CN112417248A - Recommendation method, device, model, equipment and storage medium for addressing keywords - Google Patents
Recommendation method, device, model, equipment and storage medium for addressing keywords Download PDFInfo
- Publication number
- CN112417248A CN112417248A CN202011334849.4A CN202011334849A CN112417248A CN 112417248 A CN112417248 A CN 112417248A CN 202011334849 A CN202011334849 A CN 202011334849A CN 112417248 A CN112417248 A CN 112417248A
- Authority
- CN
- China
- Prior art keywords
- addressing
- keywords
- keyword
- search
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a recommendation method for addressing keywords, and relates to the technical field of computer technology, big data and cloud computing. The specific implementation scheme is as follows: screening out addressing keywords meeting preset access behavior characteristic screening conditions from search records and search behavior logs in a preset time period; and comparing the similarity of the screened addressing keywords with official data of a preset access object, and acquiring the addressing keywords with the similarity more than or equal to a specified similarity threshold value to serve as recommended addressing keywords. The application also provides a recommendation device, a model, equipment and a storage medium for the addressing keywords. According to the recommendation method, device, model, equipment and storage medium for the addressing keywords in the embodiment of the application, the problem of passive discovery of the current official addressing keywords can be solved, and the acquisition efficiency of the official addressing keywords is improved.
Description
Technical Field
The application relates to the technical field of computer technology, big data and cloud computing, in particular to a recommendation method, device, model, equipment and storage medium for addressing keywords.
Background
With the rapid popularization of the internet and the popularization and development of keyword addressing products such as universal websites, in the application scene of search engines, keyword (Keywords) addressing (such as network real names and universal websites) provides more choices for users.
For example, a user can directly access a target website by simply inputting keywords of natural language vocabulary of products and information to be searched in an address bar; enterprises can realize more accurate internet marketing and popularization by occupying keywords of the address bar.
At the present stage, the keywords are often discovered passively by the user in the search process, and the labor cost is high.
Disclosure of Invention
A recommendation method, apparatus, model, device and storage medium for addressing keywords are provided.
According to a first aspect, there is provided a recommendation method for addressing keywords, comprising: screening out addressing keywords meeting preset access behavior characteristic screening conditions from search records and search behavior logs in a preset time period; and comparing the similarity of the screened addressing keywords with official data of a preset access object, and acquiring the addressing keywords with the similarity more than or equal to a specified similarity threshold value to serve as recommended addressing keywords.
According to a second aspect, there is provided a recommendation device for addressing keywords, comprising: the search behavior screening module is used for screening the addressing keywords which accord with the preset access behavior characteristic screening condition from the search records and the search behavior logs in the preset time period; and the keyword recommendation module is used for comparing the similarity of the screened addressing keywords with official data of a preset access object, and acquiring the addressing keywords with the similarity more than or equal to a specified similarity threshold value as recommended addressing keywords.
According to a third aspect, a recommendation model for addressing keywords is provided, which is used for executing any one of the above-mentioned recommendation methods for addressing keywords according to the received search record and search behavior log.
According to a fourth aspect, there is provided a data search method comprising: acquiring a first keyword from preset addressing keywords, wherein the preset addressing keywords are obtained according to any one of the recommendation methods of the addressing keywords; and performing data search according to the first keyword to obtain a search result of the first keyword.
According to a fifth aspect, there is provided a data search apparatus comprising: the keyword acquisition module is used for acquiring a first keyword from a preset addressing keyword, wherein the preset addressing keyword is obtained according to any one of the recommendation methods of the addressing keyword; and the keyword searching module is used for carrying out data searching according to the first keyword to obtain a searching result of the first keyword.
According to a sixth aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any of the above-described methods of recommending addressing keywords or any of the above-described methods of searching data.
According to a seventh aspect, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to execute any of the above recommendation methods for addressing keywords or any of the above data search methods.
According to the recommendation method and device for the addressing keywords, the recommendation model, the electronic device and the readable storage medium, the addressing keywords meeting the similarity condition with the official data can be recommended through the existing search records and search behaviors and by combining the official data, the problem of passive discovery of the current official addressing keywords is solved, the cost of manually discovering the addressing keywords is reduced, the acquisition efficiency of the addressing keywords is improved, the search experience and the user satisfaction are improved, and stable and continuous recommendation of the addressing keywords is realized.
According to the data searching method, the data searching device, the electronic equipment and the readable storage medium, the first keyword is obtained from the preset addressing keyword and data searching is carried out on the obtained first keyword, the preset addressing keyword is the addressing keyword obtained by any one of the above recommending methods of the addressing keyword, and through the data searching method, the data retrieval efficiency can be improved, and the searching experience and the user satisfaction degree can be improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a schematic diagram of an application scenario of a recommendation method for addressing keywords according to an embodiment of the present application;
FIG. 2 is a flowchart of a recommendation method for addressing keywords according to an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of a recommendation device for addressing keywords according to an embodiment of the present application;
FIG. 4 is a data processing flow diagram of a recommendation model for addressing keywords according to an embodiment of the present application;
FIG. 5 is a flow chart of a data search method of an embodiment of the present application;
FIG. 6 is a flowchart of a data search apparatus according to an embodiment of the present application;
FIG. 7 is a block diagram of an electronic device for implementing the method for recommending addressing keywords according to the embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The embodiments and features of the embodiments of the present application may be combined with each other without conflict.
As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
In the embodiment of the application, the official certification addressing keywords (namely, the keywords for addressing) can assist netizens to quickly identify official websites, and prevent the netizens and website bodies from being damaged by emulational websites of emulational websites of emulational. Generally, the official authentication information needs to be independently applied by third parties such as company enterprises and institutions, and related certification materials such as company or institution information and website operation qualification are submitted, or obtained by being fed back to some known websites or government agencies, and the process is complicated.
Based on the above problems, embodiments of the present application provide a recommendation method for addressing keywords, so as to implement stable and continuous recommendation for addressing keywords, reduce the cost of manually discovering addressing keywords, and improve search experience and user satisfaction.
Fig. 1 is a schematic view of an application scenario of a recommendation method for addressing keywords according to an embodiment of the present application. In the scenario shown in fig. 1, a terminal device 11, a search engine 12, a search engine server 13 and a search record and search behavior log 14 are schematically shown.
Among them, the terminal device 11, the search engine 12, the search engine server 13, and the search record and search behavior log 14 may communicate through a network.
The terminal device 11 may be configured to run a search engine 12, the search engine 12 may be configured to provide search services through a search engine server 13, and the search records and search behavior log 14 may be configured to store search records and search behavior logs generated during a search process.
Illustratively, the search record may include search terms, search time, and search results, which may include, for example: the Uniform Resource Locator (URL) obtained by the search, the search result page information, the website related to the search result page, and the website connection information. The search result page information may include, for example, information such as a main page of the search result, a sub-page of the search result, a web page title of the search result, and the like.
In the embodiment of the present application, the search engine server 13 may access the search record and the search behavior log 14, and may perform the method for recommending the addressing keyword according to the embodiment of the present application.
In practical applications, the terminal device 11 in the embodiment of the present application may include, but is not limited to, a mobile phone, a personal computer, a tablet computer, a smart wearable device, a desktop computer, a notebook computer, and the like. They can all be fitted with various applications; the search engine server 12 may be a local server or a cloud server, and the search log and the search behavior log 14 may be stored locally in the search engine server 13 or in the cloud. The number of devices and the implementation form are not limited in the embodiment of the application, and the device can be flexibly adjusted according to the actual application requirements, which is not described herein again.
Fig. 2 is a flowchart of a recommendation method for addressing keywords according to an embodiment of the present application.
In a first aspect, referring to fig. 2, an embodiment of the present application provides a recommendation method for addressing keywords, which may include the following steps.
S110, screening out addressing keywords meeting preset access behavior characteristic screening conditions from the search records and the search behavior logs in a preset time period;
and S120, comparing the similarity of the screened addressing keywords with official data of a preset access object, and acquiring the addressing keywords with the similarity more than or equal to a specified similarity threshold value as recommended addressing keywords.
At step S120, the source of official data may include at least one of the following data sources: internet Content Providers (ICP) from Internet site filing, registration filing data from corporate enterprises, organizations, etc., government announcements, network police server or administrative regulatory agency server data, and integrity review data from integrity agency servers, etc.
According to the recommendation method for the addressing keywords, the addressing keywords meeting the similarity condition with official data can be recommended through the existing search records and search behaviors and by combining the official data, the passive discovery problem of the current official addressing keywords is solved, the cost for manually discovering the addressing keywords is reduced, the search experience and the user satisfaction are improved, and the stable and continuous recommendation of the addressing keywords is realized.
In some embodiments, step S110 may specifically include the following steps.
S11, obtaining a search result corresponding to the search word from the search record and the search behavior log, and calculating behavior feature data of the search result.
And S12, screening out the behavior characteristic data which meet the preset access behavior characteristic screening condition.
And S13, taking the search word corresponding to the search result to which the screened behavior characteristic data belongs as the addressing keyword meeting the access behavior characteristic screening condition.
Through the steps S11-S14, the preliminary screening of the addressing keywords can be realized by analyzing the search records and the search behavior logs in the preset time period, so that the preliminarily screened addressing keywords conform to the search behaviors of the user, and the practicability of the finally recommended addressing keywords is improved.
In some embodiments, in order to improve timeliness of the screened addressing keywords, the predetermined time period may be set to be less than or equal to a predetermined time length from the current time, for example, the addressing keywords and the corresponding URLs may be preliminarily screened out by analyzing search records and search behavior logs within the last N days, where N is greater than or equal to 1 and less than or equal to a predetermined number of days.
In some embodiments, the behavioral characteristic data includes at least one of: click ratio, click display ratio, display rate, main page browsing amount and sub-page browsing amount.
In some embodiments, the click ratio in the behavior feature data is used to represent a ratio of the number of clicks of a certain search result of the search term to the total number of clicks of all search results of the search term in a predetermined time period. For example: within a predetermined time period, for one search keyword query1, there are 100 search results (e.g., S1-S100), wherein if the search result S1 of query1 is clicked 3 times in total and the search results S1-S100 are clicked 1000 times in total, the click ratio of the search record S1 of query1 is: 3/1000.
In some embodiments, the click presentation proportion in the behavior feature data is used for representing the ratio of the number of clicks of the search result of the search term to the number of occurrences of the search result in a preset time period. For example, within a predetermined time period, for one search keyword query1, 100 times of search, 99 times of search record S1 appear, and 1 time of click on the search record S1, the search record S1 click presentation ratio of the query1 is 1/99.
In some embodiments, the presentation rate in the behavior feature data is used to indicate a ratio of the number of clicks of a search result to the number of displays of the search result in a case where a certain search result of the search term is displayed in each search result within a predetermined time period. For example, within a predetermined time period, for one search keyword query1, the total number of search queries 1 is 100, the search result S1 of the query1 is displayed 100 times, and the presentation rate of the query1 is 1/100.
In some embodiments, the page view volume (PV) in the behavior feature data is used to indicate a total number of times a web page is viewed in a search result of a search term over a predetermined period of time. The page view amount may include a view amount of the main page and a view amount of the sub page.
In an embodiment, the behavior feature data meets the access behavior feature screening condition, which may specifically include at least one of the following conditions: the click ratio is larger than or equal to a first ratio threshold, the click display ratio is larger than or equal to a second ratio threshold, the display rate is larger than or equal to a preset display rate threshold, the main page browsing amount is larger than or equal to a first browsing amount threshold, and the sub page browsing amount is larger than or equal to a second browsing amount threshold.
In the embodiment, the behavior feature data can be refined through parameters such as the click ratio, the click display ratio, the display rate, the main page browsing amount and the sub-page browsing amount, so that search results which are screened in a targeted manner and meet the specific behavior feature data are achieved, and addressing keywords which meet the access behavior feature screening conditions are obtained.
In an embodiment, after step S110 and before step S120, the method for recommending address keywords in the embodiment of the present application further includes: and S21, performing keyword filtering on the non-addressing target keywords in the addressing keywords meeting the access behavior characteristic screening conditions, and taking the addressing keywords after the keyword filtering as the screened addressing keywords.
In this embodiment, the non-addressing target keywords can be removed from the addressing keywords meeting the preset access behavior feature screening condition, so that the accuracy of the screened addressing keywords is improved.
In one embodiment, the non-addressing destination keyword includes at least one of the following search terms: extracting search terms from pre-acquired media network data, search terms corresponding to web addresses of the media network data, and search terms corresponding to web addresses of pages where the media network data are located; wherein the media network data includes at least one of yellow page information and news data.
In this embodiment, non-addressing-purpose keywords such as yellow page information and news can be removed from addressing keywords meeting preset access behavior feature screening conditions through at least one of keyword screening, website URL screening, main page screening and sub-page screening, so that the non-addressing-purpose keywords can be removed through diverse keyword screening, and the accuracy of the selected addressing keywords can be improved through various implementation manners.
In an embodiment, after step S110 and before step S120, the method for recommending address keywords in the embodiment of the present application further includes: and S22, removing preset domain words from the selected addressing keywords, and taking the addressing keywords with the domain words removed as the selected addressing keywords.
In this embodiment, it may be implemented to remove the preset domain word from the selected addressing keyword, where the preset domain word may be domain data and regional keywords from a government department such as a civil bureau, so as to implement the influence of the domain data in the keyword data on the addressing result, reduce the data redundancy of the recommended addressing keyword, and improve the search accuracy of the recommended addressing keyword.
In one embodiment, step S120 may include the following steps.
S31, using the addressing keywords with similarity smaller than the designated similarity threshold as low-similarity addressing keywords, and obtaining the semantics of official data and the semantics of the low-similarity addressing keywords through semantic analysis.
S32, obtaining the addressing keywords conforming to the semantics of official data from the low similarity addressing keywords as the addressing keywords after semantic filtering;
and S33, according to the preset similarity recommendation requirement, taking at least one of the addressing keywords with the similarity more than or equal to the specified similarity threshold and the addressing keywords after semantic filtering as the recommended addressing keywords.
As an example, if the similarity recommendation requirement of the user is: recommending the high-similarity addressing keywords, and recommending the addressing keywords with the similarity greater than or equal to the specified similarity threshold; if the similarity recommendation requirement of the user is as follows: recommending non-high-similarity addressing keywords (such as generally similar addressing keywords), and then recommending the semantically filtered addressing keywords; if the similarity recommendation requirement is: and simultaneously recommending high-similarity addressing keywords and common similar addressing keywords, labeling the addressing keywords with the similarity greater than or equal to the specified similarity threshold and the semantically filtered addressing keywords respectively to indicate the corresponding different similarity recommendation requirements, and recommending the labeled addressing keywords with the similarity greater than or equal to the specified similarity threshold and the labeled semantically filtered addressing keywords.
In the embodiment, the addressing keywords with the similarity smaller than the specified similarity threshold can be continuously screened according to the semantic similarity with the official data to obtain the addressing keywords in the low-similarity addressing keywords, wherein the addressing keywords are consistent with the semantics of the official data, so that the diversity of the recommended addressing keywords is increased, and the addressing keywords which are more consistent with different user requirements are provided according to the actual similarity recommendation requirements of users.
In an embodiment, after step S120, the method for recommending an addressing keyword according to an embodiment of the present application may further include: s41, removing the preset existing official addressing keywords from the recommended addressing keywords to obtain updated addressing keywords, and using the updated addressing keywords as the recommended addressing keywords.
In the embodiment, the newly added addressing keywords can be quickly determined by filtering the existing official addressing keywords, and the updated addressing keywords are used as the newly added official addressing keywords, so that the new addressing keywords with higher accuracy can be continuously provided for the existing official addressing keywords, and the search experience and satisfaction of the user can be improved.
Fig. 3 is a schematic structural diagram of a recommendation device for addressing keywords according to an embodiment of the present application.
In a second aspect, referring to fig. 3, an embodiment of the present application provides a recommendation apparatus 300 for addressing keywords, which may include the following modules.
The search behavior screening module 310 is configured to screen out, from the search records and the search behavior logs within a predetermined time period, an addressing keyword that meets a preset access behavior feature screening condition;
and the keyword recommendation module 320 is configured to compare similarity between the screened addressing keywords and official data of a preset access object, and obtain the addressing keywords with similarity greater than or equal to a specified similarity threshold as recommended addressing keywords.
In some embodiments, the search behavior filtering module 310 may specifically include: an access data acquisition unit for acquiring access data of a search result corresponding to the search word from the search record and the search behavior log; a behavior feature data calculation unit, configured to calculate behavior feature data of the search result according to the access data, where the behavior feature data includes at least one of: the click ratio, the click display ratio, the display rate, the main page browsing amount and the sub page browsing amount; the search result screening unit is used for screening the behavior characteristic data of which the behavior characteristic data accord with the access behavior characteristic screening condition and determining the search result to which the screened behavior characteristic data belongs; and the keyword screening unit is used for taking the search words corresponding to the determined search results as the addressing keywords meeting the access behavior characteristic screening conditions.
In some embodiments, the recommendation device addressing the keyword may further include: and the keyword filtering module is used for filtering keywords of non-addressing target keywords in the addressing keywords meeting the access behavior characteristic screening conditions after the addressing keywords meeting the preset access behavior characteristic screening conditions are screened out and before the screened addressing keywords are compared with the official data of a preset access object in similarity, and taking the addressing keywords after the keywords are filtered out as the screened addressing keywords.
In some embodiments, the non-addressing destination keyword includes at least one of the following search terms: extracting search terms from pre-acquired media network data, search terms corresponding to websites of the media network data, and search terms corresponding to websites of pages where the media network data are located; the media network data includes at least one of yellow page information and news data.
In some embodiments, the recommendation device addressing the keyword may further include: and the regional word filtering module is used for removing the preset regional words from the selected addressing keywords after the addressing keywords meeting the preset access behavior characteristic screening condition are screened out and before the screened addressing keywords are compared with the official data of the preset access object in similarity, and taking the addressing keywords without the regional words as the screened addressing keywords.
In some embodiments, the keyword recommendation module 320 includes: the semantic analysis unit is used for taking the addressing keywords with the similarity smaller than the specified similarity threshold as low-similarity addressing keywords and obtaining the semantics of official data and the semantics of the low-similarity addressing keywords through semantic analysis; the keyword screening unit is also used for acquiring the addressing keywords which accord with the semantics of official data from the low-similarity addressing keywords as the addressing keywords after semantic filtering; the keyword recommendation module 320 is further configured to recommend at least one of the addressing keywords with the similarity greater than or equal to the specified similarity threshold and the semantically filtered addressing keywords as the recommended addressing keywords according to a preset similarity recommendation requirement.
In some embodiments, the recommendation device addressing the keyword may further include: and the existing keyword removing module is used for removing the preset existing official addressing keywords from the recommended addressing keywords to obtain updated addressing keywords after the addressing keywords with the similarity greater than or equal to the specified similarity threshold are obtained and used as the recommended addressing keywords.
According to the recommendation device for the addressing keywords, the addressing keywords meeting the similarity condition with official data can be recommended as the addressing keywords by searching records and searching behaviors in a preset time period and combining the official data, the problem that the current addressing keywords are often discovered passively can be solved, the cost for manually discovering the addressing keywords is reduced, the acquisition efficiency of the addressing keywords is improved, the searching experience and the user satisfaction are improved, and stable and continuous recommendation of the addressing keywords is realized.
In a third aspect, an embodiment of the present application further provides a recommendation model for addressing keywords, where the recommendation model is configured to process the received search record and the search behavior log, and execute the recommendation method for addressing keywords described in the foregoing embodiment with reference to fig. 1.
For convenience of understanding, in the embodiment of the present application, a process of performing addressing keyword recommendation by using a recommendation model for addressing keywords is described below with reference to fig. 4.
Fig. 4 is a schematic data processing flow diagram of a recommendation model for addressing keywords according to an embodiment of the present application. Referring to fig. 4, the recommendation model for addressing keywords according to the embodiment of the present application receives search records and search behavior logs within a predetermined time period, and performs the following processing steps.
S401, searching behavior data, screening and addressing keywords.
In this step, the recommendation model of the addressing keyword may screen out the addressing keyword meeting the preset access behavior feature screening condition and the website URL corresponding to the addressing keyword from the search record and the search behavior log in the predetermined time period.
S402, Media network filtering (Media Web Filter).
In step S402, the search terms of non-addressing purposes corresponding to the media websites such as yellow pages and news, which are acquired in advance, may be removed from the addressing keywords meeting the preset access behavior feature screening condition.
In the step, multiple strategies such as website URL screening, search term query screening, main page and sub-page screening and the like can be carried out through multiple processes, and the data processing efficiency is improved.
S403, Region Query screening (Region Query Filter).
In this step, a regional word or a regional query word may be removed from the addressing keywords meeting the preset access behavior feature screening condition.
S404, executing a Multi-Query Filter template (Multi Query Filter template).
In this step, the search words contained in the preset search word list may be removed from the addressing keywords meeting the preset access behavior feature screening condition, where the search words in the search word list may be preset keywords of non-addressing purposes or keywords of non-official data that need to be filtered.
S405, a Multi-address screening policy (Multi URL Filter Strategy) is executed.
In this step, the search terms corresponding to a plurality of preset websites, which may be preset network addresses that need to be filtered, may be removed from the addressing keywords meeting the preset access behavior feature screening condition.
S406, a Similarity Filter process (Similarity Filter) is performed.
In the step, the similarity comparison is carried out on the addressing keywords obtained by screening in the steps S401-S405 and preset official data, and the addressing keywords with the similarity larger than or equal to the specified similarity threshold are obtained from the comparison result and serve as the high-similarity addressing keywords.
It should be noted that, in the embodiment of the present application, the order of the processing steps and the number of the processing steps in S402 to S405 are not particularly limited, one or more steps may be selected according to actual needs to be processed, and the order of the selected processing steps may be determined by itself, and the change in the order of the processing steps does not affect the processing result.
S407, Lexical Analysis filtering processing (Lexical Analysis Filter) is performed.
In the step, semantic analysis is carried out on the addressing keywords with the similarity smaller than the specified similarity threshold and the official data, and the addressing keywords with the semantics not conforming to the semantics of the official data are removed from the addressing keywords with the similarity smaller than the specified similarity threshold, so that the addressing keywords conforming to the semantics of the official data are obtained.
S408, the filtering process (Official Data Filter) of the existing Official addressing keywords is executed.
In this step, the preset existing official addressing keywords may be removed from the recommended addressing keywords to obtain updated addressing keywords, and the updated addressing keywords may be recommended.
Through the steps S401-S408, the search records and the search behavior logs in the preset time period of the model can be input through the instantiated processing of the recommendation model of the addressing keywords, the official addressing words are mined and recommended through the existing search records and search behaviors and by combining official data and flexible strategy configuration, the addressing keywords with higher accuracy are continuously provided through the instantiated scheduling processing, the recommendation efficiency of the addressing keywords is improved, the cost of manual discovery and recommendation is saved, and the search experience and satisfaction of users are improved.
Fig. 5 is a flowchart of a data search method according to an embodiment of the present application.
In a fourth aspect, referring to fig. 5, an embodiment of the present application provides a data searching method, which may include the following steps.
S510, obtaining a first keyword from preset addressing keywords, where the preset addressing keywords are obtained according to any one of the methods described in the above embodiments.
S520, data searching is carried out according to the first keyword, and a searching result of the first keyword is obtained.
According to the data searching method, the first keyword can be obtained from the preset addressing keyword and data searching can be conducted on the obtained first keyword, the preset addressing keyword is the addressing keyword obtained through any one of the recommending methods of the addressing keyword, and through the data searching method, the data retrieval efficiency can be improved, and the searching experience and the user satisfaction degree can be improved.
Fig. 6 is a flowchart of a data search apparatus according to an embodiment of the present application.
In a fifth aspect, referring to fig. 6, an embodiment of the present application provides a data search apparatus 600, and the apparatus 600 may include the following modules.
A keyword obtaining module 610, configured to obtain a first keyword from a preset addressing keyword, where the preset addressing keyword is an addressing keyword obtained according to any one of the above recommendation methods for addressing keywords; and the keyword searching module 620 is configured to perform data search according to the first keyword to obtain a search result of the first keyword.
According to the data search device, the first keyword can be obtained from the preset addressing keyword and data search can be conducted on the obtained first keyword, the preset addressing keyword is the addressing keyword obtained through any one of the recommending methods of the addressing keyword, the data search efficiency can be improved through the data search device, and the search experience and the user satisfaction are improved.
According to an embodiment of the application, an electronic device and a readable storage medium are also provided.
Fig. 7 is a block diagram of an electronic device for a recommendation method for addressing keywords according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 7, the electronic apparatus includes: one or more processors 701, a memory 702, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 7, one processor 701 is taken as an example.
The memory 702 is a non-transitory computer readable storage medium as provided herein. The memory stores instructions executable by the at least one processor to cause the at least one processor to perform the proposed method for addressing keywords provided herein. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to perform the recommendation method for addressing keywords provided herein.
The memory 702, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the recommended method for addressing keywords in the embodiments of the present application. The processor 701 executes various functional applications of the server and data processing, i.e., implementing the recommendation method for addressing keywords in the above method embodiments, by running non-transitory software programs, instructions, and modules stored in the memory 702.
The memory 702 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device that performs the recommended method of addressing the keyword, and the like. Further, the memory 702 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 702 may optionally include a memory remotely located from the processor 701, and such remote memory may be connected over a network to an electronic device that performs the recommended method of addressing the keyword. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the recommendation method for addressing keywords in the embodiment of the application may further include: an input device 703 and an output device 704. The processor 701, the memory 702, the input device 703 and the output device 704 may be connected by a bus or other means, and fig. 7 illustrates an example of a connection by a bus.
The input device 703 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the electronic apparatus for implementing the recommended method of addressing keywords, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or the like. The output devices 704 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. A server may also be a server in a distributed system, or a server in a combination blockchain, with the relationship of client and server arising from computer programs running on the respective computers and having a client-server relationship to each other.
In the embodiment of the application, the recommendation method of the addressing keywords can be executed through technical means such as artificial intelligence and big data calculation, and potential addressing keywords can be mined.
Artificial intelligence is the subject of research that causes computers to simulate certain mental processes and intelligent behaviors of humans (e.g., learning, reasoning, planning, etc.), both at the hardware level and at the software level. The artificial intelligence hardware technology generally comprises the technologies of a sensor, a special artificial intelligence chip, cloud computing, distributed storage, big data processing and the like; the artificial intelligence software technology comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge map technology and the like.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (14)
1. A recommendation method for addressing keywords, comprising:
screening out addressing keywords meeting preset access behavior characteristic screening conditions from search records and search behavior logs in a preset time period;
and comparing the similarity of the screened addressing keywords with official data of a preset access object, and acquiring the addressing keywords with the similarity larger than or equal to a specified similarity threshold value to serve as recommended addressing keywords.
2. The method of claim 1, wherein the screening of the addressing keyword meeting the preset access behavior feature screening condition from the search record and the search behavior log in the predetermined time period comprises:
obtaining a search result corresponding to a search word from the search record and the search behavior log, and calculating behavior characteristic data of the search result;
screening out behavior characteristic data which meet preset access behavior characteristic screening conditions;
and taking the search word corresponding to the search result to which the screened behavior characteristic data belongs as the addressing keyword meeting the access behavior characteristic screening condition.
3. The method of claim 2,
the behavioral characteristic data includes at least one of: the click ratio, the click display ratio, the display rate, the main page browsing amount and the sub page browsing amount;
the access behavior feature screening condition comprises at least one of the following conditions: the click ratio is larger than or equal to a first ratio threshold, the click display ratio is larger than or equal to a second ratio threshold, the display rate is larger than or equal to a preset display rate threshold, the main page browsing amount is larger than or equal to a first browsing amount threshold, and the sub page browsing amount is larger than or equal to a second browsing amount threshold.
4. The method of claim 1, wherein after screening out the addressing keywords meeting the preset access behavior feature screening condition and before comparing the similarity between the screened addressing keywords and the official data of the preset access object, the method further comprises:
and performing keyword filtering on preset non-addressing target keywords in the addressing keywords meeting the access behavior characteristic screening conditions, and taking the addressing keywords after the keyword filtering as screened addressing keywords.
5. The method of claim 4, wherein the non-addressing purpose keyword comprises at least one of the following search terms:
extracting search terms from pre-acquired media network data, search terms corresponding to websites of the media network data, and search terms corresponding to websites of pages where the media network data are located; wherein the content of the first and second substances,
the media network data includes at least one of yellow page information and news data.
6. The method according to any one of claims 1 to 5, wherein after screening out the addressing keyword meeting the preset access behavior feature screening condition and before comparing the similarity of the screened addressing keyword with the official data of the preset access object, the method further comprises:
and removing preset regional words from the screened addressing keywords, and taking the addressing keywords with the regional words removed as the screened addressing keywords.
7. The method according to any one of claims 1 to 5, wherein the obtaining of the addressing keyword with the similarity greater than or equal to a specified similarity threshold as the recommended addressing keyword comprises:
taking the addressing keywords with the similarity smaller than the specified similarity threshold as low-similarity addressing keywords, and obtaining the semantics of the official data and the semantics of the low-similarity addressing keywords through semantic analysis;
acquiring addressing keywords which accord with the semantics of the official data from the low-similarity addressing keywords as the addressing keywords after semantic filtering;
and according to a preset similarity recommendation requirement, taking at least one of the addressing keywords with the similarity greater than or equal to a specified similarity threshold and the semantically filtered addressing keywords as recommended addressing keywords.
8. The method according to any one of claims 1 to 5, wherein after obtaining the addressing keyword with similarity greater than or equal to a specified similarity threshold as the recommended addressing keyword, the method further comprises:
and removing preset existing official addressing keywords from the recommended addressing keywords to obtain updated addressing keywords, and taking the updated addressing keywords as the recommended addressing keywords.
9. A recommendation device for addressing keywords, comprising:
the search behavior screening module is used for screening the addressing keywords which accord with the preset access behavior characteristic screening condition from the search records and the search behavior logs in the preset time period;
and the keyword recommendation module is used for comparing the similarity of the screened addressing keywords with official data of a preset access object, and acquiring the addressing keywords with the similarity more than or equal to a specified similarity threshold value as recommended addressing keywords.
10. A recommendation model for addressing keywords, characterized in that,
the recommendation model is for performing the method of any of claims 1-8 based on the received search record and search behavior log.
11. A method of searching data, comprising:
obtaining a first keyword from a preset addressing keyword, wherein the preset addressing keyword is obtained according to the method of any one of claims 1-8;
and performing data search according to the first keyword to obtain a search result of the first keyword.
12. A data search apparatus, comprising:
a keyword obtaining module, configured to obtain a first keyword from a preset addressing keyword, where the preset addressing keyword is an addressing keyword obtained according to the method of any one of claims 1 to 8;
and the keyword searching module is used for carrying out data searching according to the first keyword to obtain a searching result of the first keyword.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8, or claim 11.
14. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-8 or claim 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011334849.4A CN112417248A (en) | 2020-11-24 | 2020-11-24 | Recommendation method, device, model, equipment and storage medium for addressing keywords |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011334849.4A CN112417248A (en) | 2020-11-24 | 2020-11-24 | Recommendation method, device, model, equipment and storage medium for addressing keywords |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112417248A true CN112417248A (en) | 2021-02-26 |
Family
ID=74842829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011334849.4A Pending CN112417248A (en) | 2020-11-24 | 2020-11-24 | Recommendation method, device, model, equipment and storage medium for addressing keywords |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417248A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011165A (en) * | 2021-03-19 | 2021-06-22 | 支付宝(杭州)信息技术有限公司 | Method, device, equipment and medium for identifying blocked keywords |
| CN113011165B (en) * | 2021-03-19 | 2024-06-07 | 支付宝（中国）网络技术有限公司 | Method, device, equipment and medium for identifying blocked keywords |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178728A (en) * | 2007-11-21 | 2008-05-14 | 北京搜狗科技发展有限公司 | Web side navigation method and system |
| CN101398856A (en) * | 2008-11-12 | 2009-04-01 | 北京搜狗科技发展有限公司 | Method for acquiring navigation enquiry words, device and method for displaying searching result |
| CN101551806A (en) * | 2008-04-03 | 2009-10-07 | 北京搜狗科技发展有限公司 | Personalized website navigation method and system |
| KR20090119532A (en) * | 2008-05-16 | 2009-11-19 | 엔에이치엔비즈니스플랫폼 주식회사 | Method and system for recommending advertisement keyword by analyzing log |
| JP2012108795A (en) * | 2010-11-18 | 2012-06-07 | Ntt Docomo Inc | Synonym determination device, synonym determination method and program |
| CN103425742A (en) * | 2013-07-16 | 2013-12-04 | 北京中科汇联信息技术有限公司 | Method and device for searching website |
| CN103491204A (en) * | 2013-09-25 | 2014-01-01 | 人民网股份有限公司 | Method and system for network addressing |
| CN105426537A (en) * | 2015-12-21 | 2016-03-23 | 北京奇虎科技有限公司 | Recommendation method for navigation page search keywords and terminal equipment |
| CN105868227A (en) * | 2015-11-20 | 2016-08-17 | 乐视致新电子科技（天津）有限公司 | Display method and device of address bar pull-down menu |
| CN106055603A (en) * | 2016-05-24 | 2016-10-26 | 北京奇虎科技有限公司 | VPN-based browser access website recommendation method and system, and client |
| CN108664513A (en) * | 2017-03-31 | 2018-10-16 | 北京京东尚科信息技术有限公司 | Method, apparatus and equipment for pushing keyword |
| CN111414498A (en) * | 2020-04-29 | 2020-07-14 | 北京字节跳动网络技术有限公司 | Multimedia information recommendation method and device and electronic equipment |
-
2020
- 2020-11-24 CN CN202011334849.4A patent/CN112417248A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178728A (en) * | 2007-11-21 | 2008-05-14 | 北京搜狗科技发展有限公司 | Web side navigation method and system |
| CN101551806A (en) * | 2008-04-03 | 2009-10-07 | 北京搜狗科技发展有限公司 | Personalized website navigation method and system |
| KR20090119532A (en) * | 2008-05-16 | 2009-11-19 | 엔에이치엔비즈니스플랫폼 주식회사 | Method and system for recommending advertisement keyword by analyzing log |
| CN101398856A (en) * | 2008-11-12 | 2009-04-01 | 北京搜狗科技发展有限公司 | Method for acquiring navigation enquiry words, device and method for displaying searching result |
| JP2012108795A (en) * | 2010-11-18 | 2012-06-07 | Ntt Docomo Inc | Synonym determination device, synonym determination method and program |
| CN103425742A (en) * | 2013-07-16 | 2013-12-04 | 北京中科汇联信息技术有限公司 | Method and device for searching website |
| CN103491204A (en) * | 2013-09-25 | 2014-01-01 | 人民网股份有限公司 | Method and system for network addressing |
| CN105868227A (en) * | 2015-11-20 | 2016-08-17 | 乐视致新电子科技（天津）有限公司 | Display method and device of address bar pull-down menu |
| CN105426537A (en) * | 2015-12-21 | 2016-03-23 | 北京奇虎科技有限公司 | Recommendation method for navigation page search keywords and terminal equipment |
| CN106055603A (en) * | 2016-05-24 | 2016-10-26 | 北京奇虎科技有限公司 | VPN-based browser access website recommendation method and system, and client |
| CN108664513A (en) * | 2017-03-31 | 2018-10-16 | 北京京东尚科信息技术有限公司 | Method, apparatus and equipment for pushing keyword |
| CN111414498A (en) * | 2020-04-29 | 2020-07-14 | 北京字节跳动网络技术有限公司 | Multimedia information recommendation method and device and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011165A (en) * | 2021-03-19 | 2021-06-22 | 支付宝(杭州)信息技术有限公司 | Method, device, equipment and medium for identifying blocked keywords |
| CN113011165B (en) * | 2021-03-19 | 2024-06-07 | 支付宝（中国）网络技术有限公司 | Method, device, equipment and medium for identifying blocked keywords |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11163957B2 (en) | Performing semantic graph search | |
| US20210232631A1 (en) | Persisted enterprise graph queries | |
| US8495484B2 (en) | Intelligent link population and recommendation | |
| US20120290637A1 (en) | Personalized news feed based on peer and personal activity | |
| US7788251B2 (en) | System, method and computer program product for concept-based searching and analysis | |
| US9251516B2 (en) | Systems and methods for electronic distribution of job listings | |
| US9697290B2 (en) | Providing relevant information to a user based upon monitored user activities in one or more contexts | |
| WO2008141295A1 (en) | Keyword generation system and method for online activity | |
| US9892096B2 (en) | Contextual hyperlink insertion | |
| CN110674406A (en) | Recommendation method and device, electronic equipment and storage medium | |
| US20210224488A1 (en) | Business graph engine for connection recommendations | |
| US20200142938A1 (en) | Unbiasing search results | |
| US11526575B2 (en) | Web browser with enhanced history classification | |
| US9684717B2 (en) | Semantic search for business entities | |
| US20160092960A1 (en) | Product recommendations over multiple stores | |
| CN102073735A (en) | Searching method and searching system | |
| CN105808642B (en) | Recommendation method and device | |
| US10635725B2 (en) | Providing app store search results | |
| US20130239012A1 (en) | Common denominator filter for enterprise portal pages | |
| CN112084150A (en) | Model training method, data retrieval method, device, equipment and storage medium | |
| CN103793495A (en) | Application message search method and system and application message acquisition method and system | |
| CN114065765A (en) | Weapon equipment text processing method and device combining AI and RPA and electronic equipment | |
| CN111259058B (en) | Data mining method, data mining device and electronic equipment | |
| KR20190109628A (en) | Method for providing personalized article contents and apparatus for the same | |
| CN112699314A (en) | Hot event determination method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |