CN106326307A - Language interaction method - Google Patents
Language interaction method Download PDFInfo
- Publication number
- CN106326307A CN106326307A CN201510387071.6A CN201510387071A CN106326307A CN 106326307 A CN106326307 A CN 106326307A CN 201510387071 A CN201510387071 A CN 201510387071A CN 106326307 A CN106326307 A CN 106326307A
- Authority
- CN
- China
- Prior art keywords
- statement
- analysis result
- feedback
- empty
- semantic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000003993 interaction Effects 0.000 title claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 18
- 230000004044 response Effects 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 72
- 230000014509 gene expression Effects 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 10
- 230000002452 interceptive effect Effects 0.000 claims description 10
- 235000013399 edible fruits Nutrition 0.000 claims 2
- 230000000875 corresponding effect Effects 0.000 description 33
- 238000007726 management method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a language interaction method applied to a language interaction process between a user and a robot. A storage unit is used for storing a preset semantic statement, and the semantic statement comprises domain sentences representing of single domain attributes and general sentences representing multi-domain attributes. The voice interaction method of an event comprises the following steps of 1, acquiring a natural language sentence output by the user; 2, performing semantic parsing on the natural language sentence to acquire a corresponding semantic parsing result; S3, processing according to the semantic parsing result by the robot to output a corresponding response result; 4, acquiring a feedback sentence output by the user; 5, judging whether the feedback sentence is an ending command, if yes, executing the step 7, and otherwise executing the step 6; 6, performing semantic parsing on the feedback sentence to acquire the corresponding semantic parsing result, and returning to execute the step 3; and 7, ending.
Description
Technical field
The present invention relates to spoken natural language understanding field, particularly relate to a kind of based on the classification of field clause
Man-machine natural language exchange method.
Background technology
Along with the development smart machine of science and technology is universal and the progressively maturation of speech recognition technology, due to natural language
Saying advantages such as having alternately conveniently, natural, quick, therefore in interactive process, natural language is mutual
Highlight is particularly important.In interactive process, due to the multiformity of user's natural language, Yi Jiling
The particularity of territory sight, usual one takes turns man-machine interaction can not meet the action demand of robot, need through
The man-machine interaction of many wheels could provide the necessary information carrying out corresponding actions for robot.
The dialogue management technology that existing natural language uses alternately mainly includes dialogue management based on statistics
Method and rule-based dialogue management method.
The method that dialogue management method based on statistics belongs to data-driven, can enter real dialogue language material
Rower is noted, the pattern talked with from language material learning according to statistical model, thus instructs man-machine conversation process
Method.Substantial amounts of human expert knowledge is need not when building dialog management system.The dialogue management of statistics
The shortcoming that method exists there is a need to substantial amounts of real corpus data and mark.But, the most right building
At the initial stage of session management, owing to many conditions limit, designer is generally difficult to collect enough
Language material be trained.
Rule-based dialogue management method is according to expertise, the method for the artificial flow process setting dialogue.
Owing to generally there is contextual relation in many wheel interactive process, therefore the statement of user's output may
There is part and omit composition, such as: eliminate subject, predicate only retained object etc..Therefore, merely
One statement of analysis time be difficult to parse the true intention of user, that talks with several times before needing contact is upper and lower
Literary composition carries out semantic parsing to current statement.Although, it is not necessary to collect substantial amounts of data, however it is necessary that and set
Meter person has certain understanding to flow process, the rule etc. of dialogue, adds design difficulty and the phase of designer
The workload answered.
Summary of the invention
The problems referred to above existed alternately for existing natural language, now provide one to aim at and can reduce
The workload of designer and the language exchange method of design difficulty.
Concrete technical scheme is as follows:
A kind of language exchange method, in the language interaction between user and robot, uses one
The semantic statement that cell stores is preset, described semantic statement includes the field representing particular area attribute
Clause and the general clause of the multiple domain attributes of expression；
The described voice interactive method of one event comprises the steps:
Step 1. obtains the natural language statement of user's output；
Step 2. carries out semantic parsing to described natural language statement, resolves knot with the corresponding semanteme of acquisition
Really；
Robot described in step 3. processes according to described semantic analysis result, with the corresponding response of output
Result；
Step 4. obtains the feedback statement of described user output；
Step 5. judges whether described feedback statement is END instruction, the most then perform step 7；If it is not,
Then perform step 6；
Step 6. carries out semantic parsing to described feedback statement, to obtain corresponding described semantic parsing knot
Really, the described step 3 of execution is returned；
Step 7. terminates.
Preferably, the detailed process of described step 2 is:
Described natural language statement is mated by step 21. with all of described field clause preset,
To obtain the first analysis result；
Step 22. judges whether described first semantic analysis result is empty；
If described first analysis result is not empty, then perform step 23；
If described first analysis result is empty, exporting described semantic results is sky, and performs described step 3；
Described first analysis result as described semantic analysis result, is performed described step 3 by step 23..
Preferably, when described first analysis result is not empty, described first analysis result include described from
So domain attribute of language statement art, and/or the user view corresponding with described domain attribute, and
/ or described natural language statement in key message.
Preferably, the detailed process of described step 6 is:
Described feedback statement is mated, to obtain by step 61. with all of described field clause preset
Negate feedback analysis result；
Step 62. judges whether described feedback analysis result is empty；
If described feedback analysis result is not empty, then perform step 63；
If described feedback analysis result is empty, then perform step 64；
Described feedback analysis result as described semantic analysis result, is performed described step 3 by step 63.；
The all of described semanteme before that step 64. will obtain during the interactive voice of event described in this part
Analysis result mates with all of described general clause respectively, it is thus achieved that corresponding described matching result,
All of described matching result is merged, merges statement to obtain；
Step 65. judges whether described fusion statement is empty；
If described fusion statement is not empty, then perform step 66；
If described feedback analysis result is empty, exporting described semantic analysis result is sky, and performs described step
Rapid 3；
Described fusion statement as described semantic analysis result, is performed described step 3 by step 66..
Preferably, when described feedback analysis result is not empty, described feedback analysis result include described instead
The domain attribute of feedback statement art, and/or the user view corresponding with described domain attribute, and/or
Key message in described feedback statement.
Preferably, when described fusion statement is not empty, described fusion statement includes described feedback statement institute
The domain attribute in genus field, and/or the user view corresponding with described domain attribute, and/or described feedback
Key message in statement.
Preferably, described field clause uses regular expression to represent.
Preferably, described general clause uses regular expression to represent.
The beneficial effect of technique scheme:
In the technical program, the natural language statement that user exports can be resolved by language exchange method,
To obtain corresponding analysis result, and the feedback statement again exported user resolves, to realize
Context during human computer conversation is comprehensively resolved by many wheel dialogues, thus obtains the solution of optimum
Analysis result, reduces workload and the design difficulty of designer.
Accompanying drawing explanation
Fig. 1 is the flow chart of the first embodiment of language exchange method of the present invention；
Fig. 2 is the flow chart of the second embodiment of language exchange method of the present invention；
Fig. 3 is the flow chart of the another kind of embodiment of language exchange method of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out
Clearly and completely describe, it is clear that described embodiment is only a part of embodiment of the present invention, and
It is not all, of embodiment.Based on the embodiment in the present invention, those of ordinary skill in the art are not making
The every other embodiment obtained on the premise of going out creative work, broadly falls into the scope of protection of the invention.
It should be noted that in the case of not conflicting, the embodiment in the present invention and the spy in embodiment
Levy and can be mutually combined.
The invention will be further described with specific embodiment below in conjunction with the accompanying drawings, but not as the present invention's
Limit.
As it is shown in figure 1, a kind of language exchange method, for the mutual mistake of the language between user and robot
Cheng Zhong, uses the semantic statement that a cell stores is preset, semantic statement to include representing that particular area belongs to
Property field clause and represent multiple domain attributes general clause；
The voice interactive method of one event comprises the steps:
Step 1. obtains the natural language statement of user's output；
Step 2. carries out semantic parsing to natural language statement, to obtain corresponding semantic analysis result；
Step 3. robot processes according to semantic analysis result, to export corresponding response results；
Step 4. obtains the feedback statement of user's output；
Step 5. judges to feed back whether statement is END instruction, the most then perform step 7；If it is not, then
Perform step 6；
Step 6. carries out semantic parsing to feedback statement, and to obtain corresponding semantic analysis result, return is held
Row step 3；
Step 7. terminates.
Wherein, field clause refers to the clause with clear and definite domain attribute, is i.e. transmitted by clause
Semanteme, the field at its place of determination that can be clear and definite；General clause refers to do not have unique domain attribute
Clause, the semanteme i.e. transmitted by clause, it is impossible to uniquely determine the field at its place, may be corresponding
Multiple fields.
Specifically, memory element can prestore field sentence when all of relevant user wants to order plane ticket
Formula, such as: " ordering the plane ticket from origin to destination ", wherein " origin " expression is set out
Ground, " $ destination " represents destination；As a example by " ordering plane ticket " field, statement " is ordered
Plane ticket from $ origin to $ destination ", wherein, " ordering plane ticket " belongs to field clause.But
It is in some cases, such as: when robot question, " you to order plane ticket where？", user
Answer may be only a place name, such as " Shanghai ", the clause of its correspondence is " $ destination ",
Only it is difficult to judge the field at its place for this clause, because other field, such as " orders train
Ticket " also likely to be present same clause, the most this clause is general clause.
In the present embodiment, feedback statement can include END instruction, END instruction in order to represent end this
The language of event is mutual, i.e. terminates this interactive task.
In the present embodiment, the natural language statement that user exports can be resolved by language exchange method,
To obtain corresponding analysis result, and the feedback statement again exported user resolves, to realize
Context during human computer conversation is comprehensively resolved by many wheel dialogues, thus obtains the solution of optimum
Analysis result, not only reduces workload and the design difficulty of designer, and analyzing efficiency is high.
As in figure 2 it is shown, in a preferred embodiment, the detailed process of step 2 is:
Natural language statement is mated by step 21. with all of field clause preset, to obtain the
One analysis result；
Step 22. judges whether first semantic analysis result is empty；
If the first analysis result is not empty, then perform step 23；
If the first analysis result is empty, output semantic results is empty, and performs step 3；
First analysis result as semantic analysis result, is performed step 3 by step 23..
In the present embodiment, by natural language statement is mated with all of field clause preset,
The field belonging to the clause of field that nature language statement is corresponding can be obtained, to facilitate robot according to semanteme solution
The field analysing result corresponding processes accordingly or searches, thus can quickly make corresponding response,
With user interaction, to improve the experience effect of user.
In a preferred embodiment, when the first analysis result is not empty, the first analysis result includes nature
The domain attribute of language statement art, and/or the user view corresponding with domain attribute, and/or from
So key message in language statement.
In the present embodiment, each domain attribute can corresponding multiple user views, when obtain natural language language
When sentence exists the domain attribute of art, the user view corresponding with this domain attribute can be obtained simultaneously,
Quickly to obtain purpose or the requirement of user.
As it is shown on figure 3, in a preferred embodiment, the detailed process of step 6 is:
Feedback statement is mated by step 61. with all of field clause preset, to obtain feedback solution
Analysis result；
Step 62. judges to feed back whether analysis result is empty；
If feedback analysis result is not empty, then perform step 63；
If feedback analysis result is empty, then perform step 64；
Step 63. will feed back analysis result as semantic analysis result, execution step 3；
Step 64. is all of semantic analysis result before obtaining during the interactive voice of this part event
Mate with all of general clause respectively, it is thus achieved that corresponding matching result, by all of matching result
Merge, merge statement to obtain；
Step 65. judges to merge whether statement is empty；
If it is not empty for merging statement, then perform step 66；
If feedback analysis result is empty, the semantic analysis result of output is empty, and performs step 3；
Step 66. will merge statement as semantic analysis result, execution step 3.
The corresponding data that robot can search for from data base according to semantic analysis result, or according to working as
Front state is to the information of user's query necessity.
