Search engine optimization method, device, equipment and storage medium

Abstract

The application discloses a search engine optimization method and device, equipment and a storage medium. The method is applied to the natural language processing field of artificial intelligence, and comprises the following steps: acquiring a page keyword of a target website, wherein the page keyword is a keyword extracted from page information of the target website through natural language processing (NLP); determining a target keyword according to search information related to the page keyword in the search engine; and adjusting website information of the target website according to the target keyword, wherein the website information is used by the search engine to determine a search keyword of the target website. The method realizes automatic search engine optimization of the website and improves the efficiency of search engine optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of natural language processing of artificial intelligence, and in particular to a search engine optimization method and device, equipment and a storage medium. BACKGROUND

[0002] SEO (Search Engine Optimization) is a way to improve the natural ranking of a website in a search engine. For example, a user searches for the keyword "food" in a search engine and gets search results. Through SEO, the ranking of a website in the search results can be improved, and the exposure rate of the website can be improved. The ranking of each website in the search results is determined by the search engine according to the matching degree between the website content or website keywords and the search keywords searched by the user. The website with a high matching degree is ranked high. SEO optimizes the ranking of the website in the search results by optimizing the website content and the website keywords.

[0003] In related technologies, a person (SEO specialist) determines the keywords of a website according to the content of the website, and then extends the keywords according to experience to obtain more keywords. After the SEO specialist obtains the keywords, the SEO specialist searches the heat of each keyword in each search engine according to the keywords, selects part of the keywords according to the heat, and optimizes the website information such as the content and keywords of the website using the part of the keywords to improve the exposure rate of the website.

[0004] The above-mentioned SEO method needs to extract keywords and optimize websites manually according to experience for each website. When the number of websites is too large, a large amount of manpower needs to be invested, the work efficiency is too low, and the influence of human subjectivity is large. SUMMARY

[0005] The embodiments of the present application provide a search engine optimization method and device for a website, which can improve the efficiency of SEO for a website. The technical solution is as follows:

[0006] According to one aspect of the present application, a search engine optimization method is provided, which comprises:

[0007] Obtaining a page keyword of a target website, the page keyword being a keyword extracted from page information of the target website through natural language processing (NLP);

[0008] Determining a target keyword according to search information related to the page keyword in the search engine;

[0009] Adjusting website information of the target website according to the target keyword, the website information being used by the search engine to determine a search keyword of the target website.

[0010] According to another aspect of the present application, a search engine optimization device is provided, the device comprising:

[0011] an acquisition module configured to acquire a page keyword of a target website, the page keyword being a keyword extracted from page information of the target website by natural language processing (NLP);

[0012] a determination module configured to determine a target keyword according to search information related to the page keyword in the search engine;

[0013] an optimization module configured to adjust website information of the target website according to the target keyword, the website information being used by the search engine to determine a search keyword of the target website.

[0014] According to another aspect of the present application, a computer device is provided, the computer device comprising a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by the processor to implement the search engine optimization method according to the above aspect.

[0015] According to another aspect of the present application, a computer readable storage medium is provided, the storage medium storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by the processor to implement the search engine optimization method according to the above aspect.

[0016] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0017] According to the method, the server automatically acquires page information of a target website, extracts a page keyword from the page information, and determines a target keyword according to search information related to the page keyword in a search engine. Then, the server adjusts website information of the target website according to the target keyword, thereby completing the SEO process of the target website. The method can automatically perform SEO on the target website by the server, improve the exposure rate of the target website, and reduce the labor cost of SEO. Moreover, the method can adjust the website information of the target website in real time according to the real-time heat of the keyword, thereby improving the timeliness of SEO. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings.

[0019] Figure 1 is a server implementation environment block diagram provided by an exemplary embodiment of the present application;

[0020] Figure 2 is a flow chart of a search engine optimization method provided by an exemplary embodiment of the present application;

[0021] Figure 3 is a flow chart of a search engine optimization method provided by another exemplary embodiment of the present application;

[0022] Figure 4 is a flow chart of a search engine optimization method provided by another exemplary embodiment of the present application;

[0023] Figure 5 is a flow chart of a search engine optimization method provided by another exemplary embodiment of the present application;

[0024] Figure 6 is a flow chart of a search engine optimization method provided by another exemplary embodiment of the present application;

[0025] Figure 7 is a flow chart of a search engine optimization method provided by another exemplary embodiment of the present application;

[0026] Figure 8 is a flow chart of a search engine optimization method provided by another exemplary embodiment of the present application;

[0027] Figure 9 is a flow chart of a search engine optimization method provided by another exemplary embodiment of the present application;

[0028] Figure 10 is a flow chart of a search engine optimization method provided by another exemplary embodiment of the present application;

[0029] Figure 11 is an application schematic diagram of a search engine optimization method provided by another exemplary embodiment of the present application;

[0030] Figure 12 is an interface schematic diagram of a search engine optimization method provided by another exemplary embodiment of the present application;

[0031] Figure 13is a flow chart of a search engine optimization method provided by another exemplary embodiment of the present application;

[0032] Figure 14 is a block diagram of a search engine optimization device provided by another exemplary embodiment of the present application;

[0033] Figure 15 is a structural schematic diagram of a server provided by another exemplary embodiment of the present application. DETAILED DESCRIPTION

[0034] For the purpose, technical solutions and advantages of the present application to be more clear, the present application embodiments will be further described in detail below with reference to the drawings.

[0035] Firstly, the terms related to the embodiments of the present application are introduced:

[0036] Search engine optimization (SEO) is a technology of understanding how various search engines search, how to capture Internet pages, and how to determine the ranking of search results of specific keywords by analyzing the ranking rules of search engines. SEO uses means easy to be cited by search engines to optimize the website, improves the natural ranking of the website in the search engine, attracts more users to visit the website, improves the access volume of the website, and thus improves the brand effect of the website. The search engine optimization task of the website is mainly to understand how other search engines capture web pages, index, and determine search keywords, and then optimize the content of the website to ensure that it is consistent with the browsing habits of users, and makes the search engine ranking of the website improved without affecting the user experience, and thus improves the access volume of the website. Based on the search engine optimization processing, it is actually to make the search engine more easily accept the website. The search engine often compares the contents of different websites, and then provides the contents to the user in the most complete and direct website content through the browser.

[0037] Artificial intelligence (AI) is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology of computer science, which tries to understand the essence of intelligence and produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machine has the functions of perception, reasoning and decision-making.

[0038] Artificial intelligence technology is a comprehensive discipline, involving a wide range of fields, both hardware and software level technology. Artificial intelligence basic technology generally includes, such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology and machine learning / deep learning and other major directions.

[0039] Natural language processing (NLP) is an important direction in the field of computer science and artificial intelligence. It studies the various theories and methods that can realize effective communication between people and computers using natural language. Natural language processing is a science that integrates linguistics, computer science and mathematics. Therefore, the research in this field will involve natural language, i.e. the language used in daily life, so it has a close relationship with the study of linguistics. Natural language processing technology usually includes text processing, semantic understanding, machine translation, robot question and answer, knowledge graph and other technologies.

[0040] Word segmentation: in the process of natural language processing, in order to better process sentences, it is often necessary to break down sentences into individual words, which can better analyze the characteristics of sentences. This process is called word segmentation. There are many word segmentation methods for Chinese word segmentation, for example, word table-based word segmentation methods: forward maximum matching method (FMM), backward maximum matching method (BMM), N-shortest path method; Statistical model-based word segmentation method: N-gram language model-based word segmentation method; Sequence standard-based word segmentation method: HMM (Hidden Markov Model)-based word segmentation method, CRF (Conditional Random Field Algorithm)-based word segmentation method, word perception machine-based word segmentation method, deep learning-based end-to-end word segmentation method, etc. There are many word segmentation algorithms for Chinese word segmentation, such as Jieba word segmentation, Pangu word segmentation, word word segmentation, etc.

[0041] Jieba word segmentation: a Chinese word segmentation algorithm. Jieba word segmentation is based on a statistical dictionary, constructs a prefix dictionary, and then uses the prefix dictionary to split the input sentence to get all the possible cuts. According to the cutting position, a directed acyclic graph is constructed. Through the dynamic programming algorithm, the maximum probability path is calculated, and the final cutting form is obtained. For out-of-vocabulary words, Jieba word segmentation uses HMM based on the word-forming ability of Chinese characters and uses the Viterbi algorithm. Using the HMM model for word segmentation is to regard the word segmentation problem as a sequence labeling problem, in which the sentence is the observation sequence and the word segmentation result is the state sequence. First, the relevant models of HMM are trained through the corpus, and then the Viterbi algorithm is used for solving, and finally the optimal state sequence is obtained, and then the word segmentation result is output according to the state sequence.

[0042] Figure 1 A structural diagram of a computer system provided by an example embodiment of the present application is shown, which includes a terminal 120 and a server 140. The terminal 120 and the server 140 are connected to each other through a wired or wireless network.

[0043] Optionally, the terminal 120 can include at least one of a notebook computer, a desktop computer, a smart phone, a tablet computer, a smart speaker, and a smart robot.

[0044] The terminal 120 is installed with a first client, which is used to implement the website search engine optimization method provided in the present application. For example, the first client is used to send website information to the server 140, which needs to use the website search engine optimization method for SEO. The website information includes: a website address, or a website address and an expected keyword. For example, the first client is also used to receive the search engine optimization result returned by the server 140, and the optimization result includes at least one of the following: a keyword, a keyword popularity ranking, a keyword frequency ranking, a keyword comprehensive ranking, and a website optimization scheme. The terminal 120 includes a first memory and a first processor. The first memory stores a first program; the first program is called and executed by the first processor to implement the website search engine optimization method. The first memory can include but is not limited to the following: a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), and an electrically erasable programmable read-only memory (EEPROM).

[0045] The first processor can be composed of one or more integrated circuit chips. Alternatively, the first processor can be a general-purpose processor, such as a central processing unit (CPU) or a network processor (NP).

[0046] The server 140 comprises a second memory and a second processor. The second memory stores a third program, which is invoked by the second processor to implement the website search engine optimization method provided in the present application. Illustratively, the third program is used to implement: obtaining page information of a target website and an expected keyword input by a user; extracting a page keyword in the page information; obtaining long tail keywords from a search engine according to the page keyword and / or the expected keyword; obtaining a heat condition and a competitiveness condition of the page keyword, the expected keyword and the long tail keywords from the search engine; sorting the page keyword, the expected keyword and the long tail keywords according to the heat condition and the competitiveness condition; determining a suitable target keyword from the page keyword, the expected keyword and the long tail keywords, and optimizing the target website using the target keyword. Optionally, the second memory can include, but is not limited to, the following: RAM, ROM, PROM, EPROM, EEPROM. Optionally, the second processor can be a general-purpose processor, such as a CPU or an NP.

[0047] The embodiment of the present application provides a website search engine optimization method, which is used for performing SEO processing on a target website and mainly comprises the following steps:

[0048] In the first step, a server obtains page information of a target website. In the second step, the server obtains keywords of the target website, the keywords comprising at least one of an expected keyword, a page keyword and a long tail keyword. In the third step, the server optimizes the target website according to the keywords.

[0049] For the first step, illustratively, there can be many ways for the server to obtain the page information of the target website, for example, a user inputs a website address of the target website, and the server obtains the page information of the target website according to the website address; or the user directly uploads the page information of the target website to the server. Illustratively, the server obtains the page information according to the website address of the target website, the user inputs the website address of the target website on a client, and clicks to send the website address to the server. Illustratively, the user can input the expected keyword while inputting the website address of the target website. The expected keyword is a keyword that the user wants to use when performing the SEO processing.

[0050] For the second step, the keywords mainly include three types: the expected keyword, the page keyword and the long tail keyword. The expected keyword is the keyword input by the user in the first step. The page keyword is a keyword obtained by performing a word segmentation processing on the page information of the target website by the server. The long tail keyword is a keyword obtained by performing a word segmentation processing on long tail words associated with the page keyword and the expected keyword, which are obtained from a search engine by the server.

[0051] For example, the word segmentation processing manner is: using the jieba word segmentation algorithm to perform word segmentation on the input text information to obtain a word segmentation result, and then according to a part of speech table, retaining words with a word length greater than 1 and a part of speech as a noun in the word segmentation result, and outputting the part of speech as the final word segmentation result. For example, in order to avoid professional terms from being segmented, when using the jieba word segmentation algorithm for word segmentation, a local dictionary is also introduced, the local dictionary stores non-separable proper nouns, and the local dictionary can be periodically maintained and updated.

[0052] For example, after obtaining the keywords, the server also calculates the value score (hereinafter referred to as value) of each keyword, and sorts the keywords according to the value. The value of the keyword is mainly calculated by two parts: one is the total number of hot searches of the keyword; and the other is the total number of competitions of the search result of the target website obtained by searching the keyword.

[0053] Total number of hot searches: for each keyword, each search engine has a corresponding hot search index, which is used to represent the frequency of searching the keyword by users in a period of time. The total number of hot searches of the keyword is equal to the weighted sum of the hot search indexes of the keyword in each search engine.

[0054] Total number of competitions: the search engine sets a corresponding website weight for each website, for example, the search engine sets different website weights for different domain names, and the website weight of the website can be obtained by inputting the website address into a website weight obtaining tool. The website weight obtaining tool can be: Baidu index, stationmaster tool, etc. The server searches the keyword in each search engine to obtain the corresponding search result of each search engine, obtains the competitive website in front of the target website in each search result, and then obtains the website weight of each competitive website in each search engine. The competition score of the competitive website is obtained by weighting and summing the website weights of the competitive website, and the total number of competitions of the keyword is obtained by summing the competition scores of all competitive websites. For example, if there is no competitive website in front of the target website in the search result, the total number of competitions of the target website is 0. For example, the server only obtains the first 5 competitive websites in the search result.

[0055] After obtaining the total number of hot searches and the total number of competitions of the keyword, the server subtracts the weighted result of the total number of competitions from the weighted result of the total number of hot searches to obtain the value of the keyword.

[0056] For the third step, the server, after obtaining the keywords, optimizes the target website according to the keywords. The server can optimize the target website in at least one of the following ways: setting the keywords as meta tags of the target website, implanting the keywords into the pages of the target website, and using the keywords as reference data for SEM (Search Engine Marketing). For example, the server can select some keywords to optimize the target website according to the categories of the keywords and the value scores of the keywords. For example, the server can select the keywords with the top value scores to optimize the target website according to the value scores of the keywords. The server can also select all of the expected keywords and the keywords with the top value scores among the page keywords and the long-tail keywords to optimize the target website.

[0057] Figure 2 A flowchart of a search engine optimization method provided by an example embodiment of the present application is shown. The method can be performed by the server shown in the figure. The method includes the following steps. Figure 1

[0058] Step 201: Obtain the page keywords of the target website. The page keywords are keywords extracted from the page information of the target website by NLP (Natural Language Processing).

[0059] The target website is a website that needs to be optimized by SEO. For example, the target website can be any one of a website and a web page. For example, the target website can also be replaced by a target application (APP), i.e., the search engine optimization method provided by the present application is used to optimize an application. For example, the target website can be one website, or one main website and a plurality of sub-websites.

[0060] The page keywords are keywords extracted from the page information of the target website by the server. The page information includes at least one of text information, picture information, video information, audio information, and animation information in the target website. For the picture information, video information, and animation information, the server can obtain the text in the picture, video, or animation by text recognition, or can identify the content of the picture, video, or animation and generate a text description by picture recognition. For the audio information, video information, and animation information, the server can obtain the text in the audio signal by voice recognition.

[0061] ​For example, the server can obtain page information of the target website according to a URL (Uniform Resource Locator) of the target website provided by the user. The server can also directly receive page information of the target website provided by the user, for example, an HTML (HyperText Markup Language) file of the target website provided by the user.

[0062] After obtaining the page information of the target website, the server uses NLP to perform word segmentation on the page information to obtain page keywords. For example, the server performs word segmentation on the page information to obtain a word segmentation result of the page information, and then screens the page keywords from the word segmentation result according to the parts of speech and the number of words. For example, the page keywords are word groups with the part of speech of noun and the number of words greater than 1.

[0063] In step 202, the target keywords are determined according to search information related to the page keywords in the search engine.

[0064] A search engine is an information retrieval system in a World Wide Web environment. The search engine refers to a system that collects information from the Internet according to a certain strategy, organizes and processes the information, provides retrieval services for users, and displays information related to the user's search to the user.

[0065] The search information is search information related to the page keywords in the database of the search engine. For example, the search information includes at least one of a search keyword related to the page keyword, a search result related to the page keyword, search data related to the page keyword, and related search content related to the page keyword.

[0066] The search keyword is the search content input by the user, or the search keyword is the keyword sent by the user to the search engine for searching. For example, the search keyword includes the page keyword. The search result is the search result returned by the search engine after sending the search keyword to the search engine. The search result includes a plurality of websites indexed according to the search keyword, and information of the plurality of websites, for example, information in the website, frequency of user clicks on the website, website address, etc. The search data includes at least one of a hot search index of the search keyword and data of users searching for the search keyword. The related search content is content that the user may search for, which is predicted by the search engine according to the content input into the search box by the user according to a prediction algorithm. The prediction algorithm is used to comprehensively analyze the content input into the search box by the user, search keywords searched by other users when inputting the content, hot search indexes of the search keywords, etc., and output search keywords that the user may search for.

[0067] For example, when a user inputs a keyword in the search box 501, the search engine displays a drop-down menu 502 under the search box, in which the search engine automatically recommends search keywords to the user according to the input keyword, and the user can directly click one of the search keywords to perform one-key fast search. The related search content can also be search content recommended by the search engine according to the search keyword searched by the user.

[0068] The target keyword is a keyword determined from all candidate keywords of the target website according to search information related to the page keyword. The target keyword is at least one of a keyword that can best represent the content of the target website, a keyword with a high hot search index, and a keyword in which the target website has a competitive advantage. The target keyword is a keyword used to optimize the target website.

[0069] In step 203, the website information of the target website is adjusted according to the target keyword, and the website information is used by the search engine to determine the search keyword of the target website.

[0070] The server adjusts the website information of the target website according to the target keyword, thereby improving the ranking of the target website in the search result. For example, the server adjusts the related website information of the target website according to the indexing rule of the search engine, so that the ranking of the target website in the search result of some search keywords is improved, thereby improving the exposure rate of the target website. For example, the search engine determines that the target website can be used as a search result when a user searches for a search keyword according to the website information of the target website, and the search engine also determines the ranking of the target website in the search result according to the website information of the target website.

[0071] In summary, the method provided in the embodiment automatically acquires the page information of the target website by the server, extracts the page keyword from the page information, and determines the target keyword according to the search information related to the page keyword in the search engine. Then the server adjusts the website information of the target website according to the target keyword, thereby completing the SEO process of the target website. The method can automatically perform SEO on the target website by the server, improve the exposure rate of the target website, and reduce the labor cost of SEO. Moreover, the method can adjust the website information of the target website in real time according to the real-time hotness of the keyword, thereby improving the timeliness of SEO.

[0072] For example, as shown in Figure 3 An example embodiment for extracting a page keyword from page information is given. An example embodiment for determining a target keyword according to search information related to a page keyword is also given. An example embodiment for adjusting website information of a target website according to a target keyword is also given.

[0073] Figure 3A flowchart illustrating a search engine optimization method provided in an exemplary embodiment of this application is shown. This method can be... Figure 1 The server shown is used to execute the method. The method includes:

[0074] Step 201: Obtain the page keywords of the target website. The page keywords are keywords extracted from the page information of the target website through Natural Language Processing (NLP).

[0075] For example, such as Figure 4 As shown, a method for extracting page keywords from page information is presented. The server uses Jieba segmentation 601 combined with a local dictionary 602 to segment the page information, obtaining segmentation results. The local dictionary contains phrases or proper nouns that cannot be split. The server can periodically capture newly emerging nouns from various fields and store them in the local dictionary's thesaurus data table, achieving real-time updates to the local dictionary. By combining the segmentation results obtained from the local dictionary, proper nouns can be preserved, preventing Jieba segmentation 601 from splitting proper nouns and causing inaccurate segmentation results. The segmentation results obtained from the local dictionary can also be used to segment the page information in real time based on new words appearing in various fields, ensuring that the segmentation results are up-to-date. For example, other segmentation algorithms can be used to replace Jieba segmentation 601; this embodiment only uses the Jieba segmentation algorithm as an example.

[0076] After obtaining the word segmentation results, the server further filters out meaningless parts of speech. Based on the part-of-speech list 604, the server determines the part of speech for each phrase in the segmentation results. Since keywords are mostly nouns, the server selects phrases with nouns from the segmentation results as page keywords. Alternatively, the server selects phrases with nouns and more than one character from the segmentation results as page keywords.

[0077] For example, the keywords selected by the server from the word segmentation results are not directly used as page keywords. The server obtains the frequency of each selected keyword in the word segmentation results and uses the most frequent selected keywords as page keywords; or / and, the server obtains the search popularity index or total number of search popularity for each selected keyword in the search engine and determines the most frequent selected keywords as page keywords. For example, the server uses the five most frequent keywords and the five most popular keywords, a total of ten keywords, as the final page keywords.

[0078] Step 2021: Obtain long-tail keywords from the search engine based on the page keywords. Long-tail keywords are related search content recommended by the search engine based on the page keywords.

[0079] The long-tail word is a word group obtained by expanding the page keyword. The server obtains the long-tail word of the page keyword from the search engine according to the page keyword. For example, the search engine can provide the long-tail word related to the page keyword. For example, after the user inputs the content in the search box of the search engine, the search engine can recommend the content to be searched for the user according to the content input by the user. Or, after the user searches for a search keyword in the search engine, the search engine can recommend the related search of the search keyword to the user according to the search keyword. That is, the long-tail word is a word group provided in the drop-down box 502, or the long-tail word is a search provided in the related search 503. For example, the long-tail word can also be a word group provided by the search engine in other ways, for example, after the user inputs a search content with an error or a wrong word, the search engine automatically identifies the search content and automatically searches for the correct search content corresponding to the user, which can also be a long-tail word of the page keyword. For another example, after the user searches for a search keyword (page keyword), the search engine will also recommend the hot search index ranking of the related search keyword of the search keyword in the search result page, and the keyword in the hot search index ranking can also be a long-tail word of the page keyword.

[0080] Step 2022, the long-tail word is processed by word segmentation to obtain a long-tail keyword.

[0081] The long-tail keyword is a keyword obtained by processing the long-tail word by word segmentation. The long-tail keyword is an expanded keyword obtained according to the page keyword. The long-tail keyword is a keyword extracted according to the related search content generated by the search engine according to the page keyword.

[0082] For example, the server can use the word segmentation algorithm as shown in Figure 4 to process the long-tail word by word segmentation to obtain the long-tail keyword.

[0083] Step 2023, the page keyword and the long-tail keyword are determined as candidate keywords.

[0084] The candidate keyword is a collective term of the page keyword and the long-tail keyword. The candidate keyword is used for screening to obtain the target keyword. For example, in the next embodiment, the expected keyword will also be mentioned, which is a keyword directly provided by the user. In step 2023, the server can also determine the page keyword, the long-tail keyword and the expected keyword as the candidate keyword, and then screen the final target keyword from the candidate keyword in the next step. Of course, the expected keyword can also not be screened as a candidate keyword, but directly as a target keyword to adjust the website information of the target website.

[0085] Step 2024, determining the target keyword from the candidate keyword according to the keyword screening condition.

[0086] The keyword screening condition is used to screen the target keyword from the candidate keyword. The keyword screening condition can be set according to at least one of the type of the candidate keyword, a hot search index, a hot search total number, a competition total number, and a value score.

[0087] The type of the candidate keyword includes an expected keyword, a page keyword, and a long-tail keyword. For example, since the expected keyword is a keyword specified by a user, the expected keyword has a high importance and can be preferentially selected as the target keyword. Since the page keyword is directly extracted from page information of the target website, the page keyword can directly represent the actual content of the target website, and thus the page keyword has a moderate importance and can also be preferentially selected as the target keyword. Since the long-tail keyword is a keyword obtained from related search content related to the page keyword in a search engine, the long-tail keyword deviates from the actual content of the target website, and thus the long-tail keyword has a low importance and needs to be screened to select the target keyword.

[0088] The hot search index and the hot search total number are both values used to describe the frequency with which the candidate keyword is searched by a user in a period of time. The hot search index is a value provided by a search engine, and the hot search total number is a total value calculated by comprehensively considering hot search indexes provided by multiple search engines. For example, the hot search index is a value directly provided by a search engine, and each search engine has its own algorithm for calculating the hot search index of a keyword.

[0089] For example, the search information includes at least one of the hot search total number and the competition total number of the candidate keyword. The hot search total number is used to describe the frequency with which the candidate keyword is searched by a user, and the competition total number is used to describe the competitiveness of the target website in the search result of the candidate keyword.

[0090] For example, an example embodiment for calculating the hot search total number and the competition total number is given. As shown in FIG. 3, Figure 5 Before step 2024, steps 301 to 304 are further included, and step 2024 further includes step 2024-1.

[0091] In step 301, the hot search index of the candidate keyword in at least one search engine is obtained. The hot search index is used to describe the frequency with which the candidate keyword is searched in a period of time.

[0092] For example, the server can obtain the hot search index of the candidate keyword in each search engine through a search information acquisition website. The search information acquisition website can be at least one of Baidu Index and a webmaster tool. For example, the server can also obtain the hot search index of the candidate keyword from each search engine.

[0093] For example, for the candidate keyword "keyword 1", the server obtains a first hot search index 100000 of the candidate keyword in search engine A, a second hot search index 200 in search engine B, and a third hot search index 50000 in search engine C.

[0094] Step 302, calculating the total hot search number of the candidate keyword according to at least one hot search index.

[0095] For example, in response to the number of hot search indexes of the candidate keyword being equal to 1, the hot search index is determined as the total hot search number of the candidate keyword.

[0096] If the server only obtains the hot search index of the candidate keyword in one search engine, the server determines the hot search index as the total hot search number of the candidate keyword.

[0097] For example, in response to the number of hot search indexes of the candidate keyword being greater than 1, the weighted sum of at least two hot search indexes is determined as the total hot search number of the candidate keyword.

[0098] If the server obtains the hot search indexes of the candidate keyword in at least two search engines, the server first normalizes the multiple hot search indexes, then performs weighted summation, and takes the result of the weighted summation as the total hot search number of the candidate keyword. For example, because different search engines calculate hot search indexes in different ways and different search engines provide hot search indexes of different orders of magnitude, the server divides the obtained hot search index by the order of magnitude coefficient corresponding to the search engine and multiplies it by the weight coefficient corresponding to the search engine to obtain a weighted result, and adds the weighted results of the candidate keyword in each search engine to obtain the final total hot search number. For example, for the candidate keyword "keyword 1", the server obtains a first hot search index 100000 of the candidate keyword in search engine A, a second hot search index 200 in search engine B, and a third hot search index 50000 in search engine C. Among them, the order of magnitude coefficient of search engine A is 10000, and the weight coefficient is 2; the order of magnitude coefficient of search engine B is 100, and the weight coefficient is 1; the order of magnitude coefficient of search engine C is 10000, and the weight coefficient is 1. Then the total hot search number of the candidate keyword "keyword 1" = (100000 / 10000)*2 + (200 / 100)*1 + (50000 / 10000)*1 = 20 + 2 + 5 = 27.

[0099] Step 303, obtaining the competitive website of the target website from at least one search engine according to the candidate keyword, the competitive website being the website before the target website in the search result obtained by searching the candidate keyword.

[0100] A competing website is a link in search results of a search candidate keyword that is located before the target website. The competing websites are: searching the search candidate keyword in a search engine to obtain search results, if the target website is ranked first in the search results, then the target website has no competing websites in the search results; if the target website is not ranked first, then the websites ranked before the target website in the search results are all competing websites of the target website. For example, in order to improve the calculation efficiency, the server will only obtain the first five websites ranked before the target website as the competing websites. For example, the search results obtained by searching the search candidate keyword "keyword 1" are in the following order: the first website, the second website, the third website, the fourth website, the fifth website, the sixth website, and the target website, and the server determines the first website to the fifth website as the competing websites.

[0101] For example, the same search candidate keyword can obtain different search results in different search engines, and therefore the competing websites are different. For example, for the same search candidate keyword, the search results obtained by searching the same search engine on different terminals are also different. Therefore, the server obtains the competing websites from at least one search engine on at least one terminal according to the search candidate keyword. For example, the specific search engines included in the at least one search engine can be determined according to the user's needs. That is, the user wants to optimize the ranking of the target website in which search engines, and the at least one search engine includes which search engines.

[0102] Step 304: calculating the competition score of the competing website according to the website weight of the competing website in the at least one search engine, wherein the website weight is a numerical value assigned by the search engine to the website to describe the authority of the website.

[0103] For example, the competition score of the competing website is equal to the website weight of the competing website in the search engine, or is equal to the weighted sum of the website weights of the competing website in at least two search engines. For example, according to the search candidate keyword "keyword 1", the server obtains the competing websites from search engine A, and the competing websites from search engine B do not include the first website, and the competing websites from search engine C include the first website, and the competition score of the first website is equal to the sum of the website weight of the first website in search engine A multiplied by the weight coefficient of search engine A and the website weight of the first website in search engine C multiplied by the weight coefficient of search engine C.

[0104] For example, the search engines in which the target website needs to perform SEO include search engine A, search engine D, search engine B, and search engine C, and the calculation formula of the competition score of a competing website is as follows:

[0105] Competition Score = (PCBD + MBD) * a + (PC36 + M36) * b + SM * c + SG * d

[0106] Here, PCBD represents the website's weight on search engine A's PC (Personal Computer) platform, MBD represents its weight on search engine A's mobile (Mobile Internet Device) platform, PC36 represents its weight on search engine D's PC platform, M36 represents its weight on search engine D's mobile platform, SM represents its weight on search engine B, and SG represents its weight on search engine C. 'a' is the weight coefficient for search engine A, 'b' is the weight coefficient for search engine D, 'c' is the weight coefficient for search engine B, and 'd' is the weight coefficient for search engine C. For example, the weight coefficients are determined based on the importance of each search engine. For instance, if search engine A is frequently used by users, its weight coefficient 'a' can be set to a larger value. For example, a=2, b=2, c=1, d=1.

[0107] For example, a server can obtain the website ranking of competing websites in various search engines by searching for relevant information. The websites used for searching can be at least one of Baidu Index or webmaster tools.

[0108] For example, such as Figure 6 The diagram illustrates a flowchart for calculating the competition score of competing websites. The server retrieves the top five search results preceding the target website from the search engine based on the input candidate keywords, obtaining the URLs of these five links. It then determines the target website's ranking within the search results. If the target website ranks first, the competition score of these five links is 0 according to Formula 1 (605). If the target website does not rank first, the server queries the website weights of the links preceding it and calculates the competition score of the competing websites according to Formula 2 (606). Formula 2 (606) is as follows:

[0109] Competition Score = (PCBD + MBD) * 2 + PC36 + M36) * 1 + SM * 1 + SG * 1

[0110] For example, if the maximum website weight is 9, then the maximum value of formula 2, 606, is 72. Assuming that the five competing websites of the target website all have the maximum competition score of 72, then the maximum total number of competitors for the candidate keywords is 5 * 72 = 360.

[0111] Step 305: Calculate the total number of competing candidate keywords based on the competition scores of at least one competing website.

[0112] Exemplarily, the total competition number of the candidate keyword is equal to the sum of the competition scores of at least one competing website of the candidate keyword. That is, if the candidate keyword has only one competing website, the total competition number is equal to the competition score of the competing website; if the candidate keyword includes multiple competing websites, the total competition number is equal to the sum of the competition scores of the multiple competing websites.

[0113] Step 2024-1, determining the target keyword from the candidate keywords according to at least one of the total search number and the total competition number.

[0114] Exemplarily, the server can sort the candidate keywords according to at least one of the total search number and the competition score of the candidate keywords, and determine the target keyword according to the sorting result.

[0115] Exemplarily, two exemplary embodiments of screening the target keyword from the candidate keywords according to the total search number and the total competition number are given. As shown in Figure 7 , step 2024-1 further includes step 2024-11 and step 2024-12. Or, as shown in Figure 8 , step 2024-1 further includes step 2024-11 and step 2024-13.

[0116] Step 2024-11, calculating the weighted difference between the total search number and the total competition number of the candidate keyword.

[0117] Exemplarily, the server calculates the value score of each candidate keyword according to the value score calculation formula. The value score calculation formula is:

[0118] Value score = (searchScore / 100000*x - competeScore / 360*y)*100

[0119] Wherein, searchScore is the total search number; competeScore is the total competition number; x is the weight coefficient of the total search number, and the default value is 1; y is the weight coefficient of the total competition number, and the default value is 1.

[0120] Step 2024-12, determining at least one candidate keyword with the highest weighted difference as the target keyword.

[0121] Exemplarily, one way of screening the target keyword is that the server determines several candidate keywords with the highest value scores as the target keywords. For example, as shown in Table 1, the server calculates the value scores of the candidate keywords according to the total search number and the total competition number, and determines “keyword A”, “keyword B” and “keyword C” ranking the top three in the value scores as the target keywords.

[0122] Table 1

[0123]

[0124] Step 2024-13, determine the page keyword and at least one long tail keyword with the highest weight difference as the target keyword.

[0125] For example, another way to screen the target keyword is that the server first determines the page keyword in the candidate keyword as the target keyword, or / and determines the expected keyword in the candidate keyword as the target keyword according to the type of the candidate keyword. Then, the server determines the long tail keyword ranked in the top ten as the target keyword according to the value point sorting of the candidate keyword.

[0126] After the server obtains the target keyword of the target website, the server optimizes the website information of the target website according to the target keyword. For example, steps 2031 and 2032 show two methods of optimizing the target website according to the target keyword.

[0127] Step 2031, set the meta tag of the target website according to the target keyword, and the meta tag is used to describe the attribute of the target website.

[0128] For example, the server can set at least one target keyword as the meta tag of the target website. The meta tag is used to describe the attribute of an HTML web page document, such as author, date and time, web page description, keyword, page refresh, etc.

[0129] For example, the server sets the meta tag of the target website as: <meta name="keywords" content="第一目标关键词, 第二目标关键词, 第三目标关键词,…"> .

[0130] Step 2032, generate a target sentence according to the target keyword, and the target sentence is used to add the target keyword to the website content of the target website.

[0131] For example, the server can use NLP technology to automatically make a sentence according to the target keyword, and add the made sentence to the website content of the target website. For example, after adding the target sentence to the website content of the target website, the content of the target website is associated with the target keyword. When the search engine needs to extract the keyword of the target website, the search engine is more likely to take the target keyword as the keyword of the target website, thereby improving the ranking of the target website in the related search results.

[0132] For example, a method of making a sentence by using a target keyword is shown in Figure 9 Step 2032 further includes steps 2032-1 to 2032-5.

[0133] Step 2032-1, obtain a hot sentence containing the target keyword according to the target keyword.

[0134] The server crawls sentences containing the target keyword from the Internet according to the target keyword. For example, the server can obtain hot sentences containing the target keyword from hot news, hot Q&A, and hot forums.

[0135] Step 2032-2, the hot sentences are processed by word segmentation to obtain at least one hot word.

[0136] For example, the server can use a word segmentation algorithm as shown in Figure 4 to perform word segmentation processing on the hot sentences to obtain at least one hot word.

[0137] Step 2032-3, the extension words of the hot words are obtained according to natural language processing.

[0138] The server retrieves the extension words matching the hot words according to the NLP technology. For example, the extension words of "Qixi" include Qixi Festival, Valentine's Day, Spring Festival, Chinese New Year's Eve, Mid-Autumn Festival, Winter Solstice, and Dragon Boat Festival.

[0139] Step 2032-4, the extension words are reorganized into replacement word groups according to the word connection rules and the parts of speech of the extension words.

[0140] For example, the server reorganizes the extension words into replacement word groups according to the parts of speech of the extension words and the word connection rules. The word connection rules recombine the extension words into replacement word groups by adding conjunctions according to the syntax and the relationship between the extension words.

[0141] For example, "Game A" and "Game B" are two games developed by the same development company, and then according to their sibling relationship, the replacement word group of "Game A" can be obtained as "Game A developed by Game B Development Company".

[0142] Step 2032-5, at least one hot word in the hot sentence is replaced by the replacement word group to generate a target sentence.

[0143] For example, the server replaces the hot words in the hot sentence with the replacement word group to obtain the target sentence.

[0144] For example, as shown in Figure 10 , an example embodiment of generating a target sentence according to a target keyword is given. The server obtains hot sentences containing the target keyword from hot news 607 according to the input target keyword, then performs word segmentation on the hot sentences to obtain hot words according to the word segmentation algorithm 608, and then obtains related words (extension words) of the hot words using NLP technology, and generates a target sentence according to the local configuration. The local configuration includes a word connection configuration data table 609, which stores word connection rules.

[0145] In step 2033, the target sentence is added to the website content of the target website.

[0146] For example, the server adds the generated target sentence to the website content of the target website, so that the website content of the target website is related to the target keyword, without making the search engine think that the target website is simply stacking keywords.

[0147] To sum up, the method provided by the embodiment can automatically obtain the page information of the target website by the server, extract the page keywords from the page information, and crawl long-tail keywords from the search engine according to the page keywords, so as to obtain multiple keywords of the target website. Then, the server screens the target keyword from the keywords according to the importance, search popularity and competitive advantage of the multiple keywords, and adjusts the website information of the target website according to the target keyword, so as to complete the SEO process of the target website. The method can automatically perform SEO on the target website by the server, improve the exposure rate of the target website, and reduce the human cost of SEO. Moreover, the method can adjust the website information of the target website in real time according to the real-time popularity of the keywords, and improve the timeliness of SEO.

[0148] The method provided by the embodiment can obtain keywords related to the page keywords by obtaining long-tail keywords from the search engine according to the page keywords after obtaining the page keywords of the target website, so as to complete the expansion of the page keywords. The expansion of the keywords is not dependent on artificial experience, and the long-tail keywords obtained from the search engine are obtained according to the real-time search information of the search engine, so as to improve the timeliness of SEO.

[0149] The method provided by the embodiment can obtain long-tail keywords of the page keywords by obtaining related search content pushed by the search engine according to the page keywords, and then obtaining the long-tail keywords according to the long-tail keywords. The search recommendation function of the search engine is used to obtain long-tail keywords with high relevance to the page keywords, so as to improve the relevance of the long-tail keywords and the page keywords. Moreover, the related search content pushed by the search engine is updated in real time according to the real-time situation of user search keywords in the search engine, so that the long-tail keywords are real-time hot keywords, and the timeliness of SEO is improved.

[0150] The method provided by the embodiment can obtain the page keywords of the target website by decomposing the page information of the target website into multiple word groups by the server, so that the server can automatically obtain the page keywords of the target website.

[0151] The method provided in the embodiment makes the segmentation result of the page information more accurate by setting a local dictionary and storing unsegmentable word groups, such as proper nouns or user-defined nouns, in the local dictionary. Since keywords are mostly nouns, the server selects nouns with a word number greater than 1 from the segmentation result of the page information by setting a segmentation screening condition, so that the page keywords are more accurate.

[0152] The method provided in the embodiment reduces the number of page keywords and improves the accuracy of the page keywords by selecting page keywords from the segmentation result according to the search heat or appearance frequency of the word groups in the segmentation result after obtaining the segmentation result of the page information by using a segmentation algorithm.

[0153] The method provided in the embodiment selects target keywords from candidate keywords according to the total search heat or total competition of the candidate keywords in the search engine, so that the target keywords are hot search words in the search engine, or the target keywords are search keywords in which the target website has a competitive advantage, thereby improving the exposure rate of the target website after search engine optimization and obtaining a better search engine optimization result.

[0154] The method provided in the embodiment acquires the total search heat of the candidate keywords according to the search heat index of the candidate keywords in at least one search engine, so that the target keywords selected according to the total search heat are keywords that users of multiple search engines will search for, and the target keywords selected according to the total search heat are applicable to multiple search engines, thereby expanding the applicable range of the target website after search engine optimization.

[0155] The method provided in the embodiment determines the competition degree of the target website for the current candidate keywords according to the website weight of the competing website in the search engine in the search result of the candidate keywords, and determines the candidate keywords in which the target website has a competitive advantage as target keywords, so that the target website can improve the ranking of the target website in the search result and improve the exposure rate of the target website after search engine optimization.

[0156] The method provided in the embodiment can optimize the target website by directly setting the target keywords as the meta tag of the target website, so that the search engine refers to the meta tag of the target website when determining the search result of a search keyword, thereby improving the ranking of the target website in the search result and improving the exposure rate of the target website when a user searches for the target keyword.

[0157] The method provided by the embodiment can also be that a sentence is formed using the target keyword, the sentence is added to the website content of the target website, and the relevance between the website content of the target website and the target keyword is improved. Therefore, the search engine can take the target keyword as the keyword of the target website, and the exposure rate of the target website in the search result related to the target keyword is improved.

[0158] The method provided by the embodiment also provides a method for generating a hot sentence according to a target keyword. The server acquires a hot sentence related to the target keyword, for example, a hot news, a hot question and answer, and the like. The NLP technology is used to replace the words in the hot sentence with extended words, so as to generate a new sentence. The generated sentence can be close to the current search heat, and the exposure rate of the target website and the timeliness of the optimization result are improved.

[0159] Exemplarily, the application also provides an example embodiment in which a user can specify a desired keyword. Figure 9 A flowchart of a search engine optimization method provided by an example embodiment of the application is shown. The method is applied to a server and is used for Figure 2 Unlike the example embodiment shown, the method further includes:

[0160] In step 401, a desired keyword of a target website is acquired. The desired keyword is a keyword specified by a user.

[0161] Exemplarily, the user can specify a desired keyword while providing a target website URL. The desired keyword is a keyword desired by the user to be used for SEO.

[0162] In step 402, the desired keyword is determined as a target keyword.

[0163] Exemplarily, the server directly determines the desired keyword as a target keyword, and uses the desired keyword to adjust the website information of the target website.

[0164] In summary, in the method provided by the embodiment, a user can also specify a desired keyword for a target website, and directly uses the desired keyword as a target keyword to perform search engine optimization on the target website, so that the optimization result meets the user's expectation.

[0165] Exemplarily, as shown in Figure 11 Using the search engine optimization method provided by the application, the search information in the search engine 507 can be used to automatically optimize the target website 508, so that the ranking of the target website in the search result is improved, and the exposure rate of the target website is improved.

[0166] Exemplarily, as shown in Figure 12As shown, the search engine optimization method provided by the present application can have a product on the terminal side as shown. There is a URL input box 509 on the product interface. The user can input the URL of the target website in the URL input box 509. The URL of the target website is sent to the server by clicking the immediate analysis control 510. The server acquires page information, recommends keywords, and recommends hot search content according to the URL of the target website, generates an analysis result page 511, and the analysis result page includes the target keywords 512 recommended by the server for the target website, the page keywords 513 extracted by the server, the expected keywords 514 (associated words) input by the user, the long-tail keywords 515 obtained by the server according to the page keywords, and the hot content and target sentence 516 recommended by the server according to the target keywords.

[0167] As an example, Figure 13 As shown, the present application provides a flowchart of a search engine optimization method. The method is applied to a server, and the method includes:

[0168] The server obtains the URL of the target website and the expected keyword input by the user 610, uses a segmentation algorithm 611 to segment the page information (page data) of the target website to obtain N keywords 612, then selects the top five keywords with the highest frequency of occurrence in the N keywords as high-frequency keywords 615, uses a hotness query interface 613 to query the hot search index of each keyword, and selects the top five keywords with the highest hot search index as high-heat keywords 614. The server determines the high-frequency keywords, the high-heat keywords, and the expected keyword as page keywords 616, and then queries whether the long tail keywords of the page keywords are stored in the database 617. If the long tail keywords of the page keywords are stored in the database 617, the server directly segments the long tail keywords 620 according to the segmentation algorithm 618 to obtain long tail keywords. If the database does not store the long tail keywords related to the page keywords, the server places the page keywords in a to-be-queried list 619, and the server crawls the long tail keywords 620 from the search engine according to the keywords stored in the to-be-queried list. After the server obtains the long tail keywords, the server determines the long tail keywords and the page keywords as candidate keywords, obtains the hotness index 621 of the candidate keywords and the weight information 622 (website weight) of the competitive websites, calculates the total hot search number, the total competition number, and the value score of the candidate keywords according to the hotness index 621 and the weight information 622, and selects a value keyword 623 (target keyword) from the candidate keywords according to the value score. The server modifies the page meta information 624 of the target website according to the value keyword 623. The server can also input the value keyword 623 into a sentence generation algorithm 625 to obtain hot word sentence generation content 626 (target sentence). The server can also obtain news content 627 according to the value keyword 623, obtain hot word news content 628 (target sentence) according to NLP technology, and obtain question and answer content 630 related to the value keyword 623 from a question and answer content obtaining interface. The server adds the question and answer content 630 as the target sentence to the website content of the target website. For example, the server can also directly use the long tail keywords 620 as the question and answer content 630.

[0169] In summary, the method provided in the embodiment shows an example of applying the search engine optimization method provided in the application to an actual product. The user can use the product to perform search engine optimization on a target website, so that the user can perform SEO on the target website at any time, save labor costs, improve SEO timeliness, and improve the SEO optimization effect.

[0170] The following is a device embodiment of the application. For details not described in detail in the device embodiment, reference can be made to the corresponding description in the above method embodiments, which will not be described herein.

[0171] Figure 14An exemplary embodiment of the present application provides a search engine optimization device. The device can be implemented by software, hardware or a combination of both, and can be a server or a part of a server. The device comprises:

[0172] An obtaining module 701 is configured to obtain a page keyword of a target website, the page keyword being extracted from page information of the target website by natural language processing (NLP);

[0173] A determining module 702 is configured to determine a target keyword according to search information related to the page keyword in a search engine;

[0174] An optimization module 703 is configured to adjust website information of the target website according to the target keyword, the website information being used by the search engine to determine a search keyword of the target website.

[0175] In an optional embodiment, the device further comprises:

[0176] The obtaining module 701 is further configured to obtain a long-tail keyword from the search engine according to the page keyword, the long-tail keyword being related search content recommended by the search engine according to the page keyword;

[0177] A word segmentation module 704 is configured to perform word segmentation on the long-tail keyword to obtain a long-tail keyword;

[0178] The determining module 702 is further configured to determine the page keyword and the long-tail keyword as a candidate keyword;

[0179] The determining module 702 is further configured to determine the target keyword from the candidate keyword according to a keyword screening condition.

[0180] In an optional embodiment, the search information comprises at least one of a total number of hot searches and a total number of competitions of the candidate keyword, the total number of hot searches being used to describe a frequency of being searched, and the total number of competitions being used to describe a competitiveness in a search result of the target website;

[0181] The determining module 702 is further configured to determine the target keyword from the candidate keyword according to at least one of the total number of hot searches and the total number of competitions.

[0182] In an optional embodiment, the device further comprises:

[0183] The obtaining module 701 is further configured to obtain a hot search index of the candidate keyword in at least one search engine, the hot search index being used to describe a frequency of being searched within a period of time.

[0184] The computing module 705 is configured to calculate the total number of hot searches of the candidate keyword according to at least one of the hot search indexes.

[0185] In an optional embodiment, the determining module 702 is further configured to, in response to the number of the hot search indexes of the candidate keyword being equal to 1, determine the hot search index as the total number of hot searches of the candidate keyword.

[0186] Or,

[0187] The determining module 702 is further configured to, in response to the number of the hot search indexes of the candidate keyword being greater than 1, determine a weighted sum of at least two of the hot search indexes as the total number of hot searches of the candidate keyword.

[0188] In an optional embodiment, the apparatus further comprises:

[0189] The obtaining module 701 is further configured to obtain, from at least one of the search engines, a competing website of the target website according to the candidate keyword, the competing website being a website located before the target website in a search result obtained by searching the candidate keyword.

[0190] The computing module 705 is configured to calculate a competition score of the competing website according to a website weight of the competing website in at least one of the search engines, the website weight being a numerical value assigned by the search engine to a website to describe authority of the website.

[0191] The computing module 705 is further configured to calculate the total number of competitions of the candidate keyword according to the competition scores of at least one of the competing websites.

[0192] In an optional embodiment, the apparatus further comprises:

[0193] The computing module 705 is configured to calculate a weighted difference between the total number of hot searches and the total number of competitions of the candidate keyword.

[0194] The determining module 702 is further configured to determine at least one of the candidate keywords with the highest weighted difference as the target keyword.

[0195] Or,

[0196] The computing module 705 is configured to calculate a weighted difference between the total number of hot searches and the total number of competitions of the candidate keyword.

[0197] The determining module 702 is further configured to determine the page keyword and at least one of the long-tail keywords with the highest weighted difference as the target keyword.

[0198] In an optional embodiment, the acquisition module 701 is further configured to acquire a desired keyword of the target website, the desired keyword being a keyword specified by a user.

[0199] The determination module 702 is further configured to determine the desired keyword as the target keyword.

[0200] In an optional embodiment, the optimization module 703 is further configured to set a meta tag of the target website according to the target keyword, the meta tag being used to describe attributes of the target website.

[0201] In an optional embodiment, the apparatus further includes:

[0202] The generation module 706 is configured to generate a target sentence according to the target keyword, the target sentence being used to add the target keyword to the website content of the target website.

[0203] The optimization module 703 is further configured to add the target sentence to the website content of the target website.

[0204] In an optional embodiment, the apparatus further includes:

[0205] The acquisition module 701 is further configured to acquire a hot sentence containing the target keyword according to the target keyword.

[0206] The word segmentation module 704 is configured to perform word segmentation processing on the hot sentence to obtain at least one hot word.

[0207] The acquisition module 701 is further configured to acquire an extended word of the hot word according to the natural language processing.

[0208] The recombination module 707 is configured to recombine the extended word according to a word connection rule and a part of speech of the extended word to obtain a replacement word group.

[0209] The generation module 706 is further configured to replace at least one hot word in the hot sentence with the replacement word group to generate the target sentence.

[0210] Figure 15is a structural schematic diagram of a server provided by an embodiment of the present application. Specifically, the server 1800 includes a central processing unit (CPU) 1801, a system memory 1804 including a random access memory (RAM) 1802 and a read-only memory (ROM) 1803, and a system bus 1805 connecting the system memory 1804 and the central processing unit 1801. The server 1800 also includes a basic input / output (I / O) system 1806 to help transfer information between various devices in the computer, and a mass storage device 1807 for storing an operating system 1813, application programs 1814, and other program modules 1815.

[0211] The basic input / output system 1806 includes a display 1808 for displaying information and an input device 1809 such as a mouse, keyboard, or the like for inputting information by a user. The display 1808 and the input device 1809 are both connected to the central processing unit 1801 through an input / output controller 1810 connected to the system bus 1805. The basic input / output system 1806 can also include the input / output controller 1810 for receiving and processing input from a keyboard, mouse, or electronic stylus, or other devices. Similarly, the input / output controller 1810 also provides output to a display screen, printer, or other types of output devices.

[0212] The mass storage device 1807 is connected to the central processing unit 1801 through a mass storage controller (not shown) connected to the system bus 1805. The mass storage device 1807 and its associated computer-readable media provide non-volatile storage for the server 1800. That is, the mass storage device 1807 can include a computer-readable medium (not shown) such as a hard disk or a compact disc read-only memory (CD-ROM) drive.

[0213] Without loss of generality, the computer readable medium can include computer storage media and communication media. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other solid state memory technology, CD-ROM, digital versatile disks (DVD), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices. Of course, computer storage media does not limit to the above-mentioned several kinds. The system memory 1804 and the mass storage device 1807 mentioned above can be collectively referred to as a memory.

[0214] According to various embodiments of the present application, the server 1800 can also run on a remote computer connected to the network through a network such as the Internet. That is, the server 1800 can be connected to the network 1812 through the network interface unit 1811 connected to the system bus 1805, or can be connected to other types of networks or remote computer systems (not shown) using the network interface unit 1811.

[0215] The present application also provides a computer device, comprising a processor and a memory, and the memory stores at least one instruction, at least one program, a code set or an instruction set, which is loaded and executed by the processor to implement the search engine optimization method provided by the above-mentioned method embodiments.

[0216] The present application also provides a computer readable storage medium, which stores at least one instruction, at least one program, a code set or an instruction set, which is loaded and executed by the processor to implement the search engine optimization method provided by the above-mentioned method embodiments.

[0217] It should be understood that "multiple" mentioned herein refers to two or more. "And / or", which describes the association between the associated objects, means that there can be three relationships, for example, A and / or B can mean that there are three cases of A alone, A and B together, and B alone. The character " / " generally represents that the associated objects before and after are a "or" relationship.

[0218] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or a program instructing relevant hardware to complete, and the program can be stored in a computer readable storage medium. The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0219] The above is only an optional embodiment of the present application, and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A search engine optimization method, characterized in that, The method includes: Obtain the page keywords of the target website, wherein the page keywords are keywords extracted from the page information of the target website through Natural Language Processing (NLP); The target keywords are determined based on search information related to the page keywords in the search engine; the target keywords are keywords used to optimize the target website. Adjusting the website information of the target website based on the target keywords includes: obtaining hot sentences containing the target keywords; segmenting the hot sentences to obtain at least one hot word; obtaining extended words of the hot words based on natural language processing; recombining the extended words according to word connection rules and the parts of speech of the extended words to obtain replacement phrases; replacing at least one hot word in the hot sentences with the replacement phrases to obtain the target sentence; adding the target sentence to the website content of the target website; and using the website information by the search engine to determine the search keywords of the target website. The step of determining target keywords based on search information related to the page keywords in a search engine includes: Long-tail keywords are obtained from the search engine based on the page keywords. The long-tail keywords are related search content recommended by the search engine based on the page keywords. The related search content is updated in real time based on the real-time search results of the search keywords in the search engine, so that the long-tail keywords are real-time hot words. The long-tail keywords are obtained by segmenting the long-tail keywords; The page keywords and the long-tail keywords were identified as candidate keywords; The target keyword is determined from the candidate keywords based on the keyword filtering criteria.

2. The method according to claim 1, characterized in that, The search information includes at least one of the total number of trending searches and the total number of competing searches for the candidate keywords. The total number of trending searches describes the frequency with which the candidate keywords are searched, and the total number of competing searches describes the competitiveness of the target website in the search results for the candidate keywords. The step of determining the target keyword from the candidate keywords based on keyword filtering criteria includes: The target keyword is determined from the candidate keywords based on at least one of the total number of trending searches and the total number of competing searches.

3. The method according to claim 2, characterized in that, The method further includes: Obtain the search popularity index of the candidate keyword in at least one of the search engines, wherein the search popularity index is used to describe the frequency with which the candidate keyword is searched over a period of time; The total number of hot searches for the candidate keywords is calculated based on at least one of the hot search indices.

4. The method according to claim 3, characterized in that, The step of calculating the total number of hot searches for the candidate keywords based on at least one of the hot search indices includes: In response to the number of hot search indexes for the candidate keyword being equal to 1, the hot search index is determined as the total number of hot searches for the candidate keyword; or, In response to the fact that the number of hot search indices for the candidate keyword is greater than 1, the weighted sum of at least two hot search indices is determined as the total number of hot searches for the candidate keyword.

5. The method according to claim 2, characterized in that, The method further includes: Based on the candidate keywords, obtain the target website's competing websites from at least one of the search engines, wherein the competing websites are those that appear before the target website in the search results obtained by searching the candidate keywords; The competition score of the competing website is calculated based on the website weight of the competing website in at least one of the search engines, where the website weight is a numerical value assigned by the search engine to the website to describe the authority of the website; The total number of competitors for the candidate keywords is calculated based on the competition scores of at least one of the competing websites.

6. The method according to claim 2, characterized in that, The step of determining the target keyword from the candidate keywords based on at least one of the total number of trending searches and the total number of competing searches includes: Calculate the weighted difference between the total number of trending searches and the total number of competing searches for the candidate keywords; The candidate keyword with the highest weighted difference is determined as the target keyword; or, Calculate the weighted difference between the total number of trending searches and the total number of competing searches for the candidate keywords; The target keyword is determined by the page keyword and at least one of the long-tail keywords with the highest weighted difference.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Obtain the desired keywords for the target website, where the desired keywords are keywords specified by the user; The desired keywords are identified as the target keywords.

8. The method according to any one of claims 1 to 6, characterized in that, The step of adjusting the website information of the target website according to the target keywords includes: The target website's meta tags are set according to the target keywords, and the meta tags are used to describe the attributes of the target website.

9. A search engine optimization device, characterized in that, The device includes: The acquisition module is used to acquire page keywords of the target website, wherein the page keywords are keywords extracted from the page information of the target website through Natural Language Processing (NLP). The determination module is used to determine target keywords based on search information related to the page keywords in the search engine; the target keywords are keywords used to optimize the target website; An optimization module is used to adjust the website information of the target website according to the target keywords, and the website information is used by the search engine to determine the search keywords of the target website; The device further includes: The acquisition module is further configured to acquire long-tail keywords from the search engine based on the page keywords. The long-tail keywords are related search content recommended by the search engine based on the page keywords. The related search content is updated in real time based on the real-time situation of search keywords in the search engine, so that the long-tail keywords are real-time hot words. The word segmentation module is used to segment the long-tail words to obtain long-tail keywords; The determining module is further configured to determine the page keywords and the long-tail keywords as candidate keywords; The determining module is further configured to determine the target keyword from the candidate keywords based on the keyword filtering conditions; The device further includes: The generation module is used to generate target sentences based on the target keywords; The optimization module is also used to add the target sentence to the website content of the target website; The acquisition module is further configured to acquire hot sentences containing the target keyword based on the target keyword; The word segmentation module is used to segment the hot sentences to obtain at least one hot word. The acquisition module is further configured to acquire extended words of the hot words based on the natural language processing. The recombination module is used to recombine the extended words according to word connection rules and the part of speech of the extended words to obtain replacement word groups; The generation module is further configured to replace at least one of the hot words in the hot sentence with the replacement word group to obtain the target sentence.

10. The apparatus according to claim 9, characterized in that, The search information includes at least one of the total number of trending searches and the total number of competing searches for the candidate keywords. The total number of trending searches describes the frequency with which the candidate keywords are searched, and the total number of competing searches describes the competitiveness of the target website in the search results for the candidate keywords. The determining module is further configured to determine the target keyword from the candidate keywords based on at least one of the total number of hot searches and the total number of competing searches.

11. The apparatus according to claim 10, characterized in that, The device further includes: The acquisition module is further configured to acquire the hot search index of the candidate keyword in at least one of the search engines, wherein the hot search index is used to describe the frequency with which the candidate keyword is searched over a period of time. A calculation module is used to calculate the total number of hot searches for the candidate keywords based on at least one of the hot search indices.

12. The apparatus according to claim 11, characterized in that, The determining module is further configured to, in response to the number of hot search indices of the candidate keywords being equal to 1, determine the hot search index as the total number of hot searches for the candidate keywords; or, The determining module is further configured to, in response to the number of hot search indices of the candidate keyword being greater than 1, determine the weighted sum of at least two hot search indices as the total number of hot searches for the candidate keyword.

13. The apparatus according to claim 10, characterized in that, The device further includes: The acquisition module is further configured to acquire, based on the candidate keywords, competing websites of the target website from at least one of the search engines, wherein the competing websites are those websites that appear before the target website in the search results obtained by searching the candidate keywords; The calculation module is used to calculate the competition score of the competing website based on the website weight of the competing website in at least one of the search engines, wherein the website weight is a numerical value assigned by the search engine to the website to describe the authority of the website; The calculation module is further configured to calculate the total number of competitors for the candidate keywords based on the competition scores of at least one of the competing websites.

14. The apparatus according to claim 10, characterized in that, The device further includes: The calculation module is used to calculate the weighted difference between the total number of trending searches and the total number of competing keywords for the candidate keywords; The determining module is further configured to determine at least one of the candidate keywords with the highest weighted difference as the target keyword; or, The calculation module is used to calculate the weighted difference between the total number of trending searches and the total number of competing keywords for the candidate keywords; The determining module is further configured to determine at least one of the long-tail keywords with the highest weighted difference between the page keywords and the long-tail keywords as the target keywords.

15. The apparatus according to any one of claims 9 to 14, characterized in that, The acquisition module is further configured to acquire the expected keywords of the target website, wherein the expected keywords are keywords specified by the user; The determining module is further configured to determine the expected keyword as the target keyword.

16. The apparatus according to any one of claims 9 to 14, characterized in that, The optimization module is further configured to set meta tags for the target website based on the target keywords, wherein the meta tags are used to describe the attributes of the target website.

17. A computer device, the computer device comprising: A processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set, or an instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the search engine optimization method as described in any one of claims 1 to 8.

18. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or instruction set is loaded and executed by a processor to implement the search engine optimization method as described in any one of claims 1 to 8.

Images