CN113779363B - Search optimization method and device based on deep neural network - Google Patents

Search optimization method and device based on deep neural network Download PDF

Info

Publication number
CN113779363B
CN113779363B CN202111075569.0A CN202111075569A CN113779363B CN 113779363 B CN113779363 B CN 113779363B CN 202111075569 A CN202111075569 A CN 202111075569A CN 113779363 B CN113779363 B CN 113779363B
Authority
CN
China
Prior art keywords
search
keywords
content
module
searching
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.)
Active
Application number
CN202111075569.0A
Other languages
Chinese (zh)
Other versions
CN113779363A (en
Inventor
李保平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Huitong Guoxin Technology Co ltd
Original Assignee
Guangzhou Huitong Guoxin Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Huitong Guoxin Technology Co ltd filed Critical Guangzhou Huitong Guoxin Technology Co ltd
Priority to CN202111075569.0A priority Critical patent/CN113779363B/en
Publication of CN113779363A publication Critical patent/CN113779363A/en
Application granted granted Critical
Publication of CN113779363B publication Critical patent/CN113779363B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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
    • G06F16/904—Browsing; Visualisation therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a search optimization method and a search optimization device based on a deep neural network, which relate to the technical field of search optimization of the deep neural network, and aim at solving the problems of lack of utilization of the deep neural network and low search pertinence and precision in the technical field of search at present, the invention provides the following scheme, wherein the search optimization method of the deep neural network comprises the following steps: s1, searching and receiving: receiving a search request of a user and receiving search content input by the user; s2, search analysis: analyzing the input search content, and extracting keywords of the search content according to the analysis; s3, keyword comparison: and comparing the extracted search keywords with the existing data keywords of the database, judging the keywords according to the comparison, and optimizing and perfecting. The invention performs double judgment through keyword analysis comparison and search content list selection, improves the pertinence and the accuracy of search, and optimizes the search effect.

Description

Search optimization method and device based on deep neural network
Technical Field
The invention relates to the technical field of search optimization of a deep neural network, in particular to a search optimization method and device based on the deep neural network.
Background
Deep neural networks are a technology in the field of machine learning, which can be used for processing data fitting, data classification, clustering and dimension reduction problems, and can be used for trend prediction, weather forecast, text classification, image recognition, voice recognition, emotion recognition, feature extraction and feature discovery from the application perspective.
The search technology can help users to find needed information from a huge information base, but with the enlargement of data and the progress of the search technology, the searchable information is more and more, so that the search method and the search device are required to be optimized to meet the search requirement and improve the pertinence and the accuracy of the search, and therefore, in order to solve the problems, the search optimization method and the search device based on the deep neural network are provided.
Disclosure of Invention
The search optimization method and device based on the deep neural network provided by the invention solve the problems of lack of utilization of the deep neural network and low search pertinence and accuracy in the technical field of search at present.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a search optimization method based on a deep neural network comprises the following steps:
s1, searching and receiving: receiving a search request of a user and receiving search content input by the user;
s2, search analysis: analyzing the input search content, and extracting keywords of the search content according to the analysis;
s3, keyword comparison: comparing the extracted search keywords with the existing data keywords of the database, judging the keywords according to the comparison, and optimizing and perfecting;
s4, searching a list: according to the compared search keywords, performing list display on related content searched by the keywords according to selection, and enabling a user to perform search selection according to the matching degree of the searched content;
s5, list selection: the user selects the contents of the list according to the self searching content requirement;
s6, extracting contents: and extracting search contents according to the selection of the user to the search list to finish the search.
And step S1, searching and receiving the related search request of the receiving user, receiving search content input by the user, filtering, sorting and perfecting the search content after receiving the search content, and transmitting the filtered, sorted and perfected search content to the next link.
The step S2 of analyzing the input search content related to the search analysis, and extracting the keywords of the search content according to the analysis, wherein when extracting the keywords of the search content, the keyword extraction model from the database is firstly accepted, and the extraction is performed according to the search keyword extraction model of the database.
And step S3, comparing the extracted search keywords with the existing data keywords of the database, judging the keywords according to the comparison, optimizing and perfecting, continuously searching the keywords when the keywords similar to and related to the extracted keywords appear in the database, and jumping back to a search analysis step when the keywords similar to and related to the extracted keywords do not exist in the database, and re-analyzing the search content until the keywords similar to and related to the extracted keywords and the database are cancelled by a user, or canceling the search by the user, wherein the database data is derived from a deep neural network and user input.
And step S4, searching the search keywords related to the list according to the comparison, displaying the list of related contents searched by the keywords according to the selection, and allowing a user to search and select according to the matching degree of the search contents, wherein the list of the search contents is displayed according to the keywords, and the list sequence is divided into an ascending sequence and a descending sequence of relevance, time and search frequency.
And step S5, the user involved in the list selection selects the content of the list according to the self search content requirement, and when the search content required by the user does not exist in the list, the search jump returns to the search analysis of step S2, and the search content is analyzed again until the search content required by the user is matched or the user cancels the search.
And step S6, extracting search contents according to the selection of the user to the search list, completing the search, wherein the extraction of the search list contents corresponding to the search keywords designated by the user selection, and the extracted search contents are disclosed and recorded.
A deep neural network-based search optimization apparatus comprising a receiving section, an optimizing section, and an extracting section, the receiving section comprising:
the receiving module is connected with the analysis module and is used for receiving a search content request input by a user, filtering, sorting and perfecting the received search content and transmitting the filtered, sorted and perfected search content to the analysis module;
the analysis module is connected with the receiving module, the comparison module and the judging module and is used for receiving the search content transmitted by the receiving module, then combining a keyword extraction model of the deep neural network, analyzing the received search content, extracting keywords, receiving search error information returned by the comparison module and the judging module, re-analyzing the search content and extracting the keywords according to the returned information until the comparison and the judgment are correct, or the user gives up searching, carries out search termination, and transmits the extracted keywords to the comparison module;
the optimizing section includes:
the comparison module is connected with the analysis module and the search module and is used for receiving the keywords extracted by the search content transmitted by the analysis module, then combining the keywords of the database, comparing the two groups of keywords, judging the keywords of the search content according to the comparison result, optimizing and perfecting the keywords, returning to the analysis module when the keywords of the database are not similar to and related to the extracted keywords, analyzing the search content again through the analysis module until the keywords similar to and related to the keywords of the database are extracted, or canceling the search by a user, stopping the search, continuing the search on the keywords when the keywords of the database are similar to and related to the extracted keywords, and transmitting the search keywords to the search module;
the search module is connected with the comparison module and the judgment module and is used for receiving the search keywords transmitted by the comparison module, searching the keywords, displaying a search content list associated with the search keywords after searching, and transmitting the search content list to the judgment module;
the extraction section includes:
the judging module is connected with the searching module, the extracting module and the analyzing module and is used for receiving the searching content list transmitted by the searching module, judging the content displayed by the searching list, returning the searching jump to the analyzing module when no searching content required by a user exists in the searching list, analyzing the searching content again by the analyzing module until the searching content required by the user is matched, or canceling the searching by the user, carrying out searching termination, and confirming the searching content when the searching content required by the user exists in the searching list and transmitting a confirmation result to the extracting module;
