CN106815228B - Method and device for selecting class name of search keyword - Google Patents

Abstract

The application discloses a method and a device for selecting class names of search keywords. Wherein, the method comprises the following steps: clustering search keywords of a target website to obtain multiple types of search keywords, wherein the search keywords are keywords adopted when the target website is searched in a site, and the target website divides pages in the site through columns; inquiring a landing page landed when search keywords are searched in a target website, and determining column names of columns where the landing pages corresponding to the search keywords are located; and for each type of search keywords in the multi-type search keywords, selecting a column name from column names of columns where landing pages corresponding to the search keywords contained in each type of search keywords are located, and using the column name as the type name of the search keywords. The method and the device solve the technical problem that the name of the class selected by the existing selecting mode cannot reflect the characteristics of the class.

Description

Method and device for selecting class name for search keywords

technical field

The present application relates to the field of the Internet, and in particular, to a method and device for selecting a class name for a search keyword.

Background technique

In the Internet domain, a website is an important platform for providing information to users. Most websites provide in-site search for users to search for relevant information within the website. By recording the content searched by users, you can understand the information that users are more concerned about and their needs. In order to better understand users' concerns and needs, website operators usually classify users' search keywords on the website, group a series of related search keywords into one category, and define each category. its class name.

However, the existing method of selecting the class name of a search keyword is usually to select the word that is most related to other words of this class within a certain range of a class of search keywords as the class name, and the class name selected in this way is usually It is a word that is related to most words but does not reflect the characteristics of the category. For example, the category selected by the above existing methods in the category of search keywords [real estate, housing, real estate, commercial housing, property, purchase tax] The name will be "acquisition tax", because "acquisition tax" is related to other words, and other words can be substituted for each other because they are synonyms, but there is less connection. However, by analyzing these search keywords, it is obvious that using real estate as a class name will be more effective.

For the above problems, no effective solution has been proposed yet.

SUMMARY OF THE INVENTION

The embodiments of the present application provide a method and device for selecting a class name for a search keyword, so as to at least solve the technical problem that the class name selected by the existing selection method cannot reflect the characteristics of the class in which it belongs.

According to an aspect of the embodiments of the present application, a method for selecting class names of search keywords is provided, including: clustering search keywords of a target website to obtain multiple types of search keywords, wherein the search keywords are The keyword used when the target website is searched on the site, and the target website is divided into pages by columns; query the landing page that the search keyword landed on when the target website is searched on the site, and determine the search The column name of the column where the landing page corresponding to the keyword is located; for each type of search keyword in the multi-type search keywords, from the column where the landing page corresponding to the search keyword contained in each type of search keyword is located Select a column name from Column Name as the class name of this type of search keyword.

Further, select a column name from the column name of the column where the landing page corresponding to the search keyword contained in each category of search keywords is located, and the category name as the category name of the search keyword includes: statistics of each category In the search keywords, the number of occurrences of the column name of the column where the landing page corresponding to the search keyword is located; and for each type of search keyword, the column name with the largest number of occurrences after statistics is selected as the category name of this type of search keyword.

Further, before the search keywords of the target website are clustered to obtain multiple types of search keywords, the method further includes: acquiring historical access data of the target website; analyzing the historical access data to obtain the Describe the search keywords of the target website and their corresponding landing pages.

Further, after analyzing the historical access data to obtain the search keywords of the target website and their corresponding landing pages, the method further includes: establishing a corresponding relationship between the search keywords and the landing pages wherein, querying the landing page that the search keyword landed on when the target website performs in-site search includes: using the search keyword as an index, and using the corresponding relationship to query the landing page corresponding to the search keyword.

Further, clustering the search keywords of the target website to obtain multiple types of search keywords includes: using a K-means clustering algorithm to cluster the search keywords of the target website to obtain the multiple types of search keywords. .

According to another aspect of the embodiments of the present application, a device for selecting class names for search keywords is also provided, including: a clustering unit configured to cluster search keywords of a target website to obtain multiple types of search keywords, Wherein, the search keyword is a keyword used when performing an in-site search on the target website, and the target website is divided into pages in the website by columns; a query unit is used to query the search keyword in the target website. The landing page that is landed in the site search, determine the column name of the column where the landing page corresponding to the search keyword is located; the selection unit is used for each type of search keyword in the multi-type search keywords, from the each type of search keyword. A column name is selected from the column names of the column on which the landing page corresponding to the search keywords contained in a class of search keywords is located, as the class name of the class of search keywords.