In the present embodiment, the feedback statement by user being exported enters with all of field clause preset
Row coupling, can obtain the field belonging to the clause of field that nature language statement is corresponding, or man-machine according to many wheels
Matching result in dialog procedure, comprehensively resolves context, to be melted by all of matching result
Close, thus obtain the analysis result of optimum, to facilitate robot according to field corresponding to semantic analysis result
Processing accordingly or search, thus can quickly make corresponding response, and user interaction, to carry
The experience effect of high user, reduces workload and the design difficulty of designer simultaneously.
In a preferred embodiment, when feeding back analysis result and not being empty, feedback analysis result includes feedback
The domain attribute of statement art, and/or the user view corresponding with domain attribute, and/or backchannel
Key message in Ju.
In the present embodiment, each domain attribute can corresponding multiple user views, when obtain natural language language
When sentence exists the domain attribute of art, the user view corresponding with this domain attribute can be obtained simultaneously,
Quickly to obtain purpose or the requirement of user.
In a preferred embodiment, when merging statement and not being empty, merge statement and include feeding back belonging to statement
Pass in the domain attribute in field, and/or the user view corresponding with domain attribute, and/or feedback statement
Key information.
In the present embodiment, each domain attribute can corresponding multiple user views, when obtain natural language language
When sentence exists the domain attribute of art, the user view corresponding with this domain attribute can be obtained simultaneously,
Quickly to obtain purpose or the requirement of user.By the matching result during basis many wheels human computer conversations,
Context is comprehensively resolved, all of matching result can be merged, thus obtain the parsing of optimum
As a result, to facilitate robot process accordingly according to the field that semantic analysis result is corresponding or search,
So that robot quickly makes corresponding response.
In a preferred embodiment, field clause and general clause all can use regular expression to represent.
In the present embodiment, regular expression (Regular Expression), also known as normal representation method or
Conventional expressing method, regular expression is a concept of computer science, use single character string to describe,
Mate a series of character string meeting certain syntactic rule.Can be applicable in text editor, regular expressions
Formula is usually used to as the instrument retrieving, replacing the text meeting certain pattern.
The foregoing is only preferred embodiment of the present invention, not thereby limit embodiments of the present invention and
Protection domain, to those skilled in the art, it should can appreciate that all utilization description of the invention
And the equivalent done by diagramatic content and the scheme obtained by obvious change, all should comprise
Within the scope of the present invention.
Claims (8)
1. a language exchange method, in the language interaction between user and robot, it is special
Levy and be, use the semantic statement that a cell stores is preset, described semantic statement to include representing single
The field clause of domain attribute and the general clause of the multiple domain attributes of expression；
The described voice interactive method of one event comprises the steps:
Step 1. obtains the natural language statement of user's output；
Step 2. carries out semantic parsing to described natural language statement, resolves knot with the corresponding semanteme of acquisition
Really；
Robot described in step 3. processes according to described semantic analysis result, with the corresponding response of output
Result；
Step 4. obtains the feedback statement of described user output；
Step 5. judges whether described feedback statement is END instruction, the most then perform step 7；If it is not,
Then perform step 6；
Step 6. carries out semantic parsing to described feedback statement, to obtain corresponding described semantic parsing knot
Really, the described step 3 of execution is returned；
Step 7. terminates.
2. language exchange method as claimed in claim 1, it is characterised in that described step 2 concrete
Process is:
Described natural language statement is mated by step 21. with all of described field clause preset,
To obtain the first analysis result；
Step 22. judges whether described first semantic analysis result is empty；
If described first analysis result is not empty, then perform step 23；
If described first analysis result is empty, exporting described semantic results is sky, and performs described step 3；
Described first analysis result as described semantic analysis result, is performed described step 3 by step 23..
3. language exchange method as claimed in claim 2, it is characterised in that when described first resolves knot
When fruit is not empty, described first analysis result includes the domain attribute of described natural language statement art,
And/or the crucial letter in the user view corresponding with described domain attribute, and/or described natural language statement
Breath.
4. language exchange method as claimed in claim 1, it is characterised in that described step 6 concrete
Process is:
Described feedback statement is mated, to obtain by step 61. with all of described field clause preset
Negate feedback analysis result；
Step 62. judges whether described feedback analysis result is empty；
If described feedback analysis result is not empty, then perform step 63；
If described feedback analysis result is empty, then perform step 64；
Described feedback analysis result as described semantic analysis result, is performed described step 3 by step 63.；
The all of described semanteme before that step 64. will obtain during the interactive voice of event described in this part
Analysis result mates with all of described general clause respectively, it is thus achieved that corresponding described matching result,
All of described matching result is merged, merges statement to obtain；
Step 65. judges whether described fusion statement is empty；
If described fusion statement is not empty, then perform step 66；
If described feedback analysis result is empty, exporting described semantic analysis result is sky, and performs described step
Rapid 3；
Described fusion statement as described semantic analysis result, is performed described step 3 by step 66..
5. language exchange method as claimed in claim 4, it is characterised in that when described feedback resolves knot
When fruit be sky, described feedback analysis result includes the domain attribute of described feedback statement art, and/
Or the key message in the user view corresponding with described domain attribute, and/or described feedback statement.
6. language exchange method as claimed in claim 4, it is characterised in that when described fusion statement not
During for sky, described fusion statement includes the domain attribute of described feedback statement art, and/or with described
Key message in the user view that domain attribute is corresponding, and/or described feedback statement.
7. language exchange method as claimed in claim 1, it is characterised in that described field clause uses
Regular expression represents.
8. language exchange method as claimed in claim 1, it is characterised in that described general clause uses
Regular expression represents.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510387071.6A CN106326307A (en) | 2015-06-30 | 2015-06-30 | Language interaction method |
| PCT/CN2016/086490 WO2017000809A1 (en) | 2015-06-30 | 2016-06-20 | Linguistic interaction method |
| TW105120505A TWI588816B (en) | 2015-06-30 | 2016-06-29 | A language interaction method |
| HK17105103.4A HK1231595A1 (en) | 2015-06-30 | 2017-05-19 | A language interaction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510387071.6A CN106326307A (en) | 2015-06-30 | 2015-06-30 | Language interaction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106326307A true CN106326307A (en) | 2017-01-11 |
Family
ID=57607824
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510387071.6A Pending CN106326307A (en) | 2015-06-30 | 2015-06-30 | Language interaction method |
Country Status (4)
| Country | Link |
|---|---|
| CN (1) | CN106326307A (en) |
| HK (1) | HK1231595A1 (en) |
| TW (1) | TWI588816B (en) |
| WO (1) | WO2017000809A1 (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108044621A (en) * | 2017-09-20 | 2018-05-18 | 广东拓斯达科技股份有限公司 | A kind of robot of computer readable storage medium and the application medium |
| WO2019085697A1 (en) * | 2017-10-31 | 2019-05-09 | 科沃斯商用机器人有限公司 | Man-machine interaction method and system |
| CN109960806A (en) * | 2019-03-26 | 2019-07-02 | 北京博瑞彤芸文化传播股份有限公司 | A kind of natural language processing method |
| WO2019214463A1 (en) * | 2018-05-07 | 2019-11-14 | 阿里巴巴集团控股有限公司 | Man-machine dialog method, client, electronic device and storage medium |
| CN110489756A (en) * | 2019-08-23 | 2019-11-22 | 上海乂学教育科技有限公司 | Conversational human-computer interaction spoken language evaluation system |
| CN111414760A (en) * | 2018-12-18 | 2020-07-14 | 广东美的白色家电技术创新中心有限公司 | Natural language processing method and related device, system and storage device |
| WO2020220914A1 (en) * | 2019-04-30 | 2020-11-05 | 京东方科技集团股份有限公司 | Voice question and answer method and device, computer readable storage medium and electronic device |
| CN112017629A (en) * | 2020-07-15 | 2020-12-01 | 马上消费金融股份有限公司 | Conversation control method and equipment of voice robot and storage medium |
| CN113113005A (en) * | 2021-03-19 | 2021-07-13 | 大众问问(北京)信息科技有限公司 | Voice data processing method and device, computer equipment and storage medium |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115346523B (en) * | 2021-05-14 | 2024-10-22 | 联发科技（新加坡）私人有限公司 | Voice interaction method and device of voice equipment |
| CN117892828B (en) * | 2024-03-18 | 2024-05-31 | 青岛市勘察测绘研究院 | Natural language interaction method, device, equipment and medium for geographic information system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101753471A (en) * | 2008-12-04 | 2010-06-23 | 中国移动通信集团海南有限公司 | Instant massage (IM) interactive text response method and response system |
| CN101923857A (en) * | 2009-06-17 | 2010-12-22 | 复旦大学 | Extensible audio recognition method based on man-machine interaction |
| CN103078995A (en) * | 2012-12-18 | 2013-05-01 | 苏州思必驰信息科技有限公司 | Customizable individualized response method and system used in mobile terminal |
| CN103744836A (en) * | 2014-01-08 | 2014-04-23 | 苏州思必驰信息科技有限公司 | Man-machine conversation method and device |
| CN104408639A (en) * | 2014-10-22 | 2015-03-11 | 百度在线网络技术（北京）有限公司 | Multi-round conversation interaction method and system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI314271B (en) * | 2005-01-27 | 2009-09-01 | Delta Electronics Inc | Vocabulary generating apparatus and method thereof and speech recognition system with the vocabulary generating apparatus |
| TW201013635A (en) * | 2008-09-24 | 2010-04-01 | Mitac Int Corp | Intelligent voice system and method thereof |
| CN101923539B (en) * | 2009-06-11 | 2014-02-12 | 珠海市智汽电子科技有限公司 | Man-machine conversation system based on natural language |
| CN103198831A (en) * | 2013-04-10 | 2013-07-10 | 威盛电子股份有限公司 | Voice control method and mobile terminal device |
| CN103760984A (en) * | 2014-01-24 | 2014-04-30 | 成都万先自动化科技有限责任公司 | Man-machine conversation system |
| CN104008160A (en) * | 2014-05-29 | 2014-08-27 | 吴春尧 | Method and system of indistinct logic chatting robot for realizing parallel topic control |
| CN104199810A (en) * | 2014-08-29 | 2014-12-10 | 科大讯飞股份有限公司 | Intelligent service method and system based on natural language interaction |
-
2015
- 2015-06-30 CN CN201510387071.6A patent/CN106326307A/en active Pending
-
2016
- 2016-06-20 WO PCT/CN2016/086490 patent/WO2017000809A1/en active Application Filing
- 2016-06-29 TW TW105120505A patent/TWI588816B/en not_active IP Right Cessation
-
2017
- 2017-05-19 HK HK17105103.4A patent/HK1231595A1/en unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101753471A (en) * | 2008-12-04 | 2010-06-23 | 中国移动通信集团海南有限公司 | Instant massage (IM) interactive text response method and response system |
| CN101923857A (en) * | 2009-06-17 | 2010-12-22 | 复旦大学 | Extensible audio recognition method based on man-machine interaction |
| CN103078995A (en) * | 2012-12-18 | 2013-05-01 | 苏州思必驰信息科技有限公司 | Customizable individualized response method and system used in mobile terminal |
| CN103744836A (en) * | 2014-01-08 | 2014-04-23 | 苏州思必驰信息科技有限公司 | Man-machine conversation method and device |
| CN104408639A (en) * | 2014-10-22 | 2015-03-11 | 百度在线网络技术（北京）有限公司 | Multi-round conversation interaction method and system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108044621A (en) * | 2017-09-20 | 2018-05-18 | 广东拓斯达科技股份有限公司 | A kind of robot of computer readable storage medium and the application medium |
| WO2019085697A1 (en) * | 2017-10-31 | 2019-05-09 | 科沃斯商用机器人有限公司 | Man-machine interaction method and system |
| WO2019214463A1 (en) * | 2018-05-07 | 2019-11-14 | 阿里巴巴集团控股有限公司 | Man-machine dialog method, client, electronic device and storage medium |
| US11366574B2 (en) | 2018-05-07 | 2022-06-21 | Alibaba Group Holding Limited | Human-machine conversation method, client, electronic device, and storage medium |
| CN111414760A (en) * | 2018-12-18 | 2020-07-14 | 广东美的白色家电技术创新中心有限公司 | Natural language processing method and related device, system and storage device |
| CN109960806A (en) * | 2019-03-26 | 2019-07-02 | 北京博瑞彤芸文化传播股份有限公司 | A kind of natural language processing method |
| WO2020220914A1 (en) * | 2019-04-30 | 2020-11-05 | 京东方科技集团股份有限公司 | Voice question and answer method and device, computer readable storage medium and electronic device |
| US11749255B2 (en) | 2019-04-30 | 2023-09-05 | Boe Technology Group Co., Ltd. | Voice question and answer method and device, computer readable storage medium and electronic device |
| CN110489756A (en) * | 2019-08-23 | 2019-11-22 | 上海乂学教育科技有限公司 | Conversational human-computer interaction spoken language evaluation system |
| CN112017629A (en) * | 2020-07-15 | 2020-12-01 | 马上消费金融股份有限公司 | Conversation control method and equipment of voice robot and storage medium |
| CN113113005A (en) * | 2021-03-19 | 2021-07-13 | 大众问问(北京)信息科技有限公司 | Voice data processing method and device, computer equipment and storage medium |
| CN113113005B (en) * | 2021-03-19 | 2024-06-18 | 大众问问(北京)信息科技有限公司 | Voice data processing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017000809A1 (en) | 2017-01-05 |
| HK1231595A1 (en) | 2017-12-22 |
| TW201701270A (en) | 2017-01-01 |
| TWI588816B (en) | 2017-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106326307A (en) | Language interaction method | |
| US20220004714A1 (en) | Event extraction method and apparatus, and storage medium | |
| JP6309644B2 (en) | Method, system, and storage medium for realizing smart question answer | |
| CN104050160B (en) | Interpreter's method and apparatus that a kind of machine is blended with human translation | |
| CN110096570A (en) | A kind of intension recognizing method and device applied to intelligent customer service robot | |
| CN107562863A (en) | Chat robots reply automatic generation method and system | |
| CN107704453A (en) | A kind of word semantic analysis, word semantic analysis terminal and storage medium | |
| CN106357942A (en) | Intelligent response method and system based on context dialogue semantic recognition | |
| WO2020233386A1 (en) | Intelligent question-answering method and device employing aiml, computer apparatus, and storage medium | |
| CN110287482B (en) | Semi-automatic participle corpus labeling training device | |
| CN109960756A (en) | Media event information inductive method | |
| CN112115252B (en) | Intelligent auxiliary writing processing method and device, electronic equipment and storage medium | |
| CN108228701A (en) | A kind of system for realizing Chinese near-nature forest language inquiry interface | |
| Zhang et al. | Effective subword segmentation for text comprehension | |
| CN105117388A (en) | Intelligent robot interaction system | |
| CN110795544B (en) | Content searching method, device, equipment and storage medium | |
| Miao et al. | A dynamic financial knowledge graph based on reinforcement learning and transfer learning | |
| CN110929007A (en) | Electric power marketing knowledge system platform and application method | |
| Barbieri et al. | Towards a natural language conversational interface for process mining | |
| CN105302859B (en) | A kind of intelligent interactive system Internet-based | |
| CN114238595A (en) | Metallurgical knowledge question-answering method and system based on knowledge graph | |
| CN106021413A (en) | Theme model based self-extendable type feature selecting method and system | |
| CN113761919A (en) | Entity attribute extraction method of spoken short text and electronic device | |
| Ma et al. | Scenario-based microservice retrieval using Word2Vec | |
| CN109828775A (en) | A kind of WEB management system and method for multilingual translation content of text |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1231595 Country of ref document: HK |
|
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170111 |
|
| RJ01 | Rejection of invention patent application after publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: WD Ref document number: 1231595 Country of ref document: HK |