and the extraction module is connected with the judging module and is used for receiving the confirmation result transmitted by the judging module, extracting the search content data according to the confirmed list content and generating search content details.
The beneficial effects of the invention are as follows:
the search content is analyzed and extracted through the setting analysis module, the database is compared through the comparison module, so that the most suitable search keywords are extracted, the list display is carried out on the related data of the search content according to the search keywords, the users can carry out comparison selection until the most suitable search content is selected, search content details are generated, double judgment is carried out through keyword analysis comparison and search content list selection, the search is optimized, the pertinence and the accuracy of the search are improved, and the search effect is optimized.
In summary, the search optimizing method and the optimizing device based on the deep neural network perform double judgment through keyword analysis comparison and search content list selection, improve pertinence and accuracy of search, and optimize search effect.
Drawings
Fig. 1 is a flowchart of a search optimization method based on a deep neural network according to the present invention.
Fig. 2 is a block diagram of a search optimizing apparatus based on a deep neural network according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Example 1
Referring to fig. 2, a search optimizing apparatus based on a deep neural network includes a receiving part, an optimizing part, and an extracting part, the receiving part including:
the receiving module is connected with the analysis module and is used for receiving a search content request input by a user, filtering, sorting and perfecting the received search content and transmitting the filtered, sorted and perfected search content to the analysis module;
the analysis module is connected with the receiving module, the comparison module and the judging module and is used for receiving the search content transmitted by the receiving module, then combining a keyword extraction model of the deep neural network, analyzing the received search content, extracting keywords, receiving search error information returned by the comparison module and the judging module, re-analyzing the search content and extracting the keywords according to the returned information until the comparison and the judgment are correct, or the user gives up searching, carries out search termination, and transmits the extracted keywords to the comparison module;
the optimizing section includes:
the comparison module is connected with the analysis module and the search module and is used for receiving the keywords extracted by the search content transmitted by the analysis module, then combining the keywords of the database, comparing the two groups of keywords, judging the keywords of the search content according to the comparison result, optimizing and perfecting the keywords, returning to the analysis module when the keywords of the database are not similar to and related to the extracted keywords, analyzing the search content again through the analysis module until the keywords similar to and related to the keywords of the database are extracted, or canceling the search by a user, stopping the search, continuing the search on the keywords when the keywords of the database are similar to and related to the extracted keywords, and transmitting the search keywords to the search module;
the search module is connected with the comparison module and the judgment module and is used for receiving the search keywords transmitted by the comparison module, searching the keywords, displaying a search content list associated with the search keywords after searching, and transmitting the search content list to the judgment module;
the extraction section includes:
the judging module is connected with the searching module, the extracting module and the analyzing module and is used for receiving the searching content list transmitted by the searching module, judging the content displayed by the searching list, returning the searching jump to the analyzing module when no searching content required by a user exists in the searching list, analyzing the searching content again by the analyzing module until the searching content required by the user is matched, or canceling the searching by the user, carrying out searching termination, and confirming the searching content when the searching content required by the user exists in the searching list and transmitting a confirmation result to the extracting module;
and the extraction module is connected with the judging module and is used for receiving the confirmation result transmitted by the judging module, extracting the search content data according to the confirmed list content and generating search content details.
Example 2
As shown in fig. 1, a search optimization method based on a deep neural network includes the following steps:
s1, searching and receiving: receiving a search request of a user, receiving search content input by the user, filtering, sorting and perfecting the search content after receiving the search content, and transmitting the filtered, sorted and perfected search content to the next link;
s2, search analysis: analyzing input search content, extracting keywords of the search content according to the analysis, and firstly receiving a keyword extraction model from a database and extracting according to the search keyword extraction model of the database when extracting the keywords of the search content;
s3, keyword comparison: comparing the extracted search keywords with the existing data keywords of the database, judging the keywords according to the comparison, optimizing and perfecting the keywords, continuously searching the keywords when the keywords similar to and related to the extracted keywords appear in the database, returning to a search analysis step when the keywords similar to and related to the database are not found in the database, and re-analyzing the search content until the keywords similar to and related to the extracted keywords and the database are found out by a user, or canceling the search by the user, wherein the database data is input by a deep neural network and the user;
s4, searching a list: according to the compared search keywords, performing list display on related content searched by the keywords according to selection, and allowing a user to perform search selection according to the matching degree of the searched content, wherein the list display is performed on the searched content according to the keywords, and the list sequence is divided into an ascending sequence and a descending sequence of relevance, time and search frequency;
s5, list selection: the user selects the content of the list according to the own search content requirement, when the search content required by the user does not exist in the list, the search jump returns to the search analysis of the step S2, and the search content is analyzed again until the search content required by the user is matched or the user cancels the search;
s6, extracting contents: according to the selection of the user to the search list, the search content is extracted to finish the search, the extracted search list content corresponding to the designated search keyword is selected by the user, and the extracted search content is disclosed and recorded.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.

Claims (1)

1. The search optimization method based on the deep neural network is characterized by comprising the following steps of:
s1, searching and receiving: receiving a search request of a user and receiving search content input by the user;
s2, search analysis: analyzing the input search content, and extracting keywords of the search content according to the analysis;
s3, keyword comparison: comparing the extracted search keywords with the existing data keywords of the database, judging the keywords according to the comparison, and optimizing and perfecting;
s4, searching a list: according to the compared search keywords, performing list display on related content searched by the keywords according to selection, and enabling a user to perform search selection according to the matching degree of the searched content;
s5, list selection: the user selects the contents of the list according to the self searching content requirement;
s6, extracting contents: extracting search content according to the selection of the user to the search list to finish the search;
step S1, searching and receiving the related search request of the receiving user, receiving search content input by the user, filtering, sorting and perfecting the search content after receiving the search content, and transmitting the filtered, sorted and perfected search content to the next link;
s2, analyzing input search content related to search analysis, and extracting keywords of the search content according to the analysis, wherein when the keywords of the search content are extracted, a keyword extraction model from a database is received at first, and extraction is performed according to the search keyword extraction model of the database;
step S3, comparing the extracted search keywords with the existing data keywords of the database, judging the keywords according to the comparison, optimizing and perfecting the keywords, continuing searching the keywords when the keywords similar to and related to the extracted keywords appear in the database, and jumping back to a search analysis step when the keywords similar to and related to the extracted keywords do not exist in the database, and re-analyzing the search content until the keywords similar to and related to the extracted keywords and the database are cancelled by a user;
s3, comparing the extracted search keywords with the existing data keywords of the database, judging the keywords according to the comparison, optimizing and perfecting, wherein the database data is derived from a deep neural network and input by a user;
step S4, searching the search keywords related to the list according to the comparison, displaying the list of related contents searched by the keywords according to the selection, and allowing a user to search and select according to the matching degree of the search contents, wherein the list of the search contents is displayed according to the keywords, and the list sequence is divided into an ascending sequence and a descending sequence of relevance, time and search frequency;
step S5, the user involved in list selection selects the content of the list according to the self search content requirement, when the search content required by the user does not exist in the list, the search jump returns to the search analysis of step S2, the search content is analyzed again until the search content required by the user is matched, or the user cancels the search;
step S6, extracting search contents according to the selection of a user to a search list, completing the search, wherein the extraction of the search list contents corresponding to the search keywords designated by the user selection, and the extracted search contents are shown and recorded;
the optimizing device of the search optimizing method based on the deep neural network comprises a receiving part, an optimizing part and an extracting part, wherein the receiving part comprises:
the receiving module is connected with the analysis module and is used for receiving a search content request input by a user, filtering, sorting and perfecting the received search content and transmitting the filtered, sorted and perfected search content to the analysis module;
the analysis module is connected with the receiving module, the comparison module and the judging module and is used for receiving the search content transmitted by the receiving module, then combining a keyword extraction model of the deep neural network, analyzing the received search content, extracting keywords, receiving search error information returned by the comparison module and the judging module, re-analyzing the search content and extracting the keywords according to the returned information until the comparison and the judgment are correct, or the user gives up searching, carries out search termination, and transmits the extracted keywords to the comparison module;
the optimizing section includes:
the comparison module is connected with the analysis module and the search module and is used for receiving the keywords extracted by the search content transmitted by the analysis module, then combining the keywords of the database, comparing the two groups of keywords, judging the keywords of the search content according to the comparison result, optimizing and perfecting the keywords, returning to the analysis module when the keywords of the database are not similar to and related to the extracted keywords, analyzing the search content again through the analysis module until the keywords similar to and related to the keywords of the database are extracted, or canceling the search by a user, stopping the search, continuing the search on the keywords when the keywords of the database are similar to and related to the extracted keywords, and transmitting the search keywords to the search module;
the search module is connected with the comparison module and the judgment module and is used for receiving the search keywords transmitted by the comparison module, searching the keywords, displaying a search content list associated with the search keywords after searching, and transmitting the search content list to the judgment module;
the extraction section includes:
the judging module is connected with the searching module, the extracting module and the analyzing module and is used for receiving the searching content list transmitted by the searching module, judging the content displayed by the searching list, returning the searching jump to the analyzing module when no searching content required by a user exists in the searching list, analyzing the searching content again by the analyzing module until the searching content required by the user is matched, or canceling the searching by the user, carrying out searching termination, and confirming the searching content when the searching content required by the user exists in the searching list and transmitting a confirmation result to the extracting module;
and the extraction module is connected with the judging module and is used for receiving the confirmation result transmitted by the judging module, extracting the search content data according to the confirmed list content and generating search content details.
CN202111075569.0A 2021-09-14 2021-09-14 Search optimization method and device based on deep neural network Active CN113779363B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111075569.0A CN113779363B (en) 2021-09-14 2021-09-14 Search optimization method and device based on deep neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111075569.0A CN113779363B (en) 2021-09-14 2021-09-14 Search optimization method and device based on deep neural network

Publications (2)

Publication Number Publication Date
CN113779363A CN113779363A (en) 2021-12-10
CN113779363B true CN113779363B (en) 2023-12-22

Family

ID=78843746

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111075569.0A Active CN113779363B (en) 2021-09-14 2021-09-14 Search optimization method and device based on deep neural network

Country Status (1)

Country Link
CN (1) CN113779363B (en)

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001290840A (en) * 2000-04-04 2001-10-19 Matsushita Electric Ind Co Ltd Keyword retrieval device
KR20020003915A (en) * 2000-06-26 2002-01-16 김상배 A method for providing search result including recommendation of search condition, and a server thereof
CN102402561A (en) * 2010-09-19 2012-04-04 中国移动通信集团四川有限公司 Searching method and device
CN103020049A (en) * 2011-09-20 2013-04-03 中国电信股份有限公司 Searching method and searching system
CN107220386A (en) * 2017-06-29 2017-09-29 北京百度网讯科技有限公司 Information-pushing method and device
CN110287325A (en) * 2019-06-28 2019-09-27 南方电网科学研究院有限责任公司 Power grid customer service recommendation method and device based on intelligent voice analysis
CN110413764A (en) * 2019-06-18 2019-11-05 杭州熊猫智云企业服务有限公司 Long text enterprise name recognizer based on built in advance dictionary
CN110968684A (en) * 2019-12-18 2020-04-07 腾讯科技（深圳）有限公司 Information processing method, device, equipment and storage medium
CN111782770A (en) * 2020-07-03 2020-10-16 国网电子商务有限公司 Searching method and system based on category analysis recall rule
CN111797115A (en) * 2020-06-28 2020-10-20 中国工商银行股份有限公司 Employee information searching method and device
CN112241463A (en) * 2020-10-15 2021-01-19 苏州零泉科技有限公司 Search method based on fusion of text semantics and picture information
JP2021086592A (en) * 2019-12-23 2021-06-03 株式会社ＡＩ Ｓａｍｕｒａｉ Document information evaluation device and document information evaluation method, and document information evaluation program
CN112926300A (en) * 2021-03-31 2021-06-08 深圳市优必选科技股份有限公司 Image searching method, image searching device and terminal equipment
CN113220894A (en) * 2021-02-07 2021-08-06 国家卫星气象中心(国家空间天气监测预警中心) Intelligent satellite remote sensing data acquisition method based on perception calculation

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001290840A (en) * 2000-04-04 2001-10-19 Matsushita Electric Ind Co Ltd Keyword retrieval device
KR20020003915A (en) * 2000-06-26 2002-01-16 김상배 A method for providing search result including recommendation of search condition, and a server thereof
CN102402561A (en) * 2010-09-19 2012-04-04 中国移动通信集团四川有限公司 Searching method and device
CN103020049A (en) * 2011-09-20 2013-04-03 中国电信股份有限公司 Searching method and searching system
CN107220386A (en) * 2017-06-29 2017-09-29 北京百度网讯科技有限公司 Information-pushing method and device
CN110413764A (en) * 2019-06-18 2019-11-05 杭州熊猫智云企业服务有限公司 Long text enterprise name recognizer based on built in advance dictionary
CN110287325A (en) * 2019-06-28 2019-09-27 南方电网科学研究院有限责任公司 Power grid customer service recommendation method and device based on intelligent voice analysis
CN110968684A (en) * 2019-12-18 2020-04-07 腾讯科技（深圳）有限公司 Information processing method, device, equipment and storage medium
JP2021086592A (en) * 2019-12-23 2021-06-03 株式会社ＡＩ Ｓａｍｕｒａｉ Document information evaluation device and document information evaluation method, and document information evaluation program
CN111797115A (en) * 2020-06-28 2020-10-20 中国工商银行股份有限公司 Employee information searching method and device
CN111782770A (en) * 2020-07-03 2020-10-16 国网电子商务有限公司 Searching method and system based on category analysis recall rule
CN112241463A (en) * 2020-10-15 2021-01-19 苏州零泉科技有限公司 Search method based on fusion of text semantics and picture information
CN113220894A (en) * 2021-02-07 2021-08-06 国家卫星气象中心(国家空间天气监测预警中心) Intelligent satellite remote sensing data acquisition method based on perception calculation
CN112926300A (en) * 2021-03-31 2021-06-08 深圳市优必选科技股份有限公司 Image searching method, image searching device and terminal equipment

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
A web search engine-based approach to measure semantic similarity between words;Bollegala D 等;IEEE Transactions on knowledge and Data Engineering;第23卷(第7期);977-990 *
基于深度神经网络的电子商务智能客服系统设计与实现;张瀚月 等;软件工程;第24卷(第05期);33-37 *
基于知识抽取的软件问答网站搜索优化设计;梁仁华;彭鑫;Zhenchang Xing;赵文耘;;计算机应用与软件(第12期);77-82+152 *

Also Published As

Publication number Publication date
CN113779363A (en) 2021-12-10

Similar Documents

Publication Publication Date Title
CN102629246B (en) Recognize the server and browser voice command identification method of browser voice command
CN110909145B (en) Training method and device for multi-task model
CN112035599B (en) Query method and device based on vertical search, computer equipment and storage medium
CN107704453A (en) A kind of word semantic analysis, word semantic analysis terminal and storage medium
CN107305550A (en) A kind of intelligent answer method and device
CN102456054B (en) A kind of searching method and system
CN105843875A (en) Smart robot-oriented question and answer data processing method and apparatus
CN101986293A (en) Method and equipment for displaying search answer information on search interface
CN102968987A (en) Speech recognition method and system
CN107408107A (en) Text prediction is integrated
CN109255012B (en) Method and device for machine reading understanding and candidate data set size reduction
CN106951503A (en) Information providing method, device, equipment and storage medium
CN108549697A (en) Information-pushing method, device, equipment based on semantic association and storage medium
CN104077327B (en) The recognition methods of core word importance and equipment and search result ordering method and equipment
CN113076423A (en) Data processing method and device and data query method and device
CN110413645A (en) Data search method, device, terminal and computer readable storage medium
CN111125145A (en) Automatic system for acquiring database information through natural language
JPWO2016178337A1 (en) Information processing apparatus, information processing method, and computer program
CN111460114A (en) Retrieval method, device, equipment and computer readable storage medium
CN103425767B (en) A kind of determination method and system pointing out data
CN103020311B (en) A kind of processing method of user search word and system
CN115438142B (en) Conversational interactive data analysis report system
CN114238595A (en) Metallurgical knowledge question-answering method and system based on knowledge graph
CN117271739A (en) Man-machine interaction method and system based on natural language processing technology
CN113779363B (en) Search optimization method and device based on deep neural network

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
GR01 Patent grant
GR01 Patent grant