Method, device, equipment and storage medium for constructing IoT device identification

Abstract

The present invention discloses a method, apparatus, device and storage medium for constructing an IoT device identifier, and relates to the field of IoT technology. The present invention includes the following steps: obtaining first attribute information of a target IoT device, and multiple device attribute information in multiple web page data; inputting the first attribute information into a preset word vector model to obtain a first word vector of the first attribute information; wherein the preset word vector model is a model pre-trained using multiple device attribute information as a training set; based on the first word vector and the correlation between the second word vectors of multiple device attribute information, filtering out second attribute information related to the first attribute information from multiple device attribute information; based on the second attribute information, constructing the device identifier of the target IoT device. The present invention can more accurately describe the device identifier of the target IoT device.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a method, apparatus, device and storage medium for constructing an Internet of Things device identifier. Background Art

[0002] IoT device identification is essential for IoT operations, device association, situation analysis, and event backtracking. Device identification is the information data required to identify, describe, and model various IoT devices, including type, manufacturer, and model.

[0003] However, in related technologies, due to the non-standard naming of IoT devices and the existence of synonyms, it is difficult for users to accurately construct the device identification information of a certain type of IoT device.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present invention is to provide a method, device, equipment and storage medium for constructing an IoT device identification, aiming to solve the technical problem in the prior art that it is difficult to accurately extract IoT device identification information.

[0006] To achieve the above objectives, in a first aspect, the present invention provides a method for constructing an IoT device identifier, comprising the following steps:

[0007] Obtaining first attribute information of a target IoT device and multiple device attribute information from multiple web page data;

[0008] Inputting the first attribute information into a preset word vector model to obtain a first word vector of the first attribute information; wherein the preset word vector model is a model pre-trained using the plurality of device attribute information as a training set;

[0009] Filtering second attribute information related to the first attribute information from the plurality of device attribute information based on the correlation between the first word vector and the second word vectors of the plurality of device attribute information;

[0010] Based on the second attribute information, a device identification of the target Internet of Things device is constructed.

[0011] In one embodiment, after the step of filtering out second attribute information related to the first attribute information from the plurality of device attribute information based on the first word vector, the method further includes:

[0012] Inputting the first attribute information and the second attribute information into a search engine simultaneously to obtain a search result webpage;

[0013] Verifying, based on the search result webpage, whether the first attribute information and the second attribute information are related;

[0014] The step of constructing the device identification of the target IoT device based on the second attribute information includes:

[0015] If the verification is successful, a device identification of the target IoT device is constructed based on the second attribute information.

[0016] In one embodiment, the step of verifying whether the first attribute information and the second attribute information are related based on the search result webpage includes:

[0017] Extracting multiple groups of phrases to be verified from the search result webpage; wherein the multiple groups of phrases to be verified include the first attribute information and the second attribute information;

[0018] Inputting all the phrases to be verified into a preset word vector model to obtain multiple second word vectors;

[0019] performing a proximity distance calculation on the second word vector of the first attribute information and the second word vector of the second attribute information to obtain a proximity distance value;

[0020] If the proximity distance value is greater than the preset threshold, the verification is passed;

[0021] If the proximity distance value is less than or equal to the preset threshold, the verification fails.

[0022] In one embodiment, the step of obtaining the first attribute information of the target IoT device and the multiple device attribute information in the multiple web page data includes:

[0023] Based on web page data from multiple e-commerce websites, original attribute information of various IoT devices is obtained;

[0024] After preprocessing the original attribute information, multiple pieces of device attribute information are obtained.

[0025] In one embodiment, the step of obtaining original attribute information of each type of IoT device based on web page data of multiple e-commerce websites includes:

[0026] Traversing all the smallest sub-category links under the category directory of the e-commerce website to obtain multiple IoT device web page paths; wherein the links under the sub-category sell the same type of IoT devices;

[0027] Crawl each web page in the web page path of the Internet of Things device to obtain original attribute information of each type of the Internet of Things device.

[0028] In one embodiment, the step of obtaining the first attribute information of the target IoT device includes:

[0029] Crawl the Internet of Things to which the target Internet of Things device belongs, and obtain first attribute information of the target Internet of Things device.

[0030] In one embodiment, before the step of constructing the device identification of the target IoT device based on the second attribute information, the method further includes:

[0031] determining the identification category to which each of the second attribute information belongs;

[0032] The step of constructing the device identification of the target IoT device based on the second attribute information includes:

[0033] Based on the second attribute information and the identification category, a device identification of the target Internet of Things device is constructed.

[0034] In a second aspect, the present invention further provides an apparatus for constructing an IoT device identifier, comprising the following steps:

[0035] An information acquisition module, configured to acquire first attribute information of a target IoT device and multiple device attribute information from multiple web page data;

[0036] a word vector obtaining module, configured to input the first attribute information into a preset word vector model to obtain a first word vector of the first attribute information; wherein the training set of the preset word vector model includes a plurality of the device attribute information;

[0037] a related attribute obtaining module, configured to filter out second attribute information related to the first attribute information from the plurality of device attribute information based on the first word vector;

[0038] A device identification construction module is used to construct a device identification of the target Internet of Things device based on the second attribute information.

[0039] In a third aspect, the present invention also provides an IoT device identification construction device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the above-mentioned method.

[0040] In a fourth aspect, the present invention further provides a computer-readable storage medium comprising an executable program code, wherein the program code performs the above-mentioned method when executed by a processor.

[0041] When a user obtains first attribute information related to a target IoT device, the IoT device identification method of the present invention can filter out the most relevant second attribute information from device attribute information presented in multiple webpage data using the word vectors output by the word vector model. This method can then construct a device identifier for the target IoT device based on the second attribute information. Compared to existing device identification information extraction methods based on rules or named entity recognition, the second attribute information filtered out by the present invention can more accurately describe the target IoT device. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of the structure of an electronic device recommended for the method for constructing an IoT device identifier of the present invention;

[0043] Figure 2 This is a flow chart of a first embodiment of a method for constructing an IoT device identifier according to the present invention;

[0044] Figure 3 This is a schematic diagram of a classification directory of an e-commerce website according to the first embodiment of the method for constructing an IoT device identifier of the present invention;

[0045] Figure 4 This is a detailed flowchart of step S101 of the first embodiment of the method for constructing an IoT device identifier according to the present invention;

[0046] Figure 5 This is a flow chart of a second embodiment of the method for constructing an IoT device identifier according to the present invention;

[0047] Figure 6 This is a flow chart of a third embodiment of a method for constructing an IoT device identifier according to the present invention;

[0048] Figure 7 This is a schematic diagram of the functional modules of the device identification construction device for the Internet of Things of the present invention.

[0049] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0051] In related technologies, in the fields of situational awareness and time tracing of the Internet of Things, the identification information of an Internet of Things device includes identification information such as type-manufacturer, manufacturer-model, and type-model.

[0052] There are two methods for extracting IoT device identifiers:

[0053] (1) Rule-based IoT device identification

[0054] A regular expression is a string matching pattern that describes the common characteristics of a class of strings. Using a regular expression for the same text can quickly match matching strings that meet the criteria. Regular expressions are also more flexible and dynamically adaptable. However, due to the lack of a unified organizational naming standard, the scope of regular expression matching is very limited. As a result, constructing IoT device identification information requires observation and analysis, and cannot automatically and efficiently construct the identification information for a specific IoT device.

[0055] For example, research on IoT devices has found that many description pages contain collective, organization-specific names. While constructing regular expressions like ("*edu?", "*gov?") can quickly extract information related to education or government, and thus identify specific IoT devices based on this specific organization information, many websites also contain strings matching ("*edu?", "*gov?"), which significantly reduces the accuracy of organization name extraction. This requires significant manual effort to filter out valid identification information.

[0056] (2) IoT device identification based on named entity recognition

[0057] Named entity recognition, also known as proper name recognition, is a common technique in natural language processing and has a wide range of applications. Named entities typically refer to entities in text that have special meaning or are highly referential, typically including names of people, places, organizations, dates, proper nouns, and so on. Named entity recognition extracts these entities from unstructured text and can identify more categories of entities based on business needs. It can identify attribute information from application-layer data packets in device description webpages for IoT devices, such as device organization information, model information, and location information.

[0058] However, named entities typically require entities with special meaning or strong referentiality within the text. However, the information on some IoT device description pages is scattered and cannot form meaningful, continuous entity information. Furthermore, the same IoT device may have multiple synonymous IoT device attribute terms on different description pages. This makes it difficult to identify new IoT device attribute terms when they appear.

