CN105653576A - Information searching method and apparatus, manual position service method and system - Google Patents
Information searching method and apparatus, manual position service method and system Download PDFInfo
- Publication number
- CN105653576A CN105653576A CN201510946482.4A CN201510946482A CN105653576A CN 105653576 A CN105653576 A CN 105653576A CN 201510946482 A CN201510946482 A CN 201510946482A CN 105653576 A CN105653576 A CN 105653576A
- Authority
- CN
- China
- Prior art keywords
- information
- semantic
- institute
- participle
- result
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/93—Document management systems
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an information searching method and apparatus, a manual position and system. The information searching method comprises steps of segmenting a text of input to-be-searched content, conducting semantic parsing for segmenting results to achieve semantic information of each segment, matching the semantic information with multi-set questions of a knowledge base, enabling answer information corresponding to and matched with a set of questions to be a search result if the match successes, and checking the knowledge base to achieve search results corresponding to the answer information via a full-text search method if the match fails. With better semantic understanding for the input to-be-searched text, accurate answer information can be achieved; even when a relative question is not found in the knowledge base during the match, the full-text search method can be employed to search a search result in file data of the knowledge base; and search results of the knowledge base can be accurately and high-efficiently achieved.
Description
Technical field
The present invention relates to field of computer technology, particularly relate to method and device, artificial seat call method and the system of information search.
Background technology
Existing search in the knowledge base of magnanimity information has the mode of effective information to generally include following two kinds: one, searched for by the mode of full-text search; Two, searched for by the mode of keyword query. Above-mentioned way of search cannot accurately orient effective information, but just can obtain result comparatively accurately after needing user to have certain understanding for knowledge or after possessing certain searching skill.
Summary of the invention
The technical problem to be solved in the present invention is, it is provided that the method for information search and device, artificial seat call method and system, the Search Results of the offer knowledge base of precise and high efficiency more.
The technical solution used in the present invention is, the method for described information search, comprising:
The text of the content to be searched of input is carried out participle;
The result of participle is carried out the semantic information that semantic parsing obtains each participle;
Thering is provided knowledge base, described knowledge base at least comprises many groups problem and the answer information corresponding with problem of often organizing;
Many groups problem of institute's semantic information and described knowledge base is carried out matching inquiry, if matching, then using the answer information corresponding to one group of problem matching as Search Results; Otherwise, then in described knowledge base, carried out inquiring about obtaining the Search Results corresponding with institute semantic information by the mode of full-text search.
Further, described method, also comprises:
Before the result of participle carries out semantic parsing, carry out filtering error correction to the result of described participle, to filter out participle wrong in the following areas: spelling, and/or, grammer.
Further, problem of often organizing comprises one or more semantic matches structure;
Described semantic matches structure comprises following at least one item:
1) the semantic information of at least one vocabulary in multiple vocabulary and the plurality of vocabulary;
2) logic relation between described multiple vocabulary.
Further, described knowledge base also comprises: document data; Described problem comprises: standard is asked;
Described being carried out in described knowledge base by the mode of full-text search inquires about to obtain result for retrieval corresponding to institute's semantic information, comprising:
Based on institute's semantic information the document data of described knowledge base, standard ask with answer information in carry out full-text search, demonstrate the result for retrieval that institute's semantic information is corresponding one by one.
Further, demonstrate the result for retrieval that institute's semantic information is corresponding one by one, comprising:
Result for retrieval corresponding to institute's semantic information is demonstrated from high in the end successively with the semantic similarity of described content to be searched according to institute's semantic information;
When semantic similarity is identical, then: demonstrate result for retrieval corresponding to institute's semantic information according to establishment time from the evening of document data successively to order early, or, result for retrieval corresponding to institute's semantic information is demonstrated successively to order early according to amendment time from the evening of document data, or, according to the click volume of document data from how to demonstrate result for retrieval corresponding to institute's semantic information successively to few order.
Further, at least one item below described semantic information:
1) synonym of participle and/or synonym combination;
2) the similar word of participle and/or similar phrase close;
3) there is the entity of same or similar structure with participle.
The present invention provides a kind of artificial seat call method, comprises the method for above-mentioned information search.
The present invention also provides the device of a kind of information search, comprising:
Word-dividing mode, for carrying out participle to the text of the content to be searched of input;
Semantic meaning analysis module, obtains the semantic information of each participle for the result of participle carries out semantic parsing;
Matching inquiry module, for many groups problem of institute's semantic information and described knowledge base is carried out matching inquiry, if matching, then using the answer information corresponding to one group of problem matching as Search Results; Otherwise, then in described knowledge base, carried out inquiring about obtaining the Search Results corresponding with institute semantic information by the mode of full-text search; Described knowledge base at least comprises many groups problem and the answer information corresponding with problem of often organizing.
Further, described device, also comprises:
Filter correction module, for, before the result of participle carries out semantic parsing, carrying out filtering error correction to the result of described participle, to filter out participle wrong in the following areas: spelling, and/or, grammer.
Further, problem of often organizing comprises one or more semantic matches structure;
Described semantic matches structure comprises following at least one item:
1) the semantic information of at least one vocabulary in multiple vocabulary and the plurality of vocabulary;
2) logic relation between described multiple vocabulary.
Further, described knowledge base also comprises: document data; Described problem comprises: standard is asked;
Described matching inquiry module, for:
Based on institute's semantic information the document data of described knowledge base, standard ask with answer information in carry out full-text search, demonstrate the result for retrieval that institute's semantic information is corresponding one by one.
Further, described matching inquiry module, for:
Result for retrieval corresponding to institute's semantic information is demonstrated from high in the end successively with the semantic similarity of described content to be searched according to institute's semantic information;
When semantic similarity is identical, then: demonstrate result for retrieval corresponding to institute's semantic information according to establishment time from the evening of document data successively to order early, or, result for retrieval corresponding to institute's semantic information is demonstrated successively to order early according to amendment time from the evening of document data, or, according to the click volume of document data from how to demonstrate result for retrieval corresponding to institute's semantic information successively to few order.Further, at least one item below described semantic information:
1) synonym of participle and/or synonym combination;
2) the similar word of participle and/or similar phrase close;
3) there is the entity of same or similar structure with participle.
The present invention provides a kind of Agent, comprises the device of above-mentioned information search.
Adopting technique scheme, the method for information search of the present invention and device, artificial seat call method and system at least have following advantage:
1, text to be searched is first carried out matching inquiry with the problem in knowledge base by the present invention, thus preferentially provides more accurate Search Results faster, embodies higher retrieval efficiency;
2, the present invention can ensure to provide Search Results by the mode of full-text search, avoids the situation that can not have Search Results when only carrying out matching inquiry with the problem in knowledge base;
3, when the present invention carries out full-text search, not only treat search content and retrieve, and the semantic information treating search content is retrieved, thus further increase the accuracy of search;
4, the dependence of Search Results for business knowledge familiarity is reduced to greatest extent;
5, the present invention is by carrying out better semantic understanding to the text to be searched of input, it may be possible to provide answer information more accurately.
Accompanying drawing explanation
Fig. 1 is the method flow diagram of the information search of first embodiment of the invention;
Fig. 2 is the device composition structural representation of the information search of second embodiment of the invention.
Embodiment
Reach, for further setting forth the present invention, technique means and effect that predetermined object is taked, below in conjunction with accompanying drawing and better embodiment, the present invention is described in detail as after.
First embodiment of the invention, a kind of method of information search, as shown in Figure 1, comprises following concrete steps:
Step S101, carries out participle to the text of the content to be searched of input;
Step S102, carries out, to the result of participle, the semantic information that semantic parsing obtains each participle.
Concrete, at least one item below described semantic information:
1) synonym of participle and/or synonym combination;
Such as, its synonym of the semantic information " weather " etc. of participle " weather ".
2) the similar word of participle and/or similar phrase close;
Wherein, the similar word of participle represents and belongs to other vocabulary of same class with this participle. If participle belongs to place name, then the similar word of this participle can comprise other place names. Such as, the semantic information of participle " Shanghai " can comprise " Beijing ", " Tianjin " etc.
3) there is the entity of same or similar structure with participle.
Wherein, the entity with participle with same or similar structure represents that the message structure of this entity and participle are same or similar. Preferably, this entity can be special semantic meaning representation formula.
Such as, participle is a specified time structure " 10: 45 on the 1st January in 2013 ", then the entity with participle with same or similar structure can be a date semantic meaning representation formula " the XXXX XX XX month, XX day point XX minute " etc. These similar special semantic meaning representation formulas also can comprise name, address, telephone number etc.
