CN115292605A - Internet cloud data-based keyword search method - Google Patents
Internet cloud data-based keyword search method Download PDFInfo
- Publication number
- CN115292605A CN115292605A CN202210995701.8A CN202210995701A CN115292605A CN 115292605 A CN115292605 A CN 115292605A CN 202210995701 A CN202210995701 A CN 202210995701A CN 115292605 A CN115292605 A CN 115292605A
- Authority
- CN
- China
- Prior art keywords
- search
- cloud data
- keyword
- keywords
- search keyword
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000011218 segmentation Effects 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an internet cloud data-based keyword search method, which relates to the technical field of keyword search, and relates to search keywords with similar word senses by pre-calculating word sense similarity among all the search keywords; sorting the cloud data corresponding to each search keyword according to the click rate of each cloud data; the method comprises the steps that a search word input by a user is segmented by using a segmentation tool, and a plurality of search keywords are obtained; then searching a cloud data set corresponding to each search keyword; and a cloud data set corresponding to the search keyword with a similar word sense to each search keyword; preferentially displaying the cloud data sets corresponding to the search keywords, and then displaying the cloud data sets corresponding to the search keywords with similar meaning; the accuracy and the practicability of the keyword search result of the user are guaranteed.
Description
Technical Field
The invention belongs to the field of keyword search, relates to a keyword search technology, and particularly relates to an internet cloud data-based keyword search method.
Background
The keywords are the information contents which can be input by the user to summarize the information contents searched by the user to the maximum extent when the user uses the search engine; because of the openness of the internet, the content of the internet is very numerous and jumbled, so that the difficulty of searching useful information in the internet for a user is continuously increased; the search keyword can reduce the difficulty of searching the content in the Internet;
however, due to subjectivity of users in searching for keywords, the searched keywords may not be exactly what the users need to express; therefore, a search function that extends not only according to the keywords provided by the user but also the keywords is required;
therefore, the internet search method based on the cloud data keywords is provided.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. The internet cloud data-based keyword search method is characterized in that search keywords with similar word senses are associated by pre-calculating word sense similarity among all the search keywords; sorting the cloud data corresponding to each search keyword according to the click rate of each cloud data; the method comprises the steps that a search word input by a user is segmented by using a segmentation tool, and a plurality of search keywords are obtained; then searching a cloud data set corresponding to each search keyword; and a cloud data set corresponding to the search keyword with a similar word sense to each search keyword; preferentially displaying the cloud data sets corresponding to the search keywords, and then displaying the cloud data sets corresponding to the search keywords with similar meaning; the accuracy and the practicability of the keyword search result of the user are guaranteed.
In order to achieve the above object, an embodiment according to a first aspect of the present invention provides an internet search method based on cloud data keywords, including the following steps:
the method comprises the following steps: the user uploads the cloud data to the cloud platform; the cloud data comprises titles, summaries and detailed contents; and the user can autonomously select to submit or not submit the search keyword;
for the cloud data submitted with the search keywords, the submitted search keywords are the keywords needed to be used for searching the cloud data; for cloud data which are not submitted with search keywords, keyword extraction is carried out on titles, abstracts and detailed contents of the cloud data by using a keyword extraction algorithm; the extracted keywords are keywords needed to be used for searching the cloud data;
step two: sorting and numbering search keywords of a user from large to small according to the search times; numbering search keywords as 1,2, \8230, N in sequence; wherein N is the number of search keywords;
finding out a search key phrase similar to the semanteme of each search key word according to the sequence of 1,2, \8230;
step three: sorting the cloud data according to a lexicographic order of the search keywords; marking the search key words as k; for each search keyword k, storing the cloud data containing k in all the search keywords by using a set; marking the cloud data set containing the search keyword k corresponding to the search keyword k as Pk; sorting the cloud data in the cloud data set Pk from large to small according to the click rate;
step four: a user inputs a search word at a search client and clicks a search button for searching, and the search client sends the search word to a cloud platform through a wireless network; the cloud platform searches for cloud data which accord with the search terms and sends the cloud data to the search client;
for each search keyword n, finding a search keyword group similar to the search keyword in semantics specifically comprises the following steps:
step S1: calculating semantic similarity between the search keyword n and all other search keywords by using an NLP technology;
step S2: counting all search keywords with the similarity degree n larger than the similarity degree threshold t from all the search keywords; and using a set form to store the search key phrase; marking a search keyword set with similar word senses corresponding to the search keywords n as Sn; the similarity threshold t is set according to actual experience; defining the search keywords with the word meaning similarity larger than the pixel point threshold value t as word meaning similarity;
and step S3: sorting the search keywords in the search keyword set Sn from large to small according to the similarity of the search keywords;
specifically, the step of searching the cloud data which accords with the search terms by the cloud platform comprises the following steps:
step P1: it can be understood that, when the user uses the keyword search function, the filled-in search words are often in the form of sentences; therefore, keywords of a sentence need to be extracted from the searched sentence; using a word segmentation tool to segment the search word; obtaining a set of search keywords; marking the search keyword set after word segmentation as G;
step P2: it can be understood that, in the search terms, there are some interfering words that do not have specific meanings; most of the words belong to the same part of speech; for example: the quantifier "one", obviously does not help the search for the keyword; therefore, it is necessary to remove some words that do not help in advance;
pre-generating a part-of-speech blacklist; the part-of-speech blacklist is a part-of-speech set, and all parts of speech in the part-of-speech blacklist are not used as search keywords; the part-of-speech blacklist is set according to actual experience; performing part-of-speech analysis on the search keywords in the search keyword set G by using a part-of-speech tagging algorithm; removing search keywords with parts of speech in a part of speech blacklist; marking the rest search keyword sets as H;
step P3: the cloud platform sorts the search keywords in the search keyword set H in a descending order according to the search number; marking the sorted search keyword set as H1;
for each search keyword H in the search keyword set H1, the cloud platform searches cloud data related to the search keyword H; specifically, searching for relevant cloud data includes the following steps:
step Q1: the cloud platform searches the search keyword h from the sorted search keywords according to the lexicographic order of the search keyword h; if the search keyword h is not found, turning to the step Q2; otherwise, turning to the step Q3;
step Q2: calculating the word meaning similarity of the search keyword h and all search keywords; taking the search keyword with the maximum word sense similarity as a new search keyword h; and go to step Q3;
and step Q3: returning a cloud data set Ph corresponding to the search keyword h to the search client; sequencing according to the click rate of the cloud data from large to small, and displaying a cloud data title and an abstract to a user according to the sequence of the sequenced cloud data;
step Q4: acquiring a search keyword set Sh with similar meaning of the search keyword h; for each search keyword s in the search keyword set Sh, acquiring a cloud data set Ps corresponding to the search keyword s; the word sense similarity between the search keyword s and the search keyword h is marked as lsh; marking each piece of cloud data in the cloud data set Ps as p, and marking the click rate of the cloud data p as Kp; calculating the display priority Fp of each piece of cloud data p; the formula is calculated as Fp = α lsh + β kp; wherein alpha and beta are respectively proportional coefficients preset according to actual experience;
step Q5: sorting the cloud data p in the cloud data set Ps corresponding to all the search keywords s in the search keyword set Sh according to the priority Fp from large to small; and displaying titles and abstracts of the cloud data to a user according to the sorted order of all the cloud data.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of associating search keywords with similar word senses by pre-calculating word sense similarity among all the search keywords; sequencing the cloud data corresponding to each search keyword through the click rate of each cloud data; the method comprises the steps that a search word input by a user is segmented by using a segmentation tool, and a plurality of search keywords are obtained; then searching a cloud data set corresponding to each search keyword; and a cloud data set corresponding to the search keyword with a similar word sense to each search keyword; preferentially displaying the cloud data sets corresponding to the search keywords, and then displaying the cloud data sets corresponding to the search keywords with similar meaning; the accuracy and the practicability of the keyword search result of the user are guaranteed.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The technical solutions of the present invention will be described below clearly and completely in conjunction with the embodiments, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an internet search method based on cloud data keywords includes the following steps:
the method comprises the following steps: the user uploads the cloud data to the cloud platform; the cloud data comprises titles, abstracts and detailed contents; and the user can autonomously select to submit or not submit the search keyword;
for the cloud data submitted with the search keywords, the submitted search keywords are the keywords needed to be used for searching the cloud data; for cloud data which are not submitted with search keywords, keyword extraction is carried out on titles, abstracts and detailed contents of the cloud data by using a keyword extraction algorithm; the extracted keywords are keywords needed to be used for searching the cloud data;
step two: sorting and numbering search keywords of a user from large to small according to the search times; numbering search keywords as 1,2, \8230, N in sequence; wherein N is the number of search keywords;
finding out a search key phrase similar to the semanteme of each search key word according to the sequence of 1,2, \8230; for each search keyword n, finding a search keyword group similar to the search keyword in semantics specifically comprises the following steps:
step S1: calculating semantic similarity between the search keyword n and all other search keywords by using an NLP technology;
step S2: counting all search keywords with the similarity degree n larger than the similarity degree threshold t from all the search keywords; and using a set form to store the search key phrase; marking a search keyword set with similar word senses corresponding to the search keywords n as Sn; the similarity threshold t is set according to actual experience; defining the search keywords with the word sense similarity larger than the pixel point threshold value t as similar word senses;
and step S3: for the search keywords in the search keyword set Sn, sorting the search keywords from large to small according to the similarity of the search keywords;
step three: sorting the cloud data according to a lexicographic order of the search keywords; marking the search key words as k; for each search keyword k, storing the cloud data containing k in all the search keywords by using a set; marking the cloud data set containing the search keyword k corresponding to the search keyword k as Pk; sorting the cloud data in the cloud data set Pk from large to small according to the click rate;
step four: the method comprises the following steps that a user inputs a search word at a search client and clicks a search button to search, and the search client sends the search word to a cloud platform through a wireless network; the cloud platform searches for cloud data which accord with the search terms and sends the cloud data to the search client;
specifically, the cloud platform searching for the cloud data conforming to the search terms comprises the following steps:
step P1: it can be understood that, when the user uses the keyword search function, the filled-in search words are often in the form of sentences; therefore, keywords of a sentence need to be extracted from the searched sentence; segmenting the search words by using a word segmentation tool; obtaining a set of search keywords; marking the search keyword set after word segmentation as G;
step P2: it can be understood that, in the search terms, there are some interfering words that do not have specific meanings; most of the words belong to the same part of speech; for example: the quantifier "one", obviously does not help the search for the keyword; therefore, it is necessary to remove some words that do not help in advance;
generating a part-of-speech blacklist in advance; the part-of-speech blacklist is a part-of-speech set, and all parts of speech in the part-of-speech blacklist are not used as search keywords; the part-of-speech blacklist is set according to actual experience; performing part-of-speech analysis on the search keywords in the search keyword set G by using a part-of-speech tagging algorithm; removing search keywords with parts of speech in a part of speech blacklist; marking the rest search keyword sets as H;
and step P3: the cloud platform sorts the search keywords in the search keyword set H in a descending order according to the search number; marking the sorted search keyword set as H1;
for each search keyword H in the search keyword set H1, the cloud platform searches cloud data related to the search keyword H; specifically, searching for relevant cloud data includes the following steps:
step Q1: the cloud platform searches the search keyword h from the sorted search keywords according to the lexicographic order of the search keyword h; if the search keyword h is not found, turning to the step Q2; otherwise, turning to the step Q3;
and step Q2: calculating the word meaning similarity of the search keyword h and all search keywords; taking the search keyword with the maximum word sense similarity as a new search keyword h; and go to step Q3;
and step Q3: returning a cloud data set Ph corresponding to the search keyword h to the search client; sequencing according to the click quantity of the cloud data from large to small, and displaying a cloud data title and an abstract to a user according to the sequence of the sequenced cloud data;
step Q4: acquiring a search keyword set Sh with similar meaning of the search keyword h; for each search keyword s in the search keyword set Sh, acquiring a cloud data set Ps corresponding to the search keyword s; the word sense similarity between the search keyword s and the search keyword h is marked as lsh; marking each piece of cloud data in the cloud data set Ps as p, and marking the click rate of the cloud data p as Kp; calculating the display priority Fp of each piece of cloud data p; the formula is calculated as Fp = α lsh + β kp; wherein alpha and beta are respectively proportional coefficients preset according to actual experience;
and step Q5: sorting the cloud data p in the cloud data set Ps corresponding to all the search keywords s in the search keyword set Sh from large to small according to the priority Fp; all the cloud data are displayed to a user according to the sequenced sequence, and the titles and the abstracts of the cloud data are displayed to the user;
it can be understood that the cloud data displayed to the user by the cloud platform is divided into two parts; the first part is cloud data found according to the search keyword h; obviously, such cloud data is the data that best meets the needs of the user; thus, when presented to the user, has the highest priority; secondly, acquiring corresponding cloud data according to a search keyword close to the search keyword h by the second part; when the cloud data are displayed for the user, the word meaning similarity among the search keywords and the click rate of each piece of cloud data are comprehensively considered; the method can guarantee that the user can obtain the most similar and useful cloud data;
in order to facilitate searching, the cloud data needs to have a title and an abstract when being uploaded by a user; the detailed content of the cloud data can be text data or non-text data;
the search client and the cloud platform are respectively the front end and the back end of a search program; the front end is mainly used for interacting with a user, acquiring search keywords of the user and displaying titles and abstracts of cloud data to the user, and further, after the user clicks the title, detailed contents of the cloud data can be checked; the back end is mainly used for searching corresponding cloud data according to the search keywords of the user;
the click rate is the number of times that each cloud data title is clicked by a user and the detailed content of the cloud data is checked; it can be understood that the more clicked the cloud data title, the more approved the details of the cloud data title are by the user.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.
Claims (8)
1. An internet search method based on cloud data keywords is characterized by comprising the following steps:
the method comprises the following steps: the user uploads the cloud data to the cloud platform; the cloud data comprises titles, summaries and detailed contents; obtaining search keywords of each piece of cloud data;
step two: sorting and numbering search keywords of a user from large to small according to the search times; numbering search keywords in sequence as 1,2, \8230;, N; wherein N is the number of search keywords;
finding out a search key phrase similar to the semanteme of each search key word according to the sequence of 1,2, \8230;
step three: sorting the cloud data according to a lexicographic order of the search keywords; marking the search key words as k; for each search keyword k, storing the cloud data containing k in all the search keywords by using a set; marking a cloud data set containing the search keyword k corresponding to the search keyword k as Pk; sorting the cloud data in the cloud data set Pk from large to small according to the click rate;
step four: a user inputs a search word at a search client and clicks a search button for searching, and the search client sends the search word to a cloud platform through a wireless network; the cloud platform searches for cloud data conforming to the search terms and sends the cloud data titles, the summaries and the detailed contents to the search client.
2. The internet cloud data-based keyword search method of claim 1, wherein the search keyword is submitted by a user or automatically extracted by using a keyword extraction algorithm.
3. The internet cloud data-based keyword search method according to claim 1, wherein for each search keyword n, finding a search keyword group having a semantic close to the search keyword comprises the following steps:
step S1: calculating the semantic similarity between the search keyword n and all other search keywords by using an NLP (non line segment) technology;
step S2: counting all search keywords with the similarity degree n larger than the similarity degree threshold t from all the search keywords; and using a set form to store the search key phrase; marking a search keyword set with similar word senses corresponding to the search keywords n as Sn; the similarity threshold t is set according to actual experience; defining the search keywords with the word meaning similarity larger than the pixel point threshold value t as word meaning similarity;
and step S3: and sorting the search keywords in the search keyword set Sn from large to small according to the similarity of the search keywords.
4. The internet search method based on the cloud data keywords as claimed in claim 1, wherein the step of searching for the cloud data conforming to the search terms by the cloud platform comprises the following steps:
step P1: using a word segmentation tool to segment the search word; obtaining a set of search keywords; marking the search keyword set after word segmentation as G;
step P2: generating a part-of-speech blacklist in advance; performing part-of-speech analysis on the search keywords in the search keyword set G by using a part-of-speech tagging algorithm; removing search keywords with parts of speech in a part of speech blacklist; marking the rest search keyword sets as H;
and step P3: the cloud platform sorts the search keywords in the search keyword set H in a descending order according to the search number; marking the sorted search keyword set as H1;
for each search keyword H in the search keyword set H1, the cloud platform searches cloud data related to the search keyword H.
5. The internet search method based on the cloud data keywords according to claim 1, wherein the cloud platform searches the cloud data related to the search keywords h, and comprises the following steps:
step Q1: the cloud platform searches the search keyword h from the sorted search keywords according to the lexicographic order of the search keyword h; if the search keyword h is not found, turning to the step Q2; otherwise, turning to the step Q3;
and step Q2: calculating the word meaning similarity of the search keyword h and all search keywords; taking the search keyword with the maximum word sense similarity as a new search keyword h; and go to step Q3;
and step Q3: returning a cloud data set Ph corresponding to the search keyword h to the search client; sequencing according to the click rate of the cloud data from large to small, and displaying a cloud data title and an abstract to a user according to the sequence of the sequenced cloud data;
step Q4: acquiring a search keyword set Sh with similar meaning of the search keyword h; for each search keyword s in the search keyword set Sh, acquiring a cloud data set Ps corresponding to the search keyword s; the word sense similarity between the search keyword s and the search keyword h is marked as lsh; marking each piece of cloud data in the cloud data set Ps as p, and marking the click rate of the cloud data p as Kp; calculating the display priority Fp of each piece of cloud data p; the formula is calculated as Fp = α lsh + β kp; wherein alpha and beta are respectively proportional coefficients preset according to actual experience;
step Q5: sorting the cloud data p in the cloud data set Ps corresponding to all the search keywords s in the search keyword set Sh according to the priority Fp from large to small; and displaying titles and abstracts of the cloud data to a user according to the sorted sequence of all the cloud data.
6. The internet cloud data-based keyword search method according to claim 1, wherein the click rate is the number of times each cloud data title is clicked by a user and details of the cloud data are viewed.
7. The internet cloud-based data keyword search method as claimed in claim 4, wherein the part-of-speech blacklist is a set of parts-of-speech, and none of the parts-of-speech in the part-of-speech blacklist is used as a search keyword; the part of speech blacklist is set according to actual experience.
8. The internet search method based on the cloud data keywords as claimed in claim 1, wherein the search client and the cloud platform are respectively a front end and a back end of a search program; the front end is used for interacting with a user, obtaining search keywords of the user, displaying titles and abstracts of cloud data to the user, and checking detailed contents of the cloud data after the user clicks the titles; the back end is used for searching corresponding cloud data according to the search keywords of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210995701.8A CN115292605A (en) | 2022-08-18 | 2022-08-18 | Internet cloud data-based keyword search method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210995701.8A CN115292605A (en) | 2022-08-18 | 2022-08-18 | Internet cloud data-based keyword search method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115292605A true CN115292605A (en) | 2022-11-04 |
Family
ID=83830159
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210995701.8A Pending CN115292605A (en) | 2022-08-18 | 2022-08-18 | Internet cloud data-based keyword search method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115292605A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100299343A1 (en) * | 2009-05-22 | 2010-11-25 | Microsoft Corporation | Identifying Task Groups for Organizing Search Results |
| US20150058309A1 (en) * | 2013-08-23 | 2015-02-26 | Naver Corporation | Keyword presenting system and method based on semantic depth structure |
| US20160125462A1 (en) * | 2014-10-31 | 2016-05-05 | Informite Inc. | Systems and methods for semantic keyword analysis for paid search |
| US20170124081A1 (en) * | 2015-11-02 | 2017-05-04 | International Business Machines Corporation | Rank-based calculation for keyword searches |
| CN108804409A (en) * | 2017-04-28 | 2018-11-13 | 西安科技大市场创新云服务股份有限公司 | A kind of semantic retrieving method and device |
| CN112559895A (en) * | 2021-02-19 | 2021-03-26 | 深圳平安智汇企业信息管理有限公司 | Data processing method and device, electronic equipment and storage medium |
-
2022
- 2022-08-18 CN CN202210995701.8A patent/CN115292605A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100299343A1 (en) * | 2009-05-22 | 2010-11-25 | Microsoft Corporation | Identifying Task Groups for Organizing Search Results |
| US20150058309A1 (en) * | 2013-08-23 | 2015-02-26 | Naver Corporation | Keyword presenting system and method based on semantic depth structure |
| US20160125462A1 (en) * | 2014-10-31 | 2016-05-05 | Informite Inc. | Systems and methods for semantic keyword analysis for paid search |
| US20170124081A1 (en) * | 2015-11-02 | 2017-05-04 | International Business Machines Corporation | Rank-based calculation for keyword searches |
| CN108804409A (en) * | 2017-04-28 | 2018-11-13 | 西安科技大市场创新云服务股份有限公司 | A kind of semantic retrieving method and device |
| CN112559895A (en) * | 2021-02-19 | 2021-03-26 | 深圳平安智汇企业信息管理有限公司 | Data processing method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王菁;王若飞;: "基于日志挖掘的电商查询建议方法", 计算机工程与科学, no. 02, 15 February 2018 (2018-02-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649260B (en) | Product characteristic structure tree construction method based on comment text mining | |
| CN108460014B (en) | Enterprise entity identification method and device, computer equipment and storage medium | |
| CN110888990B (en) | Text recommendation method, device, equipment and medium | |
| CN112131863B (en) | Comment opinion theme extraction method, electronic equipment and storage medium | |
| CN110597988A (en) | Text classification method, device, equipment and storage medium | |
| Viola et al. | Learning to extract information from semi-structured text using a discriminative context free grammar | |
| US9477747B2 (en) | Method and apparatus for acquiring hot topics | |
| CN101872351B (en) | Method, device for identifying synonyms, and method and device for searching by using same | |
| US20100205198A1 (en) | Search query disambiguation | |
| CN111444330A (en) | Method, device and equipment for extracting short text keywords and storage medium | |
| CN112395395B (en) | Text keyword extraction method, device, equipment and storage medium | |
| CN108549723B (en) | Text concept classification method and device and server | |
| CN108509490B (en) | Network hot topic discovery method and system | |
| CN113886604A (en) | Job knowledge map generation method and system | |
| CN114065758A (en) | Document keyword extraction method based on hypergraph random walk | |
| CN113821605A (en) | Event extraction method | |
| CN112989208A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN111309916A (en) | Abstract extraction method and device, storage medium and electronic device | |
| CN108388556B (en) | Method and system for mining homogeneous entity | |
| CN110705285B (en) | Government affair text subject word library construction method, device, server and readable storage medium | |
| CN107239455B (en) | Core word recognition method and device | |
| CN118113806A (en) | Interpretable event context generation method for large model retrieval enhancement generation | |
| Bartík | Text-based web page classification with use of visual information | |
| CN108427769B (en) | Character interest tag extraction method based on social network | |
| Çano | Albmore: A corpus of movie reviews for sentiment analysis in albanian |
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 |