User information security risk assessment method and device, electronic equipment and medium

Abstract

The present disclosure provides a user information security risk assessment method and device, electronic equipment and medium, relates to the technical field of data processing, and particularly relates to the technical field of natural language processing, large language model and information security. The implementation scheme is: obtaining first page data of a first page of a target application program, wherein the first page is used to display a privacy policy describing a user information list of the target application program, and the first page includes at least one first link; processing the first page data using a large model, wherein the large model is used to: screening at least one second link from the at least one first link, wherein each second link in the at least one second link indicates a first sub-page used to display other content in addition to the privacy policy; and extracting an evaluation data list from the first page data excluding the at least one second link; and evaluating the degree of information security risk when a user uses the target application program according to the evaluation data list.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and more particularly to the fields of natural language processing, large language models and information security technology, specifically to a risk assessment method, apparatus, electronic device, computer-readable storage medium and computer program product for user information security. Background Technology

[0002] An application's privacy policy typically includes information on how the application collects, uses, stores, shares, and destroys users' personal information, as well as how users can query, correct, delete, and withdraw authorization for their personal information. It is an important way for developers to disclose this information to users.

[0003] Semantic recognition can be performed on the content of the application's privacy policy page to determine a list of user information that may be involved in the use of the application, and then the degree of information security risk when a user uses the application can be determined based on the aforementioned list of user information.

[0004] However, the privacy policy page of an application usually includes a lot of content that is not related to the privacy policy. Therefore, this method of directly performing semantic recognition on the entire privacy policy page not only consumes a lot of model resources, but also has low accuracy of semantic recognition results, which will lead to unreliable risk assessment results. Summary of the Invention

[0005] This disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for risk assessment of user information security.

[0006] According to one aspect of this disclosure, a method for risk assessment of user information security is provided, comprising: obtaining first page data of a first page of a target application, wherein the first page is used to display a privacy policy describing the target application regarding a list of user information, and the first page includes at least one first link; processing the first page data using a large model, wherein the large model is used to: filter at least one second link from the at least one first link, wherein each of the at least one second link indicates a first subpage for displaying content other than the privacy policy; and extracting associated content of the list of user information from the first page data after excluding the at least one second link to obtain an assessment data list; and assessing the degree of information security risk when a user uses the target application based on the assessment data list.

[0007] According to another aspect of this disclosure, a risk assessment apparatus for user information security is provided, comprising: an acquisition module configured to acquire first page data of a first page of a target application, wherein the first page is used to display a privacy policy describing the target application regarding a list of user information, and the first page includes at least one first link; a processing module configured to process the first page data using a large model, wherein the large model is used to: filter at least one second link from the at least one first link, wherein each of the at least one second link indicates a first subpage for displaying content other than the privacy policy; and extract associated content of the user information list from the first page data excluding the at least one second link to obtain an assessment data list; and an assessment module configured to assess the degree of information security risk when a user uses the target application based on the assessment data list.

[0008] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the methods described above.

[0009] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the above-described method.

[0010] According to another aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the above-described method.

[0011] According to one or more embodiments of this disclosure, a risk assessment method for user information security is provided, which uses a large model to process page data of an application's privacy policy display page based on two levels to extract a user information list and assess the degree of risk to user information security based on the user information list.

[0012] Specifically, privacy policy display pages typically include links to privacy policy detail pages and links to non-privacy policy detail pages. The large model first identifies and excludes links to non-privacy policy detail pages, obtaining privacy policy page data that only includes links to privacy policy detail pages. Then, it extracts the user information list from these links, thus avoiding wasting resources processing content in irrelevant link detail pages, effectively reducing the data scale processed by the large model, significantly reducing the probability of missed or false judgments in semantic recognition, and improving the reliability of the final risk assessment results.

[0013] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0014] The accompanying drawings exemplify embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0015] Figure 1 This is a schematic diagram illustrating an example system in which various methods described herein may be implemented according to exemplary embodiments;

[0016] Figure 2 A flowchart illustrating a risk assessment method for user information security according to embodiments of the present disclosure is shown;

[0017] Figure 3a and Figure 3b Schematic diagrams are shown of two first pages according to embodiments of the present disclosure for displaying a privacy policy describing a list of user information for a target application;

[0018] Figure 4 A partial flowchart of another risk assessment method for user information security according to an embodiment of the present disclosure is shown;

[0019] Figure 5 A partial flowchart of another risk assessment method for user information security according to an embodiment of the present disclosure is shown;

[0020] Figure 6 A partial flowchart of another risk assessment method for user information security according to an embodiment of the present disclosure is shown;

[0021] Figure 7 A partial flowchart of another risk assessment method for user information security according to an embodiment of this disclosure is shown.

[0022] Figure 8 A partial flowchart of another risk assessment method for user information security according to an embodiment of the present disclosure is shown;

[0023] Figure 9 A structural block diagram of a risk assessment apparatus for user information security according to embodiments of the present disclosure is shown; and

[0024] Figure 10 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0025] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0026] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0027] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.

[0028] Among the related technologies, it is proposed that semantic recognition can be performed on the content of the application's privacy policy page to determine the list of user information that may be involved in the use of the application, and then determine the degree of information security risk when the user uses the application based on the aforementioned user information list.

[0029] However, the privacy policy page of an application usually includes a lot of content that is not related to the privacy policy. Therefore, this method of directly performing semantic recognition on the entire privacy policy page not only consumes a lot of model resources, but also has low accuracy of semantic recognition results, which will lead to unreliable risk assessment results.

[0030] To address the aforementioned issues, this disclosure provides a risk assessment method for user information security. It uses a large model based on two levels to process page data from the application's privacy policy display page, extracting a user information list and assessing the degree of risk to user information security based on the user information list.

[0031] Specifically, privacy policy display pages typically include links to privacy policy detail pages and links to non-privacy policy detail pages. The large model first identifies and excludes links to non-privacy policy detail pages, obtaining privacy policy page data that only includes links to privacy policy detail pages. Then, it extracts the user information list from these links, thus avoiding wasting resources processing content in irrelevant link detail pages, effectively reducing the data scale processed by the large model, significantly reducing the probability of missed or false judgments in semantic recognition, and improving the reliability of the final risk assessment results.

[0032] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0033] Figure 1 A schematic diagram of an exemplary system 100 in which the various methods and apparatus described herein can be implemented according to embodiments of this disclosure is shown. Reference Figure 1 The system 100 includes one or more client devices 101, 102, 103, 104, 105 and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105 and 106 can be configured to execute one or more applications.

[0034] In embodiments of this disclosure, server 120 may run one or more services or software applications that enable the execution of risk assessment methods for user information security.

[0035] In some embodiments, server 120 may also provide other services or software applications that may include non-virtual and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, such as to users of client devices 101, 102, 103, 104, 105 and / or 106 under a Software as a Service (SaaS) model.

[0036] exist Figure 1 In the configuration shown, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or combinations thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 can sequentially interact with server 120 using one or more client applications to utilize the services provided by these components. It should be understood that various different system configurations are possible and may differ from system 100. Therefore, Figure 1 This is an example of a system used to implement the risk assessment method for user information security described herein, and is not intended to be limiting.

[0037] Users can use client devices 101, 102, 103, 104, 105, and / or 106 to perform risk assessment methods for user information security. The client devices can provide interfaces that allow users to interact with them. The client devices can also output information to users through these interfaces. Although... Figure 1 Only six client devices are described, but those skilled in the art will understand that this disclosure can support any number of client devices.

[0038] Client devices 101, 102, 103, 104, 105, and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptops), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors, or other sensing devices. These computer devices can run various types and versions of software applications and operating systems, such as Microsoft Windows, Apple iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as Google Chrome OS); or include various mobile operating systems, such as Microsoft Windows Mobile OS, iOS, Windows Phone, and Android. Portable handheld devices may include cellular phones, smartphones, tablets, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Gaming systems may include various handheld gaming devices, internet-enabled gaming devices, etc. Client devices are capable of executing various applications, such as various internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and can use various communication protocols.

[0039] Network 110 can be any type of network well known to those skilled in the art, and can use any of a variety of available protocols (including but not limited to TCP / IP, SNA, IPX, etc.) to support data communication. By way of example only, one or more networks 110 can be a local area network (LAN), an Ethernet-based network, a token ring network, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0040] Server 120 may include one or more general-purpose computers, special-purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices for servers). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0041] The computing unit in server 120 can run one or more operating systems, including any of the aforementioned operating systems and any commercially available server operating system. Server 120 can also run any of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0042] In some implementations, server 120 may include one or more applications to analyze and merge data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0043] In some implementations, server 120 can be a server for a distributed system or a server integrated with blockchain. Server 120 can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0044] System 100 may also include one or more databases 130. In some embodiments, these databases may be used to store user information lists and other information. For example, one or more of databases 130 may be used to store data such as application privacy policies and large model weight parameter information. Databases 130 may reside in various locations. For example, a database used by server 120 may be local to server 120, or it may be located away from server 120 and may communicate with server 120 via a network-based or dedicated connection. Databases 130 may be of different types. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve data from and from the databases in response to commands.

[0045] In some embodiments, one or more of the databases 130 may also be used by an application to store application data. The databases used by the application may be of different types, such as key-value stores, object stores, or regular stores supported by a file system.

[0046] Figure 1 The system 100 can be configured and operated in various ways to enable the application of the various methods and apparatus described in this disclosure.

[0047] Figure 2 A flowchart of a risk assessment method for user information security according to an embodiment of the present disclosure is shown.

[0048] like Figure 2 As shown, the risk assessment method 200 for user information security includes:

[0049] Step 210: Obtain the first page data of the first page of the target application, wherein the first page is used to display a privacy policy describing the target application’s list of user information, and the first page includes at least one first link;

[0050] Step 220: Process the first page data using the large model, where the large model is used to perform the following steps:

[0051] Step 221: Select at least one second link from at least one first link, wherein each of the at least one second link indicates a first subpage for displaying content other than the privacy policy; and

[0052] Step 222: Extract the associated content of the user information list from the data of the first page after excluding at least one second link to obtain the evaluation data list; and

[0053] Step 230: Assess the level of information security risk when users use the target application based on the assessment data list.

[0054] Therefore, by using a large model based on two levels to process page data of the application's privacy policy display page, a user information list can be extracted and the level of risk to user information security can be assessed based on the user information list.

[0055] Specifically, privacy policy display pages typically include links to privacy policy detail pages and links to non-privacy policy detail pages. The large model first identifies and excludes links to non-privacy policy detail pages, obtaining privacy policy page data that only includes links to privacy policy detail pages. Then, it extracts the user information list from these links, thus avoiding wasting resources processing content in irrelevant link detail pages and effectively reducing the data scale processed by the large model.

[0056] Furthermore, privacy policy texts are not structured, standard format documents. The specific descriptions of the same type of user information often differ significantly between different applications, making them inherently difficult to identify. Irrelevant links on the privacy policy page (or the large amounts of irrelevant data obtained from the details pages of those links) further exacerbate this difficulty. By excluding irrelevant links, the privacy policy data used for semantic recognition can be effectively simplified, minimizing omissions or misjudgments during subsequent extraction of user information lists, thereby improving the reliability of the final risk assessment results.

[0057] In step 210, for example, the first page data may be a program of the first page 300 (e.g., a program based on programming languages ​​such as HTML, Java, JavaScript, Kotlin, and Swift).

[0058] In one example, for a first page dynamically generated by JavaScript, the user's operation process can be simulated, for example, using a cloud phone, so that for each third link on the first page, clicking can lead to a details page and obtain the specific content of the associated privacy policy.

[0059] In another example, for other types of first pages, the corresponding first page data can also be obtained using methods such as headless browsers.

[0060] Figure 3a and Figure 3b Schematic diagrams of two first pages for displaying a privacy policy describing a list of user information for a target application, according to embodiments of the present disclosure, are shown respectively.

[0061] This place is Figure 3a and Figure 3bThe method 200 of this disclosure is illustrated by example, but it should be understood that it is not limited thereto.

[0062] In one example, such as Figure 3a As shown, for step 210, the first page 301 can be a webpage redirected to after clicking the corresponding privacy policy button in the target application. The target application can be, for example, an educational application called "XX Classroom". The first page 301 includes at least one link (such as...). Figure 3a (The location indicated by the Chinese box).

