CN106776981B - Intelligent retrieval method based on empirical knowledge - Google Patents

Intelligent retrieval method based on empirical knowledge Download PDF

Info

Publication number
CN106776981B
CN106776981B CN201611109212.9A CN201611109212A CN106776981B CN 106776981 B CN106776981 B CN 106776981B CN 201611109212 A CN201611109212 A CN 201611109212A CN 106776981 B CN106776981 B CN 106776981B
Authority
CN
China
Prior art keywords
receiving end
request
retrieval
user
sub
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
CN201611109212.9A
Other languages
Chinese (zh)
Other versions
CN106776981A (en
Inventor
黄诗平
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 isomorphic Technology Co.,Ltd.
Original Assignee
Guangzhou Isomorphic 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 Isomorphic Technology Co Ltd filed Critical Guangzhou Isomorphic Technology Co Ltd
Priority to CN201611109212.9A priority Critical patent/CN106776981B/en
Publication of CN106776981A publication Critical patent/CN106776981A/en
Application granted granted Critical
Publication of CN106776981B publication Critical patent/CN106776981B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search 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

An intelligent retrieval method based on experience knowledge comprises the following steps: a user inputs and sends a retrieval request from a client; the receiving end determines whether to call history information and records; the receiving end divides the retrieval request; the receiving end analyzes the user retrieval purpose of the client according to experience; the receiving end carries out retrieval; and displaying the retrieval results in sequence from high to low according to the degree of correlation. The method can improve the retrieval speed and efficiency, and can also improve the precision ratio and the recall ratio, so that the retrieval result is more targeted and more accurate.

Description

Intelligent retrieval method based on empirical knowledge
Technical Field
The invention relates to the field of electric digital data processing, in particular to an intelligent retrieval method based on experience knowledge.
Background
With the continuous improvement of social industrialization and informatization levels, data replaces calculation to become a center of information calculation, and the internet, cloud calculation and big data are becoming a trend and trend. Nowadays, the internet has become the most important way for people to obtain information, and a great deal of valuable information and knowledge are hidden in network resources. However, the explosive growth of network resources may be called prosperity and consummation, which brings more and more abundant information to users, and at the same time, the difficulty of obtaining relevant knowledge precisely required by users is increasing. How to quickly and efficiently extract useful information from a large amount of network information has become the most important task in information retrieval today.
In the prior art, there are several search engines that attempt to solve these problems, such as hundredths, google, dog search, necessity, etc. As an important tool for information retrieval, the information retrieval method and the information retrieval device become a main way for users to experience the Internet and obtain information, and people can conveniently obtain required information on the Internet. When a user needs to obtain required information through retrieval, the satisfaction degree of a retrieval result is often not high enough. For example, if a user wants to know the information of a Chinese, the user often appears Chinese toothpaste, Chinese pencils, Chinese tubes, Chinese cigarettes and the like after searching, but the information is not exactly the information really wanted by the user, so that the user takes time to distinguish the information. In the technical field of computers, experience is knowledge or skill obtained from a number of practices; the intelligent retrieval is based on the relevance of documents and retrieval words, indexes such as the importance of the documents are comprehensively examined, and retrieval results are ranked to provide higher retrieval efficiency, so that the result ranking is more accurate, the documents most relevant to the user desire can be ranked to the top, and the retrieval efficiency is improved. Therefore, an intelligent retrieval method based on experience knowledge is urgently needed in reality, and not only can the retrieval speed and efficiency be improved, but also the precision ratio and the recall ratio can be improved.
Disclosure of Invention
One of the purposes of the invention is to provide an intelligent retrieval method based on experience knowledge, which can improve the retrieval speed and efficiency, and also can improve the precision ratio and the recall ratio, so that the retrieval result is more targeted and more accurate.
The technical scheme adopted by the invention to solve the technical problems is as follows: an intelligent retrieval method based on experience knowledge comprises the following steps: a user inputs and sends a retrieval request from a client; the receiving end determines whether to call history information and records; the receiving end divides the retrieval request; the receiving end analyzes the user retrieval purpose of the client according to experience; the receiving end carries out retrieval; and displaying the retrieval results in sequence from high to low according to the degree of correlation.
According to another aspect of the present invention, after the user inputs and transmits the retrieval request from the client in step S1, step S11 is further performed: and the user interface in the receiving end interacts with the user of the client and acquires user identification information.
According to another aspect of the present invention, the step S11 of the user interface in the receiving end interacting with the user of the client and acquiring the user identification information further includes: in step S111, the receiving end sends a query to the user of the client through the user interface: whether a user of the client performs retrieval request interaction with a receiving end before the retrieval, if so, executing step S112, otherwise, executing step S113; in step S113, directly obtaining the identification information of the user, and returning a first retrieval message to the receiving end; in step S112, the identification information of the user is directly obtained, and a message that is not retrieved for the first time is returned to the receiving end.
According to another aspect of the present invention, the receiving end determining whether to call the history information and record further comprises the steps of, in step S2: step S21, if the receiving end determines whether to call history information and record according to the message whether to search for the first time returned by the user interaction, then step S23 is executed; step S22, if the receiving end analyzes the user' S mark information of the client end directly according to the attached information of the searching request, and determines whether to call the history information and record, then step S24 is executed; step S23, if not, calling history information and record, otherwise, not calling history information and record; step S24, if the identification information matches the history information and the entries in the record, it is called, otherwise it is not called.
According to another aspect of the present invention, in step S3, the receiver-side split search request further includes: dividing a search request S into one or more sub-requests SiI is a positive integer, where S ═ S1,……,si,……,sPAnd P is the number of the sub-requests and is a positive integer.
According to another aspect of the present invention, in step S4, the analyzing the user retrieval purpose of the client based on experience by the receiving end further includes: step S41, calling historical information and records by a calling module in the receiving end; step S42, the segmentation and classification module in the receiving end performs segmentation and classification on the calling historical information and the source data in the record to obtain the frequency of segmentation and the type of the source data; step S43, the destination analysis module in the receiving end analyzes one or more sub-requests S in the retrieval request S according to the history information and the record, the frequency of word segmentation and the type of the source dataiCalculating a target value, wherein the target value is an evaluation quantitative value of which the sub-request belongs to a certain type; step S44, the retrieval module in the receiving end matches the sub-request with the source data, and counts the correlation degree of the single source data according to the matching frequency of the sub-request in different parts of the unit source data, the destination value and the type of the source data.
According to another aspect of the present invention, the calculation manner in step S43 is: first, each sub-request s is calculatediThen calculates all sub-requests siAfter which each sub-request s is judgediIf the final sum is larger than a second threshold value, selecting the highest sum as a target and adding a label.
According to another aspect of the present invention, the receiving end performs a search for further packets in step S5Comprises the following steps: step S51, based on the sub-request SiAnd the semantic extension module is used for effectively extending.
According to another aspect of the present invention, the step S51 of performing effective expansion by the semantic expansion module further comprises: step S511: first module of semantic extension module analyzes sub-request siDetermining semantics of the user request, and associating the semantics with the determined concept or object; step S512, the semantic expansion module sends a call request to the synonym/near-synonym semantic database, wherein the call request comprises a sub-request SiThe information of (a); step S513, the synonym/near-synonym meaning database returns a calling response after traversing; step S514, the semantic expansion module receives the calling response and sends the calling response to the receiving end; in addition, sub-requests s can be added as needediAnd/or its upper and lower concepts.
According to another aspect of the present invention, in step S6, the search results are displayed in order from high to low according to the degree of correlation. And carrying out statistical sorting according to the correlation degree of the single source data, and sequentially displaying the retrieval results from high to low according to the correlation degree.
Drawings
Embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which like reference numerals refer to similar elements and in which:
fig. 1 illustrates a flowchart of an intelligent retrieval method based on empirical knowledge, according to an exemplary embodiment of the present invention.
Detailed Description
In the following description, reference is made to the accompanying drawings that show, by way of illustration, several specific embodiments. It will be understood that: other embodiments are contemplated and may be made without departing from the scope or spirit of the present disclosure. The following detailed description is, therefore, not to be taken in a limiting sense.
Fig. 1 illustrates a flowchart of an intelligent retrieval method based on empirical knowledge, according to an exemplary embodiment of the present invention. The intelligent retrieval method based on experience knowledge comprises the following steps:
in step S1, the user inputs and transmits a retrieval request from the client;
in step S2, the reception end determines whether to call history information and record;
in step S3, the receiving end segments the search request;
in step S4, the receiving end analyzes the user retrieval purpose of the client based on experience;
in step S5, the receiving end performs a search; and
in step S6, the search results are displayed in order from high to low according to the degree of correlation.
Preferably, in step S1, the client is a mobile terminal, which communicates with the receiving end through a wireless link and performs retrieval. Alternatively, in step S1, the client is a computer, including but not limited to a desktop, a laptop, a portable notebook, a netbook, a tablet computer, etc., which communicates with the receiving end through a wired link or a wireless link and performs retrieval.
Preferably, in step S1, after the user inputs and transmits the retrieval request from the client, step S11 is further performed: and the user interface in the receiving end interacts with the user of the client and acquires user identification information. Preferably, the step S11 of the receiving end interacting with the user of the client and acquiring the user identification information further includes: in step S111, the receiving end sends a query to the user of the client through the user interface: whether a user of the client performs retrieval request interaction with a receiving end before the retrieval, if so, executing step S112, otherwise, executing step S113; in step S113, directly obtaining the identification information of the user, and returning a first retrieval message to the receiving end; in step S112, the identification information of the user is directly obtained, and a message that is not retrieved for the first time is returned to the receiving end.
Specifically, the identification information described herein may be any information that can identify characteristics/attributes of the user of the client; preferably, the identification information may be, for example, an IP address, a fixed/mobile phone number, a resolved geographical location, a network access registration account, etc.
Preferably, in step S2, the receiving end determining whether to call history information and record further comprises the steps of: step S21, if the receiving end determines whether to call history information and record according to the message whether to search for the first time returned by the user interaction, then step S23 is executed; step S22, if the receiving end analyzes the user' S mark information of the client end directly according to the attached information of the searching request, and determines whether to call the history information and record, then step S24 is executed; step S23, if not, calling history information and record, otherwise, not calling history information and record; step S24, if the identification information matches the history information and the entries in the record, it is called, otherwise it is not called.
Preferably, in step S3, the receiver-side split search request further includes: dividing a search request S into one or more sub-requests SiI is a positive integer, where s is the smallest retrievable unit when the retrieval request isiIs one, otherwise is a plurality, where S ═ { S ═ S1,……,si,……,sPAnd P is the number of the sub-requests and is a positive integer.
Preferably, in step S4, the receiving end further includes, according to the user search purpose of the empirical analysis client:
step S41, calling historical information and records by a calling module in the receiving end;
step S42, the segmentation and classification module in the receiving end performs segmentation and classification on the calling historical information and the source data in the record to obtain the frequency of segmentation and the type of the source data;
step S43, the destination analysis module in the receiving end analyzes one or more sub-requests S in the retrieval request S according to the history information and the record, the frequency of word segmentation and the type of the source dataiCalculating a target value; preferably, the calculation method is as follows: first, each sub-request s is calculatediThen calculates all sub-requests siAfter which each sub-request s is judgediIf the final sum is larger than a second threshold value, selecting the highest sum as a target and adding a label. Example (b)For example, if the type of the source data obtained according to the foregoing steps is the type of the photovoltaic technology, the enterprise, the taiwan, and the like; if the input is the mapping management display, the sub-requests are the mapping management and the display, each has a certain target value, and the mapping management and the display belong to the same category, the target values are added, and finally after settlement, the target value of the type of the photoelectric technology is found to be the highest, so that the mapping management display is selected as the target and the corresponding label is added.
Step S44, the retrieval module in the receiving end matches the sub-request with the source data, and counts the correlation degree of the single source data according to the matching frequency of the sub-request in different parts of the unit source data, the destination value and the type of the source data.
Preferably, in step S5, the receiving end performing retrieval further includes: step S51, based on the sub-request SiAnd the semantic extension module is used for effectively extending.
Preferably, the step S51 of performing effective expansion by the semantic expansion module further includes: step S511: first module of semantic extension module analyzes sub-request siDetermining semantics of the user request, and associating the semantics with the determined concept or object; step S512, the semantic expansion module sends a call request to the synonym/near-synonym semantic database, wherein the call request comprises a sub-request SiThe information of (a); step S513, the synonym/near-synonym meaning database returns a calling response after traversing; step S514, the semantic expansion module receives the call response and sends the call response to the receiving end. Preferably, after receiving the call response and before sending the call response to the receiving end, the semantic extension module sends the sub-request s through the second module of the semantic extension moduleiAnd expanding the words by using a plurality of language expression modes, and packaging and sending the words and the call response sent by the synonym/near-synonym meaning database to a receiving end. Preferably, after receiving the call response and before sending the call response to the receiving end, the semantic extension module sends the sub-request s through a third module of the semantic extension moduleiExpanded by upper concepts and lower concepts, and packaged and sent to a receiving end together with the call response (and various language expressions if necessary) sent by the synonym/near-synonym meaning database.
Preferably, in step S6, the search results are displayed in order from high to low according to the degree of correlation. And carrying out statistical sorting according to the correlation degree of the single source data, and sequentially displaying the retrieval results from high to low according to the correlation degree.
In conclusion, in the technical scheme of the invention, by adopting the intelligent retrieval method based on the experience knowledge, the retrieval speed and efficiency can be improved, and the precision ratio and the recall ratio can also be improved, so that the retrieval result is more targeted and more accurate.
It will be understood that: the examples and embodiments of the invention may be implemented in hardware, software, or a combination of hardware and software. As mentioned above, any body performing such a method may be stored in the form of volatile or non-volatile storage, for example a storage device like a ROM, whether erasable or rewritable or not, or in the form of memory, such as for example a RAM, a memory chip, a device or an integrated circuit or on an optically or magnetically readable medium such as for example a CD, a DVD, a disk or a tape. It will be understood that: storage devices and storage media are examples of machine-readable storage suitable for storing one or more programs that, when executed, implement examples of the present invention. Examples of the present invention may be conveyed electronically via any medium, such as a communication signal carried over a wired or wireless connection, and the examples contain the same where appropriate.
It should be noted that: the invention solves the technical problems of improving the retrieval speed and efficiency, improving the precision ratio and the recall ratio and enabling the retrieval result to be more targeted and accurate, adopts the technical means which can be understood by technical personnel in the technical field of computers according to the teaching of the specification after reading the specification and obtains the beneficial technical effects of improving the retrieval speed and efficiency, improving the precision ratio and the recall ratio and enabling the retrieval result to be more targeted and accurate, so the scheme claimed in the appended claims belongs to the technical scheme in the meaning of patent law. Furthermore, the solution claimed in the appended claims has utility since it can be manufactured or used in industry.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Unless expressly stated otherwise, each feature disclosed is one example only of a generic series of equivalent or similar features. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (2)

1. An intelligent retrieval method based on experience knowledge, comprising the following steps:
in step S1, the user inputs and transmits a retrieval request from the client;
in step S2, the reception end determines whether to call history information and record;
in step S3, the receiving end segments the search request;
in step S4, the receiving end analyzes the user retrieval purpose of the client based on experience;
in step S5, the receiving end performs a search; and
in step S6, the search results are displayed in order from high to low according to the degree of correlation;
wherein after the user inputs and transmits the retrieval request from the client in step S1, the step S11 is further performed: a user interface in a receiving end interacts with a user of a client and acquires user identification information; wherein the step S11 of the user interface in the receiving end interacting with the user at the client and acquiring the user identification information further includes: in step S111, the receiving end sends a query to the user of the client through the user interface: whether a user of the client performs retrieval request interaction with a receiving end before the retrieval, if so, executing step S112, otherwise, executing step S113; in step S113, directly obtaining the identification information of the user, and returning a first retrieval message to the receiving end; in step S112, directly obtaining the identification information of the user, and returning a message that is not retrieved for the first time to the receiving end;
wherein in step S2, the receiving end determining whether to call the history information and record further comprises the steps of: step S21, if the receiving end determines whether to call history information and record according to the message whether to search for the first time returned by the user interaction, then step S23 is executed; step S22, if the receiving end analyzes the user' S mark information of the client end directly according to the attached information of the searching request, and determines whether to call the history information and record, then step S24 is executed; step S23, if not, calling history information and record, otherwise, not calling history information and record; step S24, if the identification information matches with the history information and the items in the record, then calling, otherwise, not calling;
wherein in step S3, the receiver-side split search request further includes: dividing a search request S into one or more sub-requests SiI is a positive integer, where S = { S = { S1,……,si,……,sPP is the number of the sub-requests and is a positive integer;
wherein in step S4, the receiving end further comprises, according to the user search purpose of the empirical analysis client: step S41, calling historical information and records by a calling module in the receiving end; step S42, the segmentation and classification module in the receiving end performs segmentation and classification on the calling historical information and the source data in the record to obtain the frequency of segmentation and the type of the source data; step S43, the destination analysis module in the receiving end analyzes one or more sub-requests S in the retrieval request S according to the history information and the record, the frequency of word segmentation and the type of the source dataiCalculating a target value, wherein the target value is an evaluation quantitative value of which the sub-request belongs to a certain type; step S44, a retrieval module in the receiving end matches the sub-request with the source data, and counts the correlation degree of the unit source data according to the matching frequency of the sub-request in different parts of the unit source data, the target value and the type of the source data;
the calculation method in step S43 is as follows: first, each sub-request s is calculatediThen calculates all sub-requests siAfter which each sub-request s is judgediThe relationship between them, if they belong to the same category, on the sum baseAdding points on the basis, otherwise subtracting points, and if the final sum is greater than a second threshold value, selecting the highest point as the target and adding a label;
wherein in step S5, the receiving end further comprises: step S51, based on the sub-request SiThe semantic expansion module is used for effectively expanding;
the step S51 of performing effective expansion by the semantic expansion module further includes: step S511: first module of semantic extension module analyzes sub-request siDetermining semantics of the user request, and associating the semantics with the determined concept or object; step S512, the semantic expansion module sends a call request to the synonym/near-synonym semantic database, wherein the call request comprises a sub-request SiThe information of (a); step S513, the synonym/near-synonym meaning database returns a calling response after traversing; step S514, the semantic expansion module receives the calling response and sends the calling response to the receiving end; in addition, sub-requests s can be added as needediAnd/or its upper and lower concepts;
the intelligent retrieval method can improve retrieval speed and efficiency and improve precision ratio and recall ratio.
2. The intelligent retrieval method based on empirical knowledge according to claim 1, wherein in step S6, the retrieval results are displayed in order from high to low in accordance with the degree of correlation, statistically sorted in accordance with the degree of correlation of the unit source data, and displayed in order from high to low in accordance with the degree of correlation.
CN201611109212.9A 2016-12-06 2016-12-06 Intelligent retrieval method based on empirical knowledge Active CN106776981B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611109212.9A CN106776981B (en) 2016-12-06 2016-12-06 Intelligent retrieval method based on empirical knowledge

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611109212.9A CN106776981B (en) 2016-12-06 2016-12-06 Intelligent retrieval method based on empirical knowledge

Publications (2)

Publication Number Publication Date
CN106776981A CN106776981A (en) 2017-05-31
CN106776981B true CN106776981B (en) 2020-12-15

Family

ID=58878293

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611109212.9A Active CN106776981B (en) 2016-12-06 2016-12-06 Intelligent retrieval method based on empirical knowledge

Country Status (1)

Country Link
CN (1) CN106776981B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104424216A (en) * 2013-08-23 2015-03-18 佳能株式会社 Method and device for intention digging
CN104699751A (en) * 2014-12-30 2015-06-10 北京奇虎科技有限公司 Search recommending method and device based on search terms
CN104866474A (en) * 2014-02-20 2015-08-26 阿里巴巴集团控股有限公司 Personalized data searching method and device
CN104933100A (en) * 2015-05-28 2015-09-23 北京奇艺世纪科技有限公司 Keyword recommendation method and device
CN105095187A (en) * 2015-08-07 2015-11-25 广州神马移动信息科技有限公司 Search intention identification method and device

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6560595B1 (en) * 1999-11-15 2003-05-06 Novell, Inc. Operator for correlated predicates in a query
CN103425662B (en) * 2012-05-16 2017-08-25 腾讯科技(深圳)有限公司 Information search method and device in a kind of Web Community
CN103488752B (en) * 2013-09-24 2017-08-25 沈阳美行科技有限公司 A kind of search method of POI intelligent retrievals
US9230041B2 (en) * 2013-12-02 2016-01-05 Qbase, LLC Search suggestions of related entities based on co-occurrence and/or fuzzy-score matching
CN105577958B (en) * 2014-10-15 2019-09-17 阿里巴巴集团控股有限公司 For adjusting distributing strategy and shunting the method, apparatus and system of user's request

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104424216A (en) * 2013-08-23 2015-03-18 佳能株式会社 Method and device for intention digging
CN104866474A (en) * 2014-02-20 2015-08-26 阿里巴巴集团控股有限公司 Personalized data searching method and device
CN104699751A (en) * 2014-12-30 2015-06-10 北京奇虎科技有限公司 Search recommending method and device based on search terms
CN104933100A (en) * 2015-05-28 2015-09-23 北京奇艺世纪科技有限公司 Keyword recommendation method and device
CN105095187A (en) * 2015-08-07 2015-11-25 广州神马移动信息科技有限公司 Search intention identification method and device

Also Published As

Publication number Publication date
CN106776981A (en) 2017-05-31

Similar Documents

Publication Publication Date Title
CN105556512B (en) Apparatus, system and method for analyzing characteristics of entities of interest
CN107844565B (en) Commodity searching method and device
CN107589855B (en) Method and device for recommending candidate words according to geographic positions
CN102479223B (en) Data query method and system
US8880512B2 (en) Method, apparatus and system, for rewriting search queries
US20240330389A1 (en) Uniform resource identifier encoding
CN106557480B (en) Method and device for realizing query rewriting
CN103136228A (en) Image search method and image search device
CN102968417A (en) Searching method and system applied to computer network
CN102982153A (en) Information retrieval method and device
CN107911448B (en) Content pushing method and device
US8983898B1 (en) Extracting instance attributes from text
KR20150036117A (en) Query expansion
CN110543477B (en) Label construction system and method
KR101344913B1 (en) System and method for providing automatically completed query by regional groups
JP6728178B2 (en) Method and apparatus for processing search data
JP2015500525A (en) Method and apparatus for information retrieval
US8799314B2 (en) System and method for managing information map
US20140344259A1 (en) Answering people-related questions
CN105159898A (en) Searching method and searching device
TWI639093B (en) Object set and processing method and device thereof
CN106776981B (en) Intelligent retrieval method based on empirical knowledge
De Rouck et al. Georeferencing Wikipedia pages using language models from Flickr
TWI547888B (en) A method of recording user information and a search method and a server
US20160203177A1 (en) Answering Requests Related to Places of Interest

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
TA01 Transfer of patent application right

Effective date of registration: 20201126

Address after: Room 405, 4 / F, building 4, Hongtai wisdom Valley, 17 Sicheng Road, Tianhe District, Guangzhou City, Guangdong Province (office use only)

Applicant after: Guangzhou isomorphic Technology Co.,Ltd.

Address before: Tianhe Road 510630 Guangdong city of Guangzhou province Tianhe District No. 490 Guangzhou EGO Digital Plaza Southern China headquarters third layer 347 shops

Applicant before: GUANGZHOU KEEN COMPUTER Co.,Ltd.

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant
CP02 Change in the address of a patent holder

Address after: 510000 room 611, 1933 Huaguan Road, Tianhe District, Guangzhou City, Guangdong Province (office only)

Patentee after: Guangzhou isomorphic Technology Co.,Ltd.

Address before: 510663 Room 405, 4th floor, building 4, Hongtai wisdom Valley, No.17 Sicheng Road, Tianhe District, Guangzhou City, Guangdong Province (office use only)

Patentee before: Guangzhou isomorphic Technology Co.,Ltd.

CP02 Change in the address of a patent holder
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: An Intelligent Retrieval Method Based on Empirical Knowledge

Effective date of registration: 20230516

Granted publication date: 20201215

Pledgee: Bank of China Limited by Share Ltd. Guangzhou Tianhe branch

Pledgor: Guangzhou isomorphic Technology Co.,Ltd.

Registration number: Y2023980040874

PE01 Entry into force of the registration of the contract for pledge of patent right