CN102737049A - Method and system for database query - Google Patents
Method and system for database query Download PDFInfo
- Publication number
- CN102737049A CN102737049A CN2011100899358A CN201110089935A CN102737049A CN 102737049 A CN102737049 A CN 102737049A CN 2011100899358 A CN2011100899358 A CN 2011100899358A CN 201110089935 A CN201110089935 A CN 201110089935A CN 102737049 A CN102737049 A CN 102737049A
- Authority
- CN
- China
- Prior art keywords
- semantic understanding
- database
- module
- problem statement
- statement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a method and a system for database query. The method includes the following steps that: a server receives a problem request from a client, and the problem request contains a problem statement submitted by a user; the server perform semantic understanding processing on the problem statement and encapsulates a semantic understanding processing result into a query format of a problem database, and queries the problem database; and the server provides a matched problem statement acquired through querying the problem database to the client. By adopting the method and the system for database query, a question raised by the user can be accurately responded, thereby improving customer service efficiency.
Description
Technical field
The present invention relates to Internet technical field, relate in particular to a kind of querying method and system of database.
Background technology
Along with the continuous development of Internet technology, the Internet user rapidly increases, and each ISP just is being devoted to constantly for the user better user experience to be provided.Yet; User experience is an aspect, when the face problem, need take usually to seek advice from or the mode complained is carried out asking for of customer service; The form of customer service is diversified, and wherein most widely used customer service form is: phone form and webpage (Web) form.
Wherein, the customer service of Web form specifically comprises following process: the user carries out replenishing of problem by system after submitting a question, check whether solve at existing issue; If existing problem then can guide the user to select existing problem, rather than ask a question again, can reduce the pressure of customer service system like this, reduce the human resources of customer service, because most of new problem finally all will transfer artificial treatment to.For example: the user submits a question " I apply for when the QQ blue diamond expires? " System is according to user's Query Database that submits a question; The content that the user is submitted a question and the content of the existing problem in the database are carried out the coupling of the vocabulary degree of correlation, and the existing problem that matches comprises:
1, how to apply for the QQ blue diamond;
2, the expired reason of QQ blue diamond;
3, what the effect of QQ blue diamond is;
Above three problems that system will match are shown to the user, and the guiding user selects, and the user selects the most the problem of coupling to submit to according to the problem that shows, are perhaps thinking submission new problem when not have the problem of coupling.This shows; This database query operations of prior art based on the vocabulary degree of correlation; Lack basic semantic understanding; Usually can't be directly the matching result of optimum be screened (sometimes even filter out semantic complete incoherent matching result), put question to, cause the customer service inefficiency thereby can't respond the user accurately.
Summary of the invention
In view of this, fundamental purpose of the present invention is to provide a kind of querying method and system of database, to realize that responding the user accurately puts question to, and improves customer service efficient.
For achieving the above object, technical scheme of the present invention is achieved in that
The querying method of a kind of database provided by the present invention, this method comprises:
Server receives the problem request from client, comprises the problem statement that the user submits in the said problem request;
Server carries out semantic understanding to said problem statement to be handled, and said semantic understanding process result is packaged into the interrogate format of issue database, and said issue database is inquired about;
The matching problem statement that server will be inquired about the issue database gained offers said client.
Said server carries out semantic understanding to the problem statement to be handled, and is specially:
Said problem statement is carried out type divide, and the problem statement that meets the type requirement is carried out participle handle with the mark part of speech;
Said participle and the problem statement that marks after part of speech is handled are carried out the stop words filtration treatment, deletion and the semantic speech that has nothing to do;
Utilize pre-configured synonym table, the problem statement after the said stop words filtration treatment is carried out synonym normalization handle, draw the semantic understanding process result.
Said the semantic understanding process result is packaged into the interrogate format of issue database, is specially:
Type according to said problem statement; From pre-configured nomenclature, extract and the corresponding Query Information of said semantic understanding process result, and said semantic understanding process result and corresponding Query Information are combined and packaged into the interrogate format of issue database.
The matching problem statement that said server will be inquired about the issue database gained offers client, is specially:
Said server carries out natural language processing to the matching problem statement of inquiry issue database gained, offers client with the mode of natural language.
This method further comprises:
Handle if can't successfully carry out semantic understanding, then said server returns the information that semantic understanding is handled failure to client.
The present invention also provides a kind of inquiry system of database, and this system comprises: problem is submitted module, question recommending module, semantic understanding module and issue database to, wherein,
Said problem is submitted module to, is used for the problem request from client is sent to said semantic understanding module through said question recommending module, comprises the problem statement that the user submits in the said problem request;
Said semantic understanding module is used for that said problem statement is carried out semantic understanding and handles, and said semantic understanding process result is packaged into the interrogate format of issue database, and said issue database is inquired about;
Said issue database is used to said semantic understanding module problem statement inquiry service is provided, and the matching problem statement of inquiring about gained is offered said semantic understanding module;
Said question recommending module is used for submitting said matching problem statement to module by the semantic understanding module forwards to problem, finally offers said client.
Said semantic understanding module is further used for,
Said problem statement is carried out type divide, and the problem statement that meets the type requirement is carried out participle handle with the mark part of speech;
Said participle and the problem statement that marks after part of speech is handled are carried out the stop words filtration treatment, deletion and the semantic speech that has nothing to do;
Utilize pre-configured synonym table, the problem statement after the said stop words filtration treatment is carried out synonym normalization handle, draw the semantic understanding process result.
Said semantic understanding module is further used for; Type according to said problem statement; From pre-configured nomenclature, extract and the corresponding Query Information of said semantic understanding process result, and said semantic understanding process result and corresponding Query Information are combined and packaged into the interrogate format of issue database.
Said semantic understanding module is further used for, and the matching problem statement of inquiring about the issue database gained is carried out natural language processing, with the mode of natural language, submits to module to offer client through said question recommending module, problem successively.
Said semantic understanding module is further used for, and in the time can't successfully carrying out the semantic understanding processing, submits module to through said question recommending module, problem successively, returns the information that semantic understanding is handled failure to client.
The querying method of a kind of database provided by the present invention and system, server receives the problem request from client, comprises the problem statement that the user submits in this problem request; Server carries out semantic understanding to this problem statement to be handled, and the semantic understanding process result is packaged into the interrogate format of issue database, and issue database is inquired about; The matching problem statement that server will be inquired about the issue database gained offers client.Through the present invention, can respond the user accurately and put question to, improve customer service efficient.
Description of drawings
Fig. 1 is the process flow diagram of the querying method of a kind of database of the present invention;
Fig. 2 is the composition structural representation of the inquiry system of a kind of database of the present invention.
Embodiment
Below in conjunction with accompanying drawing and specific embodiment technical scheme of the present invention is further set forth in detail.
The querying method of a kind of database provided by the present invention, as shown in Figure 1, mainly may further comprise the steps:
The user is connected with the server of customer service through the place client; And the problem statement that will put question to through client input; After input finished, client sent to server according to the problem request that user's indication will carry the problem statement that said user submits to.
For example: the user is through the server of place client login customer service; And the problem of customer service submit to the problem statement that page input will put question to " how many monthly payment prices of the red brill of QQ today is? " After the submission indication that receives the user, client will carry " how many monthly payment prices of the red brill of QQ today is? " The problem request send to server.
At first, server carries out type to the problem statement to be divided, and the problem statement that meets the type requirement is carried out participle handle with the mark part of speech.Wherein, the type of problem statement comprises: English sentence, yes-no question, alternative question, time question sentence, place question sentence, things question sentence, declarative sentence or the like.Need to prove, be English question sentence or declarative sentence if server is judged said problem statement, then directly returns the information that semantic understanding is handled failure to client, handles because the present invention only carries out semantic understanding to question sentence.So-called part of speech comprises: noun (n), verb (v), adjective (adj), adverbial word (adv), preposition (prep), interjection (inf), modal particle (r) or the like.
Secondly, the problem statement after server is handled participle and mark part of speech carries out the stop words filtration treatment, deletion and semantic irrelevant speech.The speech irrelevant with semanteme comprises preposition, adverbial word, interjection, modal particle or the like, and server is with deleting the problem statement of these speech after participle and mark part of speech are handled.
Then, the synonym table that server by utilizing is pre-configured is carried out synonym normalization to the problem statement after the stop words filtration treatment and is handled, and draws the semantic understanding process result.So-called synonym normalization is handled, and is meant that the speech with equivalent all replaces to same speech.
Residue speech through above operation obtains promptly constitutes the semantic understanding process result.Server is again according to the type of problem statement; From pre-configured nomenclature, extract and the corresponding Query Information of said semantic understanding process result; And said semantic understanding process result and corresponding Query Information be combined and packaged into the interrogate format of issue database, issue database is inquired about.The list that comprises all customer services in the said nomenclature.
The matching problem statement that step 103, server will be inquired about the issue database gained offers client.
Server carries out natural language processing to the matching problem statement of inquiry issue database gained, offers client with the mode of natural language.
The querying method of corresponding above-mentioned database, the present invention also provides a kind of inquiry system of database, and is as shown in Figure 2, comprising: problem is submitted module 10, question recommending module 20, semantic understanding module 30 and issue database 40 to.Wherein, problem is submitted module 10 to, is used for the problem request from client is sent to semantic understanding module 30 through question recommending module 20, comprises the problem statement that the user submits in the said problem request.Semantic understanding module 30 is used for that the problem statement is carried out semantic understanding and handles, and the semantic understanding process result is packaged into the interrogate format of issue database 40, and issue database 40 is inquired about.Issue database 40 is used to semantic understanding module 30 problem statement inquiry service is provided, and the matching problem statement of inquiring about gained is offered semantic understanding module 30.Question recommending module 20 is used for submitting the matching problem statement to module 10 by semantic understanding module 30 problem that is forwarded to, and finally offers client.
Preferable, semantic understanding module 30 also can be used for, and the problem statement is carried out type divide, and the problem statement that meets the type requirement is carried out participle handle with the mark part of speech; Participle and the problem statement that marks after part of speech is handled are carried out the stop words filtration treatment, deletion and the semantic speech that has nothing to do; Utilize pre-configured synonym table, the problem statement after the stop words filtration treatment is carried out synonym normalization handle, draw the semantic understanding process result.
Preferable; Semantic understanding module 30 also can be used for; Type according to the problem statement; From pre-configured nomenclature, extract and the corresponding Query Information of semantic understanding process result, and said semantic understanding process result and corresponding Query Information are combined and packaged into the interrogate format of issue database.
Preferable, semantic understanding module 30 also can be used for, and the matching problem statement of inquiring about issue database 40 gained is carried out natural language processing, with the mode of natural language, submits to module 10 to offer client through question recommending module 20 and problem successively.
Preferable, semantic understanding module 30 also can be used for, and in the time can't successfully carrying out the semantic understanding processing, submits module 10 to through question recommending module 20 and problem successively, returns semantic understanding to client and handles the information of failing.
Combine specific embodiment below again, the data base query method further explain that the inquiry system of above-mentioned database is realized.
The problem of the carrying statement that problem is submitted to module 10 to receive users to submit to through client " how many monthly payment prices of the red brill of QQ today is? " The problem request, this problem request is forwarded to semantic understanding module 30 through question recommending module 20.Problem statement in 30 pairs of problem requests of semantic understanding module carries out the semantic understanding of natural language to be handled, and specifically comprises following operation:
1, semantic understanding module 30 loads synonym table and nomenclature when program start.So-called synonym table is meant the synon table of record, can carry out synon normalization to the problem statement through this table and handle; For example: statement " price of today " and " price of today " be though text is different, after handling through synonym table, all becomes " price of today ", thereby help information processing.So-called nomenclature is meant the nomenclature comprising the list of all customer services; For example: the red brill of QQ, monthly payment all belong to client's list.
2, the problem statement of the user being submitted to is divided into one of following type with its type:
A) English sentence: all be English statement;
B) yes-no question: provide certainly, inquire the statement of whether setting up then;
C) alternative question: the question sentence that provides two or more selections;
D) time question sentence: the question sentence of query time;
E) place question sentence: the question sentence in inquiry place;
F) things question sentence: the question sentence of inquiring certain persons or things;
G) declarative sentence.
In the embodiment of the invention " how many monthly payment prices of the red brill of QQ today is? " Can be divided into the things question sentence.Need to prove; If judging said problem statement is English question sentence or declarative sentence; Then semantic understanding module 30 is submitted module 10 to through question recommending module 20 and problem successively; Return the information that semantic understanding is handled failure to client, handle because the present invention only carries out semantic understanding to question sentence.
3, the statement after the division type is carried out participle and the processing of mark part of speech.
For " QQ is red, and how many monthly payment prices of boring today is? ", can participle be:
The red brill of QQ/n today/n /r monthly payment/n price/n is/v what/adv/r
Wherein, n representes noun, and r representes modal particle, and v representes verb, and adv representes adverbial word, and r representes modal particle.
4, the problem statement after participle and the processing of mark part of speech is carried out the stop words filtration treatment, deletion and semantic irrelevant speech.At a problem statement preposition, adverbial word, interjection, modal particle or the like, with semantic irrelevant, can ignore usually.For example, for " how many monthly payment prices of the red brill of QQ today is? ", carry out after the stop words filtration treatment be:
The red brill of QQ/n today/n monthly payment/n price/n
5, utilize pre-configured synonym table, the problem statement after the stop words filtration treatment is carried out synonym normalization handle, the speech of equivalent is all replaced to same speech.Continue aforementioned for example, the result who carries out after synonym normalization is handled is:
The red brill of QQ/n today/n monthly payment/n price/n
6, according to the type of problem statement, use the method for keyword coupling, from pre-configured nomenclature, extract and the corresponding Query Information of said semantic understanding process result.
Continue aforementioned for example, the Query Information that extracts according to nomenclature is:
Command code: inquiry price
Time: today, be defaulted as the current time
The red brill of customer service: QQ
Unit: monthly payment
7, command conversion is combined and packaged into said semantic understanding process result and corresponding Query Information the interrogate format of issue database.
8, send querying command and give issue database, and receive the response of issue database.Issue database is searched the existing problem statement that all Query Informations all mate according to each Query Information in the querying command, with this as Query Result.
Through after the above-mentioned processing; The Query Result that 30 pairs of issue databases of semantic understanding module return (i.e. the existing problem statement of coupling) carries out natural language processing; With the mode of natural language, submit to module 10 to offer client through question recommending module 20 and problem successively.This natural language processing need not to carry out semantic analysis, directly is combined into sentence and gets final product.
Through above-mentioned processing, server can respond the user accurately and put question to (directly the matching result with optimum screens), and then improves customer service efficient.In addition, if semantic understanding module of the present invention 30 upgradings (for example synonym table, nomenclature upgrade) can not bring any additional work to the user, because client-side need not to upgrade.
Illustrative example more below is to embody advantage of the present invention.
Instance one: user inquiring " how many present monthly payment prices of Zhang San is? ", process is following:
1, the user imports " how many present monthly payment prices of Zhang San is? " The problem statement;
2, the client problem request that will comprise the problems referred to above statement sends to server;
3, the semantic understanding module 30 of server is carried out the semantic understanding processing of natural language, and result finds not have to cry the customer service of " Zhang San ";
4, semantic understanding module 30 is directly returned information: the customer service " Zhang San " that does not have you to inquire about.
Instance two: user inquiring " how many present monthly payment prices of the red brill of QQ is? ", process is following:
1, the user imports " how many present monthly payment prices of the red brill of QQ is? " The problem statement;
2, the client problem request that will comprise the problems referred to above statement sends to server;
3, the semantic understanding module 30 of the server semantic understanding that carries out natural language is handled, and converts the problem request interrogate format of issue database into from natural language, sends to issue database and inquires about;
4, the Query Result that returns of 30 pairs of issue databases of semantic understanding module carries out natural language processing, with the mode of natural language, submits to module 10 to offer client through question recommending module 20 and problem successively.
Can find out through above-mentioned instance; Existing database query operations; Handle such as " how many present monthly payment prices of Zhang San is? " Inquiry the time owing to there is not a semantic understanding, even therefore there is not semantic similar Query Result; Also can directly not return the information of inquiry failure, some are semantic uncorrelated and exist the matching result of certain vocabulary similarity to supply the user to select but filter out; And advantage of the present invention is embodied in just, handles through semantic understanding, and the result that semanteme is the most similar screens, and puts question to thereby can respond the user accurately, improves customer service efficient.
The above is merely preferred embodiment of the present invention, is not to be used to limit protection scope of the present invention.
Claims (10)
1. the querying method of a database is characterized in that, this method comprises:
Server receives the problem request from client, comprises the problem statement that the user submits in the said problem request;
Server carries out semantic understanding to said problem statement to be handled, and said semantic understanding process result is packaged into the interrogate format of issue database, and said issue database is inquired about;
The matching problem statement that server will be inquired about the issue database gained offers said client.
2. according to the querying method of the said database of claim 1, it is characterized in that said server carries out semantic understanding to the problem statement to be handled, and is specially:
Said problem statement is carried out type divide, and the problem statement that meets the type requirement is carried out participle handle with the mark part of speech;
Said participle and the problem statement that marks after part of speech is handled are carried out the stop words filtration treatment, deletion and the semantic speech that has nothing to do;
Utilize pre-configured synonym table, the problem statement after the said stop words filtration treatment is carried out synonym normalization handle, draw the semantic understanding process result.
3. according to the querying method of the said database of claim 2, it is characterized in that, said the semantic understanding process result be packaged into the interrogate format of issue database, be specially:
Type according to said problem statement; From pre-configured nomenclature, extract and the corresponding Query Information of said semantic understanding process result, and said semantic understanding process result and corresponding Query Information are combined and packaged into the interrogate format of issue database.
4. according to the querying method of the said database of claim 1, it is characterized in that the matching problem statement that said server will be inquired about the issue database gained offers client, is specially:
Said server carries out natural language processing to the matching problem statement of inquiry issue database gained, offers client with the mode of natural language.
5. according to the querying method of each said database of claim 1 to 4, it is characterized in that this method further comprises:
Handle if can't successfully carry out semantic understanding, then said server returns the information that semantic understanding is handled failure to client.
6. the inquiry system of a database is characterized in that, this system comprises: problem is submitted module, question recommending module, semantic understanding module and issue database to, wherein,
Said problem is submitted module to, is used for the problem request from client is sent to said semantic understanding module through said question recommending module, comprises the problem statement that the user submits in the said problem request;
Said semantic understanding module is used for that said problem statement is carried out semantic understanding and handles, and said semantic understanding process result is packaged into the interrogate format of issue database, and said issue database is inquired about;
Said issue database is used to said semantic understanding module problem statement inquiry service is provided, and the matching problem statement of inquiring about gained is offered said semantic understanding module;
Said question recommending module is used for submitting said matching problem statement to module by the semantic understanding module forwards to problem, finally offers said client.
7. according to the inquiry system of the said database of claim 6, it is characterized in that said semantic understanding module is further used for,
Said problem statement is carried out type divide, and the problem statement that meets the type requirement is carried out participle handle with the mark part of speech;
Said participle and the problem statement that marks after part of speech is handled are carried out the stop words filtration treatment, deletion and the semantic speech that has nothing to do;
Utilize pre-configured synonym table, the problem statement after the said stop words filtration treatment is carried out synonym normalization handle, draw the semantic understanding process result.
8. according to the inquiry system of the said database of claim 7; It is characterized in that; Said semantic understanding module is further used for; According to the type of said problem statement, from pre-configured nomenclature, extract and the corresponding Query Information of said semantic understanding process result, and said semantic understanding process result and corresponding Query Information are combined and packaged into the interrogate format of issue database.
9. according to the inquiry system of the said database of claim 6; It is characterized in that; Said semantic understanding module is further used for; Matching problem statement to inquiry issue database gained carries out natural language processing, with the mode of natural language, submits to module to offer client through said question recommending module, problem successively.
10. according to the inquiry system of each said database of claim 6 to 9; It is characterized in that; Said semantic understanding module is further used for; In the time can't successfully carrying out the semantic understanding processing, submit module to through said question recommending module, problem successively, return the information that semantic understanding is handled failure to client.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100899358A CN102737049A (en) | 2011-04-11 | 2011-04-11 | Method and system for database query |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100899358A CN102737049A (en) | 2011-04-11 | 2011-04-11 | Method and system for database query |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102737049A true CN102737049A (en) | 2012-10-17 |
Family
ID=46992569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100899358A Pending CN102737049A (en) | 2011-04-11 | 2011-04-11 | Method and system for database query |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102737049A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104735132A (en) * | 2015-02-13 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Information inquiry method, servers and terminal |
| WO2015196987A1 (en) * | 2014-06-24 | 2015-12-30 | 华为技术有限公司 | Natural language supported data query method, open platform and user terminal |
| WO2016127740A1 (en) * | 2015-02-13 | 2016-08-18 | 广州神马移动信息科技有限公司 | Information query method and device |
| WO2016179939A1 (en) * | 2015-05-12 | 2016-11-17 | 中兴通讯股份有限公司 | Intelligent customer service processing method and device thereof |
| CN106503239A (en) * | 2016-11-07 | 2017-03-15 | 上海智臻智能网络科技股份有限公司 | A kind of method and apparatus of legal information inquiry |
| CN107784064A (en) * | 2017-07-27 | 2018-03-09 | 上海壹账通金融科技有限公司 | Web data processing method, device, computer equipment and computer-readable storage medium |
| CN108228666A (en) * | 2016-12-22 | 2018-06-29 | 成都启典移动医疗***设备有限公司 | A kind of medical data base querying method, device and vehicle-mounted medical system |
| CN109241533A (en) * | 2018-09-06 | 2019-01-18 | 科大国创软件股份有限公司 | A kind of meaning of one's words based on natural language processing understands system and method |
| CN109344300A (en) * | 2018-08-31 | 2019-02-15 | 深圳壹账通智能科技有限公司 | The data query of natural language is intended to determine method, apparatus and computer equipment |
| CN110781676A (en) * | 2019-09-30 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Text processing method, device and system, electronic equipment and storage medium |
| CN111324631A (en) * | 2020-03-19 | 2020-06-23 | 成都海天数联科技有限公司 | Method for automatically generating sql statement by human natural language of query data |
| CN111599232A (en) * | 2020-06-28 | 2020-08-28 | 江苏科技大学 | Smart phone based on virtual reality and augmented reality technology and English learning assisting method |
| CN112183953A (en) * | 2020-09-08 | 2021-01-05 | 北京达佳互联信息技术有限公司 | Method and device for allocating customer service resources, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050043956A1 (en) * | 2003-07-03 | 2005-02-24 | Sony Corporation | Speech communiction system and method, and robot apparatus |
| CN1735027A (en) * | 2004-08-13 | 2006-02-15 | 上海赢思软件技术有限公司 | Chat robot system |
| CN101071418A (en) * | 2007-03-29 | 2007-11-14 | 腾讯科技（深圳）有限公司 | Chat method and system |
| CN101076060A (en) * | 2007-03-30 | 2007-11-21 | 腾讯科技（深圳）有限公司 | Chatting robot system and automatic chatting method |
| CN101076061A (en) * | 2007-03-30 | 2007-11-21 | 腾讯科技（深圳）有限公司 | Robot server and automatic chatting method |
| CN101193069A (en) * | 2006-12-13 | 2008-06-04 | 腾讯科技（深圳）有限公司 | Information inquiry system, instant communication robot server and information inquiry method |
| 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 |
-
2011
- 2011-04-11 CN CN2011100899358A patent/CN102737049A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050043956A1 (en) * | 2003-07-03 | 2005-02-24 | Sony Corporation | Speech communiction system and method, and robot apparatus |
| CN1735027A (en) * | 2004-08-13 | 2006-02-15 | 上海赢思软件技术有限公司 | Chat robot system |
| CN101193069A (en) * | 2006-12-13 | 2008-06-04 | 腾讯科技（深圳）有限公司 | Information inquiry system, instant communication robot server and information inquiry method |
| CN101071418A (en) * | 2007-03-29 | 2007-11-14 | 腾讯科技（深圳）有限公司 | Chat method and system |
| CN101076060A (en) * | 2007-03-30 | 2007-11-21 | 腾讯科技（深圳）有限公司 | Chatting robot system and automatic chatting method |
| CN101076061A (en) * | 2007-03-30 | 2007-11-21 | 腾讯科技（深圳）有限公司 | Robot server and automatic chatting method |
| 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 |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11934394B2 (en) | 2014-06-24 | 2024-03-19 | Huawei Technologies Co., Ltd. | Data query method supporting natural language, open platform, and user terminal |
| WO2015196987A1 (en) * | 2014-06-24 | 2015-12-30 | 华为技术有限公司 | Natural language supported data query method, open platform and user terminal |
| CN105279168A (en) * | 2014-06-24 | 2016-01-27 | 华为技术有限公司 | Data query method supporting natural language, open platform, and user terminal |
| US11494376B2 (en) | 2014-06-24 | 2022-11-08 | Huawei Technologies Co., Ltd. | Data query method supporting natural language, open platform, and user terminal |
| US10558655B2 (en) | 2014-06-24 | 2020-02-11 | Huawei Technologies Co., Ltd. | Data query method supporting natural language, open platform, and user terminal |
| CN105279168B (en) * | 2014-06-24 | 2019-04-23 | 华为技术有限公司 | Support data query method, open platform and the user terminal of natural language |
| WO2016127740A1 (en) * | 2015-02-13 | 2016-08-18 | 广州神马移动信息科技有限公司 | Information query method and device |
| US10860632B2 (en) | 2015-02-13 | 2020-12-08 | Alibaba Group Holding Limited | Information query method and device |
| CN104735132B (en) * | 2015-02-13 | 2017-05-24 | 腾讯科技（深圳）有限公司 | Information inquiry method, servers and terminal |
| CN104735132A (en) * | 2015-02-13 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Information inquiry method, servers and terminal |
| WO2016179939A1 (en) * | 2015-05-12 | 2016-11-17 | 中兴通讯股份有限公司 | Intelligent customer service processing method and device thereof |
| CN106294340A (en) * | 2015-05-12 | 2017-01-04 | 中兴通讯股份有限公司 | A kind of intelligent customer service processing method and device thereof |
| CN106503239A (en) * | 2016-11-07 | 2017-03-15 | 上海智臻智能网络科技股份有限公司 | A kind of method and apparatus of legal information inquiry |
| CN108228666A (en) * | 2016-12-22 | 2018-06-29 | 成都启典移动医疗***设备有限公司 | A kind of medical data base querying method, device and vehicle-mounted medical system |
| WO2019019671A1 (en) * | 2017-07-27 | 2019-01-31 | 深圳壹账通智能科技有限公司 | Webpage data processing method, device, computer apparatus and storage medium |
| CN107784064A (en) * | 2017-07-27 | 2018-03-09 | 上海壹账通金融科技有限公司 | Web data processing method, device, computer equipment and computer-readable storage medium |
| CN109344300A (en) * | 2018-08-31 | 2019-02-15 | 深圳壹账通智能科技有限公司 | The data query of natural language is intended to determine method, apparatus and computer equipment |
| WO2020042530A1 (en) * | 2018-08-31 | 2020-03-05 | 深圳壹账通智能科技有限公司 | Natural language-based data query intent determination method and apparatus, and computer device |
| CN109241533A (en) * | 2018-09-06 | 2019-01-18 | 科大国创软件股份有限公司 | A kind of meaning of one's words based on natural language processing understands system and method |
| CN110781676A (en) * | 2019-09-30 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Text processing method, device and system, electronic equipment and storage medium |
| CN111324631A (en) * | 2020-03-19 | 2020-06-23 | 成都海天数联科技有限公司 | Method for automatically generating sql statement by human natural language of query data |
| CN111324631B (en) * | 2020-03-19 | 2022-04-22 | 成都海天数联科技有限公司 | Method for automatically generating sql statement by human natural language of query data |
| CN111599232A (en) * | 2020-06-28 | 2020-08-28 | 江苏科技大学 | Smart phone based on virtual reality and augmented reality technology and English learning assisting method |
| CN112183953A (en) * | 2020-09-08 | 2021-01-05 | 北京达佳互联信息技术有限公司 | Method and device for allocating customer service resources, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102737049A (en) | Method and system for database query | |
| US20220138431A1 (en) | Method and system for securely storing private data in a semantic analysis system | |
| JP6714024B2 (en) | Automatic generation of N-grams and conceptual relationships from language input data | |
| JP6301958B2 (en) | Method and apparatus for configuring search terms, delivering advertisements, and retrieving product information | |
| US9959311B2 (en) | Natural language interface to databases | |
| US7853555B2 (en) | Enhancing multilingual data querying | |
| CN101639857B (en) | Method, device and system for establishing knowledge questioning and answering sharing platform | |
| US20110010352A1 (en) | Method and system of providing search tools | |
| US20130013616A1 (en) | Systems and Methods for Natural Language Searching of Structured Data | |
| CN107544988B (en) | Method and device for acquiring public opinion data | |
| WO2013170344A1 (en) | Method and system relating to sentiment analysis of electronic content | |
| WO2017005119A1 (en) | Method and device for implementing individualized guidance | |
| WO2014114175A1 (en) | Method and apparatus for providing search engine tags | |
| CN105404693A (en) | Service clustering method based on demand semantics | |
| CN105260365B (en) | The treating method and apparatus of end message | |
| CN110413882B (en) | Information pushing method, device and equipment | |
| JP4743766B2 (en) | Impression determination system, advertisement article generation system, impression determination method, advertisement article generation method, impression determination program, and advertisement article generation program | |
| US20190251201A1 (en) | Information searching system and information searching method | |
| CN113239177B (en) | Knowledge point query method, device, server, medium and product | |
| CN113254623B (en) | Data processing method, device, server, medium and product | |
| KR102549794B1 (en) | System and method for providing coupon service based on image | |
| WO2012099196A1 (en) | Information retrieval service provision device and method, building device for information retrieval service provision-use database, as well as computer program signal | |
| CN103473310A (en) | System and method for searching for node information sites of keywords | |
| US10031941B1 (en) | Structured search query generation and use in a computer network environment | |
| WO2019218151A1 (en) | Data searching method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20121017 |
|
| RJ01 | Rejection of invention patent application after publication |