CN104778257A - Method and device for searching applied problems - Google Patents
Method and device for searching applied problems Download PDFInfo
- Publication number
- CN104778257A CN104778257A CN201510187407.4A CN201510187407A CN104778257A CN 104778257 A CN104778257 A CN 104778257A CN 201510187407 A CN201510187407 A CN 201510187407A CN 104778257 A CN104778257 A CN 104778257A
- Authority
- CN
- China
- Prior art keywords
- application
- sentence
- user
- application topic
- topic
- 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
Abstract
The invention provides a method and a device for searching applied problems. The method for searching the applied problems comprises the following steps of formalizing the applied problems inputted by a user into mathematical templates; searching a pre-constructed question bank by using the mathematical templates to obtain solving methods of the applied problems inputted by the user and applied problems correlated with the mathematical templates; displaying the solving methods of the applied problems inputted by the user, the applied problems correlated with the mathematical templates and relevant knowledge points for the user. According to the method and the device disclosed by the invention, the user inputs the applied problems, and the solving methods of the applied problems, related data and knowledge related with the applied problems are fed back to the user, so that the search problem of the applied problems can be effectively solved, and the search requirement of the user on the applied problems can be better met.
Description
Technical field
The present invention relates to Internet technical field, particularly relate to a kind of application topic searching method and device.
Background technology
Education is the popular problem of public concern always, and therefore, the search that education is relevant also grows with each passing day.Mathematical problem is the class major issue in educational problem, and mathematical problem has comparatively multiple types, and wherein a class problem is application topic problem.Application topic problem be training of students by the ability of language formalization to mathematical formulae, be the problem that in mathematical problem, a class difficulty is higher and important.
Math problems is very important for the Ability of Mathematical Abstraction of training student, is the Focal point and difficult point in mathematical education.Existing search engine, for the search of application topic, just have matched some words in application topic, and due to dirigibility and the polytrope of application topic text description, the Search Results obtained with this does not have useful information usually, cannot obtain gratifying result.
Summary of the invention
Object of the present invention is intended to solve one of technical matters in correlation technique at least to a certain extent.
For this reason, first object of the present invention is to propose a kind of application topic searching method.The method can input application topic by user, to the knowledge that this application such as method for solving, related data topic of user feedback application topic is relevant, thus effectively can solve the search problem of application topic, can meet the search need that user inscribes application better.
Second object of the present invention is to propose a kind of application topic searcher.
To achieve these goals, the application topic searching method of first aspect present invention embodiment, comprising: application topic form user inputted turns to mathematical modulo plate; Utilize described mathematics template to search for the exam pool built in advance, obtain the method for solving of the application topic of described user input, the application topic of described mathematics template association and knowledge point; The method for solving of the application topic that described user inputs, the application topic of described mathematics template association and knowledge point is shown to described user.
The application topic searching method of the embodiment of the present invention, application topic form user inputted turns to mathematical modulo plate, above-mentioned mathematics template is utilized to search for the exam pool built in advance, obtain the method for solving of the application topic of above-mentioned user input, the application topic of above-mentioned mathematics template association and knowledge point, right rear line shows the method for solving of the application topic that this user inputs, the application topic of above-mentioned mathematics template association and knowledge point, thus effectively can solve the search problem of application topic, the search need that user inscribes application can be met better.
To achieve these goals, the application topic searcher of second aspect present invention embodiment, comprising: formalization module, turns to mathematical modulo plate for application topic form user inputted; Search module, searches for the exam pool built in advance for the mathematics template utilizing described formalization module to obtain, and obtains the method for solving of the application topic of described user input, the application topic of described mathematics template association and knowledge point; Display module, for showing the method for solving of the application topic that the described user that described search module obtains inputs, the application topic of described mathematics template association and knowledge point to described user.