[0063] For steps 221 and 222 in step 220, the data from the first page is input into the large model for understanding, enabling the large model to filter out links 320 (e.g., "Courses" and "About Us") associated with non-privacy policy detail pages from the first page 301 and exclude them from the first page 301, so as to extract a list of user information based on the first page data that only includes links 310 associated with privacy policy detail pages (e.g., "How we collect personal information" and "How we share, transfer, and publicly disclose personal information") and the remaining non-linked content (e.g., "When this version of the privacy policy was published...").

[0064] In one example, link 310 on the first page 301, which links to the privacy policy details page, can include two forms. See also Figure 3a Within the box corresponding to link 310, underlines are used to indicate the specific link location for users to click and view the details page. As you can see, for the first type of link 310, users can directly click the text description to view the details page (e.g., "How we collect personal information"). For the second type of link 310, users view the details page by clicking the specific URL (Uniform Resource Locator) address (e.g., "http: / / ..."). Text is used before and after the URL address to specifically describe the content of the details page indicated by the link.

[0065] In another example, such as Figure 3b As shown, the first page 302 of the target application can also be a page that can be viewed directly within the target application, displaying a privacy policy describing the user information list. The first page 302 includes links 330 to details of the privacy policy page (e.g., "Privacy Policy" and "Personal Information Collection List") and links 340 to details of non-privacy policy pages (e.g., "Account Information" and "Playback Settings"). The processing flow for the first page 302 is similar to that for the first page 301 described above, and will not be repeated here.

[0066] For step 230, the evaluation data list can be compared with the list of user information involved in the actual use of the target application to determine the transparency of the target application in informing users of the user information that it may collect and / or use, and the risk level of user information security can be determined based on the above transparency.

[0067] In one example, an evaluation data list can be extracted based on multiple applications, and different terms indicating the same user information type in the evaluation data list can be associated with the standard terms of the same user information type. This allows for a better comparison of the user information in the extracted evaluation data list with the actual behavior of the target application (e.g., requested user information permissions).

[0068] Figure 4 A partial flowchart of another risk assessment method for user information security according to an embodiment of this disclosure is shown.

[0069] According to some embodiments, such as Figure 4 As shown, step 221 includes:

[0070] Step 410: For each of the at least one first links,

[0071] Step 411: Determine the context information of the first link based on its position on the first page;

[0072] Step 412: Determine whether the first link points to the first subpage based on the context information; and

[0073] Step 413: In response to determining that the first link points to a first subpage, the first link is designated as the second link; and

[0074] Step 420: Traverse at least one first link to obtain at least one second link.

[0075] The context information of each link on the first page is usually highly related to the content of the details page that the link points to. Therefore, in the first-level processing, it is only necessary to selectively understand a portion of the data on the first page (the context information corresponding to each first link) to accurately filter out the second link. Compared to clicking the first link to enter the details page and then extracting the specific content for identification, this greatly reduces the processing difficulty and saves costs.

[0076] For step 411, in one example, the first page data is an HTML program. The position of each first link can be determined based on the attribute tags indicating the links in the HTML. These attribute tags can be, for example, `herf`, `target`, `rel`, `download`, and `id`. Similarly, for programming programs based on other languages, the position of each first link can also be determined based on the corresponding tags, which will not be elaborated further.

[0077] In another example, the location of each first link can be determined based on keywords, such as "http", "www", ".cn", and ".com".

[0078] According to some embodiments, step 412 includes: using a first number of text paragraphs above the first link and / or a second number of text paragraphs below the first link as context information.

[0079] Compared to sentences and words, paragraphs usually contain more complete semantic logic and semantic information. Therefore, using paragraphs as the basic unit to obtain the contextual information of the first link can more accurately determine whether the details page indicated by the first link is related to the privacy policy.

[0080] In one example, for the case where the first page data is an HTML program, after determining the location of the first link, it can be based on the paragraph attribute tag (e.g., The tag determines the context information corresponding to the first link.

[0081] It should be noted that for the first link displayed using a text description instead of a URL, this text description can also be included as contextual information for the first link, further improving recognition accuracy. For example, the program content corresponding to the first link might be "<ahref="http: / / ……"> The phrase “the personal information we collect” can be considered as at least part of the following information, following “http: / / …”.

[0082] For example, see Figure 3a In the box corresponding to link 310 on the privacy policy details page, for the link "Personal Information We Collect", the context information may be, for example, at least part of the above "This version of the privacy policy was published on...", the "Personal Information We Collect" itself, and the "III. Third Party List..." below. Figure 3b The same logic applies to the situation described above.

[0083] For example, the first quantity and the second quantity can be the same or different, and the first quantity and the second quantity can be, for example, 1, 2, 3 or 5.

[0084] Figure 5 A partial flowchart of another risk assessment method for user information security according to an embodiment of this disclosure is shown.

[0085] like Figure 5 As shown, according to some embodiments, in response to the first page data including text data describing at least part of the privacy policy, step 222 includes:

[0086] Step 510: Extract the first part associated with the user information list from the text data; and

[0087] Step 520: Add the first part to the evaluation data list.

[0088] See Figure 3a In the example, Figure 3a The "III. Third-Party List" section contains text data describing the user information list shared with third-party SDKs. Therefore, the relevant content can be extracted from this text data and added to the assessment data list to improve the data completeness of the assessment data list, thereby improving the reliability of the final risk assessment results.

[0089] Figure 6 A partial flowchart of another risk assessment method for user information security according to an embodiment of this disclosure is shown.

[0090] According to some embodiments, such as Figure 6 As shown, for step 410 in step 221, after step 412, the method further includes: step 6413, in response to determining that the first link indicates a second subpage for displaying at least part of the privacy policy, the first link is used as a third link;

[0091] Method 200 includes: step 6430, traversing at least one first link to obtain at least one third link;

[0092] Furthermore, step 222 includes:

[0093] Step 6221: Extract the second part associated with the user information list from at least one second subpage corresponding to at least one third link; and

[0094] Step 6222: Add the second part to the evaluation data list.

[0095] By traversing and identifying all third-party links, it is possible to selectively obtain content related to at least part of the privacy policy from the details page indicated by each third-party link. Based on the obtained content, semantic recognition is performed to extract a portion of the assessment data from the associated user information list and add it to the assessment data list. This further ensures the completeness of the extracted assessment data list and improves the reliability of the final risk assessment results.

[0096] According to some embodiments, the first user information list includes a first type of user information associated with the target application itself and a second type of user information associated with third-party applications.

[0097] For example, see Figure 3a The first type of user information may correspond to the user information described in the details page indicated by the "I. Personal Information We Collect" link, and the second type of user information may correspond to the user information under "III. Third-Party List".

[0098] Figure 7 A partial flowchart of another risk assessment method for user information security according to an embodiment of this disclosure is shown.

[0099] According to some embodiments, the second type of user information includes a first tag and a second tag. The first tag indicates the name of the third-party application associated with the second type of user information, and the second tag indicates the purpose of use, usage scenario, information type, and associated links of the second type of user information.

[0100] And, as Figure 7 As shown, step 222 includes:

[0101] Step 710: In response to the fact that the data of the first page after excluding at least one second link includes at least one first table, obtain the first table header of each first table in the at least one first table to obtain at least one first table header;

[0102] Step 720: Filter out the second header associated with the first label from at least one first header to obtain at least one second header;

[0103] Step 730: Based on the second tag, extract the corresponding second type of user information from at least one first table corresponding to at least one second header, to obtain at least one type of second type of user information; and

[0104] Step 740: Add at least one type II user information to the evaluation data list.

[0105] In privacy policies, the second type of user information is typically more structured than the first type. Specifically, for compliance purposes, the second type of user information usually needs to include five elements: name (i.e., the first tag), purpose of use, usage scenario, information type, and related links (i.e., the second tag). Furthermore, this type of user information is usually presented in tabular form. Therefore, the second type of user information can be identified and extracted from the tables on the first page first, thereby improving processing efficiency and reducing processing difficulty.

[0106] For example, see Figure 3a The second table can be, for example, corresponding to Figure 3a The table below "III. Third-Party List" shows that the target application "XX Classroom" will share "BB" class user information with the third-party application "AA", and each row in the second table includes at least one element of the corresponding second label for "BB" class user information.

[0107] It should be noted that, Figure 3a The table shown, associated with "BB" category user information, is for illustrative purposes only. Figure 3a The omitted portions also include forms associated with other types of user information and forms not associated with the privacy policy.

[0108] For example, the table header (i.e., the first row in the first table) typically displays the name of the third-party application, so the name can be extracted from the table header as the first label to determine that the first table is the second table (associated with the second type of user information).

[0109] For steps 710 and 720, in one example, the first page data for the HTML program type can be based on... (Table attribute tag) determines the position of each first table in the first page data, and based on In the attribute tag (Header attribute label) Determines the header of the first table, thus enabling filtering.

[0110] For steps 730 and 740, the second table obtained after filtering can be used to extract the corresponding second type of user information by parsing the table based on the second label.

[0111] Figure 8 A partial flowchart of another risk assessment method for user information security according to an embodiment of this disclosure is shown.

[0112] According to some embodiments, such as Figure 8 As shown, step 222 also includes:

[0113] Step 810: Extract at least one type of second-class user information from the data of the first page after excluding the first table and at least one second link as user information to be processed, and obtain at least one user information to be processed;

[0114] Step 820: For each piece of user information to be processed in at least one set of user information to be processed,

[0115] Step 821: Determine whether the second tag of the extracted user information to be processed is complete; and

[0116] Step 822: In response to the determination that the second tag of the user information to be processed lacks at least one element among purpose of use, use scenario, information type, and related links, extract the missing elements from the corresponding second tag of the user information to be processed from the first page data using vector recall, so as to update the user information to be processed; and

[0117] Step 830: Iterate through at least one pending user information and add the updated pending user information to the evaluation data list.

[0118] The second type of user information may also be presented in a non-tabular form. However, the probability of missed or false judgments in the second type of user information extracted from the non-tabular part through semantic recognition is higher than that extracted directly from the tabular part.

[0119] Therefore, based on the structured features of the second type of user information, the completeness of the extracted second type of user information can be verified using the above five elements for the second type of user information extracted from the non-table part, and vector recall can be performed for the second type of user information that is missing any element, thereby further improving the completeness and accuracy of the obtained evaluation data list.

[0120] According to some embodiments, the privacy policy includes a full version of the privacy policy and a reduced version of the privacy policy. Method 200 further includes: in response to determining that the first page is used to display the reduced version of the privacy policy, obtaining second page data for displaying the full version of the privacy policy and updating the first page data.

[0121] For example, the privacy policy of the target application may include a full version and an abridged version (e.g., a children's version, a simplified version, or a summary version). Only the first page of the full version of the privacy policy is used to extract the user information list to ensure the completeness of the extracted user information list and reduce resource costs.

[0122] In one example, the title of the privacy policy can be used to identify the specific version of the privacy policy.

[0123] According to some embodiments, method 200 further includes: returning the first page data and the evaluation data list as training data to a large model for training, so as to update the model parameters of the large model.

[0124] Since there is no unified industry standard for the terminology used in application privacy policies, retraining the large model by returning the first-page data and evaluation data list can enable the large model to better establish the association between the specific terminology in the privacy policy and the corresponding types of user information, thereby improving the overall performance of the large model.

[0125] Figure 9 A structural block diagram of a risk assessment apparatus for user information security according to an embodiment of the present disclosure is shown.

[0126] According to another aspect of this disclosure, a risk assessment device for user information security is provided. For example... Figure 9 As shown, the user information security risk assessment device 900 includes: an acquisition module 910 configured to acquire first page data of a first page of a target application, wherein the first page is used to display a privacy policy describing the target application's user information list, and the first page includes at least one first link; a processing module 920 configured to process the first page data using a large model, wherein the large model is used to: filter at least one second link from the at least one first link, wherein each of the at least one second link indicates a first subpage for displaying content other than the privacy policy; and extract associated content of the user information list from the first page data after excluding at least one second link to obtain an assessment data list; and an assessment module 930 configured to assess the degree of information security risk when a user uses the target application based on the assessment data list.

[0127] According to another aspect of this disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the aforementioned method.

[0128] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to cause the computer to perform the aforementioned method.

[0129] According to another aspect of this disclosure, a computer program product is also provided, comprising a computer program, wherein the computer program implements the aforementioned method when executed by a processor.

[0130] like Figure 10 As shown, the electronic device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. The RAM 1003 may also store various programs and data required for the operation of the electronic device 1000. The computing unit 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0131] Multiple components in electronic device 1000 are connected to I / O interface 1005, including: input unit 1006, output unit 1007, storage unit 1008, and communication unit 1009. Input unit 1006 can be any type of device capable of inputting information to electronic device 1000. Input unit 1006 can receive input digital or character information and generate key signal input related to user settings and / or function control of electronic device, and may include, but is not limited to, a mouse, keyboard, touchscreen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 1007 can be any type of device capable of presenting information, and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1008 may include, but is not limited to, disk and optical disk. Communication unit 1009 allows electronic device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth. TM Devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices and / or the like.

[0132] The computing unit 1001 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as GPU-based matrix computation methods. For example, in some embodiments, the GPU-based matrix computation method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by the computing unit 1001, one or more steps of the GPU-based matrix computation method described above can be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform GPU-based matrix computation methods by any other suitable means (e.g., by means of firmware).

[0133] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0135] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0136] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0137] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0138] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0139] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0140] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the methods, systems, and devices described above are merely exemplary embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.

Claims

1. A risk assessment method for user information security, comprising: Obtain first page data of the first page of the target application, wherein the first page is used to display a privacy policy describing the target application’s user information list, and the first page includes at least one first link, the user information list includes a second type of user information associated with third-party applications, and the second type of user information includes a second tag indicating the purpose of use, usage scenario, information type and associated link of the second type of user information; The first page data is processed using a large model, wherein the large model is used for: At least one second link is selected from the at least one first link, wherein each of the at least one second link indicates a first subpage for displaying content other than the privacy policy, wherein selecting at least one second link from the at least one first link includes: Use the first number of text paragraphs above the first link and / or the second number of text paragraphs below the first link as contextual information; Determine whether the first link points to the first subpage based on the context information; and In response to determining that the first link points to the first subpage, the first link is used as the second link; and Traverse the at least one first link to obtain the at least one second link; and The associated content of the user information list is extracted from the first page data after excluding the at least one second link to obtain an evaluation data list, which includes: Extract at least one type of second-class user information from the first page data after excluding the at least one second link as user information to be processed, and obtain at least one user information to be processed; For each of the at least one user information to be processed Determine whether the second tag of the extracted user information to be processed is complete; and In response to the determination that the second tag of the user information to be processed is missing at least one of the elements of purpose of use, usage scenario, information type, and related links, vector recall is used to extract the missing elements from the corresponding second tag of the user information to be processed from the first page data to update the user information to be processed; and Iterate through the at least one pending user information and add the updated at least one pending user information to the evaluation data list; and The assessment data list is used to evaluate the level of information security risk when a user uses the target application.

2. The method according to claim 1, wherein, In response to the first page data including text data describing at least a portion of the privacy policy, the step of extracting the associated content of the user information list from the first page data excluding the at least one second link to obtain an evaluation data list includes: Extract the first portion associated with the user information list from the text data; and Add the first part to the evaluation data list.

3. The method according to claim 1, wherein, After determining whether the first link points to the first subpage based on the context information, the method further includes: In response to determining that the first link indicates a second subpage for displaying at least a portion of the privacy policy, the first link is designated as a third link; The method further includes: By traversing at least one first link, at least one third link is obtained; Furthermore, the step of extracting the associated content of the user information list from the first page data after excluding the at least one second link to obtain an evaluation data list includes: Extract the second portion associated with the user information list from at least one second subpage corresponding to the at least one third link; and Add the second part to the evaluation data list.

4. The method according to any one of claims 1-3, wherein, The user information list also includes a first category of user information associated with the target application itself.

5. The method according to claim 4, wherein, The second type of user information includes a first tag and a second tag, wherein the first tag indicates the name of the third-party application associated with the second type of user information. Furthermore, the step of extracting the associated content of the user information list from the first page data after excluding the at least one second link to obtain the evaluation data list further includes: In response to the fact that the first page data after excluding the at least one second link includes at least one first table, the first table header of each of the at least one first table is obtained to obtain at least one first header; Filter out the second header associated with the first label from the at least one first header to obtain at least one second header; Based on the second tag, extract the corresponding second type of user information from at least one first table corresponding to at least one second header to obtain at least one type of second user information; and Add the at least one type of second-class user information to the evaluation data list.

6. The method according to claim 5, wherein extracting at least one type of second-class user information as user information to be processed from the first page data after excluding the at least one second link, and obtaining at least one user information to be processed includes: Extract at least one type of second-class user information from the data of the first page after excluding the first table and the at least one second link as user information to be processed, and obtain the at least one user information to be processed.

