CN109446277A - Relational data intelligent search method and system based on Chinese natural language - Google Patents
Relational data intelligent search method and system based on Chinese natural language Download PDFInfo
- Publication number
- CN109446277A CN109446277A CN201811104457.1A CN201811104457A CN109446277A CN 109446277 A CN109446277 A CN 109446277A CN 201811104457 A CN201811104457 A CN 201811104457A CN 109446277 A CN109446277 A CN 109446277A
- Authority
- CN
- China
- Prior art keywords
- relational data
- chinese
- data
- natural language
- relational
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Abstract
The invention discloses relational data intelligent search methods and system based on Chinese natural language, comprising the following steps: adds Chinese to the column name of table structure, the metadata of the Alias data and relational data is stored together by the alias referred to as arranged；Construct a search box, user's Chinese sentence corresponding to input inquiry in search box；The relational data processing engine that the Chinese sentence is sent to backstage is parsed；The data being resolved to are executed into a series of inquiry operation generated by relational data query engine, obtain final query result and result is fed back to the interface where search box, while corresponding chart is generated according to result data.The invention has the advantages that: can not only significantly reduce relational data to use threshold, and the accuracy of natural language processing is greatly improved, while very flexibly, adaptable to the structure change of relational data, without remodifying application software.
Description
Technical field
The present invention relates to the data processing fields in computer information system, it particularly relates to which a kind of be based on Chinese certainly
The relational data intelligent search method and system of right language.
Background technique
At present inquiry relational data basic skills be by execute SQL statement, this need user have English background with
And the knowledge of very strong relevant database, this is just generally using provided with relatively high threshold for relational data, although
Ordinary user can access relational data by using application software, but application is typically all immobilization, not flexible, with
The structure change data that perhaps user needs access conditions slightly to change of relational data or with business increase need
The structure of data is made an amendment, user needs to seek application software developer and is just able to satisfy to application software progress again exploitation
The demand of user.
For the problems in the relevant technologies, currently no effective solution has been proposed.
Summary of the invention
For above-mentioned technical problem in the related technology, the present invention proposes a kind of relationship type number based on Chinese natural language
According to intelligent search method and system, can not only significantly reduce relational data uses threshold, and is greatly improved certainly
The accuracy of right Language Processing, at the same very flexibly, it is adaptable to the structure change of relational data, it is answered without remodifying
Use software.
To realize the above-mentioned technical purpose, the technical scheme of the present invention is realized as follows:
A kind of relational data intelligent search method based on Chinese natural language, comprising the following steps:
S1 adds Chinese, the alias referred to as arranged, by the Alias data and relational data to the column name of table structure
Metadata be stored together；
S2 constructs a search box, user's Chinese sentence corresponding to input inquiry in search box；
S3 parses the relational data processing engine that the Chinese sentence is sent to backstage；
The data being resolved to are executed a series of inquiry operation generated by relational data query engine by S4, are obtained
Final query result is simultaneously fed back result to the interface where search box, while generating corresponding chart according to result data.
Further, the relational data processing engine that the Chinese sentence is sent to backstage is carried out in the step S3
Parsing specifically includes:
Relational data described in S31 handles engine and carries out participle solution to Chinese sentence by Chinese natural language processing technique
Analysis；
The word segmentation result being resolved to is transferred to relational data inquiry operation generator and is further parsed by S32；
Relational data inquiry operation generator described in S33 extracts data manipulation by scanning word segmentation result, generates and needs
The inquiry operation of the various types of relational datas executed.
Further, participle parsing is carried out to Chinese sentence by Chinese natural language processing technique in the step S31
It specifically includes:
Chinese sentence is carried out part-of-speech tagging by S311；
S312 parses part-of-speech tagging according to language model；
S313 obtains character string dimension after segmenting to Chinese sentence.
Further, the inquiry operation of relational data described in the step S33 includes but is not limited to the condition mistake of table
Filter inquiry operation, the conjunctive query operation of table, the projection inquiry operation of table, the cluster inquiry operation of table and query result data
Sorting operation.
Further, data manipulation includes but is not limited to keyword, period, condition limitation and system in the step S33
Meter.
Further, corresponding chart includes but is not limited to cake chart, column diagram and line graph in the step S4.
Another aspect of the present invention provides a kind of relational data intelligent searching system based on Chinese natural language, packet
It includes:
Memory module, for the column name to table structure add Chinese, the alias referred to as arranged, by the Alias data with
The metadata of relational data is stored together；
Module is constructed, for constructing a search box, user's Chinese sentence corresponding to input inquiry in search box；
First parsing module, the relational data processing engine for sending the Chinese sentence on backstage solve
Analysis；
Generation module is looked into for the data being resolved to be executed a series of of generation by relational data query engine
Operation is ask, obtains final query result and feed back result to generate to the interface where search box, while according to result data
Corresponding chart.
Further, the relational data processing that the Chinese sentence is sent to backstage is drawn in first parsing module
It holds up parse and specifically include:
Parsing module is segmented, for relational data processing engine by Chinese natural language processing technique to Chinese
Sentence carries out participle parsing；
Second parsing module is carried out for the word segmentation result being resolved to be transferred to relational data inquiry operation generator
Further parsing；
Extraction module extracts data behaviour by scanning word segmentation result for the relational data inquiry operation generator
Make, generates the inquiry operation of the various types of relational datas needed to be implemented.
Further, Chinese sentence is segmented by Chinese natural language processing technique in the participle parsing module
Parsing specifically includes:
Labeling module, for Chinese sentence to be carried out part-of-speech tagging；
Third parsing module, for parsing part-of-speech tagging according to language model；
Word segmentation module, for obtaining character string dimension after segmenting to Chinese sentence.
Further, the inquiry operation of relational data described in the extraction module includes but is not limited to the condition mistake of table
Filter inquiry operation, the conjunctive query operation of table, the projection inquiry operation of table, the cluster inquiry operation of table and query result data
Sorting operation.
Beneficial effects of the present invention:
1, significantly reduce relational data uses threshold；
2, the accuracy of natural language processing is greatly improved；
3, very flexibly, adaptable to the structure change of relational data, without remodifying application software.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the relational data intelligent search method based on Chinese natural language described according to embodiments of the present invention
One of flow chart；
Fig. 2 is the relational data intelligent search method based on Chinese natural language described according to embodiments of the present invention
The two of flow chart；
Fig. 3 is the relational data intelligent search method based on Chinese natural language described according to embodiments of the present invention
The three of flow chart；
Fig. 4 is the relational data intelligent search method based on Chinese natural language described according to embodiments of the present invention
Execute interface one；
Fig. 5 is the relational data intelligent search method based on Chinese natural language described according to embodiments of the present invention
Execute interface two；
Fig. 6 is the relational data intelligent searching system based on Chinese natural language described according to embodiments of the present invention
Schematic diagram；
Fig. 7 is the schematic diagram of the first described according to embodiments of the present invention parsing module.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art's every other embodiment obtained belong to what the present invention protected
Range.
As shown in Figs. 1-5, the relational data based on Chinese natural language according to embodiments of the present invention is intelligently searched
Suo Fangfa, comprising the following steps:
S1 adds Chinese, referred to as column alias to the column name of table structure, these Alias datas are stored in relationship type number
According to metadata, work is ready for the subsequent input inquiry based on Chinese natural language, as growth of business etc. becomes
Change, additions and deletions can be carried out to these Alias datas at any time and the operation such as change to meet new needs；
S2 constructs a search box, user institutes such as the alias of input inquiry and period and statistical operation in search box
Corresponding Chinese sentence；
S3 parses the relational data processing engine that the Chinese sentence is sent to backstage；
The data being resolved to are executed a series of inquiry operation generated by relational data query engine by S4, are obtained
Final query result is simultaneously fed back result to the interface where search box, while generating corresponding chart according to result data,
Such as cake chart, column diagram, line graph.
In one particular embodiment of the present invention, the Chinese sentence is sent in the step S3 relationship on backstage
Type data processing engine carries out parsing and specifically includes:
Relational data described in S31 handles engine and carries out participle solution to Chinese sentence by Chinese natural language processing technique
Analysis；
The word segmentation result being resolved to is transferred to relational data inquiry operation generator and is further parsed by S32；
Relational data inquiry operation generator can convert natural language to database substrate, construct from bottom
And realization, this is general enterprises and the personal ability not having.
First, accurately, as long as meeting the Chinese natural language of certain clause, data can be accurately obtained.Second, effect
Rate does not have to parsing SQL, directly generates, inquires, speed is fast.
Relational data inquiry operation generator described in S33 extracts data manipulation by scanning word segmentation result, generates and needs
The inquiry operation of the various types of relational datas executed.
Such as: according to statistic of classification average weighted valence, wherein sort by average weighted valence, preceding ten；This sentence from left to right according to
The secondary each word of scanning encounters and " wherein " then shows that subsequent sentence is condition limitation, encounters " preceding ", then read subsequent number
" ten " call underlay approach, and the limit 10 in analogy SQL is only more flexible, more easy-to-use.Ordinary people does not need
Study SQL can inquire data, this is the maximum application value of this method.
Specifically, Fudan University using open source is big at present firstly, natural language parsing NLP can segment natural language
It learns natural language processing library (FNLP), Chinese natural language is divided into character string dimension；
Such as querying condition are as follows: " according to product accounting total sales volume on July 8th, 2017 " can obtain after NLP is handled
One String [], content are { " according to ", " product ", " statistics ", " 2017 years ", " July ", " 8 days ", " always ", " sell
Volume " }, this is ordinary circumstance, just needs to carry out subsequent reprocessing under special circumstances, its complete participle can be just obtained, and it is subsequent
Reprocessing then needs research and development and written in code；
Secondly, above-mentioned String [] character string dimension is passed to relational data inquiry operation generator, inquired
The generation of operational order；
Such as: by { " according to ", " product ", " statistics ", " 2017 years ", " July ", " 8 days ", " always ", " sales volume " carry out
Scanning, the parsing segmented by a switch ... case, first from left to right, scanning is to first, left side word " it presses
According to ", then enter " according to " and branch, continue to scan on；If scanning is arrived followed by some word A, this word is different in institute
It is matched in name, the corresponding table of alias and column is returned if successful match if matching is unsuccessful and continue to scan on word
Symbol string array character late string B then matches A+B character string it is assumed herein that B is not subsequent key word inside all alias,
And so on, until finding corresponding table and column, or can not find.The above operation is because the success rate of Chinese word segmentation is often inadequate
The accuracy of natural language processing can be greatly improved in height, such processing.
If alias can not be correctly matched A+B+ ..., terminates resolving, and propose to feed back to user: column name inputs not
Correctly；
If finding corresponding alias, table and column are found, then continues to scan on the next of character string dimension；
Time interval is resolved to if encountering the time, and the period is set in inquiry operation generator；
It is that condition limits content by subsequent Context resolution if encountering " wherein " keyword；
If encountering " total " keyword, statistical operation is done, then continues to scan on the next of character string dimension, is extracted next
Alias is grouped statistics by alias, and operation is that GROUPBY is operated in corresponding SQL；
If encountering " year-on-year " " ring ratio ", the numerical value in previous period is calculated automatically, the numerical value of inquiry is compared, obtains
" year-on-year growth rate " " sequential growth rate "；
If encountering the grammer of " which is ... ", user is carrying out question and answer mode inquiry, can support such as " 2017
Year, which several most sales departments that always open an account? ", " 2017 " " total " " number of opening an account " in " sales department " is taken out at this time maximum
That data；
Entire scanning process, as soon as it can sketch whenever scanning to a keyword, then to obtain respective operations.Alias is at certain
For in kind meaning, it is configurable keyword；
Finally, entirely generating the process of inquiry operation terminates, the executable command tree of database query engine is obtained, rather than
SQL does so and not only guarantees accuracy rate, but also improves efficiency, and is generated by carrying out reversed SQL to command tree, it can be seen that above
A simple inquiry, corresponds to extremely complex, several associated query statements of table.
In one particular embodiment of the present invention, pass through the centering of Chinese natural language processing technique in the step S31
Literary sentence carries out participle parsing and specifically includes:
Chinese sentence is carried out part-of-speech tagging by S311；
S312 parses part-of-speech tagging according to language model；
S313 obtains character string dimension after segmenting to Chinese sentence.
Specifically, for example: this beginning of the sentence is first carried out part of speech mark by " according to product accounting total sales volume on July 8th, 2017 "
Note, such as: it is that noun, statistics are verbs or noun, on July 8th, 2017 are that time, total sales volume are according to being verb, product
Noun；
Next it is parsed according to language model, " according to product " is that strengthen language, " statistics " be predicate, " total " to condition is shape
Language, " sales volume " are objects；
Finally to obtain { " according to ", " after segmenting " according to product accounting total sales volume on July 8th, 2017 " produce
Product ", " statistics ", " 2017 years ", " July ", " 8 days ", " always ", " sales volume " character string dimension.
In one particular embodiment of the present invention, the inquiry operation of relational data described in the step S33 includes
But it is not limited to the condition filter inquiry operation of table, the conjunctive query operation of table, the projection inquiry operation of table, the cluster of table inquiry behaviour
Make the sorting operation with query result data.
In one particular embodiment of the present invention, in the step S33 data manipulation include but is not limited to keyword, when
Between section, condition limitation and statistics.
In one particular embodiment of the present invention, in the step S4 corresponding chart include but is not limited to cake chart,
Column diagram and line graph.
As shown in figs. 4-7, another aspect of the present invention provides a kind of relational data intelligence based on Chinese natural language
Search system, comprising:
Memory module, for the column name to table structure add Chinese, the alias referred to as arranged, by the Alias data with
The metadata of relational data is stored together；
Module is constructed, for constructing a search box, user's Chinese sentence corresponding to input inquiry in search box；
First parsing module, the relational data processing engine for sending the Chinese sentence on backstage solve
Analysis；
Generation module is looked into for the data being resolved to be executed a series of of generation by relational data query engine
Operation is ask, obtains final query result and feed back result to generate to the interface where search box, while according to result data
Corresponding chart.
In one particular embodiment of the present invention, backstage is sent by the Chinese sentence in first parsing module
Relational data processing engine carry out parsing specifically include:
Parsing module is segmented, for relational data processing engine by Chinese natural language processing technique to Chinese
Sentence carries out participle parsing；
Second parsing module is carried out for the word segmentation result being resolved to be transferred to relational data inquiry operation generator
Further parsing；
Extraction module extracts data behaviour by scanning word segmentation result for the relational data inquiry operation generator
Make, generates the inquiry operation of the various types of relational datas needed to be implemented.
In one particular embodiment of the present invention, pass through Chinese natural language processing technique in the participle parsing module
Participle parsing is carried out to Chinese sentence to specifically include:
Labeling module, for Chinese sentence to be carried out part-of-speech tagging；
Third parsing module, for parsing part-of-speech tagging according to language model；
Word segmentation module, for obtaining character string dimension after segmenting to Chinese sentence.
In one particular embodiment of the present invention, the inquiry operation of relational data described in the extraction module includes
But it is not limited to the condition filter inquiry operation of table, the conjunctive query operation of table, the projection inquiry operation of table, the cluster of table inquiry behaviour
Make the sorting operation with query result data.
In order to facilitate understanding above-mentioned technical proposal of the invention, below by way of in specifically used mode to of the invention above-mentioned
Technical solution is described in detail.
When specifically used, the relational data intelligent search side according to the present invention based on Chinese natural language
Method is scanned participle, when relational data handles engine to Chinese word segmentation progress semantic parsing in scanning from left to right
Carry out semantic analysis, it usually needs do following judgement: when the word read " according to ", relational data processing engine is just read
The mode for taking column alias, when reading " statistics ", relational data processing engine just understands that the input of user is according to these alias
Data column carry out SQL build group operation, when reading " sequence " or " arranging ", engine just understands the input of user for according to this
A little column are ranked up, when relational data processing engine reads date Value Data such as 2017, in May, 2017, last year, past ten
Year, last decade etc. just understand that the input of user needs to carry out time range constraint to table data, when relational data handles engine
When reading " total ", just understand that user needs to arrange the sum operation for build group for certain numerical value, subsequent input is exactly certain number
It is worth alias.
After relational data processing engine has collected these information, the information arranged to these is needed to carry out further
Processing, firstly, it is necessary to according to the column of the alias being collected into inquiry table in the metadata of table structure；Secondly, can be right after finding
The table answered is added in the table column for needing to inquire；Finally, relational data processing engine needs the letter according to the column being collected into
Breath builds a group information for statistics, inquires the information of restrictive condition and the information of correlation table, generates the operation for finally needing to inquire,
If inquiry operation needs to need the outer key connection according to table across table, the conjunctive query operation of table is established.At relational data
These operations can be assigned to parallel one or more node according to current system configuration and carry out parallel query behaviour by reason engine
Make, and give search end final result queries, search end can be selected according to the query result of return a variety of suitable charts into
Row is shown.
In conclusion relational data can not only be significantly reduced by means of above-mentioned technical proposal of the invention
Using threshold, and the accuracy of natural language processing is greatly improved, while very flexibly, to the structure change of relational data
It is adaptable, without remodifying application software.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of relational data intelligent search method based on Chinese natural language, which comprises the following steps:
S1 adds Chinese, the alias referred to as arranged, by the member of the Alias data and relational data to the column name of table structure
Data are stored together；
S2 constructs a search box, user's Chinese sentence corresponding to input inquiry in search box；
S3 parses the relational data processing engine that the Chinese sentence is sent to backstage；
The data being resolved to are executed a series of inquiry operation generated by relational data query engine by S4, are obtained final
Query result and result is fed back to the interface where search box, while corresponding chart is generated according to result data.
2. the relational data intelligent search method according to claim 1 based on Chinese natural language, which is characterized in that
The relational data processing engine that the Chinese sentence is sent to backstage parsing is carried out in the step S3 to specifically include:
Relational data described in S31 handles engine and carries out participle parsing to Chinese sentence by Chinese natural language processing technique；
The word segmentation result being resolved to is transferred to relational data inquiry operation generator and is further parsed by S32；
Relational data inquiry operation generator described in S33 extracts data manipulation by scanning word segmentation result, and generation needs to be implemented
Various types of relational datas inquiry operation.
3. the relational data intelligent search method according to claim 2 based on Chinese natural language, which is characterized in that
Participle parsing is carried out to Chinese sentence by Chinese natural language processing technique in the step S31 to specifically include:
Chinese sentence is carried out part-of-speech tagging by S311；
S312 parses part-of-speech tagging according to language model；
S313 obtains character string dimension after segmenting to Chinese sentence.
4. the relational data intelligent search method according to claim 2 based on Chinese natural language, which is characterized in that
The inquiry operation of relational data described in the step S33 includes but is not limited to the connection of the condition filter inquiry operation of table, table
Close the sorting operation of inquiry operation, the projection inquiry operation of table, the cluster inquiry operation of table and query result data.
5. the relational data intelligent search method according to claim 2 based on Chinese natural language, which is characterized in that
Data manipulation includes but is not limited to keyword, period, condition limitation and statistics in the step S33.
6. the relational data intelligent search method according to claim 1-5 based on Chinese natural language,
It is characterized in that, corresponding chart includes but is not limited to cake chart, column diagram and line graph in the step S4.
7. a kind of relational data intelligent searching system based on Chinese natural language characterized by comprising
Memory module adds Chinese, the alias referred to as arranged, by the Alias data and relationship for the column name to table structure
The metadata of type data is stored together；
Module is constructed, for constructing a search box, user's Chinese sentence corresponding to input inquiry in search box；
First parsing module, the relational data processing engine for sending the Chinese sentence on backstage parse；
Generation module is grasped for the data being resolved to be executed a series of inquiry generated by relational data query engine
Make, obtain final query result and result is fed back to the interface where search box, while being generated and being corresponded to according to result data
Chart.
8. the relational data intelligent searching system according to claim 7 based on Chinese natural language, which is characterized in that
It carries out the relational data processing engine that the Chinese sentence is sent to backstage to parse specific packet in first parsing module
It includes:
Parsing module is segmented, for relational data processing engine by Chinese natural language processing technique to Chinese sentence
Carry out participle parsing；
Second parsing module is carried out for the word segmentation result being resolved to be transferred to relational data inquiry operation generator into one
Step parsing；
Extraction module extracts data manipulation by scanning word segmentation result for the relational data inquiry operation generator, raw
At the inquiry operation of the various types of relational datas needed to be implemented.
9. the relational data intelligent searching system according to claim 8 based on Chinese natural language, which is characterized in that
Participle parsing is carried out to Chinese sentence by Chinese natural language processing technique in the participle parsing module to specifically include:
Labeling module, for Chinese sentence to be carried out part-of-speech tagging；
Third parsing module, for parsing part-of-speech tagging according to language model；
Word segmentation module, for obtaining character string dimension after segmenting to Chinese sentence.
10. the relational data intelligent search method based on Chinese natural language according to claim 8 or claim 9, feature
Be, the inquiry operation of relational data described in the extraction module include but is not limited to table condition filter inquiry operation,
The conjunctive query operation of table, the projection inquiry operation of table, the cluster inquiry operation of table and the sorting operation of query result data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811104457.1A CN109446277A (en) | 2018-09-21 | 2018-09-21 | Relational data intelligent search method and system based on Chinese natural language |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811104457.1A CN109446277A (en) | 2018-09-21 | 2018-09-21 | Relational data intelligent search method and system based on Chinese natural language |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109446277A true CN109446277A (en) | 2019-03-08 |
Family
ID=65533215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811104457.1A Pending CN109446277A (en) | 2018-09-21 | 2018-09-21 | Relational data intelligent search method and system based on Chinese natural language |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446277A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188163A (en) * | 2019-04-13 | 2019-08-30 | 上海策友信息科技有限公司 | Data intelligence processing system based on natural language |
| CN111460102A (en) * | 2020-03-31 | 2020-07-28 | 成都数之联科技有限公司 | Chart recommendation system and method based on natural language processing |
| CN113468174A (en) * | 2021-06-29 | 2021-10-01 | 天云融创数据科技（北京）有限公司 | Database query method and device, electronic equipment and computer storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646032A (en) * | 2013-11-11 | 2014-03-19 | 漆桂林 | Database query method based on body and restricted natural language processing |
| CN104657440A (en) * | 2015-01-30 | 2015-05-27 | 欧阳江 | Structured query statement generating system and method |
| US20160224645A1 (en) * | 2015-02-03 | 2016-08-04 | Siemens Aktiengesellschaft | System and method for ontology-based data integration |
| CN107748784A (en) * | 2017-10-26 | 2018-03-02 | 邢加和 | A kind of method that structured data searching is realized by natural language |
-
2018
- 2018-09-21 CN CN201811104457.1A patent/CN109446277A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646032A (en) * | 2013-11-11 | 2014-03-19 | 漆桂林 | Database query method based on body and restricted natural language processing |
| CN104657440A (en) * | 2015-01-30 | 2015-05-27 | 欧阳江 | Structured query statement generating system and method |
| US20160224645A1 (en) * | 2015-02-03 | 2016-08-04 | Siemens Aktiengesellschaft | System and method for ontology-based data integration |
| CN107748784A (en) * | 2017-10-26 | 2018-03-02 | 邢加和 | A kind of method that structured data searching is realized by natural language |
Non-Patent Citations (1)
| Title |
|---|
| 李虎 等: ""基于Ontology的数据库自然语言查询接口的研究"", 《计算机科学》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188163A (en) * | 2019-04-13 | 2019-08-30 | 上海策友信息科技有限公司 | Data intelligence processing system based on natural language |
| CN111460102A (en) * | 2020-03-31 | 2020-07-28 | 成都数之联科技有限公司 | Chart recommendation system and method based on natural language processing |
| CN111460102B (en) * | 2020-03-31 | 2022-09-09 | 成都数之联科技股份有限公司 | Chart recommendation system and method based on natural language processing |
| CN113468174A (en) * | 2021-06-29 | 2021-10-01 | 天云融创数据科技（北京）有限公司 | Database query method and device, electronic equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492077B (en) | Knowledge graph-based petrochemical field question-answering method and system | |
| Mishra et al. | A survey on question answering systems with classification | |
| Viola et al. | Learning to extract information from semi-structured text using a discriminative context free grammar | |
| CN108874878A (en) | A kind of building system and method for knowledge mapping | |
| CN109766417A (en) | A kind of construction method of the literature annals question answering system of knowledge based map | |
| JP2012520527A (en) | Question answering system and method based on semantic labeling of user questions and text documents | |
| IES20020647A2 (en) | A data quality system | |
| CN109446277A (en) | Relational data intelligent search method and system based on Chinese natural language | |
| CN104346331A (en) | Retrieval method and system for XML database | |
| CN112445894A (en) | Business intelligent system based on artificial intelligence and analysis method thereof | |
| Tapsai | Information processing and retrieval from CSV file by natural language | |
| Ilievski et al. | Commonsense knowledge in wikidata | |
| CN112507089A (en) | Intelligent question-answering engine based on knowledge graph and implementation method thereof | |
| Yang et al. | Ontology generation for large email collections. | |
| CN105677637A (en) | Method and device for updating abstract semantics database in intelligent question-answering system | |
| Das et al. | MyNLIDB: a natural language interface to database | |
| Bloehdorn et al. | Ontology-based question answering for digital libraries | |
| Wang et al. | Semi-supervised chinese open entity relation extraction | |
| CN114625748A (en) | SQL query statement generation method and device, electronic equipment and readable storage medium | |
| CN111831624A (en) | Data table creating method and device, computer equipment and storage medium | |
| Mvumbi | Natural language interface to relational database: a simplified customization approach | |
| Iftikhar et al. | Domain specific query generation from natural language text | |
| Lamparter et al. | Knowledge extraction from classification schemas | |
| CN113868312A (en) | Multi-method fused mechanism matching method, device, equipment and storage medium | |
| Rao et al. | Automatic identification of concepts and conceptual relations from patents using machine learning methods |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |