Website identification method and device, and electronic device

Abstract

The present disclosure provides a website identification method and device and electronic equipment, relates to the field of data processing, and particularly relates to the field of data mining. The specific implementation scheme is as follows: a plurality of keywords of a target type of website are acquired; for each keyword, website retrieval is performed with the keyword to obtain a retrieval result of the keyword; the occurrence frequency of a candidate website appearing in each retrieval result is determined; and if the occurrence frequency is greater than a preset first threshold, the candidate website is determined as the target type of website. The efficiency of website identification can be improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, and in particular, to the technical field of data mining. BACKGROUND

[0002] According to actual needs, a user can divide websites into different types according to different classification standards. For example, websites are divided into different categories according to the industries served by the websites, such as websites serving the financial industry, websites serving the tourism industry, and the like. SUMMARY

[0003] The present disclosure provides a website identification method, device and electronic equipment.

[0004] According to a first aspect of the present disclosure, a website identification method is provided, comprising:

[0005] obtaining a plurality of keywords of websites of a target type;

[0006] performing website retrieval with each keyword to obtain retrieval results of the keyword;

[0007] determining a frequency of occurrence of a candidate website in each of the retrieval results;

[0008] if the frequency of occurrence is greater than a preset first threshold, determining the candidate website as a website of the target type.

[0009] According to a second aspect of the present disclosure, a website identification device is provided, comprising:

[0010] a keyword obtaining module configured to obtain a plurality of keywords of websites of a target type;

[0011] a retrieval module configured to perform website retrieval with each keyword to obtain retrieval results of the keyword;

[0012] a frequency of occurrence statistical module configured to determine a frequency of occurrence of a candidate website in each of the retrieval results;

[0013] a first judgment module configured to determine the candidate website as a website of the target type if the frequency of occurrence is greater than a preset first threshold.

[0014] According to a third aspect of the present disclosure, an electronic equipment is provided, comprising:

[0015] at least one processor; and

[0016] a memory in communication with the at least one processor; wherein

[0017] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of the first aspect.

[0018] According to a fourth aspect provided by the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to perform the method of any one of the first aspect.

[0019] According to a fifth aspect provided by the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of any one of the first aspect.

[0020] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] The accompanying drawings are used to better understand the present scheme, and do not constitute a limitation on the present disclosure. Among them:

[0022] Figure 1 is a flowchart of a website identification method according to the present disclosure;

[0023] Figure 2 is another flowchart of a website identification method according to the present disclosure;

[0024] Figure 3 is another flowchart of a website identification method according to the present disclosure;

[0025] Figure 4 is a structural schematic diagram of a website identification device according to the present disclosure;

[0026] Figure 5 is a block diagram of an electronic device for implementing the website identification method of the embodiments of the present disclosure. DETAILED DESCRIPTION

[0027] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, descriptions of well-known functions and structures are omitted in the following description.

[0028] To more clearly illustrate the website identification method provided in this disclosure, an exemplary application scenario of the website identification method provided in this disclosure will be described below. It should be understood that the following example is only one possible application scenario of the website identification method provided in this disclosure. In other possible embodiments, the website identification method provided in this disclosure can also be applied to other possible application scenarios. The following example does not impose any limitations on this.

[0029] To facilitate website management and analysis, users need to identify website categories. For simplicity, let's assume users need to identify whether a website serves a target industry (hereinafter referred to as an industry website). This can be achieved by pre-extracting keywords from the titles and content of multiple industry websites as target features. A recognition model is then trained using these target features. The recognition model maps the input features to the recognition results, which indicate whether the website associated with the input features is an industry website.

[0030] Keywords from the title and content of the website to be identified are extracted as features for identification. It is not yet determined whether the website is an industry website. These features are then input into a pre-trained identification model to obtain the model's output. Based on this output, it can be determined whether the website is an industry website.

[0031] However, this scheme requires extracting keywords from the title and content of each website to be identified in order to obtain the features to be identified. Furthermore, it necessitates mapping these features using a recognition model, thus consuming significant computational resources and resulting in low recognition efficiency. With limited computational resources, it is difficult to identify a large number of websites, and therefore is only suitable for scenarios requiring the identification of a small number of websites.

[0032] Based on this, this disclosure provides a website identification method that can be applied to any electronic device with website identification capabilities, including but not limited to personal computers and servers. The website identification method can be as follows: Figure 1 As shown, it includes:

[0033] S101: Obtain multiple keywords from websites of the target type.

[0034] S102, for each keyword, perform a website search using the keyword to obtain the keyword search results.

[0035] S103, determine the frequency of candidate websites appearing in each search result.

[0036] S104. If the frequency of occurrence is greater than the preset first threshold, the candidate website is determined as the target type website.

[0037] In this embodiment, since the keyword used for the search is the keyword of the target type of website, it can be considered that the website appearing in the search result obtained by using the keyword has a certain similarity with the target type of website. Therefore, the greater the frequency of appearance of the candidate website in each search result, the higher the similarity of the candidate website with the target type of website. When the frequency of appearance of the candidate website is greater than the first preset threshold, it can be considered that the similarity of the candidate website with the target type of website is high enough, and the candidate website can be determined as the target type of website. It can be seen that the website identification method provided by the present disclosure can accurately identify the website.

[0038] In addition, in the identification process, the website features of each candidate website do not need to be extracted, but the keyword search and search result statistics are used to determine whether the candidate website is the target type of website. The keyword search and search result statistics can be used to process a large number of candidate websites in batches. Therefore, the website identification method provided by the present disclosure can be used to identify a large number of candidate websites in batches, thereby effectively improving the efficiency of website identification. That is, the website identification method provided by the present disclosure can accurately identify the website and improve the efficiency of website identification.

[0039] For example, in the case of identifying m websites, if the method in the foregoing example is used, the features of the m websites need to be extracted, and the features of the m websites are respectively input into the identification model, and the identification model is used for m times of mapping to obtain the identification result, and the websites belonging to the target category in the m websites are determined according to the identification result.

[0040] If the number of keywords is n, the website identification method provided by the present disclosure only needs to perform n times of search, and the search results obtained by n times of search are counted, and the websites belonging to the target category in the m websites are determined according to the frequency of appearance of each website obtained by counting.

[0041] Suppose that the calculation amount required for extracting the features of a website and performing one time of mapping by using the identification model is A, and the calculation amount required for searching with one keyword is B. According to the method in the example, the calculation amount consumed is approximately m*A, and according to the website identification method provided by the present disclosure, the calculation amount consumed is approximately n*B.

[0042] It can be understood that when the number of m is large, n is usually much smaller than m, for example, a user may need to identify tens of thousands or hundreds of thousands of websites according to actual needs, and the keywords used for searching are usually much smaller than ten thousand. Moreover, the calculation amount of mapping by using the model is usually larger or similar to the calculation amount required for searching, so m*A is obviously larger than n*B, and as m increases, that is, as the number of websites to be identified increases, the difference between the calculation amounts consumed by the two will further increase.

[0043] The foregoing S101-S104 will be described below respectively:

[0044] In S101, the target type website can be any type of website, such as an industry website serving a specific industry, or a functional website capable of providing a specific function, etc. The plurality of keywords can be input by a user according to experience, or can be extracted from the target type website.

[0045] For example, in a possible embodiment, a user considers that keywords A, B and C often appear in the target category website according to actual experience, and then inputs the keywords A-C through an operation instruction so that the execution subject obtains the keywords A-C. In another possible embodiment, the execution subject or other devices other than the execution subject extract words existing in the plurality of target type websites, count the occurrence frequencies of the extracted words, and select a plurality of words from the words in descending order of the occurrence frequencies as keywords.

[0046] In S102, each keyword is input into a search engine for website searching, and the set of websites searched by the keyword is the searching result of the keyword. For example, assuming that website searching is performed by using the keyword A, a total of 100 websites are searched, which are respectively denoted as websites 1-100, and the set of websites 1-100 is taken as the searching result of the keyword.

[0047] It can be understood that each website in the searching result obtained by using the keyword theoretically has the keyword or is associated with the keyword. The keyword is a target type website, so the keyword can reflect the characteristics of the target type website to a certain extent. Therefore, in a certain characteristic dimension, each website in the searching result is similar to the target type website.

[0048] In S103, the appearance of a website in the searching result means that the website is included in the searching result. The appearance frequency means the ratio of the number of times that the candidate website appears in the searching result to the number of the searching result. For example, assuming that there are a total of 100 searching results, and the candidate website appears in 80 of the searching results, the appearance frequency of the candidate website is 80 / 100=0.8.

[0049] The occurrence frequency in the present disclosure refers to the ratio of the occurrence times to the number of search results, but the occurrence frequency can be expressed in any form that can reflect the ratio. For example, when the ratio of the occurrence times to the number of search results belongs to [0.7, 1], the occurrence frequency is expressed as the word "high"; when the ratio of the occurrence times to the number of search results belongs to (0.3, 7), the occurrence frequency is expressed as the word "medium"; and when the ratio of the occurrence times to the number of search results belongs to [0, 0.3], the occurrence frequency is expressed as the word "low".

[0050] In S104, as analyzed in the aforementioned S102, each website in the search results is similar to the target type website in a certain feature dimension, so if the occurrence frequency of the candidate website is higher, it can be considered that the candidate website is more similar to the target type website in more feature dimensions. When the occurrence frequency is greater than the preset first threshold, it can be considered that the candidate website is similar to the target type website in more feature dimensions, so the candidate website can be considered as the target type website.

[0051] If the occurrence frequency is not greater than the preset first threshold, in one possible embodiment, it can be determined that the candidate website is not the target type website. In another possible embodiment, it can be further determined whether the candidate website is the target type website. For example, as shown in Figure 2 The method comprises the following steps:

[0052] S201, obtaining a plurality of keywords of a target type website.

[0053] This step is the same as the aforementioned S101, and the related description of the aforementioned S101 can be referred to, which will not be repeated here.

[0054] S202, performing website search based on each keyword to obtain a search result of the keyword.

[0055] This step is the same as the aforementioned S102, and the related description of the aforementioned S102 can be referred to, which will not be repeated here.

[0056] S203, determining an occurrence frequency of the candidate website in each search result.

[0057] This step is the same as the aforementioned S103, and the related description of the aforementioned S103 can be referred to, which will not be repeated here.

[0058] S204, if the occurrence frequency is greater than a preset first threshold, determining the candidate website as the target type website.

[0059] This step is the same as the aforementioned S104, and the related description of the aforementioned S104 can be referred to, which will not be repeated here.

[0060] S205, if the occurrence frequency is not greater than the preset first threshold value, determining the search result in which the seed website appears in all search results as a seed search result.

[0061] The seed website is a website of the target type. The number of seed websites can be one or multiple. If the number of seed websites is one, the occurrence of the seed website in the search result means that one seed website appears in the search result. If the number of seed websites is multiple, the occurrence of the seed website in the search result means that at least x seed websites appear in the search result, x is an arbitrary positive integer in the range of [1, r], and r is the number of seed websites.

[0062] The seed website can be set by the user according to actual needs or experience, or can be determined according to a preset rule. For example, the user knows that website A and website B are websites of the target type according to his own experience, and can set website A and website B as seed websites. For another example, the execution subject or other devices other than the execution subject can count the traffic of a plurality of websites of the target type within a preset time window, and select at least one website from the plurality of websites of the target type in descending order of traffic as a seed website.

[0063] S206, determining the co-occurrence frequency of the candidate website appearing in the seed search result.

[0064] The co-occurrence frequency refers to the ratio of the number of co-occurrences of the candidate website appearing in the seed search result to the number of seed search results. For example, assuming that there are 50 seed search results in total, and the candidate website appears in 40 of them, the co-occurrence frequency is 40 / 50 = 0.8.

[0065] Similarly, the occurrence frequency in the present disclosure refers to the ratio of the number of co-occurrences to the number of seed search results, but the co-occurrence frequency can be expressed in any form that can reflect the ratio,

[0066] S207, if the co-occurrence frequency is greater than a preset second threshold value, determining the candidate website as a website of the target type.

[0067] The preset second threshold value can be equal to, greater than, or less than the preset first threshold value, and the present embodiment does not make any limitation thereto.

[0068] It can be understood that due to the limitation of the way of obtaining the keywords, some of the obtained keywords may not accurately reflect the characteristics of the website of the target type, resulting in that even if the candidate website is a website of the target type, the keyword will not appear in the search result of the part of the keywords, and further resulting in that the occurrence frequency of the candidate website is low.

[0069] Seed retrieval results include seed websites, and the seed websites are target type websites. Therefore, if the retrieval results of a keyword are seed retrieval results, it can be considered that the keyword can relatively accurately reflect the characteristics of the target type websites. Therefore, compared with the occurrence frequency, the co-occurrence frequency of the candidate website appearing in the seed retrieval results can more accurately reflect the similarity of the candidate website and the target type websites. Therefore, the candidate website can be more accurately identified according to the co-occurrence frequency, effectively reducing the probability of identification error and improving the accuracy of identification. That is, by selecting this embodiment, the accuracy of website identification can be further improved.

[0070] For example, it is assumed that the preset first threshold and the preset second threshold are both 0.75, and there are a total of 100 keywords, 30 of which cannot accurately reflect the characteristics of the target type websites, and the occurrence frequency of the candidate website is 0.63.

[0071] If the occurrence frequency is less than the preset first threshold when determining that the candidate website is not a target type website, in this example, since the occurrence frequency is less than the preset first threshold, it is determined that the candidate website is not a target type website.

[0072] It can be understood that since the 30 keywords (hereinafter referred to as invalid keywords) cannot accurately reflect the characteristics of the target type websites, even if the candidate website is a target type website, the candidate website is more likely not to appear in the retrieval results of the 30 invalid keywords. It can be seen that even if the candidate website is a target type website, the occurrence frequency is more likely to be less than the preset first threshold, so it is not accurate to determine that the candidate website is not a target type website only by the occurrence frequency being less than the preset first threshold.

[0073] By selecting this embodiment, it is assumed that the remaining 70 keywords (hereinafter referred to as the 70 keywords as valid keywords) are seed retrieval results in addition to the 30 invalid keywords. If the co-occurrence frequency of the candidate website is 0.8, since the co-occurrence frequency is greater than the preset second threshold, it is determined that the candidate website is a target type website.

[0074] It can be understood that at this time, the candidate website appears 56 times in the 70 seed retrieval results, and appears 7 times in the retrieval results of the 30 invalid keywords. Since the invalid keywords cannot accurately reflect the characteristics of the target type websites, the retrieval results of the invalid keywords cannot reflect the similarity of the candidate website and the target type websites. Therefore, at this time, it can be considered that the candidate website is similar to the target type websites in 56 dimensions of the 70 characteristic dimensions. It can be seen that at this time, the candidate website is similar to the target type websites in most characteristic dimensions, so it is relatively accurate to determine that the candidate website is a target type website at this time.

[0075] In a possible implementation, if the co-occurrence frequency is not greater than a preset second threshold, it is determined that the candidate website is not a website of the target type.

[0076] It can be understood that, although all websites of a target type theoretically have some common features (hereinafter referred to as commonality), each different target type of website tends to have some different features (hereinafter referred to as individuality). Therefore, even if a keyword can accurately reflect the features of a website of a certain target type, the keyword can only be able to reflect the individuality of the website of the target type, and cannot accurately reflect the commonality of the website of the target type.

[0077] Therefore, even if the search result of a keyword is a seed result, the keyword can only be able to reflect the individuality of the seed website, resulting in that even if a candidate website is a website of a target type, the candidate website will not appear in the search result of the keyword because the candidate website and the seed website have different individualities, resulting in that the co-occurrence frequency of the candidate website is low.

[0078] It can be seen that, even if a candidate website is a website of a target type, the co-occurrence frequency of the candidate website can be lower than a preset second threshold. Therefore, when the co-occurrence frequency is not greater than the preset second threshold, it is not accurate enough to determine that the candidate website is not a website of the target type.

[0079] Based on this, the present disclosure provides a website identification method, which can be as shown in the following. Figure 3 The website identification method comprises the following steps.

[0080] S301, acquiring a plurality of keywords of a website of a target type.

[0081] This step is the same as the aforementioned S101, and details are referred to the related description of the aforementioned S101, which will not be repeated here.

[0082] S302, performing website search by using each keyword to obtain a search result of the keyword.

[0083] This step is the same as the aforementioned S102, and details are referred to the related description of the aforementioned S102, which will not be repeated here.

[0084] S303, determining an occurrence frequency of the candidate website in each search result.

[0085] This step is the same as the aforementioned S103, and details are referred to the related description of the aforementioned S103, which will not be repeated here.

[0086] S304, if the occurrence frequency is greater than a preset first threshold, determining the candidate website as a website of the target type.

[0087] The step is the same as S104, and details are referable to the description of S104.

[0088] S305, if the occurrence frequency is not greater than the preset first threshold, determining the search result in which the seed website appears in all search results as a seed search result.

[0089] The step is the same as S205, and details are referable to the description of S205.

[0090] S306, determining the co-occurrence frequency of the candidate website appearing in the seed search result.

[0091] The step is the same as S206, and details are referable to the description of S206.

[0092] S307, if the co-occurrence frequency is greater than the preset second threshold, determining the candidate website as a website of the target type.

[0093] The step is the same as S207, and details are referable to the description of S207.

[0094] S308, if the co-occurrence frequency is less than the preset second threshold, extracting the website features of the candidate website.

[0095] The website features include, but are not limited to, any one or more of the following features: title, keywords in content, cited links, pictures, tables, styles, feature vectors extracted by any feature extraction algorithm, etc.

[0096] S309, determining the confidence of the candidate website being the website of the target type according to the matching degree between the website features of the candidate website and the website features of the website of the target type.

[0097] The way of calculating the confidence can be different according to different application scenarios, but the confidence should be positively correlated with the matching degree. The confidence is positively correlated with the matching degree means that when other factors affecting the confidence are unchanged, the greater the matching degree is, the greater the confidence is.

[0098] For example, in one possible embodiment, the confidence = matching degree * k, where k is a preset coefficient and k is greater than 0. In another possible embodiment, the confidence can be determined according to the matching degree, the occurrence frequency and the co-occurrence frequency, and the matching degree is positively correlated with the occurrence frequency and the co-occurrence frequency, for example, the confidence = a1*matching degree + a2*occurrence frequency + a3*co-occurrence frequency, where a1, a2 and a3 are preset coefficients and a1, a2 and a3 are all greater than 0.

[0099] By using this embodiment, the confidence level can be determined by combining the occurrence frequency and co-occurrence frequency. As analyzed above, the occurrence frequency and co-occurrence frequency can reflect the similarity between the candidate website and the target type website to a certain extent. Therefore, the higher the occurrence frequency and co-occurrence frequency, the higher the confidence level that the candidate website is the target type website. Thus, combining the occurrence frequency and co-occurrence frequency to determine the confidence level can improve the accuracy of the determined confidence level, thereby classifying the candidate websites more accurately.

[0100] S310, if the confidence level is greater than the preset third threshold, the candidate website is determined as the target type website.

[0101] Understandably, confidence reflects the probability that a candidate website is the target type of website. When the confidence is greater than the preset third threshold, it can be considered that the probability of the candidate website being the target type of website is high enough, and at this time, the candidate website can be considered to be the target type of website.

[0102] By employing this embodiment, when occurrence frequency and co-occurrence frequency cannot accurately determine whether a candidate website belongs to the target type, further feature extraction and feature matching can be used to determine whether a candidate website belongs to the target type. This further reduces the likelihood of incorrectly identifying a candidate website as not belonging to the target type when it already is, thus improving the accuracy of website identification. Furthermore, since this embodiment only requires feature extraction and feature matching for candidate websites whose occurrence frequency is below a preset first threshold and whose co-occurrence frequency is below a preset second threshold, the computational cost is still lower compared to the methods in the aforementioned example application scenarios.

[0103] If the confidence level is not greater than a preset third threshold, in one possible embodiment, it can be determined that the candidate website is not a website of the target type. In another possible embodiment, other means can be further used to identify the candidate website, and this disclosure does not impose any limitations on this.

[0104] See Figure 4 , Figure 4 The diagram shown is a structural schematic of a website identification device provided in this disclosure, which may include:

[0105] Keyword acquisition module 401 is used to acquire multiple keywords for websites of the target type;

[0106] The retrieval module 402 is used to perform a website search for each of the keywords and obtain the search results for the keywords.

[0107] The frequency of occurrence statistics module 403 is used to determine the frequency of occurrence of candidate websites in each of the search results;

[0108] The first judging module 404 is configured to determine the candidate website as the website of the target type if the occurrence frequency is greater than a preset first threshold.

[0109] In a possible embodiment, the method further includes:

[0110] The screening module is configured to determine, as seed search results, search results in which seed websites appear in all the search results if the occurrence frequency is not greater than the preset first threshold, wherein the seed websites are preset websites of the target type.

[0111] The co-occurrence frequency counting module is configured to determine a co-occurrence frequency of the candidate website in each of the seed search results.

[0112] The second judging module is configured to determine the candidate website as the website of the target type if the co-occurrence frequency is greater than a preset second threshold.

[0113] In a possible embodiment, the method further includes:

[0114] The feature extraction module is configured to extract website features of the candidate website if the co-occurrence frequency is less than the preset second threshold.

[0115] The feature matching module is configured to determine a confidence degree of the candidate website as the website of the target type according to a matching degree between the website features of the candidate website and website features of the website of the target type, wherein the confidence degree is positively correlated with the matching degree.

[0116] The third judging module is configured to determine the candidate website as the website of the target type if the confidence degree is greater than a preset third threshold.

[0117] In a possible embodiment, the feature matching module is specifically configured to determine the confidence degree of the candidate website as the website of the target type according to the matching degree between the website features of the candidate website and the website features of the website of the target type, the occurrence frequency, and the co-occurrence frequency, wherein the confidence degree is positively correlated with the occurrence frequency, and the confidence degree is positively correlated with the co-occurrence frequency.

[0118] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution comply with relevant laws and regulations and do not violate public order and good customs.

[0119] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium, and a computer program product.

[0120] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0121] like Figure 5 As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0122] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0123] The computing unit 501 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs various methods and processes described above, such as the website identification method. For example, in some embodiments, the website identification method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded onto the RAM 503 and executed by the computing unit 501, one or more steps of the website identification method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the website identification method by any other appropriate means, such as by means of firmware.

[0124] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0125] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0126] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0127] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0128] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0129] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0130] It should be understood that the various forms of flow shown above can be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, without limitation herein, so long as the desired results of the technology disclosed in the present disclosure are achieved.

[0131] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A website identification method, comprising: obtaining a plurality of keywords of a target type of website; performing a website search with each of the keywords to obtain a search result of the keyword; determining a frequency of occurrence of a candidate website in each of the search results; if the frequency of occurrence is greater than a preset first threshold, determining the candidate website as the target type of website; if the frequency of occurrence is not greater than the preset first threshold, determining a search result in which a seed website occurs in all the search results as a seed search result; determining a co-occurrence frequency of the candidate website in each of the seed search results; if the co-occurrence frequency is greater than a preset second threshold, determining the candidate website as the target type of website; wherein the seed website is selected by: counting a traffic of a plurality of the target type of websites within a preset time window; and selecting at least one website from the plurality of the target type of websites in a descending order of traffic as the seed website. 2.The method of claim 1, further comprising: if the co-occurrence frequency is less than the preset second threshold, extracting a website feature of the candidate website; determining a confidence degree of the candidate website as the target type of website according to a matching degree between the website feature of the candidate website and a website feature of the target type of website, the confidence degree being positively correlated with the matching degree; if the confidence degree is greater than a preset third threshold, determining the candidate website as the target type of website.

3. The method of claim 2, wherein, The determining of the confidence degree of the candidate website as the target type of website according to the matching degree between the website feature of the candidate website and the website feature of the target type of website comprises: determining the confidence degree of the candidate website as the target type of website according to the matching degree between the website feature of the candidate website and the website feature of the target type of website, the frequency of occurrence and the co-occurrence frequency, the confidence degree being positively correlated with the frequency of occurrence and the co-occurrence frequency. 4.A website identification apparatus, comprising: a keyword obtaining module configured to obtain a plurality of keywords of a target type of website; a search module configured to perform a website search with each of the keywords to obtain a search result of the keyword; a frequency of occurrence counting module configured to determine a frequency of occurrence of a candidate website in each of the search results; a first judging module configured to, if the frequency of occurrence is greater than a preset first threshold, determine the candidate website as the target type of website; a screening module configured to, if the frequency of occurrence is not greater than the preset first threshold, determine a search result in which a seed website occurs in all the search results as a seed search result, wherein the seed website is a preset target type of website; a co-occurrence frequency counting module configured to determine a co-occurrence frequency of the candidate website in each of the seed search results; a second judging module configured to, if the co-occurrence frequency is greater than a preset second threshold, determine the candidate website as the target type of website. The seed website is selected by the following method: Statistical traffic of the target type of website in a predetermined time window; according to the order from high to low traffic, select at least one website from the target type of website as a seed website.

5. The apparatus of claim 4, further comprising: a feature extraction module configured to extract website features of the candidate website if the co-occurrence frequency is less than the preset second threshold; a feature matching module configured to determine a confidence level of the candidate website as the target type of website according to a matching degree between the website features of the candidate website and the target type of website, wherein the confidence level is positively correlated with the matching degree; a third judging module configured to determine the candidate website as the target type of website if the confidence level is greater than a preset third threshold.

6. The apparatus of claim 5, wherein, The feature matching module is specifically configured to determine a confidence level of the candidate website as the target type of website according to a matching degree between the website features of the candidate website and the target type of website, the occurrence frequency and the co-occurrence frequency, wherein the confidence level is positively correlated with the occurrence frequency and the co-occurrence frequency.

7. An electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.

8. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to make the computer execute the method according to any one of claims 1-3.

9. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-3.

Images