system permission based on the monitoring and killing cycle, and finally execute the request for the key system permission queue in the smart commercial display device playback system, and output the request execution process for each key system permission;

[0128] If the requested execution process can be completed at the end of the maximum process deadline time slice, the critical system permission is removed from the critical system permission queue; if the requested execution process cannot be completed at the end of the maximum process deadline time slice, the critical system permission is adjusted to the end of the critical system permission queue, and a permission request scheduling sequence for the critical system permission is generated;

[0129] Obtain the permission request scheduling sequence for each key system permission, and adjust and optimize the cloud virus protection program's monitoring intensity and virus detection scheduling for the permission request list according to the permission request scheduling sequence for each key system permission, so as to improve the rationality of security protection of system permission requests.

[0130] It should be noted that when the smart commercial display device runs an application, the cloud virus protection program usually monitors and checks its permission application behavior, but there may be some risk permissions and some non-risk permissions in the permissions applied for by the application. If the cloud virus protection program fails to reasonably allocate the scheduling ratio of monitoring and killing, it may cause the phenomenon of missing checks and missed checks, and the irrationality of monitoring and killing scheduling will increase the killing time of the cloud virus protection program and reduce the efficiency of security detection and evaluation. Therefore, on the one hand, this method can optimize the cloud virus protection program's monitoring intensity and killing scheduling for different application permissions in the required permission request list, thereby improving the rationality of security protection of system permission requests. On the other hand, it can improve the efficiency of security monitoring and evaluation, while avoiding the phenomenon of missing checks and missed checks when the cloud virus protection program detects permission applications, and ensuring the safety factor of permission requests when the smart commercial display device plays applications. Among them, the maximum process deadline time slice is the maximum time allowed for key system permissions to be scheduled for monitoring and killing in the monitoring and killing cycle.

[0131] The second aspect of the present invention provides a smart commercial display device playback safety detection device 3, which is applied to any of the smart commercial display device playback safety detection methods, such as Figure 3 As shown, specifically including:

[0132] A system permission configuration detection module 301, the system permission configuration detection module is used to detect whether the open configuration frequency of the key playback system permission in a preset time period exceeds a preset open configuration frequency;

[0133] A playback simulator training module 302, which is used for dynamically loading and training a series of intelligent commercial display device playback simulators;

[0134] A file scanning module 303, which is used to globally scan all media files in the media file list of the intelligent commercial display device;

[0135] An assessment report generation module 304, the assessment report generation module is used to generate a playback safety assessment report according to the new safety assessment result set;

[0136] The data processing module 305 includes a memory and a processor. The processor analyzes and processes the data obtained by each module, and the memory can store the data of each module.

[0137] A third aspect of the present invention provides a computer-readable storage medium, which stores a computer detection program. When the computer detection program is executed by at least one processor, it can implement any one of the smart commercial display device playback safety detection methods.

[0138] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for detecting the playback safety of an intelligent commercial display device, characterized in that: The following steps are involved: S102: Acquire all playback system permissions required by the smart commercial display device to meet playback requirements, recursively split and calculate key playback system permissions from all playback system permissions according to the playback system gradient level, analyze the open configuration security of the key playback system permissions, and generate a system security detection result; S104: Obtain a list of dangerous cloud applications associated with the cloud system of the smart commercial display device, build a series of smart commercial display device playback simulators based on the list of dangerous cloud applications, analyze the danger of the applications in the smart commercial display device through the smart commercial display device playback simulators, and obtain a first security detection result; S106: Based on the first security detection result, the Markov decision algorithm is used to calculate the state transition probability of each permission-related basic item required for the operation of each application program to transfer to the corresponding permission request list after executing the application permission application strategy, and the permission request security of the application program is analyzed according to the rationality of the state transition probability to obtain a second security detection result; S108: Obtain a media file list of the smart commercial display device, and scan the media file list to detect and analyze whether the actual metadata of each media file in the list is tampered with by different virus metadata tampering characters, thereby obtaining a third security detection result; S110: An initial security assessment result set of the first security detection result, the second security detection result, and the third security detection result is analyzed by mapping through a Logistic mapping model to construct a security assessment optimization model to calibrate a preset security assessment tool for the intelligent commercial display device.

2. The method for detecting the playback safety of an intelligent commercial display device according to claim 1, characterized in that: The step S102 specifically includes the following steps: Obtain the playback requirements of the smart commercial display device, and at the same time obtain the system permission list of the smart commercial display device, search in the system permission list based on the playback requirements, and obtain all playback system permissions corresponding to the playback requirements; Obtaining architecture design data of the playback system of the intelligent commercial display device, retrieving the playback system gradient level of the intelligent commercial display device in the big data network according to the architecture design data, introducing a trade-off algorithm to jointly calculate the information gain of each system authority in all the playback system authorities for each gradient level in the playback system gradient level, and generating a split information gain; Constructing the root node of all playback system permissions, defining the playback system gradient level as the branch feature benchmark, taking the root node as the starting node, and splitting all playback system permissions into N subsystem permission branches through multiple split information gains; Preset the split depth threshold, repeat the above steps to perform continuous recursive splitting on each of the system authority branches, obtain the current split depth value, and determine whether the current split depth value reaches the split depth threshold during the recursive splitting process. If so, stop the recursive splitting operation and finally output the leaf node value; Determine the membership of each system permission in all playback system permissions to each gradient level in the playback system gradient level according to the leaf node value bureau, preset a target membership interval, and only extract the playback system permissions corresponding to the membership in the target membership interval, and mark them as key playback system permissions; Obtain the system permission configuration of the smart commercial display device, and extract the open configuration frequency of the smart commercial display device for key playback system permissions in the preset time period through the system permission configuration. If the open configuration frequency does not exceed the preset open configuration frequency, the system-level permissions of the smart commercial display device are marked as open normal; if it exceeds, the system-level permissions of the smart commercial display device are marked as open abnormal risk, and the system security detection results are generated.

3. The method for detecting the playback safety of an intelligent commercial display device according to claim 1, characterized in that: The step S104 specifically includes the following steps: Obtain a list of dangerous cloud applications associated with the cloud system of the smart commercial display device, and extract source file information and permission information of each dangerous application through the list of dangerous cloud applications; Based on the big data network, a playback logic knowledge graph is obtained, and the architecture design data of the intelligent commercial display device playback system is identified in the playback logic knowledge graph to obtain the preset playback logic of the intelligent commercial display device playback system; Establish an initial rule engine according to the preset playback logic, inject the architecture design data of the intelligent commercial display device playback system into the initial rule engine for dynamic logic loading training, and generate a series of intelligent commercial display device playback simulators; The source file information and permission information of each dangerous application are run and parsed through a series of intelligent commercial display device playback simulators. During the simulation process, the security control data output by each dangerous application within a preset time period is read to obtain the security control data of each dangerous application for the intelligent commercial display device playback system simulator; The actual security control data of each application in the smart commercial display device within a preset time period is obtained through the application monitoring log, and a security control data warehouse for dangerous applications in the cloud is constructed according to the security control data set of each dangerous application by the smart commercial display device playback system simulator; Import the actual security control data of each application within a preset time period into the security control data warehouse for traversal matching, and calculate the degree of consistency between the security control data of each dangerous application and the security control data of the intelligent commercial display device playback system simulator for each dangerous application one by one; If the degree of match is not greater than the preset degree of match, the application corresponding to the actual security control data will be listed as a normal application; if the degree of match is greater than the preset degree of match, the application corresponding to the actual security control data will be listed as a risky application, generating a first security detection result.

4. The method for detecting the playback safety of an intelligent commercial display device according to claim 1, characterized in that: The step S106 specifically includes the following steps: Based on the first security detection result, a permission request list of each application of the smart commercial display device and an application permission application strategy of the smart commercial display device playback system are obtained, and functional information of each application is obtained at the same time, and several basic permission-related items required for the operation of each application are retrieved from the big data network according to the functional information; A Markov decision algorithm is introduced, in which the probability of each permission-related basic item necessary for the operation of each application program transferring to the state corresponding to the permission request list after executing the application permission application strategy is calculated, and several sub-state transition probabilities of each application program are obtained; Based on the big data network retrieval, a number of requested permissions that must be applied for when executing the application permission application strategy for each permission-related basic item are obtained, which are defined as accurate requested permissions, and abnormal state transition probabilities are preset according to the accurate requested permissions; Extract applications that have at least one or more sub-state transition probabilities greater than the abnormal state transition probability and mark them as suspicious applications, and obtain the reward value of transferring each permission-related basic item required for the operation of the suspicious application to the corresponding permission request list to obtain several actual reward functions; Use the entropy weight method to calculate the risk weight value of each requested permission in the permission request list corresponding to the suspicious application relative to the intelligent commercial display device playback system, and preset a risk reward function for each requested permission based on the risk weight value; If the permission request list corresponding to the suspicious application does not contain a requested permission whose actual reward function is greater than the risk reward function, the status of the permission request list of the suspicious application is marked as a normal permission request behavior; If at least one requested permission whose actual reward function is greater than the risk reward function appears in the permission request list corresponding to the suspicious application, the status of the permission request list applied by the suspicious application is marked as abnormal permission application behavior, and a second security detection result is generated.

5. The method for detecting the playback safety of an intelligent commercial display device according to claim 1, characterized in that: The step S108 specifically includes the following steps: Obtain a media file list of the smart commercial display device, and perform a global scan on the media file list based on the second security detection result by using a file scanning module of the detection device to obtain a standard file type and a corresponding standard file format of each media file; Searching in a big data network according to the standard file type and the standard file format to obtain multiple types of malicious viruses associated with each media file in the list of tamperable media files; Construct an inverted index map, obtain the metadata tampering characters of various malicious viruses that tamper with media files under different protection levels and different file formats based on the big data network, and write them into the inverted index map to obtain an inverted index map of malicious viruses-metadata tampering characters; Obtain the current protection level of the playback system of the intelligent commercial display device, import the current protection level into the malicious virus-metadata tampering character inverted index map for inverted indexing, obtain the metadata tampering characters of the media files tampered by various malicious virus types under the current protection level and standard file format conditions, and define them as suspected metadata tampering characters; Obtaining an original metadata package for each media file, constructing an original metadata model graph corresponding to each media file according to the original metadata package, and performing character tampering on the original metadata model graph based on the suspected metadata tampering character to obtain the tampered original metadata model graph of each media file; Obtain the current metadata model graph of each media file, and calculate the degree of overlap after aligning the current metadata model graph of each media file with the corresponding tampered original metadata model graph one by one. If the degree of overlap is lower than a preset degree of overlap, mark the media file of the current metadata model graph corresponding to the degree of overlap as a safe file; If the overlap degree is higher than a preset overlap degree, the media file of the current metadata model graph corresponding to the overlap degree is marked as a dangerous tampered file, and a third security detection result is generated.

6. The method for detecting the playback safety of an intelligent commercial display device according to claim 1, characterized in that: The step S110 specifically includes the following steps: Obtaining a preset security assessment tool of the smart commercial display device and a preset security assessment mechanism stored in the preset security assessment tool, and evaluating the first security detection result, the second security detection result, and the third security detection result one by one through the preset security assessment tool to obtain an initial security assessment result set; Extracting a security assessment criterion of a preset security assessment mechanism, and obtaining a critical assessment peak range of the preset security assessment mechanism for the first security detection result, the second security detection result, and the third security detection result based on the security assessment criterion; A Logistic mapping model is introduced, and a series of chaotic sequences are generated by performing chaotic mapping on the first safety detection result, the second safety detection result, and the third safety detection result through the Logistic mapping model, and the series of chaotic sequences are mapped to the corresponding critical assessment peak range to obtain a target safety assessment solution set; Preset M groups of initial safety assessment populations according to the initial safety assessment result set, calculate the fitness of each target safety assessment individual in each group of initial safety assessment populations based on the safety assessment criteria, extract the target safety assessment individual corresponding to the maximum fitness, and generate a series of optimal sub-individual chaotic sequences by chaotic mapping in the Logistic mapping model; Through a series of optimal sub-individual chaotic sequences, a chaotic search is performed on the target safety assessment solution set in a Logistic mapping model, and the target safety assessment solution of each target safety assessment individual is continuously updated and iterated until the fitness reaches a preset fitness, thereby obtaining the optimal target safety assessment solution of each target safety assessment individual in each group of initial safety assessment populations; Extract the optimal target safety assessment solution corresponding to the target safety assessment individuals in each group of initial safety assessment populations that respond to the first safety detection result, the second safety detection result, and the third safety detection result, and integrate and reconstruct them to construct a safety assessment optimization model; The security assessment optimization model is applied to a preset security assessment tool for adjustment, optimization and re-evaluation, and a new security assessment result set is output. A comprehensive playback security assessment report is generated in the detection device based on the new security assessment result set and uploaded to the operation and maintenance terminal of the smart commercial display device.

7. A smart commercial display device playback safety detection device, applied to the smart commercial display device playback safety detection method according to any one of claims 1 to 6, characterized in that: Specifically include: A system permission configuration detection module, the system permission configuration detection module is used to detect whether the open configuration frequency of the key playback system permission in a preset time period exceeds a preset open configuration frequency; A playback simulator training module, which is used for dynamic logic loading and training of a series of intelligent commercial display device playback simulators; A file scanning module, the file scanning module is used to globally scan all media files in the media file list of the intelligent commercial display device; An assessment report generation module, the assessment report generation module is used to generate a playback safety assessment report according to a new safety assessment result set; The data processing module includes a memory and a processor. The processor analyzes and processes the data obtained by each module, and the memory can store the data of each module.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer detection program, and when the computer detection program is executed by at least one processor, it implements the smart commercial display device playback safety detection method as described in any one of claims 1-6.

Images