CN109613917A - A kind of question and answer robot and its implementation - Google Patents
A kind of question and answer robot and its implementation Download PDFInfo
- Publication number
- CN109613917A CN109613917A CN201811303496.4A CN201811303496A CN109613917A CN 109613917 A CN109613917 A CN 109613917A CN 201811303496 A CN201811303496 A CN 201811303496A CN 109613917 A CN109613917 A CN 109613917A
- Authority
- CN
- China
- Prior art keywords
- question
- answer
- map
- robot
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- 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
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
A kind of question and answer robot of the present invention and its implementation, the robot includes: local question and answer library construction unit, for constructing local question and answer library；Map constructing unit, if constructing map using map structuring technology without map, if existing map, loads existing map it is first determined whether there is map；Semantic analysis unit obtains voice signal, the voice signal of acquisition is converted to text information, and carry out semantic analysis to the text information after conversion, matches local question and answer library according to semantic analysis result；Autonomous guide to visitors unit, the destination information of guide to visitors is extracted according to matching result, the position coordinates of destination are obtained according to destination information, and the position and destination being currently located according to robot, planning path, drive robot to designated position, present invention introduces simultaneous localization and mapping technologies to realize the automatic guide to visitors of robot, and improves the flexibility and accuracy of human-computer interaction dialogue by semantic analysis matching.
Description
Technical field
The present invention relates to speech guide technical field, more particularly to a kind of question and answer robot for being able to achieve speech guide and
Its implementation.
Background technique
With the development of robot technology, robot is applied to every field, and existing robot is divided into two classes, i.e. work
Industry robot and specialized robot.So-called industrial robot is exactly multi-joint manipulator or multiple degrees of freedom machine towards industrial circle
Device people.And specialized robot be then it is in addition to industrial robot, for nonmanufacturing industry and serve the various advanced machines of the mankind
Device people, comprising:, underwater robot, amusement robot, military robot, agricultural robot, robotization machine etc..And it services
Robot is frequently utilized in the occasions welcomes such as bank, market, restaurant, the portion that sells house, hotel reception, guide service and advertising
Equal service trades, this kind of service robot can set the operating modes such as welcome, inquiry, food delivery, checkout, amusement, server
Device people has the characteristics that intelligence substitutes manpower, in addition, having the function of interacting with people, compared to the waiter in life, server
Device people can preferably try to please and customer is attracted perhaps client etc. and to bring completely new service body to customer or client
It tests, while service robot can save the cost of labor of businessman；Can satisfy can also ensure that while working long hours it is excellent
Matter service avoids manual service due to working long hours and generates the tired feelings for causing the satisfaction of customer or client to decline
Condition greatly improves work efficiency.
One important application of service robot be the needs such as museum, exhibition park, training organization in real time and user
Interaction especially provides it the scene of guide to visitors content.Existing service robot with user when interacting, the question and answer of heap user
It handles fairly simple, does not use semantic analysis in matching problem, and only use simple character string comparison or canonical table
Compare up to formula, the matched accuracy of problem and flexibility are poor；Question and answer library generally uses the single mode of remote library or local library；
And the customization in inconvenient special scenes question and answer library.
Summary of the invention
In order to overcome the deficiencies of the above existing technologies, one of present invention be designed to provide a kind of question and answer robot and its
Implementation method introduces simultaneous localization and mapping technology (SLAM) and realizes the automatic guide to visitors of robot, and passes through semantic analysis
With the flexibility and accuracy for improving human-computer interaction dialogue.
Another object of the present invention is to provide a kind of question and answer robot and its implementation, by using local library and remote
The mode that Cheng Ku is combined, convenient for customizing question and answer library for particular demands.
In view of the above and other objects, the present invention proposes a kind of question and answer robot, comprising:
Local question and answer library construction unit, for constructing local question and answer library；
Map constructing unit judges whether there is map, if constructing map using map structuring technology without map, if
Existing map then loads existing map；
The voice signal of acquisition is converted to text information, and to conversion for obtaining voice signal by semantic analysis unit
Text information afterwards carries out semantic analysis, matches local question and answer library according to semantic analysis result；
Autonomous guide to visitors unit, the destination information of guide to visitors is extracted according to matching result, obtains mesh according to destination information
Ground position coordinates, and the position and destination being currently located according to robot, planning path, driving robot to specific bit
It sets.
Preferably, the map constructing unit further comprises:
Positioning unit obtains the location information of question and answer robot for positioning in real time to the question and answer robot；
Figure unit is built, map is first judged whether there is, if being constructed without map by simultaneous localization and mapping technology
Otherwise map loads existing map.
Preferably, the judging result processing unit uses laser scanner as detector, Yu Suoshu question and answer robot
In motion process, the data of the laser scanner are constantly obtained, the location information in conjunction with where robot, building two-dimensional grid
Figure.
Preferably, the semantic analysis unit further comprises:
Morphology syntactic analysis unit forms semantic tree for carrying out morphology and syntactic analysis to the text information after conversion；
Semantics extraction unit, for extracting the basic semantic of the text information by semantic tree, and by the modification of problem
Attribute with characterizing portion as basic semantic.
Semantic matches unit, basic semantic and local question and answer library progress for extracting the semantics extraction unit
Match, obtains matching result.
Preferably, the morphology syntactic analysis unit segments the sentence of the text information to obtain multiple points first
Word；Then entity word is identified from multiple participle；Part-of-speech tagging is carried out to multiple participle, and according to the part of speech pair of mark
The entity word and multiple participles carry out dependency analysis and obtain semantic structure, form semantic tree.
Preferably, when semantic matches, the semantic matches unit calculates every in basic semantic and the local question and answer library
The attributive distance of a problem, as the measurement of semantic matches；According to the metric calculation confidence level of semantic matches；If confidence level
Greater than a preset threshold, then the successful match in local question and answer library, obtains matching result.
Preferably, the question and answer robot further include: long-range question and answer library construction unit, for constructing long-range question and answer library, and
It is deposited on remote server, when the semantic matches unit is not matched to suitable result in local question and answer library,
It turns to and searches for long-range question and answer library acquisition matching result.
Preferably, the autonomous guide to visitors unit carries out guide to visitors explanation also according to pre-set explanation text.
In order to achieve the above objectives, the present invention also provides a kind of implementation method of question and answer robot, include the following steps:
Step S1 constructs local question and answer library；
Step S2, according to question and answer robot, current location information judges whether there is map, if utilizing ground without map
Figure constructing technology constructs map, if existing map, loads existing map；
Step S3 obtains voice signal, the voice signal of acquisition is converted to text information, and believe the text after conversion
Breath carries out semantic analysis, matches local question and answer library according to semantic analysis result；
Step S4 extracts the destination information of guide to visitors according to matching result, obtains destination according to destination information
Position coordinates, and the position and destination being currently located according to robot, planning path, driving robot to designated position.
Preferably, the method also includes following steps:
Long-range question and answer library is constructed, and is deposited on remote server；
When being not matched to suitable result in local question and answer library, it is described remote that search is turned to according to the basic semantic of acquisition
Journey question and answer library.
Compared with prior art, a kind of question and answer robot of the present invention and its implementation pass through introducing while positioning and map
Constructing technology (SLAM) realizes the automatic guide to visitors of robot, and improves the flexible of human-computer interaction dialogue by semantic analysis matching
Property and accuracy, while by the present invention in that the mode combined with local question and answer library and long-range question and answer library, convenient for being particular needs
Ask customization question and answer library.
Detailed description of the invention
Fig. 1 is a kind of structural schematic diagram of question and answer robot of the present invention；
Fig. 2 is the schematic diagram of semantic tree in the specific embodiment of the invention；
Fig. 3 is a kind of step flow chart of the implementation method of question and answer robot of the present invention.
Specific embodiment
Below by way of specific specific example and embodiments of the present invention are described with reference to the drawings, those skilled in the art can
Understand further advantage and effect of the invention easily by content disclosed in the present specification.The present invention can also pass through other differences
Specific example implemented or applied, details in this specification can also be based on different perspectives and applications, without departing substantially from
Various modifications and change are carried out under spirit of the invention.
Fig. 1 is a kind of structural schematic diagram of question and answer robot of the present invention.As shown in Figure 1, a kind of question and answer robot of the present invention,
Include:
Local question and answer library construction unit 10, for constructing local question and answer library.In the specific embodiment of the invention, the local
Several Question Logs preset according to user demand are stored in question and answer library, such as " where are you going? ", " I will go to day
River gymnasium " etc., the local question and answer library are stored in the memory module of question and answer robot, are carried out with facilitating according to user demand
Modification and customization, are stored in the form of text file.
Map constructing unit 11, for judging whether there is map according to location information, if utilizing map structure without map
Technology (SLAM) building map is built, if existing map, loads map.That is, in order to realize automatic guide to visitors function, first
It must must construct map.Specifically, map constructing unit 10 further comprises:
Positioning unit obtains the location information of question and answer robot for positioning in real time to question and answer robot；
Figure unit is built, for judging whether that having stored the location information corresponds to area according to the location information of question and answer robot
The map in domain, that is to say, that came herein when user carries the question and answer robot, then may have been stored in question and answer robot
The map in the region；If judging result is to carry out map using map structuring technology without the corresponding map of the location information
Building is loaded directly into the map if otherwise judging result is the corresponding map of the existing location information.Specifically, described
Map constructing unit 11 uses laser scanner as detector, and in Yu Suoshu question and answer robot kinematics, constantly obtaining should
The data of laser scanner, the location information in conjunction with where robot construct two-dimensional grid map.
The voice signal of acquisition is converted to text information for obtaining voice signal by semantic analysis unit 12, and to turning
Text information after changing carries out semantic analysis, matches local question and answer library according to semantic analysis result, obtains matching result.In this hair
In bright specific embodiment, the every voice messaging for obtaining a word of semantic analysis unit 12, then by the corresponding voice messaging of the word
Text information is converted to, i.e., the text information is then in short.
In the specific embodiment of the invention, semantic analysis unit 12 can pass through voice input-output device, such as Mike
Wind obtains voice signal, and converts voice signals into text information, since the present invention is converted to letter signal to voice signal
Using the prior art, it will not be described here.
Specifically, semantic analysis unit 12 further comprises including:
Morphology syntactic analysis unit 120 is formed semantic for carrying out morphology and syntactic analysis to the text information after conversion
Tree.Specifically, morphology syntactic analysis unit 120 segments the sentence of the text information to obtain multiple participles first；Then
Entity word is identified from multiple participle；Part-of-speech tagging is carried out to multiple participle, and according to the part of speech of mark to the entity
Word and multiple participles carry out dependency analysis and obtain semantic structure, form semantic tree.For example, as shown in Fig. 2, it illustrates sentences
" I will go to Milky Way gymnasium " carries out its semantic tree obtained after morphology syntactic analysis, and wherein verb " going " is in semantic tree
The heart, as root node.
Semantics extraction unit 121 for information required for being extracted by semantic tree, such as in guide to visitors, extracts in semanteme
Place, place " Milky Way gymnasium " is such as extracted from " I will go to Milky Way gymnasium ".
Semantic matches unit 122, basic semantic and local question and answer library progress for extracting semantics extraction unit 121
Match, obtains matching result.
In the specific embodiment of the invention, when semantic matches, semantic matches unit 122 calculates basic semantic and asks with local
The attributive distance for answering each problem in library, as the measurement of semantic matches；It is locally asked according to the metric calculation of semantic matches
Answer the confidence level of each problem in library, that is, calculate the similarity of the problems in basic semantic and local question and answer library；If confidence level is big
In a preset threshold (such as 0.8), then the successful match in local question and answer library, obtains matching result.If successful match illustrates this
Sentence text be one order, then extract the destination of guide to visitors from order, start autonomous guide to visitors, here it should be noted that, if
Confidence level is greater than the problem of preset threshold more than one, then selection with basic semantic similarity highest one, it is not superfluous herein
It states.
Autonomous guide to visitors unit 13, the destination information of guide to visitors is extracted according to matching result, is obtained according to destination information
The position coordinates of destination, and the position and destination being currently located according to robot, planning path, driving robot to specify
Position.Preferably, autonomous guide to visitors unit 13 can also carry out guide to visitors explanation according to pre-set explanation text.
Preferably, the question and answer robot of the present invention further include:
Long-range question and answer library construction unit, for constructing long-range question and answer library, and is deposited on remote server.In local
Confidence level of all the problems is all when being not matched to suitable result in question and answer library, such as in the basic semantic and local question and answer library
Less than preset threshold, then the long-range question and answer library of search is turned to, the searching method of remote library is identical with local question and answer library, i.e., by basic language
The adopted attributive distance with each problem in long-range question and answer library, as the measurement of semantic matches, according to the measurement of semantic matches
Confidence level is calculated, if confidence level is greater than a preset threshold (such as 0.8), the successful match in length of run question and answer library is matched
As a result.If confidence level of all the problems is both less than preset threshold in long-range question and answer library, then it represents that it is not matched to suitable problem,
One can be then chosen from the answer of preset multiple defaults, such as returning for multiple defaults is set in long-range question and answer library
It answers, such as " I is also ignorant of the problem of you ask, I will continue to effort ", " my this problem will not, you can ask other problems ",
" I am tired, I wants to rest ", can therefrom randomly select an output.
Fig. 3 is a kind of step flow chart of the implementation method of question and answer robot of the present invention.As shown in figure 3, the present invention is a kind of
The implementation method of question and answer robot, comprising:
Step S1 constructs local question and answer library.In the specific embodiment of the invention, it is stored in the local question and answer library several
The Question Log that item is preset according to user demand, such as " where are you going? ", " I will go to Milky Way gymnasium " etc., described
Ground question and answer library is stored in the memory module of question and answer robot, is modified and is customized according to user demand to facilitate, used
The form of text file is stored.
Step S2, according to question and answer robot, current location information judges whether there is map, if utilizing ground without map
Figure constructing technology (SLAM) constructs map, if existing map, loads map.That is, in order to realize automatic guide to visitors function,
Map must must be constructed first.Specifically step S2 further comprises:
Step S200 in real time positions question and answer robot, obtains the location information of question and answer robot；
Step S201 judges whether to have stored the location information corresponding region according to the location information of question and answer robot
Map；That is, coming herein when user carries the question and answer robot, then the area may be stored in question and answer robot
The map in domain；
Step S202, if judging result is to be carried out without the corresponding map of the location information using map structuring technology
Map structuring is loaded directly into the map if otherwise judging result is the corresponding map of the existing location information.Specifically,
In step S202, use laser scanner as detector, in Yu Suoshu question and answer robot kinematics, constantly obtains this and swash
The data of photoscanner construct two-dimensional grid map in conjunction with the location information where question and answer robot.
Step S3 obtains voice signal, the voice signal of acquisition is converted to text information, and believe the text after conversion
Breath carries out semantic analysis, matches local question and answer library according to semantic analysis result, obtains matching result.In the specific embodiment of the invention
In, the acquisition that voice signal is one one, every voice messaging for obtaining a word then converts the corresponding voice messaging of the word
For text information, i.e. the text information is then in short.
In the specific embodiment of the invention, voice signal can be obtained by voice input-output device, such as microphone
Voice signal is obtained, and converts voice signals into text information, is adopted since the present invention is converted to letter signal to voice signal
It is the prior art, it will not be described here.
Specifically, step S3 further comprises including:
Step S300 carries out morphology and syntactic analysis to the text information after conversion, forms semantic tree.Specifically, Yu Bu
In rapid S300, the sentence of the text information is segmented to obtain multiple participles first；Then it is identified from multiple participle
Entity word；Part-of-speech tagging is carried out to multiple participle, and interdependent to the entity word and the progress of multiple participles according to the part of speech of mark
Analysis obtains semantic structure, forms semantic tree.
Step S301, information required for being extracted by semantic tree, such as in guide to visitors, extract the place in semanteme, such as from
Place " Milky Way gymnasium " is extracted in " I will go to Milky Way gymnasium ".
Step S302, for the basic semantic extracted by step S301 to be matched with local question and answer library, acquisition
With result.
It is each in calculating basic semantic and local question and answer library first when semantic matches in the specific embodiment of the invention
The attributive distance of problem, as the measurement of semantic matches；According to each in the metric calculation local question and answer library of semantic matches
The confidence level of problem, that is, calculate the similarity of the problems in basic semantic and local question and answer library；If confidence level is greater than a default threshold
It is worth (such as 0.8), then the successful match in local question and answer library, obtains matching result if successful match and illustrate that this text is one
A order then extracts the destination of guide to visitors from order, starts autonomous guide to visitors, here it should be noted that, if confidence level is greater than
The problem of preset threshold more than one, then selection with basic semantic similarity highest one, it will not be described here.
Step S4 extracts the destination information of guide to visitors according to matching result, obtains destination according to destination information
Position coordinates, and the position and destination being currently located according to robot, planning path, driving robot to designated position.Compared with
Goodly, in step S4, also guide to visitors explanation can be carried out according to pre-set explanation text.
Preferably, the question and answer robot of the present invention further include:
Long-range question and answer library is constructed, and is deposited on remote server；
Own when being not matched to suitable result in local question and answer library, such as in the basic semantic and local question and answer library
The confidence level of problem is both less than preset threshold, then turns to the long-range question and answer library of search, the searching method of remote library and local question and answer library
It is identical, i.e., by the attributive distance of each problem in basic semantic and long-range question and answer library, as the measurement of semantic matches, according to
The metric calculation confidence level of semantic matches matches in length of run question and answer library if confidence level is greater than a preset threshold (such as 0.8)
Success obtains matching result.If confidence level of all the problems is both less than preset threshold in long-range question and answer library, then it represents that do not match
To suitable problem, then one can be chosen from the answer of preset multiple defaults, such as set in long-range question and answer library
The answer of multiple defaults, such as " I is also ignorant of the problem of you ask, I will continue to effort ", " my this problem will not, you can ask
Other problems ", " I am tired, I wants to rest ", can therefrom randomly select an output.
In conclusion a kind of question and answer robot of the present invention and its implementation are by introducing simultaneous localization and mapping skill
Art (SLAM) realizes the automatic guide to visitors of robot, and the flexibility and standard of human-computer interaction dialogue are improved by semantic analysis matching
True property, while by the present invention in that the mode combined with local question and answer library and long-range question and answer library, is convenient for customizing for particular demands
Question and answer library.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.Any
Without departing from the spirit and scope of the present invention, modifications and changes are made to the above embodiments by field technical staff.Therefore,
The scope of the present invention, should be as listed in the claims.
Claims (10)
1. a kind of question and answer robot, comprising:
Local question and answer library construction unit, for constructing local question and answer library；
Map constructing unit judges whether there is map, if map is constructed using map structuring technology without map, if existing
Map then loads existing map；
The voice signal of acquisition is converted to text information for obtaining voice signal by semantic analysis unit, and to conversion after
Text information carries out semantic analysis, matches local question and answer library according to semantic analysis result；
Autonomous guide to visitors unit, the destination information of guide to visitors is extracted according to matching result, obtains destination according to destination information
Position coordinates, and the position and destination being currently located according to robot, planning path, driving robot to designated position.
2. a kind of question and answer robot as described in claim 1, which is characterized in that the map constructing unit further comprises:
Positioning unit obtains the location information of question and answer robot for positioning in real time to the question and answer robot；
Figure unit is built, map is first judged whether there is, if using simultaneous localization and mapping technology building ground without map
Otherwise figure loads existing map.
3. a kind of question and answer robot as claimed in claim 2, it is characterised in that: the map constructing unit uses laser scanning
Instrument in Yu Suoshu question and answer robot kinematics, constantly obtains the data of the laser scanner, in conjunction with robot as detector
The location information at place constructs two-dimensional grid map.
4. a kind of question and answer robot as described in claim 1, which is characterized in that the semantic analysis unit further comprises:
Morphology syntactic analysis unit forms semantic tree for carrying out morphology and syntactic analysis to the text information after conversion；
Semantics extraction unit, for extracting the basic semantic of the text information by semantic tree, and by the modification and limit of problem
Attribute of the fixed part as basic semantic.
Semantic matches unit, the basic semantic for extracting the semantics extraction unit are matched with local question and answer library, are obtained
Obtain matching result.
5. a kind of question and answer robot as claimed in claim 4, it is characterised in that: the morphology syntactic analysis unit is first to this
The sentence of text information is segmented to obtain multiple participles；Then entity word is identified from multiple participle；To multiple point
Word carries out part-of-speech tagging, and carries out dependency analysis to the entity word and multiple participles according to the part of speech of mark and obtain semantic structure,
Form semantic tree.
6. a kind of question and answer robot as claimed in claim 4, it is characterised in that: when semantic matches, the semantic matches list
Member calculates the attributive distance of each problem in basic semantic and the local question and answer library, as the measurement of semantic matches；Root
According to the metric calculation confidence level of semantic matches；If confidence level is greater than a preset threshold, the successful match in local question and answer library is obtained
Obtain matching result.
7. a kind of question and answer robot as claimed in claim 6, it is characterised in that: the question and answer robot further include: remotely ask
Library construction unit is answered, for constructing long-range question and answer library, and is deposited on remote server, the semantic matches unit is in this
When being not matched to suitable result in ground question and answer library, turns to and search for long-range question and answer library acquisition matching result.
8. a kind of question and answer robot as described in claim 1, it is characterised in that: the autonomous guide to visitors unit also according to setting in advance
The explanation text set carries out guide to visitors explanation.
9. a kind of implementation method of question and answer robot, includes the following steps:
Step S1 constructs local question and answer library；
Step S2, according to question and answer robot, current location information judges whether there is map, if utilizing map structure without map
Technology building map is built, if existing map, loads existing map；
Step S3 obtains voice signal, and the voice signal of acquisition is converted to text information, and to the text information after conversion into
Row semantic analysis matches local question and answer library according to semantic analysis result；
Step S4 extracts the destination information of guide to visitors according to matching result, and the position of destination is obtained according to destination information
Coordinate, and the position and destination being currently located according to robot, planning path, driving robot to designated position.
10. a kind of implementation method of question and answer robot as claimed in claim 9, which is characterized in that the method also includes such as
Lower step:
Long-range question and answer library is constructed, and is deposited on remote server；
When being not matched to suitable result in local question and answer library, remotely asked according to the steering search of the basic semantic of acquisition is described
Answer library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811303496.4A CN109613917A (en) | 2018-11-02 | 2018-11-02 | A kind of question and answer robot and its implementation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811303496.4A CN109613917A (en) | 2018-11-02 | 2018-11-02 | A kind of question and answer robot and its implementation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109613917A true CN109613917A (en) | 2019-04-12 |
Family
ID=66002022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811303496.4A Pending CN109613917A (en) | 2018-11-02 | 2018-11-02 | A kind of question and answer robot and its implementation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109613917A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111958585A (en) * | 2020-06-24 | 2020-11-20 | 宁波薄言信息技术有限公司 | Intelligent disinfection robot |
| CN112286185A (en) * | 2020-10-14 | 2021-01-29 | 深圳市杉川机器人有限公司 | Floor sweeping robot, three-dimensional map building method and system thereof, and computer readable storage medium |
| CN112652073A (en) * | 2020-12-31 | 2021-04-13 | 中国电子科技集团公司信息科学研究院 | Autonomous navigation method and system based on cloud network end robot |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699126A (en) * | 2013-12-23 | 2014-04-02 | 中国矿业大学 | Intelligent tour guide robot |
| CN105082137A (en) * | 2014-05-09 | 2015-11-25 | 宁波市镇海拓迪工业产品设计有限公司 | Novel robot |
| CN105278532A (en) * | 2015-11-04 | 2016-01-27 | 中国科学技术大学 | Personalized autonomous explanation method of guidance by robot tour guide |
| CN105701253A (en) * | 2016-03-04 | 2016-06-22 | 南京大学 | Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method |
| CN106078764A (en) * | 2016-08-12 | 2016-11-09 | 李乾 | A kind of old man accompanies and attends to robot and control method thereof |
| CN107065863A (en) * | 2017-03-13 | 2017-08-18 | 山东大学 | A kind of guide to visitors based on face recognition technology explains robot and method |
| CN107655480A (en) * | 2017-09-19 | 2018-02-02 | 深圳市深层互联科技有限公司 | A kind of robot localization air navigation aid, system, storage medium and robot |
| US20180237137A1 (en) * | 2017-02-22 | 2018-08-23 | Wal-Mart Stores, Inc. | Voice Activated Unmanned Aerial Vehicle (UAV) Assistance System |
-
2018
- 2018-11-02 CN CN201811303496.4A patent/CN109613917A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699126A (en) * | 2013-12-23 | 2014-04-02 | 中国矿业大学 | Intelligent tour guide robot |
| CN105082137A (en) * | 2014-05-09 | 2015-11-25 | 宁波市镇海拓迪工业产品设计有限公司 | Novel robot |
| CN105278532A (en) * | 2015-11-04 | 2016-01-27 | 中国科学技术大学 | Personalized autonomous explanation method of guidance by robot tour guide |
| CN105701253A (en) * | 2016-03-04 | 2016-06-22 | 南京大学 | Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method |
| CN106078764A (en) * | 2016-08-12 | 2016-11-09 | 李乾 | A kind of old man accompanies and attends to robot and control method thereof |
| US20180237137A1 (en) * | 2017-02-22 | 2018-08-23 | Wal-Mart Stores, Inc. | Voice Activated Unmanned Aerial Vehicle (UAV) Assistance System |
| CN107065863A (en) * | 2017-03-13 | 2017-08-18 | 山东大学 | A kind of guide to visitors based on face recognition technology explains robot and method |
| CN107655480A (en) * | 2017-09-19 | 2018-02-02 | 深圳市深层互联科技有限公司 | A kind of robot localization air navigation aid, system, storage medium and robot |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111958585A (en) * | 2020-06-24 | 2020-11-20 | 宁波薄言信息技术有限公司 | Intelligent disinfection robot |
| CN112286185A (en) * | 2020-10-14 | 2021-01-29 | 深圳市杉川机器人有限公司 | Floor sweeping robot, three-dimensional map building method and system thereof, and computer readable storage medium |
| CN112652073A (en) * | 2020-12-31 | 2021-04-13 | 中国电子科技集团公司信息科学研究院 | Autonomous navigation method and system based on cloud network end robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021232725A1 (en) | Voice interaction-based information verification method and apparatus, and device and computer storage medium | |
| US11538459B2 (en) | Voice recognition grammar selection based on context | |
| US9223776B2 (en) | Multimodal natural language query system for processing and analyzing voice and proximity-based queries | |
| US7873654B2 (en) | Multimodal natural language query system for processing and analyzing voice and proximity-based queries | |
| US7376645B2 (en) | Multimodal natural language query system and architecture for processing voice and proximity-based queries | |
| Johnston et al. | MATCH: An architecture for multimodal dialogue systems | |
| CN110096567B (en) | QA knowledge base reasoning-based multi-round dialogue reply selection method and system | |
| CN109613917A (en) | A kind of question and answer robot and its implementation | |
| Götze et al. | Learning landmark salience models from users’ route instructions | |
| CN108491421A (en) | A kind of method, apparatus, equipment and computer storage media generating question and answer | |
| CN110377676A (en) | A kind of processing method of phonetic order, device, equipment and computer storage medium | |
| JP2011065582A (en) | Device and method for gradually developing natural language user interface | |
| CN116541504B (en) | Dialog generation method, device, medium and computing equipment | |
| CN110955818A (en) | Searching method, searching device, terminal equipment and storage medium | |
| WO2023018908A1 (en) | Conversational artificial intelligence system in a virtual reality space | |
| Ma et al. | Landmark-based location belief tracking in a spoken dialog system | |
| CN106653015A (en) | Speech recognition method by and apparatus for robot | |
| Edlund et al. | Higgins-a spoken dialogue system for investigating error handling techniques. | |
| CN111324626B (en) | Search method and device based on voice recognition, computer equipment and storage medium | |
| Bangalore et al. | Balancing data-driven and rule-based approaches in the context of a multimodal conversational system | |
| Savage-Carmona et al. | The VirBot: a virtual reality robot driven with multimodal commands | |
| CN109712606A (en) | A kind of information acquisition method, device, equipment and storage medium | |
| Aiello et al. | Knowledgeable talking robots | |
| CN111241236B (en) | Task-oriented question-answering method, system, electronic device and readable storage medium | |
| Kobori et al. | Robust comprehension of natural language instructions by a domestic service robot |
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: 20190412 |