Further, the selection unit includes: a statistics module for counting the number of occurrences of the column name of the column where the landing page corresponding to the search keyword is located in each type of search keywords; and a selection module for each type of search keyword. For a type of search keyword, select the column name with the most occurrences after statistics as the category name of this type of search keyword.

Further, the device further includes: an obtaining unit, used for obtaining historical access data of the target website before clustering the search keywords of the target website to obtain multiple types of search keywords; The historical access data is analyzed to obtain the search keywords of the target website and their corresponding landing pages.

Further, the device further includes: an establishment unit, configured to establish the search keyword and the The corresponding relationship of landing pages; wherein, the query unit is specifically configured to use the search keyword as an index, and use the corresponding relationship to query the landing page corresponding to the search keyword.

Further, the clustering unit is specifically configured to use the K-means clustering algorithm to cluster the search keywords of the target website to obtain the multi-category search keywords.

According to the embodiment of the present application, by clustering the search keywords of the target website, multiple types of search keywords are obtained, wherein the search keywords are the keywords used in the in-site search of the target website, and the target website is divided into the website by columns. page, query the landing page where the search keywords land on the target website for on-site search, and determine the column name of the column where the landing page corresponding to the search keywords is located. Select a column name from the column name of the landing page corresponding to the search keyword contained in the search keyword, as the class name of the search keyword, to solve the problem that the class name selected by the existing selection method cannot reflect the category in which it belongs. The technical problem of the characteristics of the selected category name can reflect the characteristics of the category in which the search keyword is located.

Description of drawings

The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The schematic embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the attached image:

1 is a flowchart of a method for selecting a class name for a search keyword according to an embodiment of the present application;

FIG. 2 is a schematic diagram of an apparatus for selecting a class name for a search keyword according to an embodiment of the present application.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only The embodiments are part of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the scope of protection of the present application.

It should be noted that the terms "first", "second", etc. in the description and claims of the present application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that data so used may be interchanged under appropriate circumstances so that the embodiments of the application described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

According to an embodiment of the present application, a method embodiment of a method for selecting a class name for a search keyword is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be implemented in a computer system such as a set of computer-executable instructions. and, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that herein.

1 is a flowchart of a method for selecting a class name for a search keyword according to an embodiment of the present application. As shown in FIG. 1 , the method includes the following steps:

Step S102: Clustering the search keywords of the target website to obtain multiple types of search keywords, wherein the search keywords are keywords used in the in-site search of the target website, and the target website is divided into in-site pages by columns.

In the embodiment of the present application, the target website may be any website, and the pages of the web pages of the website are divided into columns, wherein each column has a corresponding column name. "Finance", "Sports" and other columns. Record the search keywords that users use when searching on the target website, and cluster these search keywords to obtain multiple types of search keywords. For example, the recorded search keywords of a website include: real estate, housing, real estate, commercial housing , property, purchase tax, snow disaster, smog, heavy rainfall, high temperature climate, cluster these search keywords to obtain the first type of search keywords [real estate, housing, real estate, commercial housing, property, purchase tax] and the second Category search keywords [snow disaster, smog, heavy rainfall, high temperature climate].

Step S104 , query the landing page on which the search keyword lands when the target website performs an in-site search, and determine the column name of the column where the landing page corresponding to the search keyword is located.

When a user conducts an in-site search on the target website, they usually click to enter the relevant page, that is, the landing page where the user finally landed. For example, if a user uses the search keyword "smog" to search for relevant information on the target website, and enters a page about the introduction of Beijing's smog situation in the past year, then the user searches for the keyword "smog" this time. The corresponding landing page is the page about the smog situation in Beijing in the past year.

