CN107102982A - The high in the clouds semantic understanding system and its operation method of robot - Google Patents
The high in the clouds semantic understanding system and its operation method of robot Download PDFInfo
- Publication number
- CN107102982A CN107102982A CN201710229390.3A CN201710229390A CN107102982A CN 107102982 A CN107102982 A CN 107102982A CN 201710229390 A CN201710229390 A CN 201710229390A CN 107102982 A CN107102982 A CN 107102982A
- Authority
- CN
- China
- Prior art keywords
- clouds
- semantic understanding
- robot
- kbs
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Manipulator (AREA)
Abstract
The invention discloses the high in the clouds semantic understanding system and its operation method of robot, including high in the clouds and robot, information exchange is carried out between robot and high in the clouds;Robot can download the semantic understanding knowledge base in high in the clouds automatically to local system, and the interaction data that high in the clouds is collected according to robot is updated, and robot periodically downloads newest semantic understanding KBS from high in the clouds.Compared with prior art, the beneficial effects of the invention are as follows:The renewal of the semantic understanding KBS in high in the clouds is mainly completed with safeguarding by high in the clouds, and robot regularly automatic can download newest semantic understanding KBS from high in the clouds, to complete to automatically update operation, reduce the maintenance cost of product;Multiple robots can also be allowed to cooperate with completion task according to identical semantic understanding KBS, higher level level of interaction is reached.
Description
Technical field
The invention belongs to speech robot people's technical field, it is related to high in the clouds semantic understanding system and its running side of robot
Method.
Background technology
The question and answer interaction of machine person to person, depends critically upon the robot knowledge base trained.This knowledge base is needed
The support of mass data is wanted, and needs to update and safeguard to a certain extent.
Most robot all uses programmed good system in the market, locally there is a knowledge base,
These robots are primarily present Railway Project:
First, if none of the support of extremely abundant knowledge base, they can not handle non-existent in knowledge base ask
Topic, the processing for Similar Problems shows more dull, and variability is not strong;
Second, there is huge difficulty, it is necessary to which engineer enters to each robot for renewal and the maintenance of Duo Tai robots
Row operation;
3rd, data can not be collected and uploaded in the robot itself of localization, reach the purpose of more new knowledge base.
The content of the invention
The problem of present invention needs and solved is to be directed to above-mentioned the deficiencies in the prior art, and provides the high in the clouds semanteme reason of robot
Solution system and its operation method.
In order to solve the above technical problems, the technical solution adopted by the present invention is:
The high in the clouds semantic understanding system of robot, including high in the clouds and robot, carry out information exchange between robot and high in the clouds;Adopt
With the method for network mass data semantic understanding, semantic understanding knowledge is obtained from the data of magnanimity, semantic reason is built beyond the clouds
KBS is solved, the attended operation of semantic understanding KBS is completed beyond the clouds;Robot can download the language in high in the clouds automatically
To local system, and in use, collection and the interaction data of user upload to high in the clouds to reason and good sense solution knowledge base, and high in the clouds is to machine
The interaction data that device people uploads carries out cloud computing processing, and the data obtained after processing are used for the semantic understanding knowledge base for updating high in the clouds
System, robot periodically downloads newest semantic understanding knowledge base to update the knowledge base of local system from high in the clouds.
The operation method of the high in the clouds semantic understanding system of robot, comprises the following steps:
Step 1:Semantic understanding KBS is built beyond the clouds, using the method for network mass data semantic understanding, from network
The upper text data for obtaining magnanimity, is cleaned, after the operation of denoising, using the semantic understanding technology in natural language, is obtained
Keyword, the key message of context of every data are taken, is that every data builds accurately syntax tree structure;
Step 2:After semantic understanding KBS structure is finished, robot first downloads high in the clouds automatically semantic understanding after dispatching from the factory is known
Storehouse is known to local system, and robot can just build syntax tree according to the input of user, and be matched from semantic understanding knowledge base
And solution is found, answer user;
Step 3:The interaction data with user is collected in use by robot, and uploads to high in the clouds, and high in the clouds is to interaction data
Cloud computing processing is carried out, the data obtained after processing are used for the semantic understanding KBS for updating high in the clouds;
Step 4:Robot periodically downloads newest semantic understanding knowledge base to update the knowledge base of local system from high in the clouds.
The attended operation of semantic understanding KBS is completed beyond the clouds.
Robot is using sensor collection and the interaction data of user and uploads to high in the clouds.
Compared with prior art, the beneficial effects of the invention are as follows:
(1)Robot preserves a semantic understanding KBS in local system, and can be regularly automatic under high in the clouds
Newest semantic understanding KBS is carried, to complete to automatically update operation, the maintenance cost of product is reduced;
(2)The renewal of the semantic understanding KBS in high in the clouds is mainly completed with safeguarding by high in the clouds, and robot is only absorbed in basis
The knowledge base of local system completes interactive task, and using sensor collection data and uploads to high in the clouds, so eliminates
A large amount of calculating tasks, reduce the complexity of robot system;
(3)By the deployment of semantic understanding KBS beyond the clouds, multiple robots are facilitated to share knowledge base, to keep multiple machines
The knowledge consistency of people, the method dispatched also with high in the clouds can allow multiple robots to be known according to identical semantic understanding
Know storehouse systematic collaboration complete task, without thus knowledge base difference and show different behaviors, reach higher level
Level of interaction.
Brief description of the drawings
Fig. 1 is flow chart of the invention.
Embodiment
The present invention proposes the high in the clouds semantic understanding thought of robot.With reference to mass data semantic understanding, cloud computing and machine
The big task of device people three, completes construction of knowledge base, maintenance and the shared procedure of robot system.
The high in the clouds semantic understanding system of robot, including high in the clouds and robot, enter row information friendship between robot and high in the clouds
Mutually;Using the method for network mass data semantic understanding, semantic understanding knowledge is obtained from the data of magnanimity, language is built beyond the clouds
Reason and good sense solution KBS, the attended operation of semantic understanding KBS is completed beyond the clouds;Robot can download high in the clouds automatically
Semantic understanding knowledge base to local system, and collect upload to high in the clouds, high in the clouds with the interaction data of user in use
Cloud computing processing is carried out to the interaction data that robot is uploaded, the semantic understanding that the data obtained after processing are used to update high in the clouds is known
Know storehouse system, robot periodically downloads newest semantic understanding knowledge base to update the knowledge base of local system from high in the clouds.
, will be based on semanteme with reference to the thought of cloud computing for the ease of being updated and maintenance knowledge storehouse between multiple robots
The KBS deployment of understanding is beyond the clouds.The benefit following points so done:First, robot is known in local preservation one
Know storehouse, and regularly automatic newest semantic understanding knowledge base can be downloaded from high in the clouds, to complete to automatically update operation, reduce
The maintenance cost of product;Second, the renewal of semantic understanding knowledge base is mainly completed with safeguarding by high in the clouds, robot is only absorbed in
Interactive task is completed according to knowledge base, and using sensor collection data and uploads to high in the clouds, big gauge is so eliminated
Calculation task, reduces the complexity of robot system;Third, by the deployment of semantic understanding KBS beyond the clouds, facilitating multiple
Knowledge base is shared by robot, to keep the knowledge consistency of multiple robots, the method dispatched also with high in the clouds, Ke Yirang
Multiple robots according to identical knowledge base cooperate with completion task, without thus knowledge base difference and show different rows
For.
The operation method of the high in the clouds semantic understanding system of robot, comprises the following steps:
Step 1:Semantic understanding KBS is built beyond the clouds, using the method for network mass data semantic understanding, from network
The upper text data for obtaining magnanimity, is cleaned, after the operation of denoising, using the semantic understanding technology in natural language, is obtained
Keyword, the key message of context of every data are taken, is that every data builds accurately syntax tree structure;
Step 2:After semantic understanding KBS structure is finished, robot first downloads high in the clouds automatically semantic understanding after dispatching from the factory is known
Storehouse is known to local system, and robot can just build syntax tree according to the input of user, and be matched from semantic understanding knowledge base
And solution is found, answer user;Semantic understanding is advantageous in that, compared to common key word matching method, semantic understanding
The contextual information of problem can be more caught, has reached and has more accurately matched.
Step 3:The interaction data with user is collected in use by robot, and uploads to high in the clouds, and high in the clouds is to interaction
Data carry out cloud computing processing, and the data obtained after processing are used for the semantic understanding KBS for updating high in the clouds;
Step 4:Robot periodically downloads newest semantic understanding knowledge base to update the knowledge base of local system from high in the clouds.
The attended operation of semantic understanding KBS is completed beyond the clouds.
Robot is using sensor collection and the interaction data of user and uploads to high in the clouds.
Using the above-mentioned desirable embodiment according to the present invention as enlightenment, by above-mentioned description, relevant staff is complete
Various changes and amendments can be carried out without departing from the scope of the technological thought of the present invention' entirely.The technology of this invention
Property scope is not limited to the content on specification, it is necessary to its technical scope is determined according to right.
Claims (4)
1. the high in the clouds semantic understanding system of robot, it is characterised in that:Including high in the clouds and robot, enter between robot and high in the clouds
Row information is interacted;Using the method for network mass data semantic understanding, semantic understanding knowledge is obtained from the data of magnanimity, in cloud
End builds semantic understanding KBS, and the attended operation of semantic understanding KBS is completed beyond the clouds;Robot can be automatic
The semantic understanding knowledge base in high in the clouds is downloaded to local system, and collection and the interaction data of user upload to cloud in use
End, the interaction data that high in the clouds is uploaded to robot carries out cloud computing processing, and the data obtained after processing are used for the language for updating high in the clouds
Reason and good sense solution KBS, robot periodically downloads newest semantic understanding knowledge base to update the knowledge of local system from high in the clouds
Storehouse.
2. the operation method of the high in the clouds semantic understanding system of robot according to claim 1, it is characterised in that:Including with
Lower step:
Step 1:Semantic understanding KBS is built beyond the clouds, using the method for network mass data semantic understanding, from network
The upper text data for obtaining magnanimity, is cleaned, after the operation of denoising, using the semantic understanding technology in natural language, is obtained
Keyword, the key message of context of every data are taken, is that every data builds accurately syntax tree structure;
Step 2:After semantic understanding KBS structure is finished, robot first downloads high in the clouds automatically semantic understanding after dispatching from the factory is known
Storehouse is known to local system, and robot can just build syntax tree according to the input of user, and be matched from semantic understanding knowledge base
And solution is found, answer user;
Step 3:The interaction data with user is collected in use by robot, and uploads to high in the clouds, and high in the clouds is to interaction data
Cloud computing processing is carried out, the data obtained after processing are used for the semantic understanding KBS for updating high in the clouds;
Step 4:Robot periodically downloads newest semantic understanding knowledge base to update the knowledge base of local system from high in the clouds.
3. the operation method of the high in the clouds semantic understanding system of robot according to claim 2, it is characterised in that:Semanteme reason
The attended operation of solution KBS is completed beyond the clouds.
4. the operation method of the high in the clouds semantic understanding system of robot according to claim 1, it is characterised in that:Robot
Using sensor collection and the interaction data of user and upload to high in the clouds.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710229390.3A CN107102982A (en) | 2017-04-10 | 2017-04-10 | The high in the clouds semantic understanding system and its operation method of robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710229390.3A CN107102982A (en) | 2017-04-10 | 2017-04-10 | The high in the clouds semantic understanding system and its operation method of robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107102982A true CN107102982A (en) | 2017-08-29 |
Family
ID=59675007
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710229390.3A Pending CN107102982A (en) | 2017-04-10 | 2017-04-10 | The high in the clouds semantic understanding system and its operation method of robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107102982A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107493353A (en) * | 2017-10-11 | 2017-12-19 | 宁波感微知著机器人科技有限公司 | A kind of intelligent robot cloud computing method based on contextual information |
CN110970032A (en) * | 2018-09-28 | 2020-04-07 | 深圳市冠旭电子股份有限公司 | Sound box voice interaction control method and device |
CN112562662A (en) * | 2020-11-09 | 2021-03-26 | 金茂智慧科技(广州)有限公司 | Intelligent household appliance control equipment capable of realizing semantic understanding |
US11373642B2 (en) | 2019-08-29 | 2022-06-28 | Boe Technology Group Co., Ltd. | Voice interaction method, system, terminal device and medium |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN205508398U (en) * | 2015-09-30 | 2016-08-24 | 深圳光启合众科技有限公司 | Intelligent robot with high in clouds interactive function |
-
2017
- 2017-04-10 CN CN201710229390.3A patent/CN107102982A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN205508398U (en) * | 2015-09-30 | 2016-08-24 | 深圳光启合众科技有限公司 | Intelligent robot with high in clouds interactive function |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107493353A (en) * | 2017-10-11 | 2017-12-19 | 宁波感微知著机器人科技有限公司 | A kind of intelligent robot cloud computing method based on contextual information |
CN110970032A (en) * | 2018-09-28 | 2020-04-07 | 深圳市冠旭电子股份有限公司 | Sound box voice interaction control method and device |
US11373642B2 (en) | 2019-08-29 | 2022-06-28 | Boe Technology Group Co., Ltd. | Voice interaction method, system, terminal device and medium |
CN112562662A (en) * | 2020-11-09 | 2021-03-26 | 金茂智慧科技(广州)有限公司 | Intelligent household appliance control equipment capable of realizing semantic understanding |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107102982A (en) | The high in the clouds semantic understanding system and its operation method of robot | |
Zeng et al. | Boomerang: On-demand cooperative deep neural network inference for edge intelligence on the industrial Internet of Things | |
CN108093030B (en) | Artificial intelligence model deployment method based on cloud server | |
CN104049575B (en) | It is collected in Process Control System and delivers data to big data machine | |
JP6615331B2 (en) | Industrial robot process cloud system | |
CN104035392B (en) | Big data in Process Control System | |
CN104506496B (en) | The method of near-realtime data increment distribution based on Oracle Streams technologies | |
JP2017531264A5 (en) | ||
GB2590803A8 (en) | Data pipeline for process control system analytics | |
GB2458048A (en) | Method and apparatus for mobile intelligence | |
CN105159783A (en) | System task distribution method | |
CN104820733B (en) | A kind of bullet train demand meta-model method for building up and device | |
CN104753985A (en) | Session list display method and device | |
CA3007425C (en) | System and method for caching and parameterizing ir | |
CN104317970A (en) | Data flow type processing method based on data processing center | |
CN104899284A (en) | Method and device for driving scheduling system based on metadata | |
CN107733696A (en) | A kind of machine learning and artificial intelligence application all-in-one dispositions method | |
CN106777142A (en) | Service layer's system and method based on mobile Internet mass data | |
Senvar et al. | An overview to industry 4.0 | |
CN106227165A (en) | A kind of intelligence manufacture management system | |
CN107562964A (en) | A kind of crops pedigree construction method, database, retroactive method and system | |
CN104392104A (en) | Determination method for length and number of low-frequency cable conductors of spacecraft | |
WO2014022901A3 (en) | Method and system implemented by a collaborative distributed computational network, and related devices | |
CN113961612A (en) | Satellite health data comprehensive analysis system and method based on deep learning | |
CN107194616A (en) | Enterprise's production capacity statistical system and method |
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: 20170829 |