CN106776981A - A kind of intelligent search method based on Heuristics - Google Patents
A kind of intelligent search method based on Heuristics Download PDFInfo
- Publication number
- CN106776981A CN106776981A CN201611109212.9A CN201611109212A CN106776981A CN 106776981 A CN106776981 A CN 106776981A CN 201611109212 A CN201611109212 A CN 201611109212A CN 106776981 A CN106776981 A CN 106776981A
- Authority
- CN
- China
- Prior art keywords
- receiving terminal
- request
- user
- retrieval
- source data
- 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.)
- Granted
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
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of intelligent search method based on Heuristics includes：User concurrently send retrieval request from client input；Receiving terminal determines whether to call historical information and record；Receiving terminal splits retrieval request；Receiving terminal rule of thumb analyzes the user search purpose of client；Receiving terminal is retrieved；Retrieval result is shown according to degree of correlation successively from high to low.Retrieval rate and efficiency can be improved, precision ratio and recall ratio can be also improved so that retrieval result is more targeted, more accurately.
Description
Technical field
The present invention relates to a kind of electric digital data processing field, more specifically, it is related to a kind of intelligence based on Heuristics
Can search method.
Background technology
With society industrialization, the level of IT application continuous improvement, nowadays data replaced be calculated as information calculating
Center, internet, cloud computing, big data turn into a kind of trend and trend.Nowadays, internet has become people and obtains letter
The most important approach of breath, the valuable information of magnanimity and knowledge are all contained in Internet resources.However, the explosivity of Internet resources
Growth is twin pros and cons, both for user brings increasingly abundanter information, while relevant knowledge needed for user is accurate is obtained
Taking difficulty is but increasing.Useful information how is quickly, efficiently extracted from the substantial amounts of network information and is had become and worked as
Most important task in modern information retrieval.
In the prior art, multiple search engines are there are, to attempt to solve these problems, such as Baidu, Google, is searched
Dog, must wait.Used as the important tool of information retrieval, they have become Consumer's Experience internet, obtain the main way of information
Footpath, facilitates people and obtains required information on the internet.When user is needed by retrieving the information needed for obtaining, often
It is not high enough to retrieval result satisfaction.Such as user wants to know the information of China, by after retrieval, Chinese tooth often occurring
Cream, Chinese pencil, Chunghwa Picture Tubes, Chinese cigarette etc., and the really desired information of user is not all, it is special that such user screens information
It is not time-consuming.In the technical field of computer, experience is the knowledge or skills obtained from repeatedly practice；Intelligent retrieval is with text
Offer based on the degree of correlation with term, the index such as importance of comprehensive examination document is ranked up, to retrieval result to provide
Recall precision higher, such sort result is more accurate, more can will be discharged to foremost with the maximally related document of user's hope,
Improve recall precision.So in the urgent need to a kind of intelligent search method based on Heuristics in reality, retrieval speed can be improved
Degree and efficiency, can also improve precision ratio and recall ratio.
The content of the invention
An object of the present invention is to provide a kind of intelligent search method based on Heuristics, can improve retrieval rate
And efficiency, can also improve precision ratio and recall ratio so that retrieval result is more targeted, more accurately.
The present invention is to solve above-mentioned technical problem and the technical scheme taken is：A kind of intelligent retrieval based on Heuristics
Method includes：User concurrently send retrieval request from client input；Receiving terminal determines whether to call historical information and record；Receive
End segmentation retrieval request；Receiving terminal rule of thumb analyzes the user search purpose of client；Receiving terminal is retrieved；According to correlation
Degree shows retrieval result successively from high to low.
According to another aspect of the present invention, in step sl, after user concurrently send retrieval request from client input,
Further perform step S11：User interface in receiving terminal is interacted and obtains user identity information with the user of client.
According to another aspect of the present invention, the user interface in receiving terminal is interacted and obtained with the user of client
The step of user identity information, S11 was further included：In step S111, receiving terminal passes through user of the user interface to client
Send inquiry：Whether the user of client carried out retrieval request before this retrieval with receiving terminal interacts, if it is, performing
Step S112, otherwise performs S113；In step S112, the identification information of direct access user is returned to receiving terminal and examined first
The message of rope；In step S113, the identification information of direct access user returns to the non-message retrieved first to receiving terminal.
According to another aspect of the present invention, in step s 2, receiving terminal determine whether to call historical information and record into
One step includes step：Step S21, if the message whether retrieved first that receiving terminal is returned according to user mutual, it is determined whether
Historical information and record are called, then performs step D23；Step S22, if receiving terminal is directly according to the incidental information of retrieval request
Parse the identification information of the user of client, it is determined whether call historical information and record, then perform step D24；Step
S23, if retrieving first, calls historical information and record, otherwise never calls historical information and record；Step S24, if
Identification information is matched with the item in historical information and record, then called, and is otherwise never called.
According to another aspect of the present invention, in step s3, receiving terminal segmentation retrieval request is further included：Will retrieval
Request S is divided into one or more sub- request si, i is positive integer, wherein S={ s1... ..., si... ..., sP, P is asked for son
Number, is positive integer.
According to another aspect of the present invention, in step s 4, receiving terminal rule of thumb analyzes the user search of client
Purpose is further included：Step S41, the calling module in receiving terminal calls historical information and record；Step S42, in receiving terminal
Source data during participle is divided and sort module will be called historical information and be recorded carries out participle division, obtains the frequency and the source of participle
The type of data；Step S43, the purpose analysis module in receiving terminal is according to historical information and record, the frequency of participle and source data
Type, to one or more the sub- request s in retrieval request SiCarry out purpose value calculating；Step S44, the retrieval module in receiving terminal will
Son request matched with source data, and according to sub- request the different piece of unit source data the matching frequency and purpose value with
The type of source data, counts the degree of correlation M of single source dataij, wherein
Wherein Q is the different piece sum of unit source data, m1jThe quantity that expression is matched in j-th part of unit source data, and w1j
Represent the weight of j-th part of unit source data, m2Expression purpose value, and w2Represent the weight of purpose value, m3Represent source data
Type label value, and w3Represent the weight of the type of source data.
According to another aspect of the present invention, the calculation in step S43 is：First calculate and s is asked per heightiPurpose
Value, then calculates all sub- request siPurpose value summation, afterwards judge per height ask siBetween relation, if belonged to
The identical category then bonus point on the basis of summation, otherwise deduction, select highest to make if final summation is more than Second Threshold
For the purpose of and add label.
According to another aspect of the present invention, in step s 5, receiving terminal carries out retrieval and further includes：Step S51, base
In sub- request si, semantic extension module is effectively extended.
According to another aspect of the present invention, the step of semantic extension module carries out effectively extension S51 is further included：Step
Rapid S511：The first module analysis request si of semantic extension module, determines the semanteme of user's request, is associated with the concept of determination
Or object；Step S512, semantic extension module sends call request to synonym/near synonym semantic database, the call request
Information including sub- request si；Step S513, synonym/near synonym semantic database is returned after traversal and calls response；Step
Rapid S514, semantic extension module is received and calls response, and is sent to receiving terminal；The many of sub- request si can be added as needed in addition
Plant Expression of language and/or its upperseat concept and subordinate concept.
According to another aspect of the present invention, in step s 6, retrieval knot is shown according to degree of correlation successively from high to low
Really.Degree of correlation M according to single source dataijSort method is carried out, retrieval knot is shown according to degree of correlation successively from high to low
Really.
Brief description of the drawings
Embodiments of the invention, wherein phase are shown rather than by way of limitation by way of example in the accompanying drawings
Same reference represents identical element, wherein：
According to an exemplary embodiment of the invention, Fig. 1 illustrates a kind of flow of the intelligent search method based on Heuristics
Figure.
Specific embodiment
In the following description, refer to the attached drawing and several specific embodiments are diagrammatically shown.It will be appreciated that：
It is contemplated that and other embodiment can be made without deviating from the scope of the present disclosure or spirit.Therefore, it is described in detail below should not be by
Think in a limiting sense.
According to an exemplary embodiment of the invention, Fig. 1 illustrates a kind of flow of the intelligent search method based on Heuristics
Figure.The intelligent search method for being based on Heuristics includes：
In step sl, user concurrently send retrieval request from client input；
In step s 2, receiving terminal determines whether to call historical information and record；
In step s3, receiving terminal segmentation retrieval request；
In step s 4, receiving terminal rule of thumb analyzes the user search purpose of client；
In step s 5, receiving terminal is retrieved；And
In step s 6, retrieval result is shown according to degree of correlation successively from high to low.
Preferably, in step sl, the client is mobile terminal, and it passes through Radio Link and is communicated simultaneously with receiving terminal
Retrieved.Alternately, in step sl, the client be computer, include, without being limited to desktop computer, kneetop computer,
Portable notebook, net book, panel computer etc., it passes through wire link or Radio Link and is communicated with receiving terminal and carried out
Retrieval.
Preferably, in step sl, after user concurrently send retrieval request from client input, step is further performed
S11：User interface in receiving terminal is interacted and obtains user identity information with the user of client.Preferably, receiving terminal
In user interface the step of interacted with the user of client and obtain user identity information S11 further include：In step
In rapid S111, receiving terminal sends inquiry by user interface to the user of client：The user of client is before this retrieval
Whether carry out retrieval request with receiving terminal to interact, if it is, performing step S112, otherwise perform S113；In step S112,
The identification information of direct access user, the message retrieved first is returned to receiving terminal；In step S113, direct access user's
Identification information, the non-message retrieved first is returned to receiving terminal.
Specifically, identification information as herein described can be the characteristics/properties of any user that can identify client
Information；Preferably, the identification information for example can be IP address, fixation/Mobile Directory Number, the geographical position of parsing, network
Access registration account etc..
Preferably, in step s 2, receiving terminal determines whether to call historical information and record to further include step：Step
S21, if the message whether retrieved first that receiving terminal is returned according to user mutual, it is determined whether call historical information and note
Record, then perform step D23；Step S22, if receiving terminal directly parses the use of client according to the incidental information of retrieval request
The identification information at family, it is determined whether call historical information and record, then perform step D24；Step S23, if retrieving first
Historical information and record are then called, historical information and record is otherwise never called；Step S24, if identification information and historical information
With the item matching in record, then call, otherwise never call.
Preferably, in step s3, receiving terminal segmentation retrieval request is further included：Retrieval request S is divided into one
Or many height request si, i is positive integer, wherein when retrieval request is minimum detectable range cable elements, siQuantity be one, otherwise
It is multiple, wherein S={ s1... ..., si... ..., sP, P is son request number, is positive integer.
Preferably, in step s 4, receiving terminal is rule of thumb analyzed the user search purpose of client and is further included：
Step S41, the calling module in receiving terminal calls historical information and record；
Step S42, the participle in receiving terminal is divided and sort module will call the source data in historical information and record to enter
Row participle is divided, and obtains the frequency of participle and the type of source data；
Step S43, the purpose analysis module in receiving terminal is according to historical information and record, the frequency of participle and source data
Type, to one or more the sub- request s in retrieval request SiCarry out purpose value calculating；Preferably, the calculation is：First count
Calculate and s is asked per heightiPurpose value, then calculate all sub- request siPurpose value summation, afterwards judge per height ask si
Between relation, if identical category is belonged on the basis of summation bonus point, otherwise deduction, if final summation be more than second
Threshold value then selects highest as purpose and adds label.If for example, having light according to the type that abovementioned steps obtain source data
The types such as power technology, enterprise, Taiwan；If input is to reflect pipe to show, its sub- request each has certain to reflect pipe and showing
Purpose value, separately, identical category is belonged to because reflecting pipe and display, so the bonus point in respective purpose value, meeting after final every clearing
It was found that photoelectric technology this type purpose value highest, so selecting it as purpose and adding respective labels；If input is
CPTF manages, and its sub- request is for China and reflects pipe, each with certain purpose value, separately, because China with reflect pipe and belong to a different category,
So in respective purpose value deduction, can find Taiwan or this type purpose value highest of enterprise after final every clearing, so
It is selected as purpose and respective labels are added.
Step S44, the retrieval module in receiving terminal is matched sub- request with source data, and according to sub- request in unit
The matching frequency of the different piece of source data and the type of purpose value and source data, count the degree of correlation of single source data
Mij, whereinWherein Q is the different piece sum of unit source data, m1j
The quantity that expression is matched in j-th part of unit source data, and w1jRepresent the weight of j-th part of unit source data, m2
Expression purpose value, and w2Represent the weight of purpose value, m3The label value of the type of expression source data, and w3Represent the class of source data
The weight of type.
Preferably, in step s 5, receiving terminal carries out retrieval and further includes：Step S51, it is semantic based on sub- request si
Expansion module is effectively extended.
Preferably, the step of semantic extension module carries out effectively extension S51 is further included：Step S511：Semantic extension
The first module analysis request si of module, determines the semanteme of user's request, is associated with the concept or object of determination；Step
S512, semantic extension module sends call request to synonym/near synonym semantic database, and the call request includes son request si
Information；Step S513, synonym/near synonym semantic database is returned after traversal and calls response；Step S514, semanteme expands
Exhibition module is received calls response, and is sent to receiving terminal.Preferably, semantic extension module is after response is called in reception, transmission
Before to receiving terminal, sub- request si multilingual expression ways are extended by the second module of semantic extension module,
And with synonym/near synonym semantic database send call response together with transmit to receiving terminal.Preferably, semantic extension
Module after response is called in reception, be sent to receiving terminal before, by the 3rd module of semantic extension module by sub- request si
It is extended with its upperseat concept and subordinate concept, and calls response (and many with synonym/near synonym semantic database sends
Expression of language is planted, if necessary) transmit together to receiving terminal.
Preferably, in step s 6, retrieval result is shown according to degree of correlation successively from high to low.According to single source data
Degree of correlation MijSort method is carried out, retrieval result is shown according to degree of correlation successively from high to low.
To sum up, in the inventive solutions, by employing a kind of intelligent search method based on Heuristics, both
Retrieval rate and efficiency can be improved, precision ratio and recall ratio can be also improved so that retrieval result is more targeted, more accurately.
It will be appreciated that：Example of the invention and reality can be realized in the form of the combination of hardware, software or hardware and software
Apply example.As described above, any main body for performing this method can be stored, in the form of volatibility or non-volatile memories, for example
Storage device, it is no matter erasable or whether rewritable as ROM, or in the form of a memory, such as RAM, storage core
Piece, equipment or integrated circuit or on the readable medium of light or magnetic, such as CD, DVD, disk or tape.It will be appreciated that：
Storage device and storage medium are suitable for the example of the machine readable storage for storing one or more programs, upon being performed,
One or more of programs realize example of the invention.Via any medium, such as connect what is be loaded with by wired or wireless
Signal of communication, can electronically transmit example of the invention, and example suitably includes identical content.
It should be noted that：Because the present invention is solved can improve retrieval rate and efficiency, can also improve precision ratio and
Recall ratio so that retrieval result is more targeted, more accurate technical problem employs technology people in field of computer technology
Member obtains and can improve retrieval rate and effect after reading this description according to its teaching technological means to understand
Rate, can also improve precision ratio and recall ratio so that retrieval result is more targeted, more accurate Advantageous Effects, so
Claimed scheme belongs to the technical scheme on patent law purposes in the following claims.In addition, because appended right will
Claimed technical scheme is asked to can be made or used in industry, therefore the program possesses practicality.
The above, the only present invention preferably specific embodiment, but protection scope of the present invention is not limited thereto,
Any one skilled in the art the invention discloses technical scope in, the change or replacement that can be readily occurred in,
Should all be encompassed within protection scope of the present invention.Unless be otherwise expressly recited, otherwise disclosed each feature is only
Equivalent or similar characteristics a example of general series.Therefore, protection scope of the present invention should be with the guarantor of claims
Shield scope is defined.
Claims (10)
1. a kind of intelligent search method based on Heuristics, including：
In step sl, user concurrently send retrieval request from client input；
In step s 2, receiving terminal determines whether to call historical information and record；
In step s3, receiving terminal segmentation retrieval request；
In step s 4, receiving terminal rule of thumb analyzes the user search purpose of client；
In step s 5, receiving terminal is retrieved；And
In step s 6, retrieval result is shown according to degree of correlation successively from high to low.
2. the intelligent search method based on Heuristics as claimed in claim 1, wherein in step sl, user is from client
Input is concurrently sent after retrieval request, further performs step S11：User interface in receiving terminal is carried out with the user of client
Interact and obtain user identity information.
3. the intelligent search method of Heuristics, the wherein user interface in receiving terminal and visitor are based on as claimed in claim 2
The step of user at family end interacts and obtains user identity information S11 is further included：In step S111, receiving terminal leads to
Cross user interface and send inquiry to the user of client：Whether the user of client was carried out before this retrieval with receiving terminal
Retrieval request is interacted, if it is, performing step S112, otherwise performs S113；In step S112, the mark of direct access user
Information, the message retrieved first is returned to receiving terminal；In step S113, the identification information of direct access user, to receiving terminal
Return to the non-message retrieved first.
4. the intelligent search method of Heuristics is based on as claimed in claim 3, wherein in step s 2, receiving terminal determination is
It is no to call historical information and record to further include step：Step S21, if receiving terminal according to user mutual return it is whether first
The message of secondary retrieval, it is determined whether call historical information and record, then perform step D23；Step S22, if receiving terminal is direct
Incidental information according to retrieval request parses the identification information of the user of client, it is determined whether call historical information and note
Record, then perform step D24；Step S23, if retrieving first, calls historical information and record, otherwise never calls history letter
Breath and record；Step S24, if identification information is matched with the item in historical information and record, calls, and otherwise never calls.
5. the intelligent search method of Heuristics is based on as claimed in claim 4, wherein in step s3, receiving terminal segmentation inspection
Rope request is further included：Retrieval request S is divided into one or more sub- request si, i is positive integer, wherein S=
{s1... ..., si... ..., sP, P is son request number, is positive integer.
6. the intelligent search method of Heuristics is based on as claimed in claim 5, wherein in step s 4, receiving terminal is according to warp
The user search purpose for testing analysis client is further included：Step S41, the calling module in receiving terminal call historical information and
Record；Step S42, the participle in receiving terminal is divided and sort module will call the source data in historical information and record to be divided
Word is divided, and obtains the frequency of participle and the type of source data；Step S43, the purpose analysis module in receiving terminal is believed according to history
The type of breath and record, the frequency of participle and source data, to one or more the sub- request s in retrieval request SiCarry out purpose value
Calculate；Step S44, the retrieval module in receiving terminal is matched sub- request with source data, and according to sub- request in unit source
The matching frequency of the different piece of data and the type of purpose value and source data, count the degree of correlation M of single source dataij,
WhereinWherein Q is the different piece sum of unit source data, m1jRepresent
In the quantity that j-th part of unit source data matches, and w1jRepresent the weight of j-th part of unit source data, m2Represent
Purpose value, and w2Represent the weight of purpose value, m3The label value of the type of expression source data, and w3Represent the type of source data
Weight.
7. the intelligent search method of Heuristics is based on as claimed in claim 6, and the calculation in wherein step S43 is：
First calculate and s is asked per heightiPurpose value, then calculate all sub- request siPurpose value summation, afterwards judge per height please
Seek siBetween relation, if identical category is belonged on the basis of summation bonus point, otherwise deduction, if final summation is more than
Second Threshold then selects highest as purpose and adds label.
8. the intelligent search method of Heuristics is based on as claimed in claim 7, wherein in step s 5, receiving terminal is examined
Rope is further included：Step S51, based on sub- request si, semantic extension module is effectively extended.
9. the intelligent search method of Heuristics is based on as claimed in claim 8, and wherein semantic extension module is effectively expanded
The step of exhibition, S51 was further included：Step S511：The first module analysis request si of semantic extension module, determines that user please
The semanteme asked, is associated with the concept or object of determination；Step S512, semantic extension module is to synonym/near synonym semantic data
Storehouse sends call request, and the call request includes the information of son request si；Step S513, synonym/near synonym semantic database
Returned after traversal and call response；Step S514, semantic extension module is received and calls response, and is sent to receiving terminal；In addition
The multilingual expression way and/or its upperseat concept and subordinate concept of sub- request si can be added as needed on.
10. the intelligent search method of Heuristics is based on as claimed in claim 9, wherein in step s 6, according to related journey
Degree shows retrieval result successively from high to low；Degree of correlation M according to single source dataijSort method is carried out, according to related journey
Degree shows retrieval result successively from high to low.
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 true CN106776981A (en) | 2017-05-31 |
| CN106776981B 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 (10)
| 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 |
| CN103425662A (en) * | 2012-05-16 | 2013-12-04 | 腾讯科技（深圳）有限公司 | Information search method and device in network community |
| CN103488752A (en) * | 2013-09-24 | 2014-01-01 | 沈阳美行科技有限公司 | POI (point of interest) searching method |
| 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 |
| US20160042001A1 (en) * | 2013-12-02 | 2016-02-11 | Qbase, LLC | Search suggestions of related entities based on co-occurrence and/or fuzzy-score matching |
| CN105577958A (en) * | 2014-10-15 | 2016-05-11 | 阿里巴巴集团控股有限公司 | Methods of adjusting shunting strategy and shunting user request, apparatuses and system |
-
2016
- 2016-12-06 CN CN201611109212.9A patent/CN106776981B/en active Active
Patent Citations (10)
| 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 |
| CN103425662A (en) * | 2012-05-16 | 2013-12-04 | 腾讯科技（深圳）有限公司 | Information search method and device in network community |
| CN104424216A (en) * | 2013-08-23 | 2015-03-18 | 佳能株式会社 | Method and device for intention digging |
| CN103488752A (en) * | 2013-09-24 | 2014-01-01 | 沈阳美行科技有限公司 | POI (point of interest) searching method |
| US20160042001A1 (en) * | 2013-12-02 | 2016-02-11 | Qbase, LLC | Search suggestions of related entities based on co-occurrence and/or fuzzy-score matching |
| 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 |
| CN105577958A (en) * | 2014-10-15 | 2016-05-11 | 阿里巴巴集团控股有限公司 | Methods of adjusting shunting strategy and shunting user request, apparatuses and system |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| ARCHANA KURIAN等: ""Analyzing and Classifying User Search Histories for Web Search Engine Optimization"", 《2014 3RD INTERNATIONAL CONFERENCE ON ECO-FRIENDLY COMPUTING AND COMMUNICATION SYSTEMS》 * |
| 侯振宇: ""信息检索系统中的相关性评价问题"", 《现代图书情报技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106776981B (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11698261B2 (en) | Method, apparatus, computer device and storage medium for determining POI alias | |
| CN105187237B (en) | The method and apparatus for searching associated user identifier | |
| CN110019616B (en) | POI (Point of interest) situation acquisition method and equipment, storage medium and server thereof | |
| CN104143005B (en) | A kind of related search system and method | |
| US8949227B2 (en) | System and method for matching entities and synonym group organizer used therein | |
| CN110069698B (en) | Information pushing method and device | |
| CN104102639B (en) | Popularization triggering method based on text classification and device | |
| CN106033416A (en) | A string processing method and device | |
| CN108304423A (en) | A kind of information identifying method and device | |
| CN112559879B (en) | Interest model training method, interest point recommending method, device and equipment | |
| TW201214173A (en) | Methods and apparatus for displaying content | |
| US20120233096A1 (en) | Optimizing an index of web documents | |
| CN109933803B (en) | Idiom information display method, idiom information display device, electronic equipment and storage medium | |
| CN111460327B (en) | Method and device for searching for interest, storage medium and computer equipment | |
| JP2019191975A (en) | Talent selection device, talent selection system, talent selection method, and program | |
| JP7166116B2 (en) | Information processing device, information processing method, and program | |
| CN110688434B (en) | Method, device, equipment and medium for processing interest points | |
| CN107977678A (en) | Method and apparatus for output information | |
| US8799314B2 (en) | System and method for managing information map | |
| CN103955480A (en) | Method and equipment for determining target object information corresponding to user | |
| CN106919576A (en) | Using the method and device of two grades of classes keywords database search for application now | |
| CN105159898A (en) | Searching method and searching device | |
| CN110929058A (en) | Trademark picture retrieval method and device, storage medium and electronic device | |
| US20180329926A1 (en) | Image-based semantic accommodation search | |
| AU2018273369A1 (en) | Automated classification of network-accessible content |
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 | ||
| 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. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP02 | Change in the address of a patent holder | ||
| 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. |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| 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 |