[0059] To this end, the present invention provides a method for constructing an IoT device identifier. When a user obtains first attribute information related to a target IoT device, the method can use the word vectors of a word vector model to filter out the most relevant second attribute information from device attribute information presented in multiple web page data, thereby constructing a device identifier for the target IoT device based on the second attribute information. Compared to existing device identifier information extraction methods based on rules or named entity recognition, the second attribute information filtered out by the present invention can more accurately describe the target IoT device.

[0060] The inventive concept of the present application is further described below with reference to some specific embodiments.

[0061] The present invention provides a first embodiment of a method for constructing an IoT device identifier, see Figure 2 , Figure 2 This is a flow chart of the first embodiment of the method for constructing an IoT device identifier according to the present invention.

[0062] In this embodiment, the method for constructing an IoT device identifier includes the following steps:

[0063] Step S101: obtaining first attribute information of a target IoT device and multiple device attribute information from multiple web page data;

[0064] The first attribute information is a keyword or key word related to the target IoT device that can be obtained by the user. For example, in some specific embodiments, the user can obtain the first attribute information through the following steps:

[0065] Crawl the IoT to which the target IoT device belongs and obtain the first attribute information of the target IoT device.

[0066] That is, the user can perform active detection scanning or other methods in the Internet of Things to which the target Internet of Things device belongs, thereby obtaining a large amount of data related to the target Internet of Things device, from which the user can determine the first attribute information.

[0067] It is understandable that the first attribute information can also be a keyword related to the target IoT device determined by the user. For example, for a smart speaker, the user can

[0068] The multiple web page data may be web pages related to IoT devices, such as e-commerce web pages, device description web pages of IoT devices, or web page data related to IoT devices on search engines.

[0069] By crawling or parsing web page data, a large amount of device attribute information can be obtained. This large amount of device attribute information can be attribute information of different IoT devices.

[0070] In a specific embodiment, the aforementioned multiple device attribute information may be obtained based on an e-commerce website.

[0071] At this time, step S101 includes:

[0072] Step S10: obtaining original attribute information of various IoT devices based on web page data from multiple e-commerce websites;

[0073] The reason why a relatively accurate device identification cannot be used to describe a particular IoT device at present is that there is too little IoT device identification information. The limited device description web pages of IoT devices linked in the IoT cannot provide enough information to determine which identification is the most accurate or the most widely used.

[0074] Therefore, it's essential to obtain as much information as possible about IoT devices. As we all know, e-commerce websites for IoT devices regularly update information related to them. Therefore, it's possible to crawl all semantic information related to IoT devices from these websites, including the raw attribute information for various IoT devices. This allows us to determine the most comprehensive and accurate identification information for a particular IoT device or category.

[0075] Specifically, see Figure 3 and Figure 4 , step A10 includes:

[0076] (1) Traverse all the smallest sub-category links under the category directory of the e-commerce website to obtain multiple IoT device web page paths; among them, the links under the sub-category sell the same type of IoT devices.

[0077] This step first analyzes the categories related to IoT devices on the e-commerce website. Based on the tree structure, a deep root traversal is performed to obtain the smallest subcategory link in the tree directory. The traversed path is saved as a file storage path. This deep root traversal yields several key-value pairs, which can be expressed as (link, path). The path is the path to the IoT device webpage.

[0078] The obtained key-value pairs (link, path) are stored in the Redis database. Redis is a high-performance database that supports data persistence. It can save data in memory to disk and reload it for use when the system is restarted. Using Redis can effectively prevent data loss.

[0079] (2) Crawl each web page in the IoT device web page path to obtain the original attribute information of various IoT devices.

[0080] The distributed focused crawler sequentially retrieves key-value pairs from the Redis data. Each crawler program first crawls the link and then retrieves information related to the IoT device on the page. The retrieved information is the original attribute information of various IoT devices.

[0081] For example, by crawling e-commerce website A, information such as smart door locks, manufacturer B, and door lock signal C can be obtained.

[0082] Based on all the original attribute information obtained, a semantic corpus can be constructed. After the semantic corpus is constructed, the words in it are not disordered, but have semantic relevance to each other.

[0083] Step A20: After preprocessing the original attribute information, multiple pieces of device attribute information are obtained.

[0084] Preprocessing may include the following steps:

[0085] First, all the data in the semantic corpus is cleaned to remove labels, single letters, and special characters. Second, stop words in the NTLK library are used to remove everyday words such as and and or.

[0086] Furthermore, the Chinese and English characters in the corpus can be separated to obtain a Chinese corpus and an English corpus. Different processing methods are required for the Chinese and English corpora. For Chinese, a word segmentation tool is used to decompose sentences into word arrays. For English, stemming and part-of-speech restoration are performed.

[0087] Step S102: input the first attribute information into a preset word vector model to obtain a first word vector of the first attribute information; wherein the preset word vector model is a model pre-trained using multiple device attribute information as a training set.

[0088] The preprocessed semantic corpus is used as the training set. A word embedding model, such as word2vec, is selected. The model parameters include the training window, word embedding dimension, sampling threshold, number of iterations, and single-threaded word data. A training algorithm, such as the CBOW algorithm, is selected to train the preset word embedding model. Since the words in the semantic corpus are not disordered but semantically related to each other, the trained model can demonstrate the degree of semantic relevance between words.

[0089] At this time, the first attribute information obtained by the user is input into a preset word vector model to obtain a first word vector of the first attribute information.

[0090] Step S103: Based on the correlation between the first word vector and the second word vectors of the plurality of device attribute information, second attribute information related to the first attribute information is filtered out from the plurality of device attribute information.

[0091] The preset word vector model stores a second word vector for each device attribute information in the training set. A proximity distance calculation can be performed on the first word vector and the second word vector, thereby determining a preset number of second word vectors with the closest distances from the plurality of second word vectors. The device attribute information to which the preset number of second word vectors belong is determined as the second attribute information.

[0092] Therefore, in this step, the contextual relationship of a specific keyword can be quickly found through the preset word vector model, and a series of the most similar phrases can be output, which is the second attribute information.

[0093] It can be understood that the second attribute information may include one or more, which can be determined based on the specific situation.

[0094] Step S104: Construct a device identification of the target IoT device based on the second attribute information.

[0095] Therefore, in this embodiment, for a specific keyword, i.e., the first attribute information, a semantically related phrase with a high correlation can be obtained, i.e., the second attribute information. This can quickly accumulate IoT device identifiers and provide a basis for device identification.

[0096] For example, in one specific embodiment, users need to quickly identify IoT devices in a specific industrial park. After active detection and network monitoring in several local area network environments, a large amount of data on the target IoT devices is obtained. This data is then used to identify the IoT devices and determine their type, manufacturer, and model. Words can be selected from the large amount of data on the target IoT devices as first attribute information. After calculating the word vectors using a preset word vector model, a series of semantically related phrases closest to the first attribute information are returned from the semantic corpus as second attribute information. Based on this second attribute information, the device identifier of the target IoT device, such as device type, manufacturer, and model, can be constructed. If the model information of a device is entered, the semantic corpus returns information such as the device type and manufacturer. Because the device type and manufacturer information are crawled from e-commerce websites, the device type and manufacturer information are relatively accurate.

[0097] Compared with the regular expression method which has low extraction accuracy during crawling, and the named entity recognition method which cannot identify scattered information and cannot form meaningful continuous entity information, this embodiment can quickly and accurately obtain the device identification of the target IoT device.

[0098] Based on the first embodiment of the method for constructing an IoT device identification, the present invention provides a second embodiment of the method for identifying an IoT device. Figure 5 , Figure 5 This is a flow chart of the second embodiment of the method for constructing an IoT device identifier according to the present invention.

[0099] In this embodiment, the following steps are included:

[0100] Step S201: Acquire first attribute information of a target IoT device and multiple device attribute information from multiple web page data.

[0101] Step S202: input the first attribute information into a preset word vector model to obtain a first word vector of the first attribute information; wherein the preset word vector model is a model pre-trained using multiple device attribute information as a training set.

[0102] Step S203: Based on the correlation between the first word vector and the second word vectors of the plurality of device attribute information, second attribute information related to the first attribute information is filtered out from the plurality of device attribute information.

[0103] Step S204: Input the first attribute information and the second attribute information into the search engine at the same time to obtain a search result webpage.

[0104] Step S205: Based on the search result webpage, verify whether the first attribute information and the second attribute information are related.

[0105] In this embodiment, although the correlation between words has been quantified using a preset word embedding model, the word embedding model can return second attribute information that is highly correlated with the first attribute information. Although the correlation is high, the second attribute information is not necessarily the IoT device attribute word in the first attribute information. In this embodiment, the search engine's correlation is used to verify the multiple related semantic words obtained from the first attribute information, namely the second attribute information.

[0106] Based on the magnitude of the correlation with the first attribute information, a number of bigrams are constructed. The bigrams can be expressed as (first attribute information, second attribute information).

[0107] For these bigrams, we further verified whether there was a correlation between them and IoT device attributes. We used the bigram as a keyword in search engines like Bing and Baidu to obtain the search results. We then verified the correlation based on the search results.

[0108] In some embodiments, this verification can be performed by determining the type of search result webpage. For example, if a search result webpage is a sales page for an IoT device and both the first attribute information and the second attribute information are present, then the two can be considered to be related. Alternatively, if a search result webpage is a device description page for an IoT device and both the first attribute information and the second attribute information are present, then the two can be considered to be related.

[0109] Alternatively, in some other embodiments, step S205 includes:

[0110] Step B10: extract multiple groups of phrases to be verified from the search result webpage; wherein the multiple groups of phrases to be verified include first attribute information and second attribute information.

[0111] In this step, multiple groups of phrases to be verified may be extracted from the webpage abstract of the search result webpage.

[0112] Step B20: Input all phrases to be verified into a preset word vector model to obtain multiple third word vectors.

[0113] Step B30: Perform a proximity distance calculation on the third word vector of the first attribute information and the third word vector of the second attribute information to obtain a proximity distance value.

[0114] Step B40: If the proximity distance value is greater than the preset threshold, the verification is passed;

[0115] Step B50: If the proximity distance value is less than or equal to the preset threshold, the verification fails.

[0116] This embodiment still uses the preset word vector model to calculate the third word vectors between the phrases to be verified, thereby determining the degree of correlation between all phrases to be verified. At this point, if the degree of proximity between the third word vector based on the first attribute information and the third word vector based on the second attribute information is greater than a preset threshold, it indicates that the semantic correlation between the two meets the requirement and is an IoT device attribute word of the first attribute information, thereby verifying whether the two are related.

[0117] Step S206: If the verification is successful, construct a device identification of the target IoT device based on the second attribute information.

[0118] After extracting the IoT device identifier, or secondary attribute information, this embodiment uses a search engine to verify whether the extracted secondary attribute information is an IoT device attribute term. Because the secondary attribute information screened in the aforementioned step has a high probability of being an IoT device attribute term, the verification algorithm achieves higher accuracy and faster calculation speed. This helps reduce manual verification costs and improves the accuracy and speed of IoT device attribute term verification.

[0119] The present invention provides a method for constructing an IoT device identification according to the first and second embodiments, and proposes a method for identifying an IoT device according to the third embodiment. Figure 6 , Figure 6 This is a flow chart of the third embodiment of the method for constructing an IoT device identifier according to the present invention.

[0120] In this embodiment, the following steps are included:

[0121] Step S301: Acquire first attribute information of a target IoT device and multiple device attribute information from multiple web page data.

[0122] Step S302: input the first attribute information into a preset word vector model to obtain a first word vector of the first attribute information; wherein the preset word vector model is a model pre-trained using multiple device attribute information as a training set.

[0123] Step S303: Based on the correlation between the first word vector and the second word vectors of the plurality of device attribute information, second attribute information related to the first attribute information is filtered out from the plurality of device attribute information.

[0124] The detailed description of steps S301 to S303 can be referred to the above embodiment and will not be repeated here.

[0125] Step S304: Determine the identification category to which each piece of second attribute information belongs.

[0126] It is understandable that the second attribute information can be determined as an attribute word of the IoT device, such as type, brand, and model, etc. However, it remains to be determined whether the second attribute information is specifically type, brand, or model.

[0127] This step is used to determine the identification category to which each piece of second attribute information belongs, such as type, brand, and model.

[0128] It is worth mentioning that step S304 can be based on manual recognition or automatic recognition based on a deep learning model, and the comparison in this embodiment is not limited.

[0129] Step S305: Construct a device identification of the target IoT device based on the second attribute information and the identification category.

[0130] After determining the identification category of the second attribute information, the corresponding second attribute information can be added to the corresponding database as the device identification of the target IoT device. For example, the second attribute information under the type category can be added to the type library.

[0131] In addition, see Figure 7 The present invention also provides an IoT device identification construction device, comprising:

[0132] An information acquisition module 10 is configured to acquire first attribute information of a target IoT device and multiple device attribute information from multiple web page data;

[0133] A word vector obtaining module 20 is configured to input the first attribute information into a preset word vector model to obtain a first word vector for the first attribute information; wherein the preset word vector model is a model pre-trained using multiple device attribute information as a training set;

[0134] a related attribute obtaining module 30 for filtering out second attribute information related to the first attribute information from the plurality of device attribute information based on the correlation between the first word vector and the second word vector of the plurality of device attribute information;

[0135] The device identification building module 40 is configured to build a device identification of the target IoT device based on the second attribute information.

[0136] Other embodiments or specific implementations of the device for constructing an IoT device identifier of the present invention may refer to the above-mentioned method embodiments and will not be described in detail here.

[0137] Reference Figure 1 , Figure 1 This is a schematic diagram of the recommended electronic device structure for the method for constructing an IoT device identifier according to an embodiment of the present invention.

[0138] The IoT device identification construction device includes: at least one processor 301, a memory 302, and an IoT device identification construction program stored in the memory and executable on the processor. The IoT device identification construction program is configured to implement the steps of the aforementioned IoT device identification construction method.

[0139] The processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen.

[0140] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 302 is used to store at least one instruction, which is executed by the processor 301 to implement the method for constructing an IoT device identifier provided in the method embodiment of the present application.

[0141] In some embodiments, the IoT device identity construction device may optionally include a communication interface 303 and at least one peripheral device. The processor 301, memory 302, and communication interface 303 may be connected via a bus or signal lines. Each peripheral device may be connected to the communication interface 303 via a bus, signal lines, or circuit boards. Specifically, the peripheral device may include at least one of a radio frequency circuit 304 and a display screen 305.

[0142] The communication interface 303 can be used to connect at least one I / O (Input / Output)-related peripheral device to the processor 301 and the memory 302. The communication interface 303 is used to receive first attribute information uploaded by the user through the peripheral device. In some embodiments, the processor 301, the memory 302, and the communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the communication interface 303 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0143] The RF circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 304 communicates with communication networks and other communication devices via electromagnetic signals, thereby acquiring the movement trajectories and other data of multiple mobile terminals. The RF circuit 304 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the RF circuit 304 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The RF circuit 304 can communicate with other terminals via at least one wireless communication protocol. Such wireless communication protocols include, but are not limited to, metropolitan area networks, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 304 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0144] Display screen 305 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, or any combination thereof. When display screen 305 is a touch screen display, it is also capable of collecting touch signals on or above the surface of display screen 305. This touch signal can be input as a control signal to processor 301 for processing. In this case, display screen 305 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, display screen 305 can be a single display screen, the front panel of the electronic device; in other embodiments, display screen 305 can be at least two, each disposed on different surfaces of the electronic device or in a foldable design; in still other embodiments, display screen 305 can be a flexible display screen, disposed on a curved or foldable surface of the electronic device. Display screen 305 can also be configured as a non-rectangular irregular shape, i.e., a special-shaped screen. Display screen 305 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0145] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the IoT device identification construction device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0146] In addition, an embodiment of the present invention further proposes a computer-readable storage medium having program code stored thereon, and when the program code is executed by a processor, the steps of the method for constructing an IoT device identifier as described above are implemented. Therefore, no further description will be given here. In addition, the description of the beneficial effects of adopting the same method will not be repeated. For technical details not disclosed in the computer-readable storage medium embodiment involved in this application, please refer to the description of the method embodiment of this application. As an example, the program instructions can be deployed to be executed on one computing device, or on multiple computing devices located at one location, or on multiple computing devices distributed at multiple locations and interconnected by a communication network.

[0147] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The above-described program can be stored in a computer-readable storage medium. When executed, the program can include the processes in the above-described method embodiments. The above-described storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0148] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0149] Through the description of the above embodiments, it is clear to those skilled in the art that the present invention can be implemented by means of software plus necessary general-purpose hardware, and of course it can also be implemented by means of dedicated hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. In general, all functions performed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits, or dedicated circuits. However, for the present invention, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0150] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for constructing an IoT device identifier, characterized in that: The following steps are involved: Obtaining first attribute information of a target IoT device and multiple device attribute information from multiple web page data; Inputting the first attribute information into a preset word vector model to obtain a first word vector of the first attribute information; wherein the preset word vector model is a model pre-trained using the plurality of device attribute information as a training set; Based on the correlation between the first word vector and the second word vectors of the plurality of device attribute information, filtering out second attribute information related to the first attribute information from the plurality of device attribute information; Constructing a device identifier of the target IoT device based on the second attribute information; After the step of filtering out second attribute information related to the first attribute information from the plurality of device attribute information based on the correlation between the first word vector and the second word vectors of the plurality of device attribute information, the method further includes: Inputting the first attribute information and the second attribute information into a search engine simultaneously to obtain a search result webpage; Verifying, based on the search result webpage, whether the first attribute information and the second attribute information are related, so as to verify whether the second attribute information is an IoT device attribute word of the target IoT device; The step of constructing the device identification of the target IoT device based on the second attribute information includes: If the verification is successful, a device identification of the target IoT device is constructed based on the second attribute information.

2. The method for constructing an IoT device identifier according to claim 1, wherein: The step of verifying whether the first attribute information and the second attribute information are related based on the search result webpage includes: Extracting multiple groups of phrases to be verified from the search result webpage; wherein the multiple groups of phrases to be verified include the first attribute information and the second attribute information; Inputting all the phrases to be verified into a preset word vector model to obtain multiple second word vectors; performing a proximity distance calculation on the second word vector of the first attribute information and the second word vector of the second attribute information to obtain a proximity distance value; If the proximity distance value is greater than the preset threshold, the verification is passed; If the proximity distance value is less than or equal to the preset threshold, the verification fails.

3. The method for constructing an IoT device identifier according to claim 1, wherein: The step of obtaining the first attribute information of the target IoT device and the attribute information of multiple devices in the multiple web page data includes: Based on web page data from multiple e-commerce websites, original attribute information of various IoT devices is obtained; After preprocessing the original attribute information, multiple pieces of device attribute information are obtained.

4. The method for constructing an IoT device identifier according to claim 3, wherein: The step of obtaining original attribute information of various IoT devices based on webpage data of multiple e-commerce websites includes: Traversing all the smallest sub-category links under the category directory of the e-commerce website to obtain multiple IoT device web page paths; wherein the links under the sub-category sell the same type of IoT devices; Crawl each web page in the IoT device web page path to obtain original attribute information of each IoT device.

5. The method for constructing an IoT device identifier according to claim 1, wherein: The step of obtaining the first attribute information of the target IoT device includes: Crawl the Internet of Things to which the target Internet of Things device belongs, and obtain first attribute information of the target Internet of Things device.

6. The method for constructing an IoT device identifier according to any one of claims 1 to 5, characterized in that: Before the step of constructing the device identification of the target IoT device based on the second attribute information, the method further includes: determining the identification category to which each of the second attribute information belongs; The step of constructing the device identification of the target IoT device based on the second attribute information includes: Based on the second attribute information and the identification category, a device identification of the target Internet of Things device is constructed.

7. A device for constructing an identification of an Internet of Things device, characterized in that: The following steps are involved: An information acquisition module, configured to acquire first attribute information of a target IoT device and multiple device attribute information from multiple web page data; a word vector obtaining module, configured to input the first attribute information into a preset word vector model to obtain a first word vector of the first attribute information; wherein the training set of the preset word vector model includes a plurality of the device attribute information; a related attribute obtaining module, configured to filter out second attribute information related to the first attribute information from the plurality of device attribute information based on the correlation between the first word vector and the second word vectors of the plurality of device attribute information; A device identification construction module, configured to construct a device identification of the target IoT device based on the second attribute information; The IoT device identification construction device is also used to input the first attribute information and the second attribute information into a search engine at the same time to obtain a search result webpage; based on the search result webpage, verify whether the first attribute information and the second attribute information are related; if the verification is successful, construct the device identification of the target IoT device based on the second attribute information.

8. An IoT device identification construction device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The method comprises an executable program code, wherein when the program code is executed by a processor, the method according to any one of claims 1 to 6 is performed.

Images