Browser webpage early warning interception method, device and equipment and storage medium

Abstract

The invention relates to the field of computers, and discloses a browser webpage early warning interception method and device, equipment and a storage medium. The method comprises the following steps: acquiring a list of browsing device applications, and judging whether the currently opened application is a browser or not according to the list of browsing device applications; if yes, reading the interface information of the currently accessed webpage through the auxiliary function event; obtaining text information and pictures in the current browser webpage according to the webpage interface information, and judging whether the current browser webpage is abnormal or not according to the text information and pictures in the current browser webpage; and if the current browser webpage is abnormal, pushing a preset local webpage to the current browser to cover the current browser webpage, and sending early warning information to the equipment terminal. In the embodiment of the invention, the specified content information in the browser webpage can be supervised, and the supervising and intercepting contents are refined, so that the early warning and intercepting efficiency of the browser webpage is improved.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to a browser web page warning interception method, device, equipment and storage medium. Background Art

[0002] In the Internet age, users' online behaviors and browsing history contain a large amount of personal information. If this information is improperly used or leaked, it will pose potential risks to users. With the rapid development of big data and artificial intelligence technologies, the risk of personal information leakage is increasing, threatening personal privacy protection and data security. Cybercrime activities are also increasing, including malware, phishing websites, etc. These threats not only endanger users' property safety, but may also affect the healthy development of the digital economy.

[0003] Currently, there are many browser softwares, and there is no unified special mandatory control, which leads to unlimited access of teenagers to non-compliant information, affecting their physical and mental development and health. Currently, some smart devices provide youth mode, but when this mode is turned on, a certain application may be blocked, without more detailed supervision and blocking of the content in the software. Summary of the invention

[0004] The main purpose of the present invention is to solve the technical problem that browser web page interception is not detailed enough.

[0005] A first aspect of the present invention provides a browser web page warning interception method, the browser web page warning interception method comprising:

[0006] Obtaining a list of browsing device applications, and determining whether the currently opened application is a browser according to the list of browsing device applications;

[0007] If yes, then read the currently visited web page interface information through the auxiliary function event, wherein the auxiliary function event is used to receive the callback content of the current browser interface information;

[0008] Acquire text information and images in the current browser webpage according to the webpage interface information, and determine whether the current browser webpage has an abnormality according to the text information and images in the current browser webpage;

[0009] If there is an abnormality, the preset local web page is pushed to the current browser to cover the current browser web page, and an early warning message is sent to the device terminal.

[0010] Optionally, in a first implementation of the first aspect of the present invention, before reading the currently visited web page interface information through the auxiliary function event, the method further includes:

[0011] Get the URL information of the current browser web page;

[0012] Parse the website information, read the host information, and determine whether the current domain name is a risky domain name based on the host information;

[0013] If not, the process proceeds to the step of reading the interface information of the currently accessed web page through the auxiliary function event.

[0014] Optionally, in a second implementation of the first aspect of the present invention, acquiring text information and images in the current browser webpage according to the webpage interface information, and judging whether there is an abnormality in the current browser webpage according to the text information and images in the current browser webpage includes:

[0015] Scan the web page interface information and extract text information from the current browser web page through auxiliary function services;

[0016] Detecting the text information to determine whether a preset keyword is triggered;

[0017] If yes, it is determined that there is an abnormality in the current browser webpage;

[0018] If not, extract the picture in the current browser webpage, and determine whether the current browser webpage has any abnormality based on the picture.

[0019] Optionally, in a third implementation of the first aspect of the present invention, extracting an image from the current browser webpage, and judging whether the current browser webpage is abnormal according to the image includes:

[0020] Obtaining each node type in the current browser webpage through the auxiliary function service;

[0021] According to the node types, the image area in the current browser webpage is identified;

[0022] Identify the image content in the image area, and determine whether the image content contains sensitive information;

[0023] If so, it is determined that there is an abnormality in the current browser web page.

[0024] Optionally, in a fourth implementation manner of the first aspect of the present invention, the identifying the image content in the image area and determining whether the image content contains sensitive information includes:

[0025] Upload the pictures in the picture area to the Azure platform;

[0026] Obtaining a selected analysis type, where the analysis type is used to identify and analyze the specified image content;

[0027] According to the analysis type, the Azure AI Vision service is used to detect and identify the image content to determine whether there is sensitive information in the image content.