It should be noted that the landing page on which the search keyword lands when the target website conducts an in-site search may refer to the page that the search keyword lands on each time it is searched, that is, each search keyword may correspond to multiple For example, when different users use the same search keywords to search on the site, the landing pages that end up landing are different, then the search keyword corresponds to multiple landing pages, and these landing pages are queried; if different When the user's landing page contains the same page, it can also be recorded as different correspondences, that is, the number of times the search keyword is used is used as the unit to determine the landing page corresponding to the search keyword for each search on the site.

In this embodiment, after the landing page corresponding to each search keyword is searched in each site, the column name of the column where each landing page is located is determined. For example, in the above search results about "smog", the landing page is the page about the smog situation in Beijing in the past year. This page belongs to the column named "weather". Determine the column where the landing page is located. The column name is "Weather".

Step S106, for each type of search keyword in the multi-type search keywords, select a column name from the column names of the column where the landing page corresponding to the search keyword contained in each type of search keyword is located as the search key of this type. The class name of the word.

Since the search keywords have been clustered, multiple search keywords are obtained. Each search keyword in each type of search keyword has its corresponding landing page and the column name of the column where the landing page is located. Therefore, each type of search keyword corresponds to multiple landing pages and the column of the column where the landing page is located. name. Because websites usually have good column structure, each column has its own column name. The information that users want to get by searching keywords in the site is the information of this column page, and the column name of the website is a kind of information about the information. Classification and summary can well summarize and summarize the content of such pages. Therefore, selecting the class name as the search keyword from the column name can well reflect the characteristics of the category in which the search keyword is located. For example, in a class of search keywords [snow disaster, smog, heavy rainfall, high temperature climate] obtained from the above clustering, when this type of search keyword is determined for on-site search, the column name of the column where the landing page is located includes: "weather" , "natural disaster", etc., therefore, "weather" can be selected from these column names as the class name of this type of search keyword, and the class name of each type of search keyword can be selected in this way.

According to the embodiment of the present application, by clustering the search keywords of the target website, multiple types of search keywords are obtained, wherein the search keywords are the keywords used in the in-site search of the target website, and the target website is divided into the website by columns. page, query the landing page where the search keywords land on the target website for on-site search, and determine the column name of the column where the landing page corresponding to the search keywords is located. Select a column name from the column name of the landing page corresponding to the search keyword contained in the search keyword, as the class name of the search keyword, to solve the problem that the class name selected by the existing selection method cannot reflect the category in which it belongs. The technical problem of the characteristics of the selected category name can reflect the characteristics of the category in which the search keyword is located.

In the embodiment of the present application, the class name of each type of search keyword may be selected from the column names of the column where the landing page corresponding to each type of search keyword is located according to preset rules, or the column name with the most occurrences may be directly used as the column name. Class The class name of the search keyword.

Preferably, a column name is selected from the column names of the column where the landing page corresponding to the search keywords contained in each type of search keywords is located. The number of occurrences of the column name of the column where the landing page corresponding to the search keyword is located; and for each type of search keyword, the column name with the most occurrences is selected as the class name of the type of search keyword.

In this embodiment, the number of occurrences of a column name refers to the number of times the landing page of the user using the search keyword to search the site is in the column name, because the more the column name appears, the more times the search keyword has landed on the column Therefore, the column name of the column can better reflect the characteristics of this type of search keywords.

Take a class of search keywords [snow disaster, haze, heavy rainfall, high temperature climate] obtained from the above clustering as an example, in which the search keywords "snow disaster", "smog", "heavy rainfall", "high temperature climate" are used as an example. The number of searches for each word in the list is 8, 4, 3, and 5. Among them, the column name "Natural Disaster" in "Snow Disaster" appears 3 times, "Weather" appears 5 times, and all other search keywords are "" "Weather", therefore, the statistics show that "natural disaster" appears 3 times, and "weather" appears 27 times. Therefore, "weather" is used as the class name of this type of search keyword.

Preferably, before the search keywords of the target website are clustered to obtain multiple types of search keywords, the method further includes: acquiring historical access data of the target website; analyzing the historical access data to obtain the search keywords of the target website and Its corresponding landing page.

In this embodiment, the keywords used by the user for in-site search on the target website and the access behavior thereof are recorded in the access data of the target website. In the process of selecting the class name of the search keyword, first obtain the historical access data of the target website, and parse out the search keywords used by the user and the landing page for each search, so as to facilitate the subsequent analysis of the search keywords. The clustering and the statistics of the number of occurrences of the column name.

Further, after analyzing the historical access data to obtain the search keywords of the target website and their corresponding landing pages, the method further includes: establishing a corresponding relationship between the search keywords and the landing pages; wherein, the query search keywords are in the target website. The landing page that is landed when performing the in-site search includes: using the search keyword as an index, and using the corresponding relationship to query the landing page corresponding to the search keyword.

In this embodiment, after the search keywords used by the user and their landing pages are parsed, the landing pages landed on each time the search keywords are used for in-site search are associated to establish a corresponding relationship. After clustering, the corresponding landing pages can be queried using search keywords.

Preferably, clustering the search keywords of the target website to obtain multiple types of search keywords includes: using a K-means clustering algorithm to cluster the search keywords of the target website to obtain multiple types of search keywords.

In the embodiment of the present application, the K-means clustering algorithm is preferably used to cluster the search keywords, so as to obtain multiple types of search keywords.

To sum up, in the embodiment of the present application, by linking the search keywords of the clustering with the column names, and using the desired column name obtained by the user through the search keyword search as the clustering keyword class name, it reflects the clustering well. characteristics of the result.

An embodiment of the present application further provides a device for selecting a class name for a search keyword, and the device can be used to execute the method for selecting a class name for a search keyword according to the embodiment of the present application. As shown in FIG. 2 , the device includes: clustering unit 10 , query unit 20 and selection unit 30 .

The clustering unit 10 is used for clustering the search keywords of the target website to obtain multiple types of search keywords, wherein the search keywords are the keywords used in the in-site search of the target website, and the target website is divided into in-site pages by columns .

In the embodiment of the present application, the target website may be any website, and the pages of the web pages of the website are divided into columns, wherein each column has a corresponding column name. "Finance", "Sports" and other columns. Record the search keywords that users use when searching on the target website, and cluster these search keywords to obtain multiple types of search keywords. For example, the recorded search keywords of a website include: real estate, housing, real estate, commercial housing , property, purchase tax, snow disaster, smog, heavy rainfall, high temperature climate, cluster these search keywords to obtain the first type of search keywords [real estate, housing, real estate, commercial housing, property, purchase tax] and the second Category search keywords [snow disaster, smog, heavy rainfall, high temperature climate].

The query unit 20 is configured to query the landing page on which the search keyword lands when the target website is searched within the site, and determine the column name of the column on which the landing page corresponding to the search keyword is located.

When a user conducts an in-site search on the target website, they usually click to enter the relevant page, that is, the landing page where the user finally landed. For example, if a user uses the search keyword "smog" to search for relevant information on the target website, and enters a page about the introduction of Beijing's smog situation in the past year, then the user searches for the keyword "smog" this time. The corresponding landing page is the page about the smog situation in Beijing in the past year.

It should be noted that the landing page on which the search keyword lands when the target website conducts an in-site search may refer to the page that the search keyword lands on each time it is searched, that is, each search keyword may correspond to multiple For example, when different users use the same search keywords to search on the site, the landing pages that end up landing are different, then the search keyword corresponds to multiple landing pages, and these landing pages are queried; if different When the user's landing page contains the same page, it can also be recorded as different correspondences, that is, the number of times the search keyword is used is used as the unit to determine the landing page corresponding to the search keyword for each search on the site.

In this embodiment, after the landing page corresponding to each search keyword is searched in each site, the column name of the column where each landing page is located is determined. For example, in the above search results about "smog", the landing page is the page about the smog situation in Beijing in the past year, and this page belongs to the column named "weather". The column name is "Weather".

The selection unit 30 is configured to, for each type of search keyword in the multi-type search keywords, select a column name from the column names of the column where the landing page corresponding to the search keyword contained in each type of search keyword is located, as the type of search keyword. The class name of the search keyword.

Since the search keywords have been clustered, multiple search keywords are obtained. Each search keyword in each type of search keyword has its corresponding landing page and the column name of the column where the landing page is located. Therefore, each type of search keyword corresponds to multiple landing pages and the column of the column where the landing page is located. name. Because websites usually have good column structure, each column has its own column name. The information that users want to get by searching keywords in the site is the information of this column page, and the column name of the website is a kind of information about the information. Classification and summary can well summarize and summarize the content of such pages. Therefore, selecting the class name as the search keyword from the column name can well reflect the characteristics of the category in which the search keyword is located. For example, in a class of search keywords [snow disaster, smog, heavy rainfall, high temperature climate] obtained from the above clustering, when this type of search keyword is determined for on-site search, the column name of the column where the landing page is located includes: "weather" , "natural disaster", etc., therefore, "weather" can be selected from these column names as the class name of this type of search keyword, and the class name of each type of search keyword can be selected in this way.

According to the embodiment of the present application, by clustering the search keywords of the target website, multiple types of search keywords are obtained, wherein the search keywords are the keywords used in the in-site search of the target website, and the target website is divided into the website by columns. page, query the landing page where the search keywords land on the target website for on-site search, and determine the column name of the column where the landing page corresponding to the search keywords is located. Select a column name from the column name of the landing page corresponding to the search keyword contained in the search keyword, as the class name of the search keyword, to solve the problem that the class name selected by the existing selection method cannot reflect the category in which it belongs. The technical problem of the characteristics of the selected category name can reflect the characteristics of the category in which the search keyword is located.

In the embodiment of the present application, the class name of each type of search keyword may be selected from the column names of the column where the landing page corresponding to each type of search keyword is located according to preset rules, or the column name with the most occurrences may be directly used as the column name. Class The class name of the search keyword.

Preferably, the selection unit includes: a statistics module for counting the number of occurrences of the column name of the column where the landing page corresponding to the search keyword is located in each type of search keyword; and a selection module for each type of search keyword, Select the column name with the most occurrences as the category name of this type of search keyword.

In this embodiment, the number of occurrences of a column name refers to the number of times the landing page of the user using the search keyword to search on the site is in the column name. Since the more the column name appears, the more search keywords of the table name land on the column. Therefore, the column name of the column can better reflect the characteristics of this type of search keywords.

Take a class of search keywords [snow disaster, haze, heavy rainfall, high temperature climate] obtained from the above clustering as an example, in which the search keywords "snow disaster", "smog", "heavy rainfall", "high temperature climate" are used as an example. The number of searches for each word in the list is 8, 4, 3, and 5. Among them, the column name "Natural Disaster" in "Snow Disaster" appears 3 times, "Weather" appears 5 times, and all other search keywords are "" "Weather", therefore, the statistics show that "natural disaster" appears 3 times, and "weather" appears 27 times. Therefore, "weather" is used as the class name of this type of search keyword.

Preferably, the device further includes: an obtaining unit, used for obtaining historical access data of the target website before clustering the search keywords of the target website to obtain multiple types of search keywords; and an analysis unit, used for analyzing the historical access data Parse to obtain the search keywords of the target website and their corresponding landing pages.

In this embodiment, the keywords used by the user for in-site search on the target website and the access behavior thereof are recorded in the access data of the target website. In the process of selecting the class name of the search keyword, first obtain the historical access data of the target website, and parse out the search keywords used by the user and the landing page for each search, so as to facilitate the subsequent analysis of the search keywords. The clustering and the statistics of the number of occurrences of the column name.

Further, the device further includes: an establishment unit, configured to establish a corresponding relationship between the search keywords and the landing pages after analyzing the historical access data to obtain the search keywords of the target website and their corresponding landing pages; wherein the query The unit is specifically used to use the search keyword as an index, and use the corresponding relationship to query the landing page corresponding to the search keyword.

In this embodiment, after the search keywords used by the user and their landing pages are parsed, the landing pages landed on each time the search keywords are used for in-site search are associated to establish a corresponding relationship. After clustering, the corresponding landing pages can be queried using search keywords.

Preferably, the clustering unit is specifically configured to use the K-means clustering algorithm to cluster the search keywords of the target website to obtain multiple types of search keywords.

To sum up, in the embodiment of the present application, by linking the search keywords of the clustering with the column names, and using the desired column name obtained by the user through the search keyword search as the clustering keyword class name, it reflects the clustering well. characteristics of the result.

The class name selection device for the search keyword includes a processor and a memory, the above-mentioned clustering unit 10, the query unit 20 and the selection unit 30 are all stored in the memory as program units, and the processor executes the above-mentioned program stored in the memory. unit.

The processor includes a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to one or more, and the class name of each type of search keyword can be selected by adjusting the kernel parameters.

Memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read only memory (ROM) or flash memory (flash RAM), the memory including at least one memory chip.

The present application also provides an embodiment of a computer program product, which, when executed on a data processing device, is suitable for executing program codes initialized with the following method steps: clustering search keywords of a target website to obtain multi-category searches Keywords, among which, the search keywords are the keywords used in the in-site search of the target website. The target website divides the in-site pages by columns, and queries the landing pages where the search keywords land when the target website is in the in-site search to determine the search key. The column name of the column where the landing page corresponding to the word is located. For each type of search keyword in the multi-type search keywords, select one from the column names of the column where the landing page corresponding to the search keyword contained in each type of search keyword is located. Column name, as the class name of this type of search keyword.

The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

In the above-mentioned embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are only illustrative, for example, the division of the units may be a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components may be combined or Integration into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of units or modules, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes .

The above are only the preferred 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 (8)

1. a kind of class name selection method of search keyword, is characterized in that, comprises: The search keywords of the target website are clustered to obtain multiple types of search keywords, wherein the search keywords are keywords used when the target website is searched on the site, and the target website is divided into pages by columns. ; Query the landing page where the search keyword lands when the target website performs an in-site search, and determine the column name of the column where the landing page corresponding to the search keyword is located; For each type of search keyword in the multi-type search keywords, count the number of occurrences of the column name of the column where the landing page corresponding to the search keyword in each type of search keyword is located; and for each type of search keyword Keywords, select the column name with the most occurrences after statistics as the category name of this type of search keyword. 2. The method according to claim 1, wherein before the search keywords of the target website are clustered to obtain multiple types of search keywords, the method further comprises: Obtain historical access data of the target website; The historical access data is analyzed to obtain the search keywords of the target website and their corresponding landing pages. 3. The method according to claim 2, characterized in that, after parsing the historical access data to obtain the search keywords of the target website and their corresponding landing pages, the method further comprises: establishing a corresponding relationship between the search keyword and the landing page; Wherein, querying the landing page on which the search keyword landed during the in-site search of the target website includes: using the search keyword as an index, and using the corresponding relationship to query the landing page corresponding to the search keyword. 4. The method according to claim 1, wherein the search keywords of the target website are clustered to obtain multiple types of search keywords comprising: The K-means clustering algorithm is used to cluster the search keywords of the target website to obtain the multi-category search keywords. 5. a class name selection device for searching keywords, is characterized in that, comprising: The clustering unit is used for clustering the search keywords of the target website to obtain multiple types of search keywords, wherein the search keywords are keywords used in the in-site search of the target website, and the target website The website is divided into pages by columns; a query unit, configured to query the landing page on which the search keyword lands when the target website performs an in-site search, and determine the column name of the column where the landing page corresponding to the search keyword is located; The selection unit is configured to, for each type of search keyword in the multi-type search keywords, count the number of occurrences of the column name of the column where the landing page corresponding to the search keyword in each type of search keyword is located; and for all the search keywords Describe each category of search keywords, and select the column name with the most occurrences after statistics as the category name of this category of search keywords. 6. The apparatus according to claim 5, wherein the apparatus further comprises: an obtaining unit, used to obtain historical access data of the target website before clustering the search keywords of the target website to obtain multiple types of search keywords; The parsing unit is used for parsing the historical access data to obtain the search keywords of the target website and their corresponding landing pages. 7. The apparatus of claim 6, wherein the apparatus further comprises: a establishing unit, configured to establish a corresponding relationship between the search keywords and the landing pages after analyzing the historical access data to obtain the search keywords of the target website and their corresponding landing pages; The query unit is specifically configured to use the search keyword as an index, and use the corresponding relationship to query the landing page corresponding to the search keyword. 8 . The device according to claim 5 , wherein the clustering unit is specifically configured to use K-means clustering algorithm to cluster the search keywords of the target website to obtain the multi-category search keys. 9 . word.

Images