Asset classification method and device, electronic equipment and storage medium
By extracting webpage tag fingerprints from IoT assets and performing clustering, the problems of low efficiency and insufficient accuracy in IoT asset classification are solved, achieving higher classification accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SANGFOR TECH INC
- Filing Date
- 2022-06-02
- Publication Date
- 2026-06-02
AI Technical Summary
Existing IoT asset classification methods suffer from low efficiency and insufficient accuracy, especially in unsupervised classification where clustering accuracy cannot be guaranteed.
By acquiring webpage type data of IoT assets, extracting webpage tags and calculating fingerprints, and using clustering algorithms to group fingerprints with similarity less than a threshold into the same group, the asset category is determined. Then, unsupervised clustering algorithms are used to further optimize each category through clustering.
It improves the accuracy of IoT asset clustering, ensuring that assets in each asset category after clustering belong to the same category, thus enhancing the accuracy of classification.
Smart Images
Figure CN115017441B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of Internet of Things (IoT) technology, and more specifically, to an asset classification method, apparatus, electronic device, and computer-readable storage medium. Background Technology
[0002] With the advent of the big data era, especially the rapid development of 5G networks, a large number of IoT assets are being widely used in people's lives, such as cameras, routers, gateways, and web service components. However, while IoT assets bring great convenience, they also harbor numerous risks, such as frequent online data breaches and malicious cyberattacks that can severely impact businesses. Therefore, effectively managing IoT assets is crucial for patching and preventing potential vulnerabilities.
[0003] In related technologies, clustering methods are used to classify IoT assets, grouping similar assets together and then analyzing each asset within each group to complete the classification of that category. There are two approaches to classifying IoT assets: supervised classification and unsupervised clustering. Supervised classification requires manually labeling the data before model training, but this involves a large number of manual labels and is inefficient. Unsupervised clustering eliminates the need for manual labeling, but it compromises the accuracy of the clustering.
[0004] Therefore, improving the accuracy of asset clustering is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention
[0005] The purpose of this application is to provide an asset classification method, apparatus, electronic device, and computer-readable storage medium that improve the accuracy of asset clustering.
[0006] To achieve the above objectives, this application provides an asset classification method, comprising:
[0007] Obtain feature data for each asset; wherein, the feature data includes response data under a preset protocol, and the response data is webpage type data;
[0008] Extract the webpage tags corresponding to the webpage type data, and calculate the fingerprints corresponding to the webpage tags;
[0009] Clustering operations are performed on the fingerprints to obtain the asset categories corresponding to the assets.
[0010] After obtaining the feature data of each asset, the process further includes:
[0011] Clustering is performed on the characteristic data of different assets to divide each asset into multiple categories;
[0012] Accordingly, clustering operations are performed on the fingerprints to obtain the asset categories corresponding to the assets, including:
[0013] Clustering is performed on the fingerprints of assets in each category to obtain the asset category corresponding to the asset.
[0014] The step of extracting the webpage tags corresponding to the webpage type data includes:
[0015] The webpage type data is converted into a DOM tree structure, and webpage tags are extracted from the DOM tree structure.
[0016] Before extracting the webpage tags corresponding to the webpage type data, the method further includes:
[0017] Separate the body portion and other portions of the webpage type data;
[0018] Accordingly, extracting the webpage tags corresponding to the webpage type data includes:
[0019] Extract web page tags from the body portion of the web page type data.
[0020] The calculation of the fingerprint of the webpage tag includes:
[0021] The language features of the webpage tags are extracted based on a preset sliding window, and the fingerprint of the language features is calculated.
[0022] The step of performing clustering operations on the fingerprints corresponding to assets in each category to obtain the asset category includes:
[0023] Based on the similarity between fingerprints corresponding to different assets, different fingerprints with similarity less than a first preset value are grouped into the same group;
[0024] Assets corresponding to fingerprints in the same group are classified into the same asset class.
[0025] Prior to classifying the IoT assets corresponding to fingerprints in the same group into the same asset category, the process also includes:
[0026] Identify the target group containing the most fingerprints in each category, and calculate the ratio between the number of fingerprints in the target group and the total number of fingerprints in its category;
[0027] If the ratio is less than the second preset value, then the step of classifying the IoT assets corresponding to the fingerprints in the same group into asset categories is executed.
[0028] To achieve the above objectives, this application provides an asset classification device, comprising:
[0029] The acquisition module is used to acquire feature data of each asset; wherein, the feature data includes response data under a preset protocol, and the response data is webpage type data;
[0030] An extraction module is used to extract web page tags corresponding to the web page type data and calculate the fingerprints corresponding to the web page tags;
[0031] The clustering module is used to perform clustering operations on the fingerprint to obtain the asset category corresponding to the asset.
[0032] To achieve the above objectives, this application provides an electronic device, comprising:
[0033] Memory, used to store computer programs;
[0034] A processor is used to implement the steps of the asset classification method described above when executing the computer program.
[0035] To achieve the above objectives, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the asset classification method described above.
[0036] As can be seen from the above scheme, the asset classification method provided in this application includes: acquiring feature data of each asset; wherein, the feature data includes response data under a preset protocol, and the response data is web page type data; extracting web page tags corresponding to the web page type data, and calculating fingerprints corresponding to the web page tags; performing clustering operations on the fingerprints to obtain the asset category corresponding to the asset.
[0037] The asset classification method provided in this application extracts webpage tags based on the webpage type data of the assets, and clusters the assets by combining the fingerprints of the webpage tags, thereby ensuring that the assets in each asset category after clustering belong to the same asset category, improving the accuracy of asset clustering. This application also discloses an asset classification device, an electronic device, and a computer-readable storage medium, which can achieve the same technical effects.
[0038] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description
[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. The drawings are used to provide a further understanding of this disclosure and constitute a part of the specification. They are used together with the following detailed description to explain this disclosure, but do not constitute a limitation of this disclosure.
[0040] In the picture:
[0041] Figure 1 This is a flowchart illustrating an asset classification method according to an exemplary embodiment;
[0042] Figure 2 A flowchart illustrating another asset classification method according to an exemplary embodiment;
[0043] Figure 3 This is a structural diagram illustrating an asset classification device according to an exemplary embodiment;
[0044] Figure 4 This is a structural diagram of an electronic device according to an exemplary embodiment. Detailed Implementation
[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Furthermore, in the embodiments of this application, "first," "second," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.
[0046] This application discloses an asset classification method that improves the accuracy of asset clustering.
[0047] See Figure 1 A flowchart illustrating an asset classification method according to an exemplary embodiment, such as... Figure 1 As shown, it includes:
[0048] S101: Obtain feature data for each asset; wherein, the feature data includes response data under a preset protocol, and the response data is webpage type data;
[0049] The purpose of this embodiment is to classify assets. Specifically, the assets in this embodiment can be Internet of Things (IoT) assets. IoT assets can include devices, components, services, etc. Devices include cameras, routers, gateways, etc. Components include web service components, etc., and services include web services, etc.
[0050] In this step, the characteristic data of each asset is obtained, which may include response data under a preset protocol. This response data can specifically be web page type data, such as HTML (Hypertext Markup Language) or XML (Extensible Markup Language) data. Different characteristic data acquisition methods can be used for different assets. For the device, this step may include: sending a request message to the device to obtain a response message of the preset protocol from the device, and using the response message as the characteristic data of the device. The preset protocol here can be HTTP (Hypertext Transfer Protocol) or HTTPS (Hypertext Transfer Protocol Secure). In specific implementations, a common communication library (such as the socket library that comes with Python) is used to establish communication with the device, send a request message to the open port of the device's HTTP protocol, and obtain the HTTP protocol response message from the device as the characteristic data of the device. Alternatively, you can send a request message to the device's open HTTPS port to obtain the HTTPS response message. This HTTPS response message can then be redirected and analyzed, and the redirected message can be retrieved as the device's characteristic data. It's understood that HTTP typically uses port 80 and HTTPS typically uses port 443. However, some devices may change their HTTP or HTTPS open ports. Therefore, you can first use a scanning tool (such as nmap) to scan the device's open HTTP or HTTPS ports, and then obtain the HTTP or HTTPS response messages through those open ports.
[0051] S102: Extract the webpage tags corresponding to the webpage type data, and calculate the fingerprints corresponding to the webpage tags;
[0052] In this step, webpage tags are extracted from the webpage type data of each asset, for example... , Then, calculate the fingerprint corresponding to the webpage tag, for example, perform a hash calculation on the webpage tag, and use the calculated hash value as the fingerprint corresponding to the webpage tag.
[0053] As a feasible implementation method, extracting the webpage tags corresponding to the webpage type data includes: converting the webpage type data into a DOM tree structure, and extracting the webpage tags from the DOM tree structure. In a specific implementation, the webpage type data is converted into a DOM tree structure. DOM, or Document Object Model, is a standard API (Application Programming Interface) for processing HTML and XML files. Each node in the DOM tree structure represents a webpage tag, which can be extracted from the DOM tree structure.
[0054] It should be noted that before converting the webpage type data into a DOM tree structure, preprocessing is required to remove parts irrelevant to clustering. For example, webpage type data for routers and cameras includes headers and bodies. For these two IoT assets, only the body needs to be extracted for subsequent webpage tag extraction. Therefore, before converting the webpage type data into a DOM tree structure, the header and body need to be segmented. That is, before extracting the webpage tags corresponding to the webpage type data, the process includes: segmenting the body and other parts of the webpage type data; correspondingly, extracting the webpage tags corresponding to the webpage type data includes: extracting webpage tags from the body of the webpage type data.
[0055] Furthermore, as a feasible implementation, calculating the fingerprint of the webpage tag includes: extracting the language features of the webpage tag based on a preset sliding window, and calculating the fingerprint of the language features. In a specific implementation, firstly, a sliding window can be set, and a language model can be used to extract the language features of the webpage tag for each asset based on the sliding window. For example, N-gram (a language model commonly used in large-vocabulary continuous speech recognition) can be used to extract the language features of the webpage tag. For example, for webpage tags... For example, if the sliding window is 3, then extract respectively<br、br> 、r><、> < / 、< / b、 / br、br> The language features are then analyzed. Next, the fingerprint of these language features is calculated. One feasible implementation is to use Simhash to perform a hash calculation on the extracted language features to obtain a hash fingerprint, which serves as the fingerprint of the webpage tag for that asset.
[0056] S103: Perform a clustering operation on the fingerprint to obtain the asset category corresponding to the asset.
[0057] In this step, assets corresponding to web page tags with similar fingerprints are clustered. That is, based on the similarity between fingerprints corresponding to different assets, assets corresponding to fingerprints with similarity less than a threshold are classified into the same asset category, thereby determining the asset category corresponding to each asset.
[0058] As one possible implementation, this step may include: grouping different fingerprints with similarity less than a first preset value into the same group based on the similarity between fingerprints corresponding to different assets; and classifying the assets corresponding to fingerprints in the same group into the same asset category. In a specific implementation, the similarity between different fingerprints is calculated, such as the Hammington distance, and different fingerprints with similarity less than the first preset value are grouped into the same group, thereby classifying the assets corresponding to fingerprints in the same group into the same asset category.
[0059] The asset classification method provided in this application extracts webpage tags based on the webpage type data of the assets, and clusters the assets by combining the fingerprints of the webpage tags, thereby ensuring that the assets in each asset category after clustering belong to the same asset category, thus improving the accuracy of asset clustering.
[0060] This application discloses an asset classification method. Compared to the previous embodiment, this embodiment further explains and optimizes the technical solution. Specifically:
[0061] See Figure 2 A flowchart illustrating another asset classification method according to an exemplary embodiment, such as Figure 2 As shown, it includes:
[0062] S201: Obtain feature data for each asset; wherein, the feature data includes response data under a preset protocol, and the response data is webpage type data;
[0063] S202: Cluster the feature data of different assets to divide each asset into multiple categories;
[0064] In this step, an unsupervised clustering algorithm can be used to cluster the feature data of different assets to divide IoT assets into multiple categories. This embodiment does not specifically limit the unsupervised clustering algorithm. For example, the kmeans algorithm can be used to cluster the feature data of different IoT assets.
[0065] S203: Extract the webpage tags corresponding to the webpage type data, and calculate the fingerprint of the webpage tags;
[0066] In practical implementation, the webpage type data of assets in each category can be converted into a DOM tree structure. Webpage tags can then be extracted from the DOM tree structure, and fingerprints of these tags can be calculated. It is understood that extracting webpage tags and calculating fingerprints from feature data can effectively reduce the dimensionality of the feature data, thereby reducing the amount of subsequent similarity calculations and improving the efficiency of subsequent similarity calculations. It should be noted that this embodiment does not specifically limit the execution order of S202 and S203.
[0067] S204: Based on the similarity between different fingerprints in each category, different fingerprints in each category with a similarity less than a first preset value are grouped into the same group;
[0068] S205: Classify assets corresponding to fingerprints in the same group into the same asset class.
[0069] In this embodiment, assets corresponding to webpage tags with similar fingerprints in each category are clustered again. That is, based on the similarity between fingerprints corresponding to different assets in each category, assets corresponding to fingerprints with similarity less than a threshold in each category are classified into the same subcategory, thereby ensuring that assets in each category after re-clustering belong to the same category. In specific implementation, the following operations are performed on each category: the similarity between different fingerprints in the category is calculated, such as the Hammington distance; different fingerprints in the category with similarity less than a first preset value are classified into the same group; and then the assets corresponding to fingerprints in the same group are classified into the same subcategory.
[0070] As a preferred embodiment, before classifying the IoT assets corresponding to fingerprints in the same group into the same asset category, the method further includes: determining the target group containing the most fingerprints in each category, calculating the ratio between the number of fingerprints in the target group and the total number of fingerprints in the category; if the ratio is less than a second preset value, then performing the step of classifying the IoT assets corresponding to fingerprints in the same group into asset categories.
[0071] In practical implementation, the clustering effect of each category can be determined based on the grouping results of fingerprints in each category. First, the target group containing the most fingerprints in each category is identified. Second, the total number of fingerprints in each category is determined. Then, the ratio between the number of fingerprints in the target group and the total number of fingerprints in its category is calculated as an indicator to evaluate the clustering effect of each category. The larger the ratio, the more similar the feature data between IoT assets in that category, indicating a better clustering effect for that category. For example, category A contains fingerprints a1, a2, a3, a4, and a5, and is divided into two groups: {a1, a2} and {a3, a4, a5}. The target group containing the most fingerprints contains 3 fingerprints, and the total number of fingerprints in the category is 5. The ratio between the number of fingerprints in the target group and the total number of fingerprints in the category is 0.6. Category B contains fingerprints b1, b2, b3, b4, b5, and b6, and is divided into three groups: {b1}, {b2, b3}, and {b4, b5, b6}. The target group containing the most fingerprints contains 3 fingerprints, and the total number of fingerprints in the category is 6. The ratio between the number of fingerprints in the target group and the total number of fingerprints in the category is 0.5. Since 0.6 > 0.5, the clustering effect of category A is better than that of category B. If the calculated ratio is less than the second preset value, it indicates that there are few similar fingerprints in the category, which means that the clustering effect of the category is poor. The category needs to be clustered again, that is, the IoT assets corresponding to fingerprints in the same group are divided into the same subclass, thereby further optimizing the category into multiple subclasses, ensuring that the feature data of IoT assets in each subclass are similar, and thus optimizing the results of the unsupervised clustering algorithm.
[0072] Therefore, the IoT asset classification method provided in this application, based on unsupervised clustering, extracts web page tags based on the characteristic features of IoT assets, and combines the fingerprints of the web page tags to further cluster IoT assets in each category, optimizing the clustering process. This ensures that IoT assets in each category after the second clustering belong to the same category, improving the accuracy of IoT asset clustering under the unsupervised clustering algorithm. Furthermore, this embodiment determines the clustering effect of each category based on the grouping results of fingerprints in each category. Specifically, the ratio of the maximum number of similar fingerprints in each category to the total number of fingerprints in each category is used as an indicator to evaluate the clustering effect of each category, achieving accurate evaluation of the clustering effect of each category. For categories with poor clustering effects, a second distance analysis is performed, further optimizing the category into multiple subcategories. This ensures that the characteristic data of IoT assets in each subcategory are similar, further improving the accuracy of IoT asset clustering under the unsupervised clustering algorithm.
[0073] The following describes an asset classification device provided in an embodiment of this application. The asset classification device described below and the asset classification method described above can be referred to each other.
[0074] See Figure 3 A structural diagram of an asset classification device is shown according to an exemplary embodiment, such as... Figure 3 As shown, it includes:
[0075] The acquisition module 301 is used to acquire feature data of each asset; wherein, the feature data includes response data under a preset protocol, and the response data is webpage type data;
[0076] Extraction module 302 is used to extract web page tags corresponding to the web page type data and calculate the fingerprints corresponding to the web page tags;
[0077] Clustering module 303 is used to perform clustering operations on the fingerprint to obtain the asset category corresponding to the asset.
[0078] The asset classification device provided in this application extracts web page tags based on the web page type data of the assets, and clusters the assets by combining the fingerprints of the web page tags, thereby ensuring that the assets in each asset category after clustering belong to the same asset category, thus improving the accuracy of asset clustering.
[0079] Based on the above embodiments, as a preferred embodiment, it further includes:
[0080] The segmentation module is used to cluster the feature data of different assets to divide each asset into multiple categories;
[0081] Accordingly, the clustering module 303 is specifically used to: perform a clustering operation on the fingerprints corresponding to the assets in each category to obtain the asset category corresponding to the asset.
[0082] Based on the above embodiments, as a preferred implementation, the extraction module 302 is specifically used to: convert the web page type data into a DOM tree structure, extract web page tags from the DOM tree structure, and calculate the fingerprints corresponding to the web page tags.
[0083] Based on the above embodiments, as a preferred embodiment, it further includes:
[0084] A segmentation module is used to segment the body portion and other portions of the webpage type data;
[0085] Accordingly, the extraction module 302 is specifically used to: extract web page tags from the body portion of the web page type data, and calculate the fingerprints corresponding to the web page tags.
[0086] Based on the above embodiments, as a preferred implementation, the extraction module 302 is specifically used to: extract web page tags corresponding to the web page type data, extract the language features of the web page tags based on a preset sliding window, and calculate the fingerprint of the language features.
[0087] Based on the above embodiments, as a preferred implementation, the clustering module 303 includes:
[0088] The first segmentation unit is used to group different fingerprints with similarity less than a first preset value into the same group based on the similarity between fingerprints corresponding to different assets.
[0089] The second segmentation unit is used to classify assets corresponding to fingerprints in the same group into the same asset category.
[0090] Based on the above embodiments, as a preferred implementation, the clustering module 303 further includes:
[0091] The calculation unit is used to determine the target group containing the most fingerprints in each category, and calculate the ratio between the number of fingerprints in the target group and the total number of fingerprints in the category; if the ratio is less than a second preset value, the workflow of the second division unit is started.
[0092] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0093] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of this application, the embodiments of this application also provide an electronic device. Figure 4 This is a structural diagram of an electronic device according to an exemplary embodiment, such as... Figure 4 As shown, the electronic device includes:
[0094] Communication interface 1 enables information exchange with other devices, such as network devices;
[0095] Processor 2 is connected to communication interface 1 to enable information exchange with other devices and, when running a computer program, executes the asset classification method provided by one or more of the above-mentioned technical solutions. The computer program is stored in memory 3.
[0096] Of course, in practical applications, the various components in an electronic device are coupled together through bus system 4. It can be understood that bus system 4 is used to achieve communication and connection between these components. In addition to the data bus, bus system 4 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 4The general will label all buses as Bus System 4.
[0097] The memory 3 in this embodiment is used to store various types of data to support the operation of the electronic device. Examples of such data include any computer program used to operate on the electronic device.
[0098] It is understood that memory 3 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 3 described in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.
[0099] The methods disclosed in the embodiments of this application can be applied to processor 2, or implemented by processor 2. Processor 2 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 2 or by instructions in the form of software. The processor 2 may be a general-purpose processor, DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 2 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in memory 3. Processor 2 reads the program in memory 3 and completes the steps of the aforementioned method in combination with its hardware.
[0100] When processor 2 executes the program, it implements the corresponding processes in the various methods of the embodiments of this application. For the sake of brevity, these will not be described in detail here.
[0101] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a memory 3 that stores a computer program, which can be executed by a processor 2 to complete the steps described in the aforementioned method. The computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.
[0102] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.
[0103] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.
[0104] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. An asset classification method, characterized in that, include: Obtain feature data for each asset; wherein, the feature data includes response data under a preset protocol, and the response data is webpage type data; Clustering of characteristic data of different assets to divide each asset into multiple categories; Extract the webpage tags corresponding to the webpage type data, and calculate the fingerprints corresponding to the webpage tags; Perform a clustering operation on the fingerprints corresponding to the assets in each category to obtain the asset category corresponding to the asset; The step of performing clustering operations on the fingerprints corresponding to assets in each category to obtain the asset category includes: Based on the similarity between fingerprints corresponding to different assets, different fingerprints with similarity less than a first preset value are grouped into the same group; Identify the target group containing the most fingerprints in each category, and calculate the ratio between the number of fingerprints in the target group and the total number of fingerprints in its category; If the ratio is less than the second preset value, the assets corresponding to the fingerprints in the same group will be classified into the same asset category.
2. The asset classification method according to claim 1, characterized in that, The step of extracting the webpage tags corresponding to the webpage type data includes: The webpage type data is converted into a DOM tree structure, and webpage tags are extracted from the DOM tree structure.
3. The asset classification method according to claim 1, characterized in that, Before extracting the webpage tags corresponding to the webpage type data, the process also includes: Separate the body portion and other portions of the webpage type data; Accordingly, extracting the webpage tags corresponding to the webpage type data includes: Extract web page tags from the body portion of the web page type data.
4. The asset classification method according to claim 1, characterized in that, The calculation of the fingerprint of the webpage tag includes: The language features of the webpage tags are extracted based on a preset sliding window, and the fingerprint of the language features is calculated.
5. An asset classification device, characterized in that, include: The acquisition module is used to acquire feature data of each asset; wherein, the feature data includes response data under a preset protocol, and the response data is webpage type data; The segmentation module is used to cluster the feature data of different assets to divide each asset into multiple categories; An extraction module is used to extract web page tags corresponding to the web page type data and calculate the fingerprints corresponding to the web page tags; The clustering module is used to perform clustering operations on the fingerprints corresponding to assets in each category to obtain the asset category corresponding to the asset. Specifically, the clustering module is used to: classify different fingerprints with similarity less than a first preset value into the same group based on the similarity between fingerprints corresponding to different assets; determine the target group containing the most fingerprints in each category, and calculate the ratio between the number of fingerprints in the target group and the total number of fingerprints in the category; if the ratio is less than a second preset value, then classify the assets corresponding to the fingerprints in the same group into the same asset category.
6. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the asset classification method as described in any one of claims 1 to 4.
7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the asset classification method as described in any one of claims 1 to 4.