[0028] Optionally, in a fifth implementation manner of the first aspect of the present invention, the detecting the text information to determine whether a preset keyword is triggered includes:

[0029] Detecting whether the text information contains a preset keyword by a keyword matching algorithm, wherein the keyword matching algorithm includes full word matching or partial matching;

[0030] If the preset keyword is included, obtaining context information of the keyword in the text information;

[0031] According to the context information, it is determined whether the preset keyword is triggered.

[0032] Optionally, in a sixth implementation of the first aspect of the present invention, before reading the currently visited web page interface information through the auxiliary function event, the method further includes:

[0033] Determine whether the browser is the browser to be blocked;

[0034] If not, the process proceeds to the step of reading the interface information of the currently accessed web page through the auxiliary function event.

[0035] The second aspect of the present invention provides a browser web page warning interception device, comprising: a memory and at least one processor, wherein instructions are stored in the memory, and the memory and the at least one processor are interconnected via a line; the at least one processor calls the instructions in the memory so that the browser web page warning interception device executes the above-mentioned browser web page warning interception method.

[0036] A third aspect of the present invention provides a computer-readable storage medium, in which instructions are stored, and when the computer-readable storage medium is run on a computer, the computer executes the above-mentioned browser web page warning interception method.

[0037] In an embodiment of the present invention, a list of browsing device applications is obtained, and according to the list of browsing device applications, it is determined whether the currently opened application is a browser; if so, the currently accessed web page interface information is read through an auxiliary function event, and the auxiliary function event is used to receive the callback content of the current browser interface information; according to the web page interface information, the text information and pictures in the current browser web page are obtained, and according to the text information and pictures in the current browser web page, it is determined whether the current browser web page has an abnormality; if there is an abnormality, a preset local web page is pushed to the current browser to cover the current browser web page, and an early warning message is sent to the device terminal. In the present invention, by reading the currently accessed web page interface information and identifying the text information and pictures in the current browser web page, it is determined whether the current browser web page has an abnormality, and if there is an abnormality, a preset local web page is pushed to the current browser to cover the current browser web page, which can realize the supervision of the specified content information in the browser web page, refine the supervision and interception content, and thus improve the efficiency of browser web page early warning interception. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic diagram of an embodiment of a browser webpage warning interception method in an embodiment of the present invention;

[0039] Figure 2 A schematic diagram of an embodiment of a browser webpage warning interception device in an embodiment of the present invention;

[0040] Figure 3 It is a schematic diagram of an embodiment of a browser web page warning interception device in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The embodiments of the present invention provide a browser web page warning interception method, device, equipment and storage medium.

[0042] The embodiments disclosed in the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments disclosed in the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments disclosed in the present invention are only for exemplary purposes and are not intended to limit the scope of protection disclosed in the present invention.

[0043] In the description of the embodiments disclosed in the present invention, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0044] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the browser webpage warning interception method in an embodiment of the present invention includes:

[0045] S100, obtaining a list of browsing device applications, and determining whether a currently opened application is a browser according to the list of browsing device applications.

[0046] In this embodiment, to obtain a list of browsing device applications and determine whether the currently opened application is a browser based on the list of browsing device applications, JavaScript can be used to detect the user agent string. The user agent string contains information about the browser and the operating system. Common browser identifiers are usually included in the user agent string. By parsing this string, it can be determined whether the current application is a browser. Specifically, first obtain the user agent string. Optionally, the user agent string can be obtained through navigator.userAgent; secondly, define the browser identifier and list common browser identifiers, such as Chrome, Firefox, Safari, etc.; then, traverse the identifier list to check whether these identifiers are included in the user agent string. If a matching identifier is found, true is returned, otherwise false is returned.

[0047] S200: If yes, read the currently visited web page interface information through the auxiliary function event.