7. The method according to any one of claims 1-3, wherein, The privacy policy includes a full version and a reduced version, and the method also includes: In response to determining that the first page is used to display the abridged version of the privacy policy, the first page data is updated by obtaining the second page data for displaying the full version of the privacy policy.

8. The method according to any one of claims 1-3, further comprising: The data from the first page and the evaluation data list are returned as training data to the large model for training, thereby updating the model parameters of the large model.

9. A risk assessment device for user information security, comprising: The acquisition module is configured to acquire first page data of a first page of a target application, wherein the first page is used to display a privacy policy describing the target application’s user information list, and the first page includes at least one first link, the user information list includes a second type of user information associated with third-party applications, and the second type of user information includes a second tag indicating the purpose of use, usage scenario, information type and associated link of the second type of user information; The processing module is configured to process the first page data using a large model, wherein the large model is used for: At least one second link is selected from the at least one first link, wherein each of the at least one second link indicates a first subpage for displaying content other than the privacy policy, wherein selecting at least one second link from the at least one first link includes: Use the first number of text paragraphs above the first link and / or the second number of text paragraphs below the first link as contextual information; Determine whether the first link points to the first subpage based on the context information; and In response to determining that the first link points to the first subpage, the first link is used as the second link; and Traverse the at least one first link to obtain the at least one second link; and The associated content of the user information list is extracted from the first page data after excluding the at least one second link to obtain an evaluation data list, which includes: Extract at least one type of second-class user information from the first page data after excluding the at least one second link as user information to be processed, and obtain at least one user information to be processed; For each of the at least one user information to be processed Determine whether the second tag of the extracted user information to be processed is complete; and In response to the determination that the second tag of the user information to be processed is missing at least one of the elements of purpose of use, usage scenario, information type, and related links, vector recall is used to extract the missing elements from the corresponding second tag of the user information to be processed from the first page data to update the user information to be processed; and Iterate through the at least one pending user information and add the updated at least one pending user information to the evaluation data list; and The assessment module is configured to assess the level of information security risk when a user uses the target application based on the assessment data list.

10. The apparatus according to claim 9, wherein, In response to the first page data including text data describing at least a portion of the privacy policy, the processing module is further configured to: Extract the first portion associated with the user information list from the text data; and Add the first part to the evaluation data list.

11. The apparatus according to claim 9, wherein, After determining whether the first link points to the first subpage based on the context information, the method further includes: In response to determining that the first link indicates a second subpage for displaying at least a portion of the privacy policy, the first link is designated as a third link; The processing module is further configured as follows: By traversing at least one first link, at least one third link is obtained; Extract the second portion associated with the user information list from at least one second subpage corresponding to the at least one third link; and Add the second part to the evaluation data list.

12. The apparatus according to any one of claims 9-11, wherein, The user information list also includes a first category of user information associated with the target application itself.

13. The apparatus according to claim 12, wherein, The second type of user information includes a first tag and a second tag, wherein the first tag indicates the name of the third-party application associated with the second type of user information. Furthermore, the processing module is further configured as follows: In response to the fact that the first page data after excluding the at least one second link includes at least one first table, the first table header of each of the at least one first table is obtained to obtain at least one first header; Filter out the second header associated with the first label from the at least one first header to obtain at least one second header; Based on the second tag, extract the corresponding second type of user information from at least one first table corresponding to at least one second header to obtain at least one type of second user information; and Add the at least one type of second-class user information to the evaluation data list.

14. The apparatus of claim 13, wherein the processing module is further configured to: Extract at least one type of second-class user information from the data of the first page after excluding the first table and the at least one second link as user information to be processed, and obtain the at least one user information to be processed.

15. The apparatus according to any one of claims 9-11, wherein, The privacy policy includes a full version and a reduced version. The device also includes: The determination module is configured to update the first page data in response to determining that the first page is used to display the abridged version of the privacy policy, by obtaining second page data for the second page used to display the full version of the privacy policy.

16. The apparatus according to any one of claims 9-11, further comprising: The update module is configured to return the first page data and the evaluation data list as training data to the large model for training, so as to update the model parameters of the large model.

17. An electronic device comprising: At least one processor; as well as A memory that is communicatively connected to the at least one processor; in The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-8.

19. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method of any one of claims 1-8.

Images