An asset identification method and device, electronic equipment and storage medium

Abstract

The application discloses an asset identification method and device, an electronic device and a computer readable storage medium. The method comprises the following steps: acquiring a webpage address of each asset; scanning the webpage address to acquire a webpage snapshot corresponding to each asset; clustering webpage snapshots of all assets to obtain a clustering result; and determining an asset category of the asset according to the clustering result and the webpage snapshot. The asset identification method provided by the application extracts a webpage snapshot corresponding to each asset, and determines the asset type of the asset according to the number of categories divided by the webpage snapshot. Therefore, the asset identification method provided by the application improves the identification accuracy of Internet of Things assets.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and more specifically, to an asset identification method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] Currently, the security risks of IoT assets are increasing year by year, and security issues cannot be ignored. Screening of IoT assets has revealed that a large number of IoT assets are directly exposed to the internet, with routers and video surveillance devices being the most numerous. These are easily discovered by web crawlers and malicious attackers, enabling them to launch large-scale DDoS attacks, causing severe damage and impact on businesses on the internet.

[0003] In related technologies, it is possible to summarize, organize, and analyze exposed IoT assets to address their security issues. While current technologies can identify the device manufacturers of many IoT assets and prevent and patch potential vulnerabilities in their devices, the accuracy of IoT asset identification still needs improvement due to the diverse types of IoT assets and the lack of unified standards for management. For example, many large manufacturers control sales channels and outsource production to smaller companies, thus labeling the equipment as OEM (Original Equipment Manufacturer). OEM, commonly known as contract manufacturing, essentially means that the brand manufacturer does not directly produce products but uses its core technologies to design and develop new products, controls sales channels, and the manufacturer undertaking the processing tasks is the OEM manufacturer, and the equipment produced by the OEM manufacturer is called OEM equipment. Currently, there is no technology specifically for identifying OEM equipment. However, if the OEM manufacturer can be identified, and it can be determined which large manufacturer it is contract manufacturing for, then, since the OEM manufacturer uses the core technologies of the large manufacturer, accessing the corresponding vulnerability database of the large manufacturer would allow for vulnerability prevention and patching of the OEM manufacturer's equipment.

[0004] Therefore, improving the accuracy of IoT asset identification 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 identification method, apparatus, electronic device, and computer-readable storage medium, which improves the accuracy of IoT asset identification.

[0006] To achieve the above objectives, this application provides an asset identification method, comprising:

[0007] Obtain the web address for each asset;

[0008] Scan the web page addresses to obtain a snapshot of the web page corresponding to each asset;

[0009] Cluster the webpage snapshots of all assets to obtain the clustering results;

[0010] The asset category of the asset is determined based on the clustering results and the webpage snapshot.

[0011] The clustering of webpage snapshots for all assets yields the following clustering results:

[0012] The webpage snapshots are input into the artificial intelligence model, and the feature vector of each webpage snapshot is extracted using the artificial intelligence model.

[0013] Clustering is performed on all feature vectors to obtain the clustering results.

[0014] The step of obtaining the web address of each asset includes:

[0015] Determine the open ports corresponding to each of the aforementioned assets;

[0016] Send probe packets to the open port to obtain response messages from each asset in response to the probe packets;

[0017] The response message is analyzed to determine the webpage address.

[0018] The asset categories include OEM equipment and non-OEM equipment. Determining the asset category based on the clustering results and the webpage snapshot includes:

[0019] If the clustering result indicates that the webpage snapshots of all assets are divided into one category, then the webpage snapshot corresponding to an asset is matched with the first preset mapping relationship. If the match is successful, then it is determined that the asset category of all assets is non-OEM equipment.

[0020] If the clustering result indicates that the web page snapshots of all assets are divided into multiple categories, then each web page snapshot is matched with the first preset mapping relationship. If the match is successful, the asset category corresponding to the successfully matched web page snapshot is determined to be non-OEM equipment. If the match fails, the asset type corresponding to the unmatched web page snapshot is determined to be OEM equipment.

[0021] The step of determining the asset category of the asset based on the clustering results and the webpage snapshot further includes:

[0022] The manufacturer information corresponding to the asset is determined based on the second preset mapping relationship and the webpage snapshot. The second preset mapping relationship includes the correspondence between the webpage snapshot and the manufacturer information.

[0023] The step of determining the manufacturer corresponding to the asset based on the second preset mapping relationship and the asset category includes:

[0024] Determine whether the webpage snapshot is included in the second preset mapping relationship;

[0025] If the webpage snapshot is not included in the second preset mapping relationship, extract the feature information from the webpage snapshot, and identify the manufacturer information corresponding to the asset based on the feature information.

[0026] The feature information includes manufacturer identification information and / or network message information of a preset protocol.

[0027] To achieve the above objectives, this application provides an asset identification device, comprising:

[0028] The first acquisition module is used to obtain the web address of each asset;

[0029] The second acquisition module is used to scan the web page address and acquire a web page snapshot corresponding to each asset;

[0030] The clustering module is used to cluster web snapshots of all assets to obtain clustering results;

[0031] The first determining module is used to determine the asset category of the asset based on the clustering results and the webpage snapshot.

[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 identification 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 identification method described above.

[0036] As can be seen from the above scheme, the asset identification method provided in this application includes: obtaining the web address of each asset; scanning the web address to obtain a web snapshot corresponding to each asset; clustering the web snapshots of all assets to obtain a clustering result; and determining the asset category of the asset based on the clustering result and the web snapshot.

[0037] The asset identification method provided in this application extracts a webpage snapshot corresponding to each asset and determines the asset type based on the number of categories into which the webpage snapshot is divided. Therefore, the asset identification method provided in this application improves the accuracy of IoT asset identification. This application also discloses an asset identification 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. In the drawings:

[0040] Figure 1 This is a flowchart illustrating an asset identification method according to an exemplary embodiment;

[0041] Figure 2 A flowchart illustrating another asset identification method according to an exemplary embodiment;

[0042] Figure 3 This is a structural diagram illustrating an asset identification device according to an exemplary embodiment;

[0043] Figure 4 This is a structural diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0044] 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.

[0045] This application discloses an asset identification method that improves the accuracy of IoT asset identification.

[0046] See Figure 1 A flowchart illustrating an asset identification method according to an exemplary embodiment is shown below. Figure 1 As shown, it includes:

[0047] S101: Obtain the web address for each asset;

[0048] The purpose of this embodiment is to identify the asset categories of IoT assets, which may include devices, components, and services. In this step, the web address of the access page for each asset is obtained. As a possible implementation, obtaining the web address of each asset includes: determining the open port corresponding to each asset; sending a probe packet to the open port to obtain the response message of each asset to the probe packet; and analyzing the response message to determine the web address.

[0049] In practice, the first step is to determine the open ports for each asset's HTTP or HTTPS protocols. Typically, HTTP uses port 80 and HTTPS uses port 443, but some assets may change these ports. Therefore, scanning tools (such as nmap) can be used to scan for these open ports. Next, a common communication library is used to establish communication with the asset. A request message is sent to the asset's open HTTP port to retrieve its HTTP response. Similarly, a request message can be sent to the asset's open HTTPS port to retrieve its HTTPS response. The HTTPS response is then analyzed for redirection, and the redirected message is retrieved again.

[0050] S102: Scan the web page addresses to obtain a snapshot of the web page corresponding to each asset;

[0051] In this step, each obtained webpage address is accessed sequentially, and a webpage snapshot tool is used to capture a snapshot of the webpage corresponding to each webpage address.

[0052] S103: Cluster the webpage snapshots of all assets to obtain the clustering results;

[0053] In this step, webpage snapshots are clustered based on their similarity to obtain clustering results. In specific implementations, unsupervised clustering algorithms can be used to cluster webpage snapshots corresponding to the same tag vendor, thereby dividing webpage snapshots corresponding to the same tag vendor into multiple categories. This embodiment does not specifically limit the unsupervised clustering algorithm; for example, the k-means algorithm can be used to cluster webpage snapshots corresponding to the same tag vendor.

[0054] As a feasible implementation, this step may include: inputting the webpage snapshots into an artificial intelligence model, using the artificial intelligence model to extract feature vectors for each webpage snapshot; and clustering all feature vectors to obtain the clustering results. In a specific implementation, each webpage snapshot is input into a pre-trained artificial intelligence model. This embodiment does not specifically limit the artificial intelligence model; for example, ResNet50 can be used. The artificial intelligence model extracts feature vectors for each webpage snapshot, and an unsupervised clustering algorithm is used to cluster the feature vectors of the webpage snapshots.

[0055] S104: Determine the asset category of the asset based on the clustering results and the webpage snapshot.

[0056] In this step, the category to which the webpage snapshot of each asset belongs is determined based on the clustering results, thereby determining the asset category of that asset.

[0057] The asset identification method provided in this application extracts a webpage snapshot corresponding to each asset and determines the asset type based on the number of categories into which the webpage snapshot is divided. Therefore, the asset identification method provided in this application improves the accuracy of IoT asset identification.

[0058] The device identification and asset identification method provided in the above embodiments can be applied to identify whether an asset is an OEM (Original Equipment Manufacturer) device, that is, the asset category includes OEM devices and / or non-OEM devices. After obtaining the webpage snapshot of the asset, the webpage snapshot can also be classified according to the marked manufacturer of each asset. In specific implementation, the marked manufacturer of the asset by the customer is obtained. Generally, the customer will mark the developer of the asset. For assets where the customer has not marked the developer, automatic identification can be performed through a rule base. As a feasible implementation method, scanning tools such as nmap can be used to scan the private protocol development port of the asset, and common communication libraries (such as the socket library that comes with Python) can be used to establish communication with the asset, send request messages to the open port of the device's private protocol, and obtain the private protocol response message replied by the asset. The response message is analyzed to determine the developer of the asset. In specific implementation, a fingerprint device information mapping table is pre-built, which records the correspondence between device information and fields. The device information may include manufacturer information, device name, instructions for use, etc. In the response message of the private protocol, the target fields related to the device information are identified, and the contents corresponding to the target fields are matched in the fingerprint device information mapping table to determine the developer of the asset, that is, the tag manufacturer.

[0059] Clustering is performed on webpage snapshots of all devices to obtain clustering results. The asset category of the device is determined based on the clustering results and the webpage snapshots. In specific implementation, if the clustering results indicate that all asset webpage snapshots are classified into one category, the webpage snapshot corresponding to an asset is matched with a first preset mapping relationship. The first preset mapping relationship records the correspondence between webpage snapshots and developers; developers can be understood as common large manufacturers. If the match is successful, all assets are determined to be non-OEM devices. If the match fails, the developer corresponding to the webpage snapshot is manually analyzed to see if it is a new developer. If so, the webpage snapshot and its corresponding developer are added to the first preset mapping relationship. For each asset corresponding to a marked manufacturer, if the webpage snapshot corresponding to that marked manufacturer is classified into one category, the webpage snapshots classified into that category are matched in the developer mapping table. The developer mapping table records the correspondence between webpage snapshots and developers; developers can be understood as common large manufacturers. If a match is successful, the asset corresponding to the webpage snapshot classified into a category is determined to be a non-OEM device. If a match fails, the marker manufacturer is manually analyzed to determine if it is a new developer manufacturer. If so, the webpage snapshot classified into a category and its corresponding marker manufacturer are added to the developer manufacturer mapping table.

[0060] Furthermore, if the clustering results indicate that all asset webpage snapshots are divided into multiple categories, then each webpage snapshot is matched with a first preset mapping relationship. If the match is successful, the asset category corresponding to the successfully matched webpage snapshot is determined to be non-OEM equipment; if the match fails, the asset type corresponding to the unmatched webpage snapshot is determined to be OEM equipment. In specific implementation, if webpage snapshots of assets with the same tagged manufacturer are divided into multiple categories, then the webpage snapshot corresponding to each category is selected and matched in the manufacturer mapping table. If the match is successful, the asset corresponding to that webpage snapshot is determined to be non-OEM equipment; if the match fails, the asset corresponding to that webpage snapshot is determined to be OEM equipment. For example, if webpage snapshots of assets from the same vendor include A1, A2, A3, A4, A5, and A6, and are divided into three categories: {A1}, {A2, A3}, and {A4, A5, A6}, and A1 matches successfully in the vendor mapping table, while A2 and A4 do not match, then the asset corresponding to A1 is a non-OEM device, and the assets corresponding to A2, A3, A4, A5, and A6 are OEM devices.

[0061] It should be noted that if none of the webpage snapshots corresponding to each category match successfully in the developer vendor mapping table, the system will manually analyze whether the tagged vendor is a new developer vendor. If so, the webpage snapshot and the corresponding tagged vendor will be added to the developer vendor mapping table. If webpage snapshots corresponding to multiple categories match successfully in the developer vendor mapping table, it means that the assets corresponding to the successfully matched webpage snapshots are different models of assets under the tagged vendor. For example, if webpage snapshots of assets under the same tagged vendor include A1, A2, A3, A4, A5, and A6, and are divided into three categories, {A1}, {A2, A3}, and {A4, A5, A6}, and A1 and A2 match successfully in the developer vendor mapping table, while A4 does not match, then the assets corresponding to A1, A2, and A3 are non-OEM equipment. However, the assets corresponding to A1 and A2 and A3 are different models of assets under the same tagged vendor, while the assets corresponding to A4, A5, and A6 are OEM equipment.

[0062] This application discloses an asset identification method. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution. Specifically:

[0063] See Figure 2 A flowchart illustrating another asset identification method according to an exemplary embodiment, such as... Figure 2 As shown, it includes:

[0064] S201: Obtain the web address for each asset;

[0065] S202: Scan the web page addresses to obtain a snapshot of the web page corresponding to each asset;

[0066] S203: Input the webpage snapshot into the artificial intelligence model, use the artificial intelligence model to extract the feature vector of each webpage snapshot, cluster all feature vectors, and obtain the clustering result;

[0067] S204: If the clustering result indicates that the web page snapshots of all assets are divided into one category, then the web page snapshot corresponding to an asset is matched with the first preset mapping relationship. If the match is successful, then it is determined that the asset category of all assets is non-OEM equipment.

[0068] S205: If the clustering result represents that the web page snapshots of all assets are divided into multiple categories, then each web page snapshot is matched with the first preset mapping relationship. If the match is successful, the asset category corresponding to the asset whose web page snapshot is successfully matched is determined to be non-OEM equipment. If the match fails, the asset type corresponding to the asset whose web page snapshot fails to match is determined to be OEM equipment.

[0069] S206: Determine the manufacturer information corresponding to the asset based on the second preset mapping relationship and the webpage snapshot, wherein the second preset mapping relationship includes the correspondence between the webpage snapshot and the manufacturer information.

[0070] In this embodiment, after determining whether an asset is an OEM or a non-OEM device, the manufacturer information of the asset is determined. For OEM devices, the developer and the manufacturer are determined respectively. For non-OEM devices, the developer and the manufacturer are the same manufacturer.

[0071] Under normal circumstances, the manufacturer marked by the customer is the same as the developer. However, in some cases, if the customer mismarks the developer of the OEM equipment, it is necessary to re-identify the developer of the OEM equipment. As a feasible implementation method, determining the manufacturer corresponding to the asset based on the second preset mapping relationship and the asset category of the asset includes: determining whether the webpage snapshot is included in the second preset mapping relationship; if the webpage snapshot is not included in the second preset mapping relationship, extracting feature information from the webpage snapshot, and identifying the manufacturer information corresponding to the asset based on the feature information.

[0072] In practice, the webpage snapshot of the OEM equipment is matched in a second preset mapping relationship. The second preset mapping relationship records the correspondence between the webpage snapshot and the manufacturer information. The manufacturer information here can include both the development manufacturer and the processing manufacturer. If the match is successful, the manufacturer information corresponding to the asset can be directly determined. If the match fails, the feature information in the webpage snapshot is used to identify the manufacturer information corresponding to the asset.

[0073] As a feasible implementation method, the feature information can specifically be manufacturer identification information. In a specific implementation, text recognition technologies such as OCR (Optical Character Recognition) can be used to extract manufacturer identification information, i.e., the manufacturer logo, from the web snapshot of the OEM equipment. It is understandable that since the OEM equipment corresponds to at least two types of web snapshots—one for the development manufacturer and one for the processing manufacturer—identifying the manufacturer identification information will reveal the identification information of both the development manufacturer and the processing manufacturer, corresponding to two manufacturer names respectively. That is, when using text recognition technology, two manufacturers will be identified simultaneously, but it is uncertain which manufacturer is the development manufacturer and which is the processing manufacturer. Therefore, a first preset mapping disrelation is needed for auxiliary judgment. Manufacturers included in the first preset mapping disrelation are identified as development manufacturers, and manufacturers not included in the first preset mapping disrelation are identified as processing manufacturers.

[0074] As another feasible implementation, the feature information can specifically be network message information of a preset protocol. In a specific implementation, a common communication library is used to establish communication with the asset, and a request message is sent to the open port of the asset's preset protocol. This preset protocol can be HTTP (Hypertext Transfer Protocol) or HTTPS (Hypertext Transfer Protocol Secure). The response message of the preset protocol from the asset is obtained and analyzed to determine the asset's manufacturer. A fingerprint device information mapping table is pre-built, recording the correspondence between device information and fields. Device information may include manufacturer information, device name, and usage instructions. The webpage source code of the target asset's access page is extracted from the response message. A first target field related to the device information is identified in the webpage source code, and the content corresponding to this first target field is matched in the fingerprint device information mapping table to determine the asset's manufacturer. Furthermore, scanning tools such as nmap can be used to scan whether the asset has developed a private protocol development port. If so, a request message is sent to the open port of the asset's private protocol, and the response message of the private protocol from the asset is obtained and analyzed to determine the asset's manufacturer. In the response message of the private protocol, a second target field related to the device information is identified, and the content corresponding to the second target field is matched in the fingerprint device information mapping table to determine the developer of the asset.

[0075] Therefore, this embodiment determines whether an asset is an OEM (Original Equipment Manufacturer) or a non-OEM asset, and then identifies the asset's manufacturer information. For non-OEM assets, the developer and manufacturer are the same. For OEM assets, the developer and manufacturer are identified separately, and by obtaining the corresponding developer's vulnerability database, vulnerability prevention and remediation can be performed on the OEM asset.

[0076] The following describes an asset identification device provided in an embodiment of this application. The asset identification device described below and the asset identification method described above can be referred to each other.

[0077] See Figure 3 A structural diagram of an asset identification device is shown according to an exemplary embodiment, such as... Figure 3 As shown, it includes:

[0078] The first acquisition module 301 is used to acquire the web address of each asset;

[0079] The second acquisition module 302 is used to scan the web page address and acquire a web page snapshot corresponding to each asset;

[0080] Clustering module 303 is used to cluster webpage snapshots of all assets to obtain clustering results;

[0081] The first determining module 304 is used to determine the asset category of the asset based on the clustering results and the webpage snapshot.

[0082] The asset identification device provided in this application extracts a webpage snapshot corresponding to each asset and determines the asset type based on the number of categories into which the webpage snapshot is divided. Therefore, the asset identification device provided in this application improves the accuracy of IoT asset identification.

[0083] Based on the above embodiments, as a preferred implementation, the clustering module 303 is specifically used to: input the webpage snapshot into the artificial intelligence model, use the artificial intelligence model to extract the feature vector of each webpage snapshot; and cluster all feature vectors to obtain the clustering result.

[0084] Based on the above embodiments, as a preferred implementation, the first acquisition module 301 is specifically used for: determining the open port corresponding to each asset; sending a probe packet to the open port to obtain the response message of each asset to the probe packet; and analyzing the response message to determine the web address.

[0085] Based on the above embodiments, as a preferred implementation, the asset category includes OEM equipment or non-OEM equipment. The first determining module 304 is specifically used for: if the clustering result indicates that the web page snapshots of all assets are divided into one category, then matching the web page snapshot corresponding to an asset with a first preset mapping relationship. If the matching is successful, then determining that the asset category of all assets is non-OEM equipment; if the clustering result indicates that the web page snapshots of all assets are divided into multiple categories, then matching each web page snapshot with the first preset mapping relationship respectively. If the matching is successful, then determining that the asset category corresponding to the asset whose web page snapshot is successfully matched is non-OEM equipment; if the matching fails, then determining that the asset type corresponding to the asset whose web page snapshot is not matched is OEM equipment.

[0086] Based on the above embodiments, as a preferred embodiment, it further includes:

[0087] The second determining module is used to determine the manufacturer information corresponding to the asset based on the second preset mapping relationship and the webpage snapshot, wherein the second preset mapping relationship includes the correspondence between the webpage snapshot and the manufacturer information.

[0088] Based on the above embodiments, as a preferred implementation, the second determining module is specifically used to: determine whether the webpage snapshot is included in the second preset mapping relationship; if the webpage snapshot is not included in the second preset mapping relationship, extract feature information from the webpage snapshot, and identify the manufacturer information corresponding to the asset based on the feature information.

[0089] Based on the above embodiments, as a preferred implementation, the feature information includes manufacturer identification information and / or network message information of a preset protocol.

[0090] 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.

[0091] 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:

[0092] Communication interface 1 enables information exchange with other devices, such as network devices;

[0093] Processor 2 is connected to communication interface 1 to enable information exchange with other devices and, when running a computer program, executes the asset identification method provided by one or more of the above-mentioned technical solutions. The computer program is stored in memory 3.

[0094] 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 4 The general will label all buses as Bus System 4.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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 identification method, characterized in that, include: Obtain the web address for each asset; Scan the web page addresses to obtain a snapshot of the web page corresponding to each asset; Cluster the webpage snapshots of all assets to obtain the clustering results; If the clustering result indicates that the webpage snapshots of all assets are divided into one category, then the webpage snapshot corresponding to an asset is matched with the first preset mapping relationship. If the match is successful, then it is determined that the asset category of all assets is non-OEM equipment. If the clustering result indicates that the web page snapshots of all assets are divided into multiple categories, then each web page snapshot is matched with the first preset mapping relationship. If the match is successful, the asset category corresponding to the asset whose web page snapshot is successfully matched is determined to be non-OEM equipment. If the match fails, the asset type corresponding to the asset whose web page snapshot fails to match is determined to be OEM equipment. The manufacturer information corresponding to the asset is determined based on the second preset mapping relationship and the webpage snapshot. The second preset mapping relationship includes the correspondence between the webpage snapshot and the manufacturer information. For OEM equipment, the developer and the processing manufacturer are determined respectively. For non-OEM equipment, the developer and the processing manufacturer are the same manufacturer.

2. The asset identification method according to claim 1, characterized in that, The clustering of webpage snapshots for all assets yields the following clustering results: The webpage snapshots are input into the artificial intelligence model, and the feature vector of each webpage snapshot is extracted using the artificial intelligence model. Clustering is performed on all feature vectors to obtain the clustering results.

3. The asset identification method according to claim 1, characterized in that, The process of obtaining the web address for each asset includes: Determine the open ports corresponding to each of the aforementioned assets; Send probe packets to the open port to obtain response messages from each asset in response to the probe packets; The response message is analyzed to determine the webpage address.

4. The asset identification method according to claim 1, characterized in that, The step of determining the manufacturer corresponding to the asset based on the second preset mapping relationship and the asset category includes: Determine whether the webpage snapshot is included in the second preset mapping relationship; If the webpage snapshot is not included in the second preset mapping relationship, extract the feature information from the webpage snapshot, and identify the manufacturer information corresponding to the asset based on the feature information.

5. The asset identification method according to claim 4, characterized in that, The feature information includes manufacturer identification information and / or network message information of a preset protocol.

6. An asset identification device, characterized in that, include: The first acquisition module is used to obtain the web address of each asset; The second acquisition module is used to scan the web page address and acquire a web page snapshot corresponding to each asset; The clustering module is used to cluster web snapshots of all assets to obtain clustering results; The first determining module is configured to: if the clustering result indicates that the webpage snapshots of all assets are divided into one category, then match the webpage snapshot corresponding to an asset with a first preset mapping relationship; if the match is successful, then determine that the asset category of all assets is non-OEM equipment; if the clustering result indicates that the webpage snapshots of all assets are divided into multiple categories, then match each webpage snapshot with the first preset mapping relationship respectively; if the match is successful, then determine that the asset category corresponding to the successfully matched webpage snapshot is non-OEM equipment; if the match fails, then determine that the asset category corresponding to the unmatched webpage snapshot is OEM equipment. The second determining module is used to determine the manufacturer information corresponding to the asset based on the second preset mapping relationship and the webpage snapshot. The second preset mapping relationship includes the correspondence between the webpage snapshot and the manufacturer information. For OEM equipment, the developer and the processing manufacturer are determined respectively. For non-OEM equipment, the developer and the processing manufacturer are the same manufacturer.

7. 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 identification method as described in any one of claims 1 to 5.

8. 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 identification method as described in any one of claims 1 to 5.

Images