[0048] In this embodiment, an application is written and installed, and an auxiliary function is set in the manifest file of the application. In the auxiliary function configuration, the callback content of the interface information that the application needs to receive is set. Specifically, first, the auxiliary function is turned on, and then, according to the list of browsing device applications, it is determined whether the currently opened application is a browser. If so, the currently accessed web page interface information is read through the auxiliary function event, wherein the auxiliary function event is used to receive the callback content of the current browser interface information. Specifically, by defining an interface and declaring an instance of the interface in a class, when an auxiliary function event occurs, the system will call the callback method in the interface to handle the event, thereby obtaining the currently accessed web page interface information. In this way, the implementation class can be flexibly replaced, thereby achieving the purpose of interface unification, so that all browser applications can be effectively and uniformly managed.

[0049] S300, obtaining text information and images in the current browser webpage according to the webpage interface information, and judging whether there is an abnormality in the current browser webpage according to the text information and images in the current browser webpage.

[0050] In the present embodiment, the website information is read for analysis, and then the text information and pictures in the current browser webpage are directly captured for identification through the auxiliary function service. Specifically, some browser plug-ins or automation tools can be used. For example, a web crawler developed by JavaScript can be used to parse the webpage content by building a DOM tree and extract the required data. In addition, some Web data extraction tools such as VisualScraper can be used. Such tools can help users extract data from multiple webpages in real time. In addition, the auxiliary function service can also monitor HTTP requests through browser plug-ins, thereby collecting data submitted by forms, and then realizing the extraction of dynamic JavaScript content. This method can effectively improve the accuracy and efficiency of information extraction. Then, it is judged whether the text information and pictures in the current browser webpage contain sensitive information. If sensitive information is contained, it is judged that the current browser webpage has an abnormality.

[0051] S400, if there is an abnormality, the preset local web page is pushed to the current browser to cover the current browser web page, and an early warning message is sent to the device terminal.

[0052] In this embodiment, if the current browser webpage is abnormal, a new browser intention is directly initiated to allow the preset local webpage to cover the current browser webpage content, ensuring that the user will not browse abnormal information, and send an early warning message to the device terminal to prompt the user. The early warning message can be sent through SMS push or APP push. At the same time, the current URL is set as an abnormal URL to prevent the need for image recognition next time.

[0053] In an optional implementation of the first aspect of the present invention, before reading the currently accessed web page interface information through the auxiliary function event, the method further includes:

[0054] Obtain the URL information of the current browser web page; parse the URL information, read the host information, and determine whether the current domain name is a risky domain name based on the host information; if not, enter the step of reading the interface information of the currently visited web page through the auxiliary function event.

[0055] In this embodiment, first, it is necessary to obtain the URL information of the current browser web page and read the host information. Specifically, after obtaining the URL information, the domain name can be tested by modifying the hosts file to see if it can be maliciously pointed to. For example, by adding a line in the hosts file to resolve a domain name to a specific IP address, and then accessing the domain name, if the returned result is consistent with the normal access, it means that the website may be easily pointed to by malicious intent. Then, query the domain name history. If it is found that the domain name has been used for malicious activities, it should be considered as a high risk. In addition, the security of the domain name can be evaluated by querying the domain name credit rating. Optionally, the security of the domain name can be more comprehensively judged by comprehensively considering factors such as registration time, PR value, filing information, DNS information, website status, and historical records. Some online tools such as the domain name detection tool provided by DNSPod can be used. These tools can check the basic information, DNS information, filing information, and website status of the domain name.

[0056] In an optional implementation of the first aspect of the present invention, obtaining text information and images in the current browser webpage according to the webpage interface information, and judging whether there is an abnormality in the current browser webpage according to the text information and images in the current browser webpage includes:

[0057] Scan the web page interface information, and extract the text information in the current browser web page through the auxiliary function service; detect the text information to determine whether it triggers the preset keywords; if so, determine that there is an abnormality in the current browser web page; if not, extract the pictures in the current browser web page, and determine whether there is an abnormality in the current browser web page based on the pictures.

[0058] In this embodiment, the URL information of the browser webpage is first read, and then the host information is read. According to the host information, it is determined whether the current domain name is a risky domain name. If the current domain name is not a risky domain name, it will also be scanned through the current screen, and the text information of the entire current browser webpage will be directly extracted through the auxiliary function service. The text information is detected and compared to see whether the preset keywords are triggered. If the preset keywords are triggered, it is determined that there is an abnormality in the current browser webpage. If the preset keywords are not triggered, the content of the picture / video playback in the current browser webpage is extracted and analyzed to determine whether there is sensitive information therein. If there is sensitive information, it is determined that there is an abnormality in the current browser webpage. By judging the current domain name and identifying the text information and pictures in the webpage, it can be guaranteed that the viewed webpage content is completely safe and legal.

[0059] In an optional implementation of the first aspect of the present invention, extracting a picture from a current browser webpage, and judging whether the current browser webpage has an abnormality according to the picture includes:

[0060] Through the auxiliary function service, the node types in the current browser web page are obtained; according to the node types, the image area in the current browser web page is identified; the image content in the image area is identified to determine whether there is sensitive information in the image content; if so, it is determined that there is an abnormality in the current browser web page.

[0061] In this embodiment, in order to obtain the image information in the current browser web page, first, it is necessary to identify the various node types in the current browser web page, obtain the image areas in the current browser web page, and identify which areas are images (such as imageview). Then, the image content of these areas can be extracted, and the Azure AI service can be used to determine whether there is sensitive information in the image content. If there is sensitive information, it is determined that there is an abnormality in the current browser web page. Optionally, the Azure custom vision service can be used to build and train the image model through the Azure AI service. Specifically, first, the user needs to upload images containing target sensitive content and mark these images. The marking process must specify the objects in the image and their bounding boxes. This step is the basis for training the model; then, through deep learning technology, a large number of labeled images are trained, and the model can automatically learn and identify sensitive features in the image, such as indecent images, infringing images, etc.

[0062] In an optional implementation of the first aspect of the present invention, identifying the image content in the image area and determining whether the image content contains sensitive information includes:

[0063] Upload the images in the image area to the Azure platform; obtain the selected analysis type, which is used to identify and analyze the specified image content; based on the analysis type, detect and identify the image content through the Azure AI Vision service to determine whether there is sensitive information in the image content.

[0064] In this embodiment, to extract the content of the picture / video played in the browser webpage for analysis, it can be achieved with the help of Azure AI service. First, it is necessary to use the auxiliary function to obtain the type of each node in the webpage and identify the picture area. Then, the content of these areas can be extracted and further detected using Azure AI service. Azure AI service provides a series of image and video analysis functions, including but not limited to image recognition, object detection, sensitive content detection, etc. Specifically, Azure's computer vision service can identify objects and their bounding boxes in the image, detect sensitive or inappropriate content, and extract text from the image. After identifying the image area, upload the image to the Azure platform, and then select the analysis type according to the needs. For example, you can use Azure AI Vision service to analyze text, objects, faces, etc. in the image. These functions can be used directly through pre-built models or through custom models for more personalized analysis. If you need to analyze video content, you can use Azure AI Video Indexer, which can process uploaded videos and create a cognitive index to extract insights from them. To identify specific images or objects, you can use Azure Custom Vision function to train and publish image models in Azure Custom Vision.

[0065] In an optional implementation of the first aspect of the present invention, detecting the text information to determine whether a preset keyword is triggered includes:

[0066] A keyword matching algorithm is used to detect whether the text information contains preset keywords. The keyword matching algorithm includes full word matching or partial matching. If the preset keywords are contained, the context information of the keywords in the text information is obtained. Based on the context information, it is determined whether the preset keywords are triggered.

[0067] In this embodiment, first, the text information needs to be preprocessed, including operations such as word segmentation and removal of stop words. After the text is preprocessed, a keyword matching algorithm is used to find whether the text contains preset keywords. When matching keywords, full word matching or partial matching can be selected. Full word matching requires that the keyword must appear completely in the text, while partial matching allows partial forms of the keyword to appear. In order to improve the accuracy of matching, contextual information can be combined for analysis. For example, the key semantic information in the sentence can be captured through a local attention mechanism, or the semantic information at the document level can be understood using a global attention mechanism. According to the contextual information, it is determined whether the preset keywords are triggered. If the preset keywords are triggered, the current web page is overwritten with a preset local web page.

[0068] In an optional implementation of the first aspect of the present invention, before reading the currently accessed web page interface information through the auxiliary function event, the method further includes:

[0069] Determine whether the browser is the browser to be blocked; if not, proceed to the step of reading the interface information of the currently visited web page through the auxiliary function event.

[0070] In this embodiment, first, it is determined whether the currently opened browser is the browser to be blocked, wherein the type and version of the browser can be checked, and whether there are specific blocking rules or settings to determine whether the browser is the browser to be blocked. If the browser is not the browser to be blocked, the currently accessed web page interface information is read to identify the text and image information in the web page interface.

[0071] See also Figure 2 The second aspect of the present invention provides a browser webpage warning interception device, the browser webpage warning interception device comprising:

[0072] The application determination module 10 is used to obtain a list of applications of the browsing device and determine whether the currently opened application is a browser according to the list of applications of the browsing device;

[0073] The interface information reading module 20 is used to read the interface information of the currently visited web page through the auxiliary function event, and the auxiliary function event is used to receive the callback content of the current browser interface information;

[0074] The webpage abnormality judgment module 30 is used to obtain the text information and pictures in the current browser webpage according to the webpage interface information, and judge whether the current browser webpage has abnormality according to the text information and pictures in the current browser webpage;

[0075] The webpage interception and coverage module 40 is used to push a preset local webpage to the current browser to cover the current browser webpage if there is an abnormality, and send an early warning message to the device terminal.

[0076] In an optional implementation of the second aspect of the present invention, the browser web page warning interception device also includes: a risky domain name judgment module, which is used to obtain the URL information of the current browser web page; parse the URL information, read the host information, and judge whether the current domain name is a risky domain name based on the host information; if not, enter the step of reading the currently visited web page interface information through the auxiliary function event.

[0077] In an optional implementation of the second aspect of the present invention, the web page anomaly judgment module 30 is also used to scan the web page interface information, and extract the text information in the current browser web page through the auxiliary function service; detect the text information to determine whether the preset keywords are triggered; if so, determine that there is an anomaly in the current browser web page; if not, extract the picture in the current browser web page, and determine whether there is an anomaly in the current browser web page based on the picture.

[0078] In an optional implementation of the second aspect of the present invention, the web page anomaly judgment module 30 is also used to obtain each node type in the current browser web page through the auxiliary function service; identify the image area in the current browser web page according to each node type; identify the image content in the image area, and judge whether there is sensitive information in the image content; if so, judge that there is an anomaly in the current browser web page.

[0079] In an optional implementation of the second aspect of the present invention, the web page anomaly judgment module 30 is also used to upload images in the image area to the Azure platform; obtain a selected analysis type, the analysis type is used to identify and analyze the specified image content; according to the analysis type, through the Azure AI Vision service, detect and identify the image content, and determine whether there is sensitive information in the image content.

[0080] In an optional implementation of the second aspect of the present invention, the web page anomaly judgment module 30 is also used to detect whether the text information contains preset keywords through a keyword matching algorithm, and the keyword matching algorithm includes full word matching or partial matching; if the preset keywords are contained, the context information of the keywords in the text information is obtained; based on the context information, it is determined whether the preset keywords are triggered.

[0081] In an optional implementation of the second aspect of the present invention, the browser web page warning interception device also includes: a browser interception module, used to determine whether the browser is the browser to be intercepted; if not, entering the step of reading the currently visited web page interface information through auxiliary function events.

[0082] Figure 31 is a schematic diagram of the structure of a browser web page warning interception device provided by an embodiment of the present invention. The browser web page warning interception device 500 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 510 (for example, one or more processors) and a memory 520, and one or more storage media 530 (for example, one or more mass storage devices) storing application programs 533 or data 532. Among them, the memory 520 and the storage medium 530 can be short-term storage or permanent storage. The program stored in the storage medium 530 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the browser web page warning interception device 500. Furthermore, the processor 510 can be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the browser web page warning interception device 500.

[0083] The browser webpage warning interception device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input and output interfaces 560, and / or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 3 The browser web page warning interception device structure shown does not constitute a limitation on the browser web page warning interception device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0084] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the browser web page warning interception method.

[0085] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0086] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.

[0087] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A browser webpage warning interception method, characterized in that: The browser webpage early warning interception method comprises: Obtaining a list of browsing device applications, and determining whether the currently opened application is a browser according to the list of browsing device applications; If yes, then read the currently visited web page interface information through the auxiliary function event, wherein the auxiliary function event is used to receive the callback content of the current browser interface information; Acquire text information and images in the current browser webpage according to the webpage interface information, and determine whether the current browser webpage has an abnormality according to the text information and images in the current browser webpage; If there is an abnormality, the preset local web page is pushed to the current browser to cover the current browser web page, and an early warning message is sent to the device terminal.

2. The browser webpage warning interception method according to claim 1, characterized in that: Before reading the currently visited web page interface information through the auxiliary function event, the method further includes: Get the URL information of the current browser web page; Parse the website information, read the host information, and determine whether the current domain name is a risky domain name based on the host information; If not, the process proceeds to the step of reading the interface information of the currently accessed web page through the auxiliary function event.

3. The browser webpage warning interception method according to claim 1, characterized in that: The acquiring text information and images in the current browser webpage according to the webpage interface information, and judging whether the current browser webpage has an abnormality according to the text information and images in the current browser webpage includes: Scan the web page interface information and extract text information from the current browser web page through auxiliary function services; Detecting the text information to determine whether a preset keyword is triggered; If yes, it is determined that there is an abnormality in the current browser webpage; If not, extract the picture in the current browser webpage, and determine whether the current browser webpage has any abnormality based on the picture.

4. The browser webpage warning interception method according to claim 3 is characterized in that: The extracting the image from the current browser webpage and judging whether the current browser webpage has an abnormality according to the image comprises: Obtaining each node type in the current browser webpage through the auxiliary function service; According to the node types, the image area in the current browser webpage is identified; Identify the image content in the image area, and determine whether the image content contains sensitive information; If so, it is determined that there is an abnormality in the current browser web page.

5. The browser webpage warning interception method according to claim 4, characterized in that: The identifying the image content in the image area and determining whether the image content contains sensitive information comprises: Upload the pictures in the picture area to the Azure platform; Obtaining a selected analysis type, where the analysis type is used to identify and analyze the specified image content; According to the analysis type, the Azure AI Vision service is used to detect and identify the image content to determine whether there is sensitive information in the image content.

6. The browser webpage warning interception method according to claim 3, characterized in that: The detecting of the text information to determine whether a preset keyword is triggered includes: Detecting whether the text information contains a preset keyword by a keyword matching algorithm, wherein the keyword matching algorithm includes full word matching or partial matching; If the preset keyword is included, obtaining context information of the keyword in the text information; According to the context information, it is determined whether the preset keyword is triggered.

7. The browser webpage warning interception method according to claim 1, characterized in that: Before reading the currently visited web page interface information through the auxiliary function event, the method further includes: Determine whether the browser is the browser to be blocked; If not, the process proceeds to the step of reading the interface information of the currently accessed web page through the auxiliary function event.

8. A browser webpage warning interception device, characterized in that: The browser webpage early warning interception device comprises: An application determination module, used to obtain a list of browsing device applications and determine whether the currently opened application is a browser according to the list of browsing device applications; An interface information reading module, used to read the interface information of the currently visited web page through an auxiliary function event, wherein the auxiliary function event is used to receive the callback content of the current browser interface information; A webpage abnormality judgment module is used to obtain text information and pictures in the current browser webpage according to the webpage interface information, and judge whether the current browser webpage has abnormality according to the text information and pictures in the current browser webpage; The webpage interception and coverage module is used to push a preset local webpage to the current browser to cover the current browser webpage if there is an abnormality, and send an early warning message to the device terminal.

9. A browser webpage warning interception device, characterized in that: The browser webpage warning interception device comprises: a memory and at least one processor, the memory stores instructions, and the memory and the at least one processor are interconnected via a line; The at least one processor calls the instruction in the memory so that the browser web page warning interception device executes the browser web page warning interception method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the browser web page warning interception method as described in any one of claims 1 to 7 is implemented.

Images