CN114663164A - E-commerce site promotion configuration method and its device, equipment, medium and product - Google Patents

Abstract

The application discloses a method for popularizing and configuring E-commerce sites, and a device, equipment, medium and product thereof, wherein the method comprises the following steps: constructing a search text according to the product words and the attribute words of the commodity titles in the commodity display page; acquiring statistical data matched with a search text, wherein the statistical data comprises a plurality of candidate long-tail words and historical search statistical indexes thereof; determining a unique candidate long tail word semantically matched with the commodity title as a target long tail word according to the statistical index; and configuring the target long tail word into a page title of the commodity display page. According to the method and the device, the long-tail keywords can be determined based on the commodity titles corresponding to the commodity display pages and are automatically configured to be the page titles of the commodity display pages, search engine keyword optimization is achieved, the long-tail effect is utilized, the effect that the search ranking is advanced is achieved through the large number of long-tail keywords of the single commodity display page, and the effect of improving the drainage capacity of the search engine of the whole independent site of the e-commerce platform is achieved.

Description

E-commerce site promotion configuration method and its device, equipment, medium and product

technical field

The present application relates to the field of e-commerce information technology, and in particular, to a method for promoting and configuring an e-commerce site and its corresponding apparatus, computer equipment, computer-readable storage medium, and computer program product.

Background technique

With the rapid development of cross-border e-commerce and e-commerce websites in the form of independent stations, it is becoming more and more difficult for products to be searched by search engines and ranked first. become increasingly important.

Web page title is a highly generalized language for the content provided by a web page, and it is one of the main basis for search engine retrieval. Designing a good page title can greatly improve the ranking of the page in the search results. Corresponding to the e-commerce website, it is to design a multi-dimensional and scientific SEO page title based on search volume, competition and product content, which can greatly improve the probability of the product being retrieved, thereby increasing the exposure rate and conversion rate.

The current SEO page title generation of the product page mainly relies on the seller's staff, which is set by using various query tools and experience, which is very inefficient and the effect is difficult to guarantee.

SUMMARY OF THE INVENTION

The primary purpose of the present application is to solve at least one of the above problems and provide an e-commerce site promotion configuration method and its corresponding apparatus, computer equipment, computer-readable storage medium, and computer program product.

In order to meet the various purposes of the application, the application adopts the following technical solutions:

An e-commerce site promotion configuration method provided to meet one of the purposes of this application includes the following steps:

Construct the search text according to the product word and attribute word of the product title in the product display page;

Obtaining statistical data matching the search text, the statistical data includes a plurality of candidate long-tail words and historical search statistical indicators thereof;

Determining, according to the statistical index, the only candidate long-tail word that semantically matches the product title as the target long-tail word;

The target long-tail keyword is configured into the page title of the product display page.

In some further embodiments, the search text is constructed according to the product word and attribute word of the product title in the product display page, including the following steps:

Get the product title that has been entered in the product display page;

Perform word segmentation and part-of-speech recognition on the product title, and obtain a word segmentation set composed of multiple word segmentations, which includes not only word segmentations belonging to product words, but also word segmentations belonging to attribute words;

The keyword extraction is performed on the word segmentation set in association with the commodity title, and the search weight corresponding to each word segmentation is determined, and the search weight represents the potential search value of the corresponding word segmentation;

Determine the unique product word with the highest search weight and a plurality of attribute words in a predetermined number, and concatenate them into a search text.

In some further embodiments, the statistical data matching the search text is obtained, and the statistical data includes a plurality of candidate long-tail words and their historical search statistical indicators, including the following steps:

Invoke the search interface to obtain statistical data of candidate long-tail words that match the search text, the statistical data includes keywords and statistical indicators based on the historical search behavior data of a large number of users, and the statistical indicators include corresponding The average search volume of keywords that are long-tail keywords and their competition for adoption by different websites.

In some further embodiments, determining, according to the statistical index, the only candidate long-tail word that semantically matches the product title as the target long-tail word, includes the following steps:

Perform data cleaning on the statistical data according to the statistical indicators to obtain valid candidate long-tail words;

Quantitatively determine the semantic similarity between each valid candidate long-tail word and the product title;

The average search volume is used as the matching weight of the semantic similarity, and the comprehensive score of each valid candidate long-tail word is calculated;

Determine the effective candidate long-tail words with the highest comprehensive score as the target long-tail words.

In some specific embodiments, data cleaning is performed on the statistical data according to the statistical indicators to obtain valid candidate long-tail words, including any one or any of the following steps:

Delete the candidate long-tail words whose number of words in the statistical data is less than the preset value;

Delete the candidate long-tail words within the preset time range in the statistical data;

Delete the candidate long-tail words whose competition degree is higher than the preset level in the statistical data;

The candidate long-tail words whose average search volume is higher than the preset threshold in the statistical data are deleted.

In some specific embodiments, quantitatively determining the semantic similarity between each of the effective candidate long-tail words and the product title includes the following steps:

Encoding to obtain effective candidate long-tail words and the embedding vector of the product title;

Use a pre-trained text feature extraction model to extract the high-level semantic information of the effective candidate long-tail words and the embedding vector of the commodity title, and obtain their respective semantic feature vectors;

Using a preset data distance algorithm, the data distance between the semantic feature vector of the product title and the tone feature vector of each valid candidate long-tail word is calculated as the corresponding semantic similarity.

In some further embodiments, configuring the target long-tail word into the page title of the product display page includes the following steps:

displaying a search optimization page corresponding to the product display page to display the page title input box;

Configuring the target long-tail word as the content data of the page title input box;

In response to the user submitting the instruction, the product display page and the search optimization page are published.

An e-commerce site promotion configuration device provided in accordance with one of the purposes of this application includes a search construction module, an index acquisition module, a target determination module, and a search optimization module, wherein the search construction module is used for displaying according to commodities The product word and attribute word of the product title in the page construct the search text; the indicator acquisition module is used to acquire statistical data matching the search text, the statistical data includes a plurality of candidate long-tail words and their historical search statistical indicators; The target determination module is used to determine the only candidate long-tail word that semantically matches the product title according to the statistical index as the target long-tail word; the search optimization module is used to determine the target long-tail word. The tail word is configured into the page title of the product display page.

In some further embodiments, the search construction module includes: a title acquisition unit, which is used to acquire the commodity title that has been input on the commodity display page; a word segmentation recognition unit is used to perform word segmentation and part-of-speech recognition on the commodity title, and obtain the A word segmentation set composed of multiple word segmentations, which includes both the word segmentation belonging to the product word and the word segmentation belonging to the attribute word; the weight quantization unit is used to associate the product title to perform keyword extraction on the word segmentation set, and determine each word segmentation The corresponding search weight represents the potential search value of its corresponding word segment; the search expression unit is used to determine the unique product word with the highest search weight and a predetermined number of multiple attribute words, and concatenate them into a search text.

In some further embodiments, the indicator obtaining module includes: calling a search interface to obtain statistical data of candidate long-tail words matching the search text, the statistical data including statistical data based on historical search behavior data statistics of a large number of users. The obtained keywords and their statistical indicators, the statistical indicators include the average search volume of the corresponding keywords and the degree of competition adopted by different websites, and the keywords are long-tail keywords.

In some further embodiments, the target determination module includes: a data cleaning unit for performing data cleaning on the statistical data according to the statistical indicators to obtain valid candidate long-tail words; a similarity quantification unit for quantitative determination The semantic similarity between each valid candidate long-tail word and the product title; the scoring quantification unit is used to use the average search volume as the matching weight of the semantic similarity, and calculate the comprehensive score of each valid candidate long-tail word; target selection The unit is used to determine the effective candidate long-tail words with the highest comprehensive score as the target long-tail words.

In some specific embodiments, the data cleaning unit includes any one or any of the following sub-modules: a word-count cleaning sub-module, which is used to remove candidate long-tail words whose word count is less than a preset value in the statistical data delete; a time cleaning sub-module for deleting candidate long-tail words within a preset time range in the statistical data; a competition cleaning sub-module for removing candidates whose competitiveness is higher than a preset level in the statistical data Deletion of long-tail words; a search volume cleaning sub-module, which is used to delete candidate long-tail words whose average search volume is higher than a preset threshold in the statistical data.

In some specific embodiments, the similarity quantization unit includes: a vector encoding subunit, used for encoding and obtaining the embedding vector of valid candidate long-tail words and the commodity title; a semantic extraction subunit, used for using pre-trained The text feature extraction model extracts the high-level semantic information of the effective candidate long-tail words and the embedding vectors of the product titles to obtain their respective semantic feature vectors; the similarity calculation subunit is used to calculate the The data distance between the semantic feature vector of the product title and the tone feature vector of each valid candidate long-tail word is used as the corresponding semantic similarity.

In some further embodiments, the search optimization module includes: a page display unit for displaying a search optimization page corresponding to the product display page to display a page title input box; an automatic editing unit for displaying the page title input box; The target long-tail word is configured as the content data of the page title input box; the optimization publishing unit is configured to respond to the user submitting an instruction and publish the product display page and the search optimization page.

A computer device provided in accordance with one of the purposes of the present application includes a central processing unit and a memory, the central processing unit is used to call and run a computer program stored in the memory to execute the e-commerce site promotion described in the present application Steps to configure the method.

A computer-readable storage medium provided for another purpose of this application, which stores a computer program implemented according to the described e-commerce site promotion configuration method in the form of computer-readable instructions, and the computer program is called by a computer At run time, the steps included in the method are performed.

A computer program product provided in accordance with another object of the present application includes a computer program/instruction, when the computer program/instruction is executed by a processor, the steps of the method described in any one of the embodiments of the present application are implemented.

Compared with the prior art, the technical solution of the present application includes at least the following technical advantages:

First, the present application constructs a search text for the product words and attribute words in the product title used on the product display page, retrieves candidate long-tail words and their statistical indicators from the search text, and then determines the optimal candidate long-tail word according to the statistical indicators. The tail word is used as the target long-tail word, and the target long-tail word is used as the page title of the product display page, so as to realize the search engine optimization of the product display page in a personalized way by product, and serve the product display of the e-commerce independent station. Page production, without manual participation, improves the efficiency of configuring the information required for massive product display pages.

Secondly, the long-tail keywords in this application, as the name suggests, are keywords with long-tail effect, also known as long-tail keywords. Although their search volume is relatively small, they have the advantage of being highly targeted. When there are a large number of products, and each product corresponds to a product display page, configuring the preferred long-tail keywords that match the product title as the page title of the product display page will help improve the search engine performance of each product display page. The probability of ranking top in the search results, thereby increasing the overall traffic of the entire independent site of the e-commerce platform.

In addition, when determining target long-tail words for the page title of the product display page, this application not only considers the semantic matching relationship between the candidate long-tail words and the product title, but also considers the historical search statistical indicators of the candidate long-tail words themselves. The indicator itself is the information about the popularity of long-tail words in the historical process of being searched, which helps to optimize the candidate long-tail words. The long-tail words determined based on this are combined with product titles After being used as a reference, it is not only highly semantically consistent with the product title, but also more effective.

Description of drawings

The above and/or additional aspects and advantages of the present application will become apparent and readily understood from the following description of embodiments taken in conjunction with the accompanying drawings, wherein:

FIG. 1 is a schematic flowchart of a typical embodiment of an e-commerce site promotion configuration method of the present application;

2 is a schematic flowchart of a process of constructing a search text according to a commodity title in an embodiment of the application;

Fig. 3 is a graphical user interface exemplarily provided by the present application, and the product display page and the search engine optimization page are displayed on both sides separately;

4 is a schematic flowchart of a specific process for determining a target long-tail word in an embodiment of the application;

5 is a schematic flowchart of a process of performing data cleaning on statistical data in an embodiment of the present application;

6 is a schematic flowchart of a process of calculating the semantic similarity between a commodity title and a valid candidate long-tail word in an embodiment of the application;

FIG. 7 is a schematic flowchart of configuring a page title to complete the publishing of a product display page in an embodiment of the application;

Fig. 8 is the principle block diagram of the e-commerce site promotion configuration device of the present application;

FIG. 9 is a schematic structural diagram of a computer device used in this application.

Detailed ways

The following describes in detail the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, but not to be construed as a limitation on the present application.

It will be understood by those skilled in the art that the singular forms "a", "an", "the" and "the" as used herein can include the plural forms as well, unless expressly stated otherwise. It should be further understood that the word "comprising" used in the specification of this application refers to the presence of stated features, integers, steps, operations, elements and/or components, but does not preclude the presence or addition of one or more other features, Integers, steps, operations, elements, components and/or groups thereof. It will be understood that when we refer to an element as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Furthermore, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combination of one or more of the associated listed items.

It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It should also be understood that terms, such as those defined in a general dictionary, should be understood to have meanings consistent with their meanings in the context of the prior art and, unless specifically defined as herein, should not be interpreted in idealistic or overly formal meaning to explain.

Those skilled in the art can understand that the "client", "terminal" and "terminal device" used herein include both a wireless signal receiver device that only has a wireless signal receiver without transmission capability, and a wireless signal receiver device. A device with receive and transmit hardware that has receive and transmit hardware capable of two-way communication over a two-way communication link. Such devices may include: cellular or other communication devices such as personal computers, tablet computers, which have a single-line display or a multi-line display or a cellular or other communication device without a multi-line display; PCS (Personal Communications Service, Personal Communications System) ), which can combine voice, data processing, fax and/or data communication capabilities; PDA (Personal Digital Assistant), which can include radio frequency receivers, pagers, Internet/Intranet access, web browsers, notepads , calendar and/or GPS (Global Positioning System) receivers; conventional laptop and/or palmtop computers or other devices having and/or conventional laptop and/or palmtop radio frequency receivers computer or other device. As used herein, "client", "terminal", "terminal device" may be portable, transportable, mounted in a vehicle (air, marine and/or land), or adapted and/or configured to be locally operate, and/or in distributed form, operate at any other location on Earth and/or space. The "client", "terminal" and "terminal device" used here can also be a communication terminal, an Internet terminal, and a music/video playing terminal, such as a PDA, MID (Mobile Internet Device) and/or A mobile phone with music/video playback function, or a smart TV, set-top box, etc.

The hardware referred to by names such as "server", "client" and "service node" in this application is essentially an electronic device with the equivalent capability of a personal computer, which is a central processing unit (including an arithmetic unit and a controller). ), memory, input device and output device and other necessary components disclosed by the Von Neumann principle, the computer program is stored in its memory, and the central processing unit transfers the program stored in the external memory into the memory to run, and executes the program. The instructions in the interface interact with input and output devices to complete specific functions.

It should be pointed out that the concept of "server" referred to in this application can also be extended to the case of server clusters in the same way. According to the principles of network deployment understood by those skilled in the art, the servers should be logically divided. In physical space, these servers can be independent from each other but can be called through interfaces, or can be integrated into a physical server. A computer or a group of computers. Those skilled in the art should understand this modification, but should not limit the implementation of the network deployment manner of the present application.

Unless explicitly specified, one or more technical features of the present application can be deployed on the server and remotely invoked by the client to obtain the online service interface provided by the server to implement access, or can be directly deployed and run on the client to implement access.

The neural network model cited or possibly cited in this application, unless specified in plain text, can either be deployed on a remote server and invoked remotely on the client, or deployed on a client with competent device capabilities to directly invoke, in some embodiments , when it runs on the client, its corresponding intelligence can be obtained through transfer learning, so as to reduce the requirements on the client hardware running resources and avoid excessively occupying the client hardware running resources.

All kinds of data involved in this application, unless specified in plain text, can be stored in a server remotely or in a local terminal device, as long as it is suitable for being called by the technical solution of this application.

Those skilled in the art should know that: although the various methods of the present application are described based on the same concept to show commonality with each other, unless otherwise specified, these methods can be independently executed. Similarly, for the various embodiments disclosed in this application, they are all proposed based on the same inventive concept. Therefore, the concepts expressed in the same way, and the concepts that are appropriately transformed for convenience even though the concept expressions are different, should be regarded as equivalent. understand.

In the various embodiments to be disclosed in this application, unless the mutually exclusive relationship between each other is clearly indicated, the related technical features involved in the various embodiments can be cross-combined to flexibly construct new embodiments, as long as the combination does not deviate from the present invention. The creative spirit of the application can meet the needs in the prior art or solve a certain aspect of the deficiencies in the prior art. Variations on this will be known to those skilled in the art.

A method for promoting and configuring an e-commerce site of the present application can be programmed as a computer program product and implemented by being deployed in a client or server to run. For example, in the application scenario of an e-commerce platform including live e-commerce The deployment is implemented in the server, whereby the method can be executed by man-machine interaction with the process of the computer program product through a graphical user interface by accessing the interface opened after the computer program product runs.

Please refer to FIG. 1, the e-commerce site promotion configuration method of the present application, in its typical embodiment, includes the following steps:

Step S1100: Construct a search text according to the product word and attribute word of the product title in the product display page:

When the independent site of the e-commerce platform needs to publish a certain product, it needs to enter the product information, usually including but not limited to the product title, product summary, product description and other information, and then use these product information to generate the product display page corresponding to the product. End user invokes browse. In order to facilitate the improvement of the probability of products being searched, it is also allowed to configure search engine optimization parameters together, so that the corresponding product display pages are easier to be included and displayed by search engines.

When the content data of the corresponding commodity title is input in the commodity title input box of the commodity display page, the commodity title can be obtained. Accordingly, various traditional word segmentation methods can be used to segment the commodity title and determine its corresponding part of speech, and correspondingly obtain a word segmentation set. The participles in the participle set are usually part of nouns and part of adjectives and/or adverbs in terms of part of speech. The nouns generally contain product words that indicate the content of the product, while adjectives and/or adverbs are usually used to describe the attributes of a certain aspect of the product , so it is also called attribute word. Thus, the product word and attribute word in the product title are also determined.

In order to obtain candidate long-tail words according to the product title, each product word and all attribute words can be arbitrarily spliced to form one or more search texts, which can be submitted to the search interface for search to obtain the candidate long-tail words. suffix. When constructing the search text, the product words and attribute words can also be filtered and selected, so as to reduce the number of search texts and improve the operation speed. Similarly, a unique splicing rule can also be set for the splicing method of the product word and the attribute word, so that the product word and the attribute word can be uniquely spliced according to the splicing rule.

Step S1200: Obtain statistical data matching the search text, where the statistical data includes multiple candidate long-tail words and their historical search statistical indicators:

According to the search text, any one of a variety of ways can be used to obtain the corresponding candidate long-tail words and the statistical indicators formed by the historical searches of the candidate long-tail words.

In one way, the candidate long-tail words and their corresponding statistical indicators can be directly obtained through the search interface provided by the search engine, and the invocation interface is implemented as a preset long-tail word according to the search text. Part of the semantically matching long-tail words are searched in the ranking table as the candidate long-tail words, and corresponding statistical indicators of the candidate long-tail words are provided. Generally speaking, the search engine is a target search engine that expects to search for the product display page.

In another way, the long-tail word ranking table can be obtained by the e-commerce platform's own statistics or other traditional data retrieval methods, and then the search interface provided by the e-commerce platform can be invoked to obtain the customized long-tail word ranking table. The candidate long-tail words and their corresponding statistical indicators.

The long-tail words, that is, long-tail keywords, generally refer to search strings with a small average search volume per unit time and containing multiple words. Long-tail words have a long-tail effect. Although the average search volume per unit is small, they have the advantage of accurate hits. When a user of a search engine inputs a long-tail word, the page with the long-tail word as the title of the page can obtain a top priority ranking effect. Since there are often a large number of product display pages in each independent site of an e-commerce platform, by configuring long-tail keywords in a large number of product display pages as page titles required for search engine optimization, a single page can be accurately searched and ranked. The first advantage will trigger the scale effect, thereby increasing the user traffic of the entire independent site, and achieving the effect of the whole site promotion of the independent site.

The statistical indicators generally include the average search volume and competition degree of each long-tail keyword. Generally speaking, each search engine will analyze the user's search expression by itself, and count the frequency of user use of the keywords in the search expression and the frequency of the corresponding keywords used by website pages. From the website side, you can use the periodicity of user usage frequency, for example, to conduct statistics in units of months, and count the average search volume of keywords used by users; Calculate the competition of keywords used by the page. The average search volume can be numerical data, and the competition degree can be grade data such as high, medium, and low options {1, 2, 3}, depending on the quantification habits of each search engine for related data. . The average search volume and competition of each keyword constitute the corresponding statistical indicators of each keyword. In other embodiments, the statistical indicators may further include other information such as the corresponding usage time of the long-tail words. By organizing each keyword and its average search volume and competition into mapping relationship data, a keyword ranking table can be formed, in which keywords containing more than a preset number of words, such as more than two words, are regarded as long tails. The long-tail word ranking table can be constructed by filtering out the keyword ranking table.

It can be seen that the long-tail word ranking table actually stores statistical data based on the long-tail words corresponding to the historical search behavior data of a large number of users, and the statistical data includes each long-tail word and its corresponding Statistical indicators, the statistical indicators include the average search volume of the corresponding long-tail words and the degree of competition adopted by different websites.

According to the principle that the search engine constructs the long-tail word ranking table, the e-commerce platform can also obtain the corresponding data and construct the long-tail word ranking table by itself, or directly call the long-tail word ranking released by the search engine and store it in Local for calling.

When the long-tail words matching the search text are obtained from the long-tail word ranking table as candidate long-tail words, the statistical indicators corresponding to the candidate long-tail words are also obtained. Wherein, the search text and the long-tail words can be matched based on rules, including fuzzy matching or exact matching, or semantic-based matching, etc. Those skilled in the art can flexibly apply the principles disclosed herein. Thus, the matched candidate long-tail words and their corresponding statistical indicators constitute a subset of candidate long-tail words.

Step S1300, according to the statistical index, determine the only candidate long-tail word that semantically matches the commodity title as the target long-tail word:

Since each product display page only needs to use one page title, it is necessary to determine a candidate long-tail word from the subset of candidate long-tail words determined in the previous step as the target long-tail word. To this end, you can refer to the corresponding statistical indicators of each candidate long-tail word, including the average search volume and/or competition, and the degree of semantic matching between the candidate long-tail word and the product title, for each candidate long-tail word. Make optimization.

For example, the average search volume, the semantic similarity between the candidate long-tail words and the product title can be used as the primary sorting field and the secondary sorting field, respectively, to perform multi-field reverse sorting, and then determine the candidate long tail that ranks first in the reverse sorting. words as target long-tail keywords to use as page titles.

For another example, the degree of competition, the semantic similarity between the candidate long-tail words and the product title can be used as the primary sorting field and the secondary sorting field, respectively, to perform multi-field reverse sorting, and then determine that the degree of competition is low and the similarity is the highest. as the target long-tail keywords for the page title.

For another example, the average search volume, competition degree, and the semantic similarity between the candidate long-tail words and the product title can be combined for multi-field comprehensive sorting, and it is determined that the average search volume is high, the competition degree is low, and the similarity degree is relatively high. Therefore, the first candidate long-tail word is comprehensively used as the target long-tail word for the page title.

In addition, other methods can also be flexibly used, such as semantic judgment based on a deep learning model pre-trained to a convergent state, to determine that it is highly similar to the product title, and its average search volume is high, and/or The only candidate long-tail word with low competition is used as the target long-tail word.

It can be seen that, with the help of the statistical indicators, a unique target long-tail word can be determined for the product title in various ways. One or more related characteristics in the statistical indicators, so as to realize the optimization of candidate long-tail words.

Step S1400, configure the target long-tail word into the page title of the product display page:

After the target long-tail word is determined, it can be configured as the page title of the product display page. After the product display page is published, each search engine, according to its own implementation logic, The product display page is searched and included, and then the target long-tail keyword is used to search in the search engine, which can more accurately hit the product display page, thereby achieving the purpose of page promotion.

Through the typical embodiment of the present application and its corresponding multiple modified embodiments, it can be seen that, compared with the prior art, the technical solution of the present application at least includes the following technical advantages:

First, the present application constructs a search text for the product words and attribute words in the product title used on the product display page, retrieves candidate long-tail words and their statistical indicators from the search text, and then determines the optimal candidate long-tail word according to the statistical indicators. The tail word is used as the target long-tail word, and the target long-tail word is used as the page title of the product display page, so as to realize the search engine optimization of the product display page in a personalized manner, and serve the product display of the e-commerce independent station. Page production, without manual participation, improves the efficiency of configuring information required for massive product display pages.

Secondly, the long-tail keywords in this application, as the name suggests, are keywords with long-tail effect, also known as long-tail keywords. Although their search volume is relatively small, they have the advantage of being highly targeted. When there are a large number of products, and each product corresponds to a product display page, configuring the preferred long-tail keywords that match the product title as the page title of the product display page will help improve the search engine performance of each product display page. The probability of ranking top in the search results, thereby increasing the overall traffic of the entire independent site of the e-commerce platform.

In addition, when determining target long-tail words for the page title of the product display page, this application not only considers the semantic matching relationship between the candidate long-tail words and the product title, but also considers the historical search statistical indicators of the candidate long-tail words themselves. The indicator itself is the information about the popularity of long-tail words in the historical process of being searched, which helps to optimize the candidate long-tail words. The long-tail words determined based on this are combined with product titles After being used as a reference, it is not only highly semantically consistent with the product title, but also more effective.

Referring to FIG. 2, in some further embodiments, the step S1100, constructing a search text according to the product word and attribute word of the product title in the product display page, includes the following steps:

Step S1110: Obtain the title of the commodity that has been input on the commodity display page:

As shown in Figure 3, when the user edits the product display page, a search engine optimization area is displayed. The user enters the set product title in the product title input box on the left side of the figure, and the text data of the product title is obtained in the background. .

Step S1120: Perform word segmentation and part-of-speech recognition on the product title, and obtain a word segmentation set composed of multiple word segmentations, which includes both the word segmentations belonging to product words and the word segmentations belonging to attribute words:

In order to realize the word segmentation of the commodity title, any traditional word segmentation algorithm based on statistics such as N-Gram can be used to segment the commodity title to obtain a corresponding word segmentation set. Concentration usually includes multiple product words and multiple attribute words. Product words are usually used to describe or refer to commodity names, and are mostly nouns; attribute words are usually used to describe commodity attributes, mostly adjectives or adverbs.

In order to realize the part-of-speech analysis of each word segment in the word segment set, a neural network model pre-trained to a convergent state can be used for implementation, and the recommended model can be based on a basic network architecture such as LSTM+CRF and BERT+CRF. Those skilled in the art can select the model flexibly. Such neural network models can be fine-tuned and trained to a convergent state by those skilled in the art on the basis of pre-training, so that they can learn to perform word segmentation and part-of-speech analysis according to the embedding vector of the word segmentation set of the input product title. Thereby, the product word and the attribute word in the product title can be divided and determined.

Step S1130: Extract keywords from the word segment set in association with the product title, and determine the search weight corresponding to each word segment, where the search weight represents the potential search value of its corresponding word segment:

As mentioned above, there may be multiple product words and attribute words in the word segmentation set, but the syntax required to construct the search text generally follows the usage habits of natural language, so it needs to be simplified as much as possible. , a single representative product word combined with multiple representative attribute words can be used to construct the search text. To this end, it is necessary to quantitatively determine the search weight of the product word and the attribute word, that is, to determine the word segmentation set. The potential search value corresponding to each participle.

In one embodiment, the TF-IDF algorithm may be used to determine the TF-IDF value of each word segment in the word segmentation set as the search weight. In another embodiment, the TextRank algorithm may also be used to construct a word segmentation map for each word segmentation, The graph determines the corresponding weight of each word segment as the search weight. In addition, those skilled in the art can also flexibly adopt other alternative implementations according to the principles disclosed herein, as long as the potential search value of each word segment can be quantified.

Step S1140: Determine the unique product word with the highest search weight and a plurality of attribute words in a predetermined number, and construct the search text by splicing:

According to the search weight, each word segment in the word segment set is reversely sorted, and the product words and attribute words are arranged in an orderly manner according to their corresponding search weights. Based on this, the unique product word with the highest search weight can be determined as the The core product word of the product title, at the same time, according to a preset number, such as 3, select a plurality of the attribute words in the corresponding number at the top of the ranking, and compare the core product word with the selected attributes. Words are spliced, such as orderly splicing according to preset rules, so that attribute words are in the front and core product words are in the back, so as to construct the search text. Of course, the splicing sequence can also be adjusted to obtain multiple search texts, which can be flexibly implemented by those skilled in the art.

In this embodiment, by performing word segmentation and part-of-speech recognition on the product title, and then calculating the search weight of each word segment representing the potential search value, and selecting the core product word and a plurality of preferred attribute words according to the search weight, according to the core product word and multiple preferred attribute words to construct a search text, the search text has higher potential search value, and the preliminary screening of candidate long-tail words can improve the matching accuracy.

Referring to FIG. 4 , in some further embodiments, the step S1300 , determining the only candidate long-tail word that semantically matches the commodity title according to the statistical index as the target long-tail word, includes the following steps:

Step S1310, performing data cleaning on the statistical data according to the statistical index to obtain valid candidate long-tail words:

As mentioned earlier, the statistics include statistical indicators, the statistical indicators include the average search volume and/or competition, and may even contain other information. Therefore, the statistics can be based on the average search volume and/or the candidate long-tail keywords in the statistical data. Or the constraints of competition degree, data cleaning is performed on the statistical indicators, so as to filter out some invalid candidate long-tail words, and the remaining part can be confirmed as valid long-tail words. The constraints can be flexibly set by those skilled in the art according to the principles disclosed herein.

Step S1320, quantitatively determine the semantic similarity between each valid candidate long-tail word and the product title:

In order to examine the semantic closeness between each valid candidate long-tail word and the product title, the semantic similarity can be calculated between the two. When calculating the semantic similarity, the deep semantic information of the valid candidate long-tail words and the product title can be determined respectively, and on this basis, the data distance algorithm is used to determine the data between each candidate long-tail word and the product title. The distance can be expressed as a value corresponding to the semantic similarity through normalization.

Step S1330, taking the average search volume as the matching weight of the semantic similarity, and calculating the comprehensive score of each valid candidate long-tail word:

In order to facilitate the selection of each valid candidate long-tail word, the comprehensive score of each valid candidate long-tail word can be determined according to its statistical index and its similarity with the product title. The exemplary formula is as follows:

final_score=ln(2.001-(search_score/max_search_score))*sim_score

Among them, search_score is the average search volume corresponding to the current valid candidate long-tail words, and max_search_score is the largest average search volume among all valid candidate long-tail words. The constant 2.001 minus the logarithm of the ratio of the two is similar to the corresponding semantics Multiply the degrees to achieve weight matching, and ensure that the data is more stable, distinguish different differences, and quantitatively determine the corresponding comprehensive score final_score.

It should be understood that the above formula is only an example to illustrate the principle of using the average search volume of valid candidate long-tail words to weight their semantic similarity with the product title to achieve quantification. Those skilled in the art can flexibly construct the formula according to the principles disclosed here. , as long as the same purpose is achieved, which shall be regarded as not breaking the scope embodied by the inventive spirit of the present application.

After each candidate long-tail word has its corresponding comprehensive score determined, the comprehensive score comprehensively reflects the average search popularity of the candidate long-tail word and its closeness to the product title, and the pros and cons of the effective candidate long-tail words Unified to the same dimension, therefore, each valid candidate long-tail word can be selected according to the size of the comprehensive score.

Step S1340, determine the effective candidate long-tail word with the highest comprehensive score as the target long-tail word:

In order to obtain the best effective candidate long-tail words as the target long-tail words, each effective candidate long-tail word can be reversely sorted according to the comprehensive score, and then the effective candidate long-tail words ranked first, that is, the comprehensive score. The highest valid candidate long-tail word can be determined as the target long-tail word required for generating the page title for this application.

In this embodiment, after data cleaning is performed on the statistical data matched according to the search text to obtain valid candidate long-tail words, the closeness of the valid candidate long-tail words to the product title and its own statistical indicators are used to reflect the average search The average search volume of the popularity, the corresponding comprehensive score is determined by the preset formula, and the quantification of the pros and cons of each valid candidate long-tail word is realized, and then the valid candidate long-tail word with the highest comprehensive score is selected as the page title. Target long-tail words to achieve preferential matching of valid candidate long-tail words.

The target long-tail words determined in this embodiment are not only semantically closer to the product title, but also have relatively good access popularity, because the effective candidate long-tail words themselves are the result of data cleaning for statistical data , itself filters some extreme cases. Therefore, the determined target long-tail keywords are comprehensive and optimal, which can ensure that after the product display page is released, the advantages of long-tail keyword search can be obtained, thereby helping to increase the traffic of the whole site.

Referring to FIG. 5 , in some of the specific embodiments, in order to achieve high-quality data cleaning effect and filter out effective candidate long-tail words, in step S1310 , perform data cleaning on the statistical data according to the statistical index to obtain effective candidate long-tail words. suffix, including any one or more of the following steps:

Step S1311, delete the candidate long-tail words whose number of words in the statistical data is less than the preset value:

Long-tail words, as the name suggests, are generally sentences with more than 2 or 3 words. For example, long-tail words can be set to contain no less than 3 words. Filter to remove candidate long-tail words with less than 3 words, thus constraining the definition range of long-tail words.

Step S1312, delete the candidate long-tail words within the preset time range in the statistical data:

Sometimes, the statistical data obtained by the search interface includes candidate long-tail words generated within a long period of time, but some products are time-sensitive. Then, according to the preset time range, the candidate long-tail words are filtered, and the candidate long-tail words that fall within the preset time range are deleted from the statistical data, so as to realize the data of the expired candidate long-tail words. cleaning.

Step S1313, delete the candidate long-tail words whose competition degree is higher than the preset level in the statistical data:

The competition degree is generally characterized in the form of a corresponding degree of "high, medium, and low", and of course, it can also be represented in a numerical form, depending on the specific situation. In any case, due to the high competition of a candidate long-tail word, it means that a large number of websites and pages use the candidate long-tail word. If such a candidate long-tail word is still used, it will easily lead to the product display page even if it is searched. It is also difficult to rank high, so this feature can be used to remove candidate long-tail words with a higher level of competition from the statistical data to moderately avoid competition.

Step S1314, delete the candidate long-tail words whose average search volume is higher than the preset threshold in the statistical data:

If the average search volume of candidate long-tail words is too high, it means that such candidate long-tail words are more popular, and it also means that a large number of websites and pages may use such candidate long-tail words. There is also a problem of competition, even in product display Using such candidate long-tail words in the page, it is also difficult to improve its search ranking. According to this principle, a preset threshold corresponding to the average search volume can be set in advance, and the average search volume of candidate long-tail words higher than the preset threshold can be set. Removed from said stats, moderately avoiding competition.

The various embodiments disclosed herein can be used in any combination by those skilled in the art. For example, all the embodiments corresponding to steps S1311 to S1314 are used in full. In any case, those skilled in the art can flexibly apply the disclosed herein based on different purposes. The various embodiments of the method realize the cleaning of the statistical data matched with the search text, and ensure the validity of the effective candidate long-tail words that are relied upon when the target long-tail words are subsequently determined, thereby ensuring the quality of the final target long-tail words. .

Referring to FIG. 6, in some specific embodiments, step S1320, quantitatively determining the semantic similarity between each of the effective candidate long-tail words and the commodity title, includes the following steps:

Step S1321, coding to obtain the effective candidate long-tail words and the embedding vector of the product title:

In order to calculate the semantic similarity between the valid candidate long-tail words and the product title, for the product title and each valid candidate long-tail word, after conventional word segmentation, convert their respective word segmentation sets according to the vocabulary For the embedding vector, complete the encoding.

Step S1322, using a pre-trained text feature extraction model to extract the high-level semantic information of the effective candidate long-tail words and the embedding vectors of the product titles, and obtain their respective semantic feature vectors:

Furthermore, a text feature extraction model is used to perform representation learning on the embedding vectors of the commodity titles and the effective candidate long-tail words involved in the calculation, extract their deep semantic information, and obtain corresponding semantic feature vectors, that is, sentence vectors. The text feature extraction model can be a pre-trained model, or a model obtained by fine-tuning training by those skilled in the art on the basis of the pre-trained model, as long as it has the corresponding semantic feature vector extracted from the text embedding vector. Can.

The text feature extraction model may be based on any common basic model such as LSTM, Bert, Sentence-Transformer, etc., and can be selected flexibly by those skilled in the art.

Step S1323, using the preset data distance algorithm to calculate the data distance between the semantic feature vector of the commodity title and the tone feature vector of each valid candidate long-tail word as the corresponding semantic similarity:

After determining the product title and the semantic feature vector of each valid candidate long-tail word, a preset data distance algorithm can be used to calculate the similarity between the product title and the respective semantic feature vector of each valid candidate long-tail word. The data distance algorithm can use any traditional calculation data point and the distance between the points, such as the cosine similarity algorithm, the Euclidean distance algorithm, the Min's distance algorithm, the Pearson correlation coefficient algorithm, the Jaccard coefficient algorithm, etc. algorithm.

Taking the cosine similarity algorithm as an example, the corresponding formula is as follows:

where A is the product title, B is a single valid candidate long-tail word, and n is the total number of elements of the semantic feature vector.

After calculating the data distance between the product title and each valid candidate long-tail word by applying the preset data distance algorithm, it can be normalized to the same dimension according to actual needs, so that the higher the value, the semantic similarity. The higher the value is, the numerical value corresponding to the semantic similarity corresponding to each valid candidate long-tail word can be obtained, and then the target long-tail word can be optimized accordingly.

In this embodiment, the semantic similarity between the valid candidate long-tail words and the product title is calculated by means of the deep learning text feature model, and the obtained semantic similarity can better represent the relationship between the valid candidate long-tail words and the product title. According to the semantic closeness, the subsequent selection of effective candidate long-tail words will be made, and the results will be more accurate.

Referring to FIG. 7, in some further embodiments, the step S1400, configuring the target long-tail word into the page title of the product display page, includes the following steps:

Step S1410: Display the search optimization page corresponding to the product display page to display the page title input box:

Please continue to refer to FIG. 3. In the interface shown in FIG. 3, a search optimization page is displayed in advance corresponding to the product display page, which includes a page title input box, and the input box is used to input any one of the above in this application. The target long-tail words determined by the examples.

Step S1420, configuring the target long-tail word as the content data of the page title input box:

After the application obtains the target long-tail word through any of the above embodiments, it can be automatically filled in the page title input box of the search optimization page, and configured as the content data of the page title. The operating user can also make further edits to it, or simply default the automatically generated target long-tail words.

Step S1430, in response to the user submitting the instruction, publish the product display page and the search optimization page:

After the operating user has completely entered the various data in the product display page and the search optimization page, the user can be triggered to submit an instruction by operating the submit control, and the product display page and the search optimization page can be submitted to the background of the independent site to realize When the product display page is published, various data entered in the search optimization page, including the page title, are submitted simultaneously. So far, the publishing process of a product display page is completed.

Each product display page can determine its corresponding page title in this way, so as to use the long-tail effect of keywords to attract traffic to independent e-commerce sites.

This embodiment exemplarily shows the usage scenario of the target long-tail words automatically generated by this application. It can be seen that with the help of the technical solution of this application, independent sites do not need to pay too much attention to search engines when publishing each commodity For the optimization problem, the target long-tail word automatically generated by the application based on the given product title can be used as the page title of the product, which greatly improves the processing efficiency of the product release link of the independent site, and ensures that the display pages for a large number of products are automatically displayed accordingly. The generated page title can help increase the overall traffic of the independent site under the action of the long tail effect.

Please refer to FIG. 8 , an e-commerce site promotion and configuration device provided to meet one of the purposes of the present application is a functional embodiment of the e-commerce site promotion and configuration method of the present application. The device includes a search construction module 1100 and an index acquisition module. 1200, the target determination module 1300, and the search optimization module 1400, wherein, the search construction module 1100 is used to construct the search text according to the product words and attribute words of the commodity title in the commodity display page; the indicator acquisition module 1200 is used for Obtaining statistical data matching the search text, the statistical data includes a plurality of candidate long-tail words and their historical search statistical indicators; the target determination module 1300 is configured to determine, according to the statistical indicators, semantically related to the product title. The only candidate long-tail word that matches the above is used as the target long-tail word; the search optimization module 1400 is configured to configure the target long-tail word into the page title of the product display page.

In some further embodiments, the search construction module 1100 includes: a title acquisition unit, which is used to acquire the title of the commodity that has been input on the commodity display page; a word segmentation recognition unit, which is used to perform word segmentation and part-of-speech recognition on the commodity title, A word segmentation set consisting of multiple word segmentations is obtained, which includes both the word segmentation belonging to the product word and the word segmentation belonging to the attribute word; the weight quantization unit is used to associate the product title to perform keyword extraction on the word segmentation set, and determine each The search weight corresponding to the word segment, the search weight represents the potential search value of the corresponding word segment; the search expression unit is used to determine the unique product word with the highest search weight and a predetermined number of multiple attribute words, and spliced to construct a search text.

In some further embodiments, the indicator obtaining module 1200 includes: calling a search interface to obtain statistical data of candidate long-tail words that match the search text, the statistical data including statistics based on historical search behavior data of a large number of users The obtained keywords and their statistical indicators, the statistical indicators include the average search volume of the corresponding keywords and the degree of competition adopted by different websites, and the keywords are long-tail keywords.

In some further embodiments, the target determination module 1300 includes: a data cleaning unit for performing data cleaning on the statistical data according to the statistical indicators to obtain effective candidate long-tail words; a similarity quantification unit for quantifying Determine the semantic similarity between each valid candidate long-tail word and the product title; the scoring quantification unit is used to use the average search volume as the matching weight of the semantic similarity, and calculate the comprehensive score of each valid candidate long-tail word; It is used to determine the effective candidate long-tail word with the highest comprehensive score as the target long-tail word.

In some specific embodiments, the data cleaning unit includes any one or any of the following sub-modules: a word-count cleaning sub-module, which is used to remove candidate long-tail words whose word count is less than a preset value in the statistical data delete; a time cleaning sub-module for deleting candidate long-tail words within a preset time range in the statistical data; a competition cleaning sub-module for removing candidates whose competitiveness is higher than a preset level in the statistical data Deletion of long-tail words; a search volume cleaning sub-module for deleting candidate long-tail words whose average search volume in the statistical data is higher than a preset threshold.

In some specific embodiments, the similarity quantization unit includes: a vector encoding subunit, used for encoding and obtaining the embedding vector of valid candidate long-tail words and the commodity title; a semantic extraction subunit, used for using pre-trained The text feature extraction model extracts the high-level semantic information of the effective candidate long-tail words and the embedding vectors of the product titles to obtain their respective semantic feature vectors; the similarity calculation subunit is used to calculate the The data distance between the semantic feature vector of the product title and the tone feature vector of each valid candidate long-tail word is used as the corresponding semantic similarity.

In some further embodiments, the search optimization module 1400 includes: a page display unit for displaying a search optimization page corresponding to the product display page to display the page title input box; an automatic editing unit for The target long-tail word is configured as the content data of the page title input box; the optimization publishing unit is used for publishing the product display page and the search optimization page in response to the user submitting an instruction.

To solve the above technical problems, the embodiments of the present application also provide computer equipment. As shown in FIG. 9 , a schematic diagram of the internal structure of the computer equipment. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected by a system bus. Wherein, the computer-readable storage medium of the computer device stores an operating system, a database and computer-readable instructions, and the database may store a sequence of control information. When the computer-readable instructions are executed by the processor, the processor can be made to implement a E-commerce site promotion configuration method. The processor of the computer device is used to provide computing and control capabilities and support the operation of the entire computer device. Computer-readable instructions may be stored in the memory of the computer device, and when the computer-readable instructions are executed by the processor, the processor may execute the e-commerce site promotion configuration method of the present application. The network interface of the computer equipment is used for communication with the terminal connection. Those skilled in the art can understand that the structure shown in FIG. 9 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In this embodiment, the processor is used to execute the specific functions of each module and its sub-modules in FIG. 8 , and the memory stores program codes and various types of data required to execute the above-mentioned modules or sub-modules. The network interface is used for data transmission between user terminals or servers. The memory in this embodiment stores the program codes and data required to execute all modules/sub-modules in the e-commerce site promotion and configuration device of the present application, and the server can call the server's program codes and data to execute the functions of all sub-modules.

The present application further provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the e-commerce site promotion configuration of any embodiment of the present application. steps of the method.

The present application also provides a computer program product, including computer programs/instructions, when the computer program/instructions are executed by one or more processors, to implement the steps of the method described in any embodiment of the present application.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments of the present application can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it may include the flow of the embodiments of the above-mentioned methods. The aforementioned storage medium may be a computer-readable storage medium such as a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM).

To sum up, the present application can determine long-tail keywords based on the product titles of the products corresponding to the product display pages, and automatically configure them as the page titles of the product display pages, so as to achieve search engine keyword optimization, using the long-tail effect, through massive The long-tail keywords of a single product display page play a top search ranking effect, and achieve the effect of improving the search engine drainage capacity of the independent site of the e-commerce platform.

Those skilled in the art can understand that various operations, methods, steps, measures, and solutions in the process discussed in this application may be alternated, modified, combined or deleted. Further, other steps, measures, and solutions in the various operations, methods, and processes that have been discussed in this application may also be alternated, modified, rearranged, decomposed, combined, or deleted. Further, steps, measures and solutions in the prior art with various operations, methods, and processes disclosed in this application may also be alternated, modified, rearranged, decomposed, combined or deleted.

The above are only part of the embodiments of the present application. It should be pointed out that for those skilled in the art, without departing from the principles of the present application, several improvements and modifications can also be made. It should be regarded as the protection scope of this application.

Claims (10)

1. an electric business site promotion configuration method, is characterized in that, comprises the steps: Construct the search text according to the product word and attribute word of the product title in the product display page; Obtaining statistical data matching the search text, the statistical data includes a plurality of candidate long-tail words and historical search statistical indicators thereof; Determining, according to the statistical index, the only candidate long-tail word that semantically matches the product title as a target long-tail word; The target long-tail keyword is configured into the page title of the product display page. 2. The e-commerce site promotion configuration method according to claim 1, wherein the search text is constructed according to the product word and the attribute word of the commodity title in the commodity display page, comprising the following steps: Get the product title that has been entered in the product display page; Perform word segmentation and part-of-speech recognition on the product title, and obtain a word segmentation set composed of multiple word segmentations, which includes not only word segmentations belonging to product words, but also word segmentations belonging to attribute words; The keyword extraction is performed on the word segmentation set in association with the commodity title, and the search weight corresponding to each word segmentation is determined, and the search weight represents the potential search value of the corresponding word segmentation; Determine the unique product word with the highest search weight and a plurality of attribute words in a predetermined number, and concatenate them into a search text. 3. The method for promoting and configuring an e-commerce site according to claim 1, wherein statistical data matching the search text is obtained, and the statistical data includes a plurality of candidate long-tail words and historical search statistical indicators thereof, including the following step: Invoke the search interface to obtain statistical data of candidate long-tail words that match the search text, the statistical data includes keywords and statistical indicators based on the historical search behavior data of a large number of users, and the statistical indicators include corresponding The average search volume of keywords that are long-tail keywords and their competition for adoption by different websites. 4 . The method for promoting and configuring an e-commerce site according to claim 3 , wherein determining, according to the statistical index, the only candidate long-tail word that semantically matches the commodity title as the target long-tail word, 4 . Follow the steps below: Perform data cleaning on the statistical data according to the statistical indicators to obtain valid candidate long-tail words; Quantitatively determine the semantic similarity between each valid candidate long-tail word and the product title; The average search volume is used as the matching weight of the semantic similarity, and the comprehensive score of each valid candidate long-tail word is calculated; Determine the effective candidate long-tail words with the highest comprehensive score as the target long-tail words. 5. The method for promoting and configuring an e-commerce site according to claim 4, characterized in that, performing data cleaning on the statistical data according to the statistical index to obtain valid candidate long-tail words, comprising any one or any of the following steps : Delete the candidate long-tail words whose number of words in the statistical data is less than the preset value; Delete the candidate long-tail words within the preset time range in the statistical data; Delete the candidate long-tail words whose competition degree is higher than the preset level in the statistical data; The candidate long-tail words whose average search volume is higher than the preset threshold in the statistical data are deleted. 6. The method for promoting and configuring an e-commerce site according to claim 4, wherein quantitatively determining the semantic similarity between each of the effective candidate long-tail words and the commodity title comprises the following steps: Encoding to obtain effective candidate long-tail words and the embedding vector of the product title; Use a pre-trained text feature extraction model to extract the high-level semantic information of the effective candidate long-tail words and the embedding vector of the commodity title, and obtain their respective semantic feature vectors; Using a preset data distance algorithm, the data distance between the semantic feature vector of the product title and the tone feature vector of each valid candidate long-tail word is calculated as the corresponding semantic similarity. 7. The method for promoting and configuring an e-commerce site according to any one of claims 1 to 6, wherein configuring the target long-tail word into the page title of the product display page comprises the following steps: displaying a search optimization page corresponding to the product display page to display the page title input box; Configuring the target long-tail word as the content data of the page title input box; In response to the user submitting the instruction, the product display page and the search optimization page are published. 8. An e-commerce site promotion configuration device, characterized in that, comprising: The search construction module is used to construct the search text according to the product word and attribute word of the product title in the product display page; an indicator acquisition module, used for acquiring statistical data matching the search text, the statistical data including a plurality of candidate long-tail words and their historical search statistical indicators; A target determination module, configured to determine, according to the statistical index, the only candidate long-tail word that semantically matches the commodity title as a target long-tail word; A search optimization module, configured to configure the target long-tail keyword into the page title of the product display page. 9. A computer device comprising a central processing unit and a memory, wherein the central processing unit is used to call and run a computer program stored in the memory to execute the computer program according to any one of claims 1 to 7 steps of the method. 10. A computer-readable storage medium, characterized in that it stores a computer program implemented by the method according to any one of claims 1 to 7 in the form of computer-readable instructions, and the computer program is called by a computer At runtime, the steps included in the corresponding method are executed.

Images