Step S103, it is provided that knowledge base, described knowledge base at least comprises many groups problem and the answer information corresponding with problem of often organizing. Described knowledge base, along with the increased frequency of search, has from learning perfect function, also accepts supervising professional simultaneously.
Described knowledge base can also comprise document data, and described document data can comprise business datum, working method etc. content, therefore described knowledge base is not limited only to mutual function, also can provide more function.
Further, problem of often organizing comprises one or more semantic matches structure; Preferably, a semantic matches structure also can be formula semantic matches structure or modus tollens semantic matches structure certainly; Semantic similarity expressed by one group of problem.
Wherein, a semantic matches structure can show as a semantic meaning representation formula. Preferably, this semantic matches structure includes but not limited to following at least one item:
A) the semantic information of at least one vocabulary in multiple vocabulary and the plurality of vocabulary, wherein, the semantic information of a vocabulary is mutually similar with the semantic information of a participle, does not repeat them here;
B) logic relation between described multiple vocabulary, such as the sequencing relation between the plurality of vocabulary, qualified relation (if a vocabulary is the qualifier of another vocabulary) etc.
Such as, three semantic matches structures below one group of semantic matches information " [date is correlated with ?] [rain kind] [for] [weather area name] [having] [impact] ", " [weather area name] [weather is correlated with] [or] [rain kind] " and " [inquiry ?] [the regional name of weather] [and the date is relevant | the time ?] [whether ?] [and needs | passable ?] [band umbrella] ". Wherein, " | " presentation logic or, a content representation vocabulary in each " [] " and/or the semantic information of this vocabulary, if " band umbrella " is a vocabulary, " weather area name " refers to the special expression formula etc. of generation area class vocabulary.
Step S104, carries out matching inquiry by many groups problem of institute's semantic information and described knowledge base, if matching, then using the answer information corresponding to one group of problem matching as Search Results; Otherwise, then in described knowledge base, carried out inquiring about obtaining the Search Results corresponding with institute semantic information by the mode of full-text search.
Concrete, in this step, the semantic information of text to be searched is first carried out matching inquiry with the problem in knowledge base, by the mechanism personalized, text to be searched is carried out precise positioning, thus more accurate Search Results faster is preferentially provided, embody higher retrieval efficiency. such as, in step S101, the text of content to be searched is " 10 yuan local flow bag how ", how about the text carries out the result that participle obtains is: participle " 10 yuan of local flow bags " and " ", how participle " 10 yuan of local flow bags " and " " carry out semantic parsing in step s 102 obtain both and distinguish corresponding semantic information, both semantic information is mated by step S104 with the many groups problem in the knowledge base provided in step S103, and determine both semantic information and three problems " what service of 10 yuan of local flow bag offers is ", " I wants to ask, you know 10 yuan of local flow bags ", one group of problem that " 10 yuan of local flow bags can give me what service " is formed is mated mutually, then " 10 yuan of local flow bags are the preferential activities of flow released for XX user to the answer information of this group correspondence, you only need to pay 10 yuan of monthly fees, can enjoy ... " how namely can be used as the answer information corresponding with the semantic information of participle " 10 yuan of local flow bags " and " ".
In the step S104 of the present embodiment, if many groups problem of institute's semantic information and described knowledge base is carried out matching inquiry, if not matching, then carried out by the mode of full-text search inquiring about to obtain result for retrieval corresponding to institute's semantic information in described knowledge base, also need to use in described knowledge base the document data also comprised in this case; The type of described document data comprises: working method and/or business datum etc.Described problem comprises: standard is asked. The document data obtain mode store with distinctive atomize, fine particulates; non-structured business document is decomposed; the structured data that problem user taken out by the mode of service template associates out with various dimensions answer and polymorphic type material mode (such as: the annexes such as multi-media) carries out template and applies mechanically, and reaches many sections of non-structured documents and converts high multiplexing atomize support thin knowledge point multi-platform by all kinds of means to.
The embodiment of the present invention can ensure to provide Search Results by the mode of full-text search, avoids the situation that may not have Search Results when only carrying out matching inquiry with the problem in knowledge base.
Further, carried out by the mode of full-text search inquiring about to obtain result for retrieval corresponding to institute's semantic information in described knowledge base, comprising:
Based on institute's semantic information the document data of described knowledge base, standard ask with answer information in carry out full-text search, demonstrate the result for retrieval that institute's semantic information is corresponding one by one.
Further, adopt taking the problem in structurizing as least unit during full-text search, complete to represent by the problem of document data catalogue content and storage, answer and the disposable search in search in full of related materials file. Represent in result and comprise: the answer of the gathering of the document data catalogue relevant to the semantic information of text to be searched, semantic precise positioning, the semantic synergistic data recommending associated problem and bottom algorithm to recommend, support that the direct preview of Multi-media Material wherein represents.
Further, demonstrate the result for retrieval that institute's semantic information is corresponding one by one, comprising:
Result for retrieval corresponding to institute's semantic information is demonstrated from high in the end successively with the semantic similarity of described content to be searched according to institute's semantic information;
When semantic similarity is identical, then: demonstrate result for retrieval corresponding to institute's semantic information according to establishment time from the evening of document data successively to order early, or, result for retrieval corresponding to institute's semantic information is demonstrated successively to order early according to amendment time from the evening of document data, or, according to the click volume of document data from how to demonstrate result for retrieval corresponding to institute's semantic information successively to few order. Find the example of result for retrieval below finally by full-text search for one:
If input " credit card ", then credit card participle obtains: credit card, credit, card, letter, use;
Can also obtain semantic very close with credit card after semanteme is resolved: bank card, bank, card, silver.
After semantic parsing, except the participle that " credit card " is own, also obtaining other words that implication is relevant, therefore, the present invention is by carrying out better semantic understanding to the text to be searched of input, it is possible in follow-up offer answer information more accurately.
During full-text search, eight words above retrieving respectively in the answer that the document data of knowledge base and problem and problem are corresponding also return Search Results, the result retrieved based on document data comprises: associated traffic data or the service datas such as how credit card bandwidth ranking list, credit card are applied for, credit card forum, credit card arbitrage, the result retrieved based on the answer that problem and problem are corresponding comprises: how to apply for the answer of credit card and correspondence thereof, how to identify the answer etc. of credit card fraud and correspondence thereof. Owing to the embodiment of the present invention is when carrying out full-text search, not only treat search content to retrieve, and the semantic information treating search content retrieves, thus further increase the accuracy of search, the content comprised in the resources and knowledge storehouse of another aspect due to retrieval, comparatively comprehensive compared to the database only comprising document data in prior art, also reduce the dependence of Search Results for business knowledge familiarity to greatest extent.
Second embodiment of the invention, a kind of method of information search, method described in the present embodiment is roughly the same with the first embodiment, and difference is, the described method of the present embodiment, also comprises following concrete steps:
Before the result of participle carries out semantic parsing, carry out filtering error correction to the result of described participle, to filter out participle wrong in the following areas: spelling, and/or, grammer.
The result of participle is first carried out filtering error correction and carries out semantic parsing again by the present embodiment, it is possible to makes the result of semantic parsing more accurate, thus promotes the accuracy of Search Results.
Third embodiment of the invention, the device of introducing a kind of information search corresponding to the first embodiment, as shown in Figure 2, comprises following integral part:
1) word-dividing mode 201, for carrying out participle to the text of the content to be searched of input;
2) semantic meaning analysis module 202, obtain the semantic information of each participle for the result of participle carries out semantic parsing;
Concrete, at least one item below described semantic information:
1. the synonym of participle and/or synonym combination;
2. the similar word of participle and/or similar phrase close;
3. there is the entity of same or similar structure with participle.
3) matching inquiry module 203, for many groups problem of institute's semantic information and described knowledge base is carried out matching inquiry, if matching, then using the answer information corresponding to one group of problem matching as Search Results; Otherwise, then in described knowledge base, carried out inquiring about obtaining the Search Results corresponding with institute semantic information by the mode of full-text search; Described knowledge base at least comprises many groups problem and the answer information corresponding with problem of often organizing.
Concrete, problem of often organizing comprises one or more semantic matches structure;
Described semantic matches structure comprises following at least one item:
1. the semantic information of at least one vocabulary in many vocabulary and the plurality of vocabulary;
2. logic relation between multiple vocabulary described in.
Further, described knowledge base also comprises: document data; The type of described document data comprises: working method and/or business datum etc. Described problem comprises: standard is asked
Matching inquiry module 203, specifically for:
Based on institute's semantic information the document data of described knowledge base, standard ask with answer information in carry out full-text search, demonstrate the result for retrieval that institute's semantic information is corresponding one by one.
Further, matching inquiry module 203, for:
Result for retrieval corresponding to institute's semantic information is demonstrated from high in the end successively with the semantic similarity of described content to be searched according to institute's semantic information;
When semantic similarity is identical, then: demonstrate result for retrieval corresponding to institute's semantic information according to establishment time from the evening of document data successively to order early, or, result for retrieval corresponding to institute's semantic information is demonstrated successively to order early according to amendment time from the evening of document data, or, according to the click volume of document data from how to demonstrate result for retrieval corresponding to institute's semantic information successively to few order.
Fourth embodiment of the invention, the device of introducing a kind of information search corresponding with the 2nd embodiment, device described in the present embodiment is roughly the same with the 3rd embodiment, and difference is, the described device of the present embodiment, also comprises following concrete integral part:
Filter correction module, for, before the result of participle carries out semantic parsing, carrying out filtering error correction to the result of described participle, to filter out participle wrong in the following areas: spelling, and/or, grammer.
Fifth embodiment of the invention, a kind of artificial seat call method, comprises the method for the information search described in the first embodiment or the 2nd embodiment.
Sixth embodiment of the invention, a kind of Agent, comprises the device of the information search described in the 3rd embodiment or the 4th embodiment.
The method of the described information search of the embodiment of the present invention and device, artificial seat call method and system, by carrying out better semantic understanding to the text to be searched of input, it may be possible to provide answer information more accurately. Even if based on semantic information could not in knowledge base, matching inquiry is to corresponding problem time, can also transfer to adopt in the document data of the mode of full-text search in knowledge base and carry out retrieving to provide corresponding result for retrieval, accordingly, it may be possible to the Search Results of the offer knowledge base of precise and high efficiency more.
By the explanation of embodiment, it should can be reach technique means that predetermined object takes and effect is able to more deeply and concrete understanding to the present invention, but appended diagram is only to provide with reference to the use with explanation, is not used for the present invention being limited.
Claims (14)
1. the method for an information search, it is characterised in that, comprising:
The text of the content to be searched of input is carried out participle;
The result of participle is carried out the semantic information that semantic parsing obtains each participle;
Thering is provided knowledge base, described knowledge base at least comprises many groups problem and the answer information corresponding with problem of often organizing;
Many groups problem of institute's semantic information and described knowledge base is carried out matching inquiry, if matching, then using the answer information corresponding to one group of problem matching as Search Results; Otherwise, then in described knowledge base, carried out inquiring about obtaining the Search Results corresponding with institute semantic information by the mode of full-text search.
2. the method for information search according to claim 1, it is characterised in that, described method, also comprises:
Before the result of participle carries out semantic parsing, carry out filtering error correction to the result of described participle, to filter out participle wrong in the following areas: spelling, and/or, grammer.
3. the method for information search according to claim 1, it is characterised in that, problem of often organizing comprises one or more semantic matches structure;
Described semantic matches structure comprises following at least one item:
1) the semantic information of at least one vocabulary in multiple vocabulary and the plurality of vocabulary;
2) logic relation between described multiple vocabulary.
4. the method for information search according to claim 1, it is characterised in that, described knowledge base also comprises: document data; Described problem comprises: standard is asked;
Described being carried out in described knowledge base by the mode of full-text search inquires about to obtain result for retrieval corresponding to institute's semantic information, comprising:
Based on institute's semantic information the document data of described knowledge base, standard ask with answer information in carry out full-text search, demonstrate the result for retrieval that institute's semantic information is corresponding one by one.
5. the method for information search according to claim 4, it is characterised in that, demonstrate the result for retrieval that institute's semantic information is corresponding one by one, comprising:
Result for retrieval corresponding to institute's semantic information is demonstrated from high in the end successively with the semantic similarity of described content to be searched according to institute's semantic information;
When semantic similarity is identical, then: demonstrate result for retrieval corresponding to institute's semantic information according to establishment time from the evening of document data successively to order early, or, result for retrieval corresponding to institute's semantic information is demonstrated successively to order early according to amendment time from the evening of document data, or, according to the click volume of document data from how to demonstrate result for retrieval corresponding to institute's semantic information successively to few order.
6. the method for information search according to any one of Claims 1 to 5, it is characterised in that, at least one item below described semantic information:
1) synonym of participle and/or synonym combination;
2) the similar word of participle and/or similar phrase close;
3) there is the entity of same or similar structure with participle.
7. an artificial seat call method, it is characterised in that, comprise the method for the information search as according to any one of claim 1-6.
8. the device of an information search, it is characterised in that, comprising:
Word-dividing mode, for carrying out participle to the text of the content to be searched of input;
Semantic meaning analysis module, obtains the semantic information of each participle for the result of participle carries out semantic parsing;
Matching inquiry module, for many groups problem of institute's semantic information and described knowledge base is carried out matching inquiry, if matching, then using the answer information corresponding to one group of problem matching as Search Results; Otherwise, then in described knowledge base, carried out inquiring about obtaining the Search Results corresponding with institute semantic information by the mode of full-text search; Described knowledge base at least comprises many groups problem and the answer information corresponding with problem of often organizing.
9. the device of information search according to claim 8, it is characterised in that, described device, also comprises:
Filter correction module, for, before the result of participle carries out semantic parsing, carrying out filtering error correction to the result of described participle, to filter out participle wrong in the following areas: spelling, and/or, grammer.
10. the device of information search according to claim 8, it is characterised in that, problem of often organizing comprises one or more semantic matches structure;
Described semantic matches structure comprises following at least one item:
1) the semantic information of at least one vocabulary in multiple vocabulary and the plurality of vocabulary;
2) logic relation between described multiple vocabulary.
The device of 11. information searches according to claim 8, it is characterised in that, described knowledge base also comprises: document data; Described problem comprises: standard is asked;
Described matching inquiry module, for:
Based on institute's semantic information the document data of described knowledge base, standard ask with answer information in carry out full-text search, demonstrate the result for retrieval that institute's semantic information is corresponding one by one.
The device of 12. information searches according to claim 11, it is characterised in that, described matching inquiry module, for:
Result for retrieval corresponding to institute's semantic information is demonstrated from high in the end successively with the semantic similarity of described content to be searched according to institute's semantic information;
When semantic similarity is identical, then: demonstrate result for retrieval corresponding to institute's semantic information according to establishment time from the evening of document data successively to order early, or, result for retrieval corresponding to institute's semantic information is demonstrated successively to order early according to amendment time from the evening of document data, or, according to the click volume of document data from how to demonstrate result for retrieval corresponding to institute's semantic information successively to few order.
The device of 13. information searches according to any one of claim 8��12, it is characterised in that, at least one item below described semantic information:
1) synonym of participle and/or synonym combination;
2) the similar word of participle and/or similar phrase close;
3) there is the entity of same or similar structure with participle.
14. 1 kinds of Agents, it is characterised in that, comprise the device of the information search as according to any one of claim 8-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510946482.4A CN105653576A (en) | 2015-12-16 | 2015-12-16 | Information searching method and apparatus, manual position service method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510946482.4A CN105653576A (en) | 2015-12-16 | 2015-12-16 | Information searching method and apparatus, manual position service method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105653576A true CN105653576A (en) | 2016-06-08 |
Family
ID=56476586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510946482.4A Pending CN105653576A (en) | 2015-12-16 | 2015-12-16 | Information searching method and apparatus, manual position service method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105653576A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372191A (en) * | 2016-08-31 | 2017-02-01 | 广东华邦云计算股份有限公司 | Data search method and device |
| CN106682221A (en) * | 2017-01-04 | 2017-05-17 | 上海智臻智能网络科技股份有限公司 | Response method and device for question and answer interaction and question and answer system |
| CN107992543A (en) * | 2017-11-27 | 2018-05-04 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer-readable recording medium |
| CN109739964A (en) * | 2018-12-27 | 2019-05-10 | 北京拓尔思信息技术股份有限公司 | Knowledge data providing method, device, electronic equipment and storage medium |
| CN110765343A (en) * | 2019-12-10 | 2020-02-07 | 北京中电普华信息技术有限公司 | Semantic retrieval method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7257530B2 (en) * | 2002-02-27 | 2007-08-14 | Hongfeng Yin | Method and system of knowledge based search engine using text mining |
| CN101674259A (en) * | 2008-09-11 | 2010-03-17 | 多友科技（北京）有限公司 | Full-text retrieval realizing method for instant communication system of enterprise |
| CN104216913A (en) * | 2013-06-04 | 2014-12-17 | Sap欧洲公司 | Problem answering frame |
| CN104573028A (en) * | 2015-01-14 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Intelligent question-answer implementing method and system |
| CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
| CN104951456A (en) * | 2014-03-26 | 2015-09-30 | 上海智臻网络科技有限公司 | Method, device and equipment used for obtaining answer information |
-
2015
- 2015-12-16 CN CN201510946482.4A patent/CN105653576A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7257530B2 (en) * | 2002-02-27 | 2007-08-14 | Hongfeng Yin | Method and system of knowledge based search engine using text mining |
| CN101674259A (en) * | 2008-09-11 | 2010-03-17 | 多友科技（北京）有限公司 | Full-text retrieval realizing method for instant communication system of enterprise |
| CN104216913A (en) * | 2013-06-04 | 2014-12-17 | Sap欧洲公司 | Problem answering frame |
| CN104951456A (en) * | 2014-03-26 | 2015-09-30 | 上海智臻网络科技有限公司 | Method, device and equipment used for obtaining answer information |
| CN104573028A (en) * | 2015-01-14 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Intelligent question-answer implementing method and system |
| CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372191A (en) * | 2016-08-31 | 2017-02-01 | 广东华邦云计算股份有限公司 | Data search method and device |
| CN106682221A (en) * | 2017-01-04 | 2017-05-17 | 上海智臻智能网络科技股份有限公司 | Response method and device for question and answer interaction and question and answer system |
| CN106682221B (en) * | 2017-01-04 | 2020-04-21 | 上海智臻智能网络科技股份有限公司 | Question-answer interaction response method and device and question-answer system |
| CN107992543A (en) * | 2017-11-27 | 2018-05-04 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer-readable recording medium |
| CN107992543B (en) * | 2017-11-27 | 2020-11-17 | 上海智臻智能网络科技股份有限公司 | Question-answer interaction method and device, computer equipment and computer readable storage medium |
| CN109739964A (en) * | 2018-12-27 | 2019-05-10 | 北京拓尔思信息技术股份有限公司 | Knowledge data providing method, device, electronic equipment and storage medium |
| CN110765343A (en) * | 2019-12-10 | 2020-02-07 | 北京中电普华信息技术有限公司 | Semantic retrieval method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cafarella et al. | Data integration for the relational web | |
| CN110704411B (en) | Knowledge graph building method and device suitable for art field and electronic equipment | |
| CN105653576A (en) | Information searching method and apparatus, manual position service method and system | |
| US8166013B2 (en) | Method and system for crawling, mapping and extracting information associated with a business using heuristic and semantic analysis | |
| CN105630938A (en) | Intelligent question-answering system | |
| US20110153654A1 (en) | Natural language-based tour destination recommendation apparatus and method | |
| CN101794307A (en) | Vehicle navigation POI (Point of Interest) search engine based on internetwork word segmentation idea | |
| CN106202294A (en) | The related news computational methods merged based on key word and topic model and device | |
| CN103198067A (en) | Business searching method and system | |
| US20150199402A1 (en) | Computerized systems and methods for indexing and serving recurrent calendar events | |
| CN105760380A (en) | Database query method, device and system | |
| KR20160005563A (en) | System for replying telephone number using analysis of user's voice and method thereof | |
| CN106156111A (en) | Patent document search method, device and system | |
| CN108228663A (en) | A kind of paging search method and device | |
| CN108829651A (en) | A kind of method, apparatus of document treatment, terminal device and storage medium | |
| CN107370830B (en) | Trade information supplying system based on big data and method | |
| CN110674365A (en) | Searching method, device, equipment and storage medium | |
| CN103914486B (en) | Document search and display system | |
| CN103914487A (en) | Document collection, identification and association system | |
| CN106202038A (en) | Synonym method for digging based on iteration and device | |
| CN103294670A (en) | Searching method and system based on word list | |
| CN110362732A (en) | A kind of method of information system content search | |
| WO2019179208A1 (en) | Drop-down suggestion list | |
| KR20160002199A (en) | Issue data extracting method and system using relevant keyword | |
| CN104463460B (en) | Processing method and processing device for the waiting information that network data is launched |
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: 20160608 |
|
| RJ01 | Rejection of invention patent application after publication |