The application topic searcher of the embodiment of the present invention, the application topic form that user inputs by formalization module turns to mathematical modulo plate, search module utilizes above-mentioned mathematics template to search for the exam pool built in advance, obtain the method for solving of the application topic of above-mentioned user input, the application topic of above-mentioned mathematics template association and knowledge point, then display module shows the method for solving of the application topic that this user inputs to user, the application topic of above-mentioned mathematics template association and knowledge point, thus effectively can solve the search problem of application topic, the search need that user inscribes application can be met better.
The aspect that the present invention adds and advantage will part provide in the following description, and part will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
The present invention above-mentioned and/or additional aspect and advantage will become obvious and easy understand from the following description of the accompanying drawings of embodiments, wherein:
Fig. 1 is the process flow diagram of an application of the present invention topic searching method embodiment;
Fig. 2 is the schematic diagram of a web results embodiment of application of the present invention topic searching method;
Fig. 3 is the schematic diagram of a Search Results embodiment of application of the present invention topic searching method;
Fig. 4 is the structural representation of an application of the present invention topic searcher embodiment;
Fig. 5 is the structural representation of another embodiment of application of the present invention topic searcher.
Embodiment
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Being exemplary below by the embodiment be described with reference to the drawings, only for explaining the present invention, and can not limitation of the present invention being interpreted as.On the contrary, embodiments of the invention comprise fall into attached claims spirit and intension within the scope of all changes, amendment and equivalent.
Fig. 1 is the process flow diagram of an application of the present invention topic searching method embodiment, and as shown in Figure 1, this application topic searching method can comprise:
Step 101, application topic form user inputted turns to mathematical modulo plate.
Particularly, application topic form user inputted turns to mathematical modulo plate and can be: in the application topic input above-mentioned user, the sentence at digital place is analyzed, extract at least one feature in above-mentioned sentence, wherein, at least one feature above-mentioned comprises the N unit syntax (N-Gram), part of speech (the Part of Speech in above-mentioned sentence; Hereinafter referred to as at least one in the dependence (such as: the measurer that addition, subtraction operation relates to has same units) of element in: the dependence (dependences) POS), in above-mentioned sentence between word and word and formula, N is integer, N >=1; Then, utilize at least one feature above-mentioned, maximize in advance by the posterior probability model that training obtains, obtain above-mentioned user and input mathematics template corresponding to application topic.
Further, in the application topic input above-mentioned user, the sentence at digital place is analyzed, before extracting at least one feature in above-mentioned sentence, also need to analyze the sentence at digital place in the application topic for training, extract at least one feature in above-mentioned sentence, at least one feature above-mentioned comprises N unit's syntax (N-Gram) in above-mentioned sentence, POS, in dependence (dependences) in above-mentioned sentence between word and word and formula, the dependence of element (such as: add, subtract the measurer that computing relates to and have same units) at least one, N is integer, N >=1, then utilize the feature of extraction, obtain posterior probability model by training, above-mentioned posterior probability model is used for reflection and inscribes for described application, and described formal mathematics template can explain the degree that this application is inscribed.
Step 102, utilizes above-mentioned mathematics template to search for the exam pool built in advance, obtains the method for solving of the application topic of above-mentioned user input, the application topic of above-mentioned mathematics template association and knowledge point.
Step 103, shows the method for solving of the application topic that above-mentioned user inputs, the application topic of above-mentioned mathematics template association and knowledge point to user.
Further, application topic form user inputted can also utilize the attribute of above-mentioned mathematics template to carry out web search, obtain the web results of the Attribute Association of above-mentioned mathematics template after turning to mathematical modulo plate; Right rear line shows above-mentioned web results.Wherein, the attribute of above-mentioned mathematics template can be specified by the mode of artificial mark.
In the present embodiment, utilizing before above-mentioned mathematics template searches for the exam pool built in advance, the process that can also be turned to mathematical modulo plate by application topic form user inputted carries out automatic classification to exam pool, obtains the label information of above-mentioned exam pool, to complete the structure of above-mentioned exam pool.
Above-mentioned application topic searching method, application topic form user inputted turns to mathematical modulo plate, above-mentioned mathematics template is utilized to search for the exam pool built in advance, obtain the method for solving of the application topic of above-mentioned user input, the application topic of above-mentioned mathematics template association and knowledge point, right rear line shows the method for solving of the application topic that this user inputs, the application topic of above-mentioned mathematics template association and knowledge point, thus effectively can solve the search problem of application topic, the search need that user inscribes application can be met better.
Application topic searching method provided by the invention, the related content of the application that user can be helped to find user to input topic.The essence of application topic search is the retrieval of the knowledge point that this application topic contains, and traditional method based on keyword retrieval can not meet the demand of user.This is because the description of same class application topic is ever-changing, be therefore the problem of a comparatively difficulty to the search of similar application topic problem.Such as, there is following twice application to inscribe, represent with Q1 and Q2 respectively:
Q1: the mother of Xiao Zhou allows Xiao Zhou go to buy meat.The unit price of the mutton that shop is sold and beef is respectively 8.5 yuan and 9 yuan.Xiao Zhou has bought altogether 4 jin of mutton and beef, cost 35 yuan altogether, may I ask Xiao Zhou and have purchased how many jin of mutton and beef respectively?
Q2: children's clothing factory produces red jacket and yellow jacket.The red jacket of every part needs 2 buttons, and the yellow jacket of every part needs 4 buttons.The jacket of the two kinds of colors made, dress up a case for every 30, every case clothes needs button 72 altogether.Red jacket and each how many of yellow jacket is there in every case?
Q1 and Q2 has identical derivation algorithm, but it describes but completely different.The application topic that if Q1 is user to be inputted, Q2 ∈ D, wherein D is the relevant exam pool of Q1, comprises the contents such as the method for solving of the application topic that Q1 is correlated with.Can see, because Q1 and Q2 is completely different, the algorithm based on keyword match cannot obtain gratifying Search Results, also cannot obtain relevant educational resource.
Although the text description of application topic problem is ever-changing, and its formula solved is but comparatively limited.Such as, the solution formula of this two methods of Q1 and Q2 topic problem is formula T, shown in (1).
Therefore, can Q1->T be set up, the corresponding relation of Q2->T, then can be set up the incidence relation of Q1 and Q2 by formula T, thus return to the solution throughway of user's relevant issues.Suppose Q
i∈ D is that the application associated with T is inscribed, can by the form of link by Q
ireturn to user.
Meanwhile, T can also attach certain attribute T.p.Application topic problem knowledge point widely can be obtained by T.p.Such as, in the problems referred to above, T can comprise following attribute T.p:{ linear equation in two unknowns, and application is inscribed, primary school, teacher ....
Carry out web search by above-mentioned several attribute, can obtain the web results shown in Fig. 2, Fig. 2 is the schematic diagram of a web results embodiment of application of the present invention topic searching method.As can see from Figure 2, the relevant information of a large amount of T.p is contained in above-mentioned web results.
Comprehensively above-mentioned two search steps, can obtain the result shown in Fig. 3, and Fig. 3 is the schematic diagram of a Search Results embodiment of application of the present invention topic searching method.
That is, application provided by the invention topic searching method have employed two search steps, and a class that the application inputted with user inscribes exact matching is inscribed to utilize T to search in exam pool, is the method for solving that user provides this class to inscribe.T.p then more fully inscribes relevant knowledge for user provides to the application that user inputs.Such as, in the above example, Q2 is inscribed in the application utilizing T to search the Q1 exact matching inputted with user in exam pool, utilizes T.p then to search the web page contents relevant to " linear equation in two unknowns ".
As can be seen from introduction above, application topic searching method provided by the invention can solve the search problem of application topic, for common search subscriber, application topic searching method provided by the invention can meet the search need of user better, effectively provides educational resource; For commercial user, application topic searching method provided by the invention can recommend the education product of these commercial accounts to search subscriber.
Fig. 4 is the structural representation of an application of the present invention topic searcher embodiment, application topic searcher in the present embodiment can realize the present invention's flow process embodiment illustrated in fig. 1, as shown in Figure 4, this application topic searcher can comprise: formalization module 41, search module 42 and display module 43;
Wherein, formalization module 41, turns to mathematical modulo plate for application topic form user inputted;
Search module 42, the mathematics template obtained for utilizing formalization module 41 is searched for the exam pool built in advance, obtains the method for solving of the application topic of above-mentioned user input, the application topic of above-mentioned mathematics template association and knowledge point;
Display module 43, for showing the method for solving of the application topic that the above-mentioned user that search module 42 obtains inputs, the application topic of above-mentioned mathematics template association and knowledge point to above-mentioned user.
Further, search module 42, the attribute also for the mathematics template utilizing formalization module 41 to obtain carries out web search, obtains the web results of the Attribute Association of above-mentioned mathematics template; Wherein, the attribute of above-mentioned mathematics template can be specified by the mode of artificial mark.
Display module 43, also for showing above-mentioned web results to above-mentioned user.
Above-mentioned application topic searcher, the application topic form that user inputs by formalization module 41 turns to mathematical modulo plate, search module 42 utilizes above-mentioned mathematics template to search for the exam pool built in advance, obtain the method for solving of the application topic of above-mentioned user input, the application topic of above-mentioned mathematics template association and knowledge point, then display module 43 shows the method for solving of the application topic that this user inputs to user, the application topic of above-mentioned mathematics template association and knowledge point, thus effectively can solve the search problem of application topic, the search need that user inscribes application can be met better.
Fig. 5 is the structural representation of another embodiment of application of the present invention topic searcher, compared with inscribing searcher with the application shown in Fig. 4, difference is, in the application topic searcher shown in Fig. 5, formalization module 41 can comprise: feature extraction submodule 411 and predictor module 412;
Wherein, feature extraction submodule 411, analyze for the sentence at digital place in the application topic that inputs above-mentioned user, extract at least one feature in above-mentioned sentence, at least one feature above-mentioned comprises at least one in the dependence of element in the N unit syntax in above-mentioned sentence, part of speech, dependence in above-mentioned sentence between word and word and formula, N is integer, N >=1;
Predictor module 412, at least one feature extracted for utilizing feature extraction submodule 411, maximizes in advance by the posterior probability model that training obtains, and obtains above-mentioned user and inputs mathematics template corresponding to application topic.
Further, formalization module 41 can also comprise: training submodule 413;
Feature extraction submodule 411, sentence also for digital place in the application topic inputted above-mentioned user is analyzed, before extracting at least one feature in above-mentioned sentence, the sentence at digital place in application topic for training is analyzed, extract at least one feature in above-mentioned sentence, at least one feature above-mentioned can comprise at least one in the dependence of element in the N unit syntax in above-mentioned sentence, part of speech, dependence in above-mentioned sentence between word and word and formula, N is integer, N >=1;
Training submodule 413, feature also for utilizing feature extraction submodule 411 to extract, obtain posterior probability model by training, above-mentioned posterior probability model is used for reflection and inscribes for described application, and described formal mathematics template can explain the degree that this application is inscribed.
Further, above-mentioned application topic searcher can also comprise:
Exam pool builds module 44, for utilizing before above-mentioned mathematics template searches for the exam pool built in advance at search module 42, the process that application topic form user inputted by above-mentioned formalization module 41 turns to mathematical modulo plate carries out automatic classification to exam pool, obtain the label information of above-mentioned exam pool, to complete the structure of above-mentioned exam pool.
Above-mentioned application topic searcher can solve the search problem of application topic, for common search subscriber, can meet the search need of user better, effectively provide educational resource; For commercial user, the education product of these commercial accounts can be recommended to search subscriber.
It should be noted that, in describing the invention, term " first ", " second " etc. only for describing object, and can not be interpreted as instruction or hint relative importance.In addition, in describing the invention, except as otherwise noted, the implication of " multiple " is two or more.
Describe and can be understood in process flow diagram or in this any process otherwise described or method, represent and comprise one or more for realizing the module of the code of the executable instruction of the step of specific logical function or process, fragment or part, and the scope of the preferred embodiment of the present invention comprises other realization, wherein can not according to order that is shown or that discuss, comprise according to involved function by the mode while of basic or by contrary order, carry out n-back test, this should understand by embodiments of the invention person of ordinary skill in the field.
Should be appreciated that each several part of the present invention can realize with hardware, software, firmware or their combination.In the above-described embodiment, multiple step or method can with to store in memory and the software performed by suitable instruction execution system or firmware realize.Such as, if realized with hardware, the same in another embodiment, can realize by any one in following technology well known in the art or their combination: the discrete logic with the logic gates for realizing logic function to data-signal, there is the special IC of suitable combinational logic gate circuit, programmable gate array (Programmable Gate Array; Hereinafter referred to as: PGA), field programmable gate array (Field ProgrammableGate Array; Hereinafter referred to as: FPGA) etc.
Those skilled in the art are appreciated that realizing all or part of step that above-described embodiment method carries is that the hardware that can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, this program perform time, step comprising embodiment of the method one or a combination set of.
In addition, each functional module in each embodiment of the present invention can be integrated in a processing module, also can be that the independent physics of modules exists, also can two or more module integrations in a module.Above-mentioned integrated module both can adopt the form of hardware to realize, and the form of software function module also can be adopted to realize.If described integrated module using the form of software function module realize and as independently production marketing or use time, also can be stored in a computer read/write memory medium.
The above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.
In the description of this instructions, specific features, structure, material or feature that the description of reference term " embodiment ", " some embodiments ", " example ", " concrete example " or " some examples " etc. means to describe in conjunction with this embodiment or example are contained at least one embodiment of the present invention or example.In this manual, identical embodiment or example are not necessarily referred to the schematic representation of above-mentioned term.And the specific features of description, structure, material or feature can combine in an appropriate manner in any one or more embodiment or example.
Although illustrate and describe embodiments of the invention above, be understandable that, above-described embodiment is exemplary, can not be interpreted as limitation of the present invention, and those of ordinary skill in the art can change above-described embodiment within the scope of the invention, revises, replace and modification.
Claims (10)
1. an application topic searching method, is characterized in that, comprising:
Application topic form user inputted turns to mathematical modulo plate;
Utilize described mathematics template to search for the exam pool built in advance, obtain the method for solving of the application topic of described user input, the application topic of described mathematics template association and knowledge point;
The method for solving of the application topic that described user inputs, the application topic of described mathematics template association and knowledge point is shown to described user.
2. method according to claim 1, is characterized in that, described application topic form user inputted also comprises after turning to mathematical modulo plate:
Utilize the attribute of described mathematics template to carry out web search, obtain the web results of the Attribute Association of described mathematics template;
Described web results is shown to described user.
3. method according to claim 1 and 2, is characterized in that, described application topic form user inputted turns to mathematical modulo plate and comprises:
In the application topic input described user, the sentence at digital place is analyzed, extract at least one feature in described sentence, at least one feature described comprises at least one in the dependence of element in the N unit syntax in described sentence, part of speech, dependence in described sentence between word and word and formula, N is integer, N >=1;
Utilize at least one feature described, maximize in advance by the posterior probability model that training obtains, obtain described user and input mathematics template corresponding to application topic.
4. method according to claim 3, is characterized in that, in the described application topic inputted described user, the sentence at digital place is analyzed, and before extracting at least one feature in described sentence, also comprises:
The sentence at digital place in application topic for training is analyzed, extract at least one feature in described sentence, at least one feature described comprises at least one in the dependence of element in the N unit syntax in described sentence, part of speech, dependence in described sentence between word and word and formula, N is integer, N >=1;
Utilize the feature extracted, obtain posterior probability model by training, described posterior probability model is used for reflection and inscribes for described application, and described formal mathematics template can explain the degree that described application is inscribed.
5. method according to claim 1, is characterized in that, describedly utilizes before described mathematics template searches for the exam pool built in advance, also comprises:
The process being turned to mathematical modulo plate by application topic form user inputted carries out automatic classification to exam pool, obtains the label information of described exam pool, to complete the structure of described exam pool.
6. an application topic searcher, is characterized in that, comprising:
Formalization module, turns to mathematical modulo plate for application topic form user inputted;
Search module, searches for the exam pool built in advance for the mathematics template utilizing described formalization module to obtain, and obtains the method for solving of the application topic of described user input, the application topic of described mathematics template association and knowledge point;
Display module, for showing the method for solving of the application topic that the described user that described search module obtains inputs, the application topic of described mathematics template association and knowledge point to described user.
7. device according to claim 6, is characterized in that,
Described search module, the attribute also for the mathematics template utilizing described formalization module to obtain carries out web search, obtains the web results of the Attribute Association of described mathematics template;
Described display module, also for showing described web results to described user.
8. the device according to claim 6 or 7, is characterized in that, described formalization module comprises:
Feature extraction submodule, analyze for the sentence at digital place in the application topic that inputs described user, extract at least one feature in described sentence, at least one feature described comprises at least one in the dependence of element in the N unit syntax in described sentence, part of speech, dependence in described sentence between word and word and formula, N is integer, N >=1;
Predictor module, at least one feature utilizing described feature extraction submodule to extract, maximizes in advance by the posterior probability model that training obtains, and obtains described user and inputs mathematics template corresponding to application topic.
9. device according to claim 8, is characterized in that, described formalization module also comprises: training submodule;
Described feature extraction submodule, sentence also for digital place in the application topic inputted described user is analyzed, before extracting at least one feature in described sentence, the sentence at digital place in application topic for training is analyzed, extract at least one feature in described sentence, at least one feature described comprises at least one in the dependence of element in the N unit syntax in described sentence, part of speech, dependence in described sentence between word and word and formula, N is integer, N >=1;
Described training submodule, feature also for utilizing described feature extraction submodule to extract, obtain posterior probability model by training, described posterior probability model is used for reflection and inscribes for described application, and described formal mathematics template can explain the degree that described application is inscribed.
10. device according to claim 6, is characterized in that, also comprises:
Exam pool builds module, for utilizing before described mathematics template searches for the exam pool built in advance at described search module, the process that application topic form user inputted by described formalization module turns to mathematical modulo plate carries out automatic classification to exam pool, obtain the label information of described exam pool, to complete the structure of described exam pool.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510187407.4A CN104778257B (en) | 2015-04-20 | 2015-04-20 | Using topic searching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510187407.4A CN104778257B (en) | 2015-04-20 | 2015-04-20 | Using topic searching method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104778257A true CN104778257A (en) | 2015-07-15 |
| CN104778257B CN104778257B (en) | 2018-09-07 |
Family
ID=53619721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510187407.4A Active CN104778257B (en) | 2015-04-20 | 2015-04-20 | Using topic searching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104778257B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107092593A (en) * | 2017-04-12 | 2017-08-25 | 华中师范大学 | The sentence semantics role recognition method and system of elementary mathematics stratified sampling application topic |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004102818A (en) * | 2002-09-11 | 2004-04-02 | Toshiba Corp | Retrieval support method and retrieval support device |
| CN1664835A (en) * | 2005-03-30 | 2005-09-07 | 结信网络技术服务（上海）有限公司 | Intelligent client service system for enterprises |
| CN1916898A (en) * | 2006-09-07 | 2007-02-21 | 上海交通大学 | Automatic answering system for online consultation oriented to information safety |
| CN101369265A (en) * | 2008-01-14 | 2009-02-18 | 北京百问百答网络技术有限公司 | Method and system for automatically generating semantic template of problem |
| CN101667998A (en) * | 2008-09-03 | 2010-03-10 | 华为技术有限公司 | Method, device and system for mobile search |
| CN103902652A (en) * | 2014-02-27 | 2014-07-02 | 深圳市智搜信息技术有限公司 | Automatic question-answering system |
| CN103955525A (en) * | 2014-05-09 | 2014-07-30 | 北京奇虎科技有限公司 | Method and client for searching answer to test question |
| CN104063443A (en) * | 2014-06-13 | 2014-09-24 | 百度在线网络技术（北京）有限公司 | Method and device for providing search result |
-
2015
- 2015-04-20 CN CN201510187407.4A patent/CN104778257B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004102818A (en) * | 2002-09-11 | 2004-04-02 | Toshiba Corp | Retrieval support method and retrieval support device |
| CN1664835A (en) * | 2005-03-30 | 2005-09-07 | 结信网络技术服务（上海）有限公司 | Intelligent client service system for enterprises |
| CN1916898A (en) * | 2006-09-07 | 2007-02-21 | 上海交通大学 | Automatic answering system for online consultation oriented to information safety |
| CN101369265A (en) * | 2008-01-14 | 2009-02-18 | 北京百问百答网络技术有限公司 | Method and system for automatically generating semantic template of problem |
| CN101667998A (en) * | 2008-09-03 | 2010-03-10 | 华为技术有限公司 | Method, device and system for mobile search |
| CN103902652A (en) * | 2014-02-27 | 2014-07-02 | 深圳市智搜信息技术有限公司 | Automatic question-answering system |
| CN103955525A (en) * | 2014-05-09 | 2014-07-30 | 北京奇虎科技有限公司 | Method and client for searching answer to test question |
| CN104063443A (en) * | 2014-06-13 | 2014-09-24 | 百度在线网络技术（北京）有限公司 | Method and device for providing search result |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107092593A (en) * | 2017-04-12 | 2017-08-25 | 华中师范大学 | The sentence semantics role recognition method and system of elementary mathematics stratified sampling application topic |
| CN107092593B (en) * | 2017-04-12 | 2020-11-03 | 华中师范大学 | Sentence semantic role recognition method and system for elementary mathematics hierarchical sampling application questions |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104778257B (en) | 2018-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145153B (en) | Intention category identification method and device | |
| US20170193393A1 (en) | Automated Knowledge Graph Creation | |
| US9460386B2 (en) | Passage justification scoring for question answering | |
| Smirnov et al. | Action patterns in business process model repositories | |
| CN103473409B (en) | The FPGA automatic fault diagnosis method in a kind of knowledge based storehouse | |
| CN107257970A (en) | The problem of being carried out from structuring and unstructured data sources answer | |
| CN105205096A (en) | Text modal and image modal crossing type data retrieval method | |
| Agrawal et al. | Data mining for improving textbooks | |
| CN104462212A (en) | Information exhibiting method and device | |
| CN107656921A (en) | A kind of short text dependency analysis method based on deep learning | |
| Plu et al. | A hybrid approach for entity recognition and linking | |
| CN105786971A (en) | International Chinese-teaching oriented grammar point identification method | |
| Kim | An implications of computer education in Korea from the US, UK and Germany computer curriculums | |
| CN104778257A (en) | Method and device for searching applied problems | |
| Raviya et al. | An Approach for Recommender System Based on Multilevel Sentiment Analysis Using Hybrid Deep Learning Models | |
| CN105786999A (en) | Software-developer visualization recommendation method based on complex network relationship | |
| Kanerva et al. | Post-hoc manipulations of vector space models with application to semantic role labeling | |
| Matuschek et al. | High performance word sense alignment by joint modeling of sense distance and gloss similarity | |
| KR101595314B1 (en) | Smart teaching system based on one-click content service | |
| CN114491209A (en) | Method and system for mining enterprise business label based on internet information capture | |
| Mart et al. | Hunting and Gathering on the Legal Information Savannah | |
| Schouten et al. | Preprocessing Requirements Documents for Automatic UML Modelling | |
| CN105808522A (en) | Method and apparatus for semantic association | |
| Gleize et al. | A unified kernel approach for learning typed sentence rewritings | |
| Elkaimbillah et al. | Comparative study of knowledge graph models in education domain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |