CN106649706A - Natural language knowledge learning method and apparatus - Google Patents
Natural language knowledge learning method and apparatus Download PDFInfo
- Publication number
- CN106649706A CN106649706A CN201611185192.3A CN201611185192A CN106649706A CN 106649706 A CN106649706 A CN 106649706A CN 201611185192 A CN201611185192 A CN 201611185192A CN 106649706 A CN106649706 A CN 106649706A
- Authority
- CN
- China
- Prior art keywords
- natural language
- language information
- content
- information
- data base
- 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to a natural language knowledge learning method and apparatus. The method comprises: receiving natural language information input by a user; when it is detected that the natural language information satisfies a preset requirement, analyzing the contents of the natural language information; determining whether the natural language information is qualified or not according to the analysis result; and when the natural language information is determined to be qualified, updating the knowledge database of the electronic equipment according to the contents of the natural language information. Through the technical scheme, the electronic equipment can automatically learn according to the input natural language information, and do not need to update the knowledge database artificially, thus reducing the user operation, and enhancing the user experience; and at the same time, the voice interactive product has the ability of self learning, and with the increase in the number of products being used, the knowledge will be more abundant.
Description
Technical field
The present invention relates to voice processing technology field, more particularly to a kind of natural language knowledge learning and device.
Background technology
In correlation technique, the electronic equipment that can be interacted with user speech can all arrange a natural-sounding knowledge data base.
Natural language knowledge data base is the very important part in VUI (voice Interaction Interface) product, and what it was stored is to user
The knowledge of interactive voice experience is provided.The conventional knowledge base maintenance in VUI products, otherwise be dispatch from the factory before set and unalterable
, or being to carry out maintenance renewal beyond the clouds by product producer.When the natural language information of user input is received, knowing
Know and search in database feedback content corresponding with natural language information, but the natural language knowledge data base is repaiied if desired
Change, then need to be modified using other poorly efficient interactive meanses, such as database rewriting operation or GUI are input into, Consumer's Experience
It is not good.
The content of the invention
The embodiment of the present invention provides a kind of natural language knowledge learning method and device, to realize according to user input
Natural language information automatically updates natural language knowledge data base.
A kind of first aspect according to embodiments of the present invention, there is provided natural language knowledge learning, is mainly used in VUI products,
Including：
The natural language information of receiving user's input；
When detecting the natural language information and meeting preset requirement, the content of the natural language information is solved
Analysis；
Determine whether the natural language information is qualified according to analysis result；
When it is determined that the natural language information is qualified, the electronics according to the content update of the natural language information sets
Standby natural language knowledge data base.
In this embodiment, when the natural language information of user input is received, if detect natural language information expiring
Sufficient preset requirement, it is determined that whether natural language information is qualified, when natural language information is qualified, according to the natural language information
Content automatically update the natural language knowledge data base of electronic equipment, so so that electronic equipment can according to input from
So language message learns automatically, it is not necessary to artificial to update natural language knowledge data base, so as to reduce user operation, improves
The experience of user, while so that interactive voice product is provided with the ability of self study, as the number of times that product is used increases
Many, the knowledge that it possesses can more be enriched.
In one embodiment, the preset requirement includes following any one：
The clause of the natural language information is default clause；
Predetermined keyword is included in the natural language information；
There is context relation between the natural language information that the natural language information and last time receive.
In this embodiment, preset requirement can be the clause of natural language information to preset clause, such as natural language letter
The clause of breath is the declarative sentence of definitional, and such as a is b.Preset requirement can also be and include in natural language information preset critical
Word, such as specific order word, for example, remember.Certainly, preset requirement can also be what natural language information and last time received
There is context relation between natural language information, a question sentence has such as been said before user, current this is precisely returning for problem
Answer.
In one embodiment, it is described to determine whether the natural language information is qualified according to analysis result, including：
Whether determine in the content of the natural language information includes illegal keyword；
When illegal keyword is included in the content, determine that the natural language information is unqualified；
When illegal keyword is not included in the content, the semanteme of the content is parsed；
Determine whether the natural language information is qualified according to the semanteme of the content.
In this embodiment, before the content update natural language knowledge data base according to natural language information, also need
Determine whether natural language information is legal, specifically, it can be determined that whether comprising illegal pass in the content of natural language information
Keyword, such as some political sensitivity words, unhealthy vocabulary etc., determine that natural language information does not conform to if comprising illegal keyword
Lattice, it is impossible to enough that natural language knowledge data base is updated according to the natural language information.It is, of course, also possible to according to natural language information
The semantic of content determine whether natural language information qualified.Natural language information " Li Xiaoming is not people " is such as received, should be certainly
So do not include illegal keyword in the content of language message, but the semanteme of entire content is uncultivated, at this time it is also possible to really
Determine natural language information unqualified.
In this embodiment, before the content update knowledge data base according to natural language information, in addition it is also necessary to it is determined that from
So whether language message is qualified.Underproof natural language information mainly includes two kinds：The first invalid information, political sensitivity,
Terrorism, racial discrimination, illegal, porns, gambling and drugs, uncivil etc. are all invalid informations；The falseness for being to run counter to objective fact second
Information, such as " earth side of being ", " Liu Dehua is woman ".Realize the detection of both above unqualified natural language information, one
As realized with keyword or the method for semantic analysis.Keyword " Falun Gong " is such as detected, then judges the natural language information
Illegally.Receive natural language information " Li Xiaoming is not people ", although not comprising illegal pass in the content of the natural language information
Keyword, but the semanteme of entire content is uncultivated, at this time it is also possible to determine that the natural language information is unqualified.
In one embodiment, the natural language of the electronic equipment according to the content update of the natural language information
Speech knowledge data base, including：
Determine in the natural language knowledge data base and gone through with the presence or absence of related to the content of the natural language information
History content；
When it is determined that there is no the historical content in the natural language knowledge data base, by the natural language information
Content Transformation be target natural language contents corresponding with electronic equipment, and record the target natural language contents；
When it is determined that there is the historical content in the natural language knowledge data base, with the natural language information
Content replaces the historical content, and the Content Transformation by the natural language information is target nature language corresponding with electronic equipment
Speech content, and record the target natural language contents.
In this embodiment, in the content update natural language knowledge data base according to natural language information, Ke Nengcun
In two kinds of situations, a kind of is that before presence is related to the content of the natural language information in natural language knowledge data base
Historical content, at this point it is possible to directly by the Content Transformation of the natural language information into the corresponding target natural language of electronic equipment
Content, such as changes person and time, and records the target natural language contents.Another kind is in natural language knowledge data base
There is the historical content related to the content of the natural language information before, now, the content of the natural language information is being turned
Change the corresponding target natural language contents of electronic equipment into, using the target natural language contents natural language knowledge number is replaced
According to the historical content recorded in storehouse, so as to realize the renewal of natural language knowledge data base.
For example, user input natural language information：What is your name, and electronic equipment is replied：I is little Bai.Now use
Family is input into natural language information：No, you cry little black, please remember.It is assumed that " please remember " is predetermined keyword, and now, electronics
Equipment is replied：Remember.And electronic equipment can determine whether whether the natural language information " you cry little black " of user input is qualified,
After it is determined that the natural language information is qualified, by the Content Transformation of the natural language information into the corresponding target nature of electronic equipment
Language message, that is, change person, becomes " I cries little black ", and replaces note in natural language knowledge data base with " I cries little black "
" I cries little black " of record, so, when user is input into again natural language information：What you cry, and electronic equipment can be answered：I cries little
It is black.So, according to the natural language information of the user for receiving, learn and update natural language knowledge data base automatically, so as to
Lift the experience of user.
In one embodiment, methods described also includes：
The setting command of receiving user's input；
According to the setting command, following any one is set：Default clause, predetermined keyword, illegal keyword.
In this embodiment, user or manufacturer can arrange default clause, predetermined keyword, illegal according to demands of individuals
Keyword etc., so that default clause, predetermined keyword, illegal keyword etc. can meet the different demands of different user,
Further lift the experience of user.
A kind of second aspect according to embodiments of the present invention, there is provided natural language knowledge device, including：
First receiver module, for the natural language information of receiving user's input；
Parsing module, for when detecting the natural language information and meeting preset requirement, believing the natural language
The content of breath is parsed；
Determining module, for determining whether the natural language information is qualified according to analysis result；
Update module, for when it is determined that the natural language information is qualified, according to the content of the natural language information
Update the natural language knowledge data base of the electronic equipment.
In one embodiment, the preset requirement includes following any one：
The clause of the natural language information is default clause；
Predetermined keyword is included in the natural language information；
There is context relation between the natural language information that the natural language information and last time receive.
In one embodiment, the determining module includes：
First determination sub-module, for whether including illegal keyword in the content for determining the natural language information；
Second determination sub-module, for when illegal keyword is included in the content, determining the natural language information
It is unqualified；
Analyzing sub-module, for when illegal keyword is not included in the content, solving to the semanteme of the content
Analysis；
3rd determination sub-module, for determining whether the natural language information is qualified according to the semanteme of the content.
In one embodiment, the update module includes：
4th determination sub-module, for determining the natural language knowledge data base in whether there is and the natural language
The related historical content of the content of information；
Transform subblock, for when it is determined that there is no the historical content in the natural language knowledge data base, inciting somebody to action
The Content Transformation of the natural language information is target natural language contents corresponding with electronic equipment, and records the target certainly
Right language content；
Submodule is replaced, for when it is determined that there is the historical content in the natural language knowledge data base, using institute
The content for stating natural language information replaces the historical content, and the Content Transformation by the natural language information is and electronic equipment
Corresponding target natural language contents, and record the target natural language contents.
In one embodiment, described device also includes：
Second receiver module, for the setting command of receiving user's input；
Setup module, for according to the setting command, arranging following any one：It is default clause, predetermined keyword, illegal
Keyword.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not
The present invention can be limited.
Other features and advantages of the present invention will be illustrated in the following description, also, the partly change from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages can be by the explanations write
Specifically noted structure is realizing and obtain in book, claims and accompanying drawing.
Below by drawings and Examples, technical scheme is described in further detail.
Description of the drawings
Accompanying drawing herein is merged in specification and constitutes the part of this specification, shows the enforcement for meeting the present invention
Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is a kind of flow chart of the natural language knowledge learning according to an exemplary embodiment.
Fig. 2 is the flow chart of step S103 in a kind of natural language knowledge learning according to an exemplary embodiment.
Fig. 3 is the flow chart of step S104 in a kind of natural language knowledge learning according to an exemplary embodiment.
Fig. 4 is the flow chart of another kind of natural language knowledge learning according to an exemplary embodiment.
Fig. 5 is a kind of block diagram of the natural language knowledge device according to an exemplary embodiment.
Fig. 6 is the block diagram of determining module in a kind of natural language knowledge device according to an exemplary embodiment.
Fig. 7 is the block diagram of update module in a kind of natural language knowledge device according to an exemplary embodiment.
Fig. 8 is the block diagram of another kind of natural language knowledge device according to an exemplary embodiment.
Specific embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Explained below is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent and the consistent all embodiments of the present invention.Conversely, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects described in detail in claims, the present invention.
Fig. 1 is a kind of flow chart of the natural language knowledge learning according to an exemplary embodiment.The natural language
Knowledge learning is applied in electronic equipment, and the electronic equipment can be mobile phone, and computer, digital broadcast terminal, message is received
The equipment of sending out, game console, tablet device, Medical Devices, body-building equipment, personal digital assistant etc. is arbitrary with phonetic function
Equipment.As shown in figure 1, the method comprising the steps of S101-S104：
In step S101, the natural language information of receiving user's input；
In step s 102, when detecting natural language information and meeting preset requirement, the content to natural language information
Parsed；
In one embodiment, preset requirement includes following any one：
The clause of natural language information is default clause；
Predetermined keyword is included in natural language information；
There is context relation between the natural language information that natural language information and last time receive.
In this embodiment, preset requirement can be the clause of natural language information to preset clause, such as natural language letter
The clause of breath is the declarative sentence of definitional, and such as a is b.Preset requirement can also be and include in natural language information preset critical
Word, such as specific order word, for example, remember.Certainly, preset requirement can also be what natural language information and last time received
There is context relation between natural language information, a question sentence has such as been said before user, current this is precisely returning for problem
Answer.
In step s 103, determine whether natural language information is qualified according to analysis result；
Wherein, the result that parsing is obtained is divided to two kinds：Structuring characterizing semanticses, or question and answer pair.
In step S104, when it is determined that natural language information is qualified, according to the content update electronics of natural language information
The natural language knowledge data base of equipment.
In this embodiment, when the natural language information of user input is received, if detect natural language information expiring
Sufficient preset requirement, it is determined that whether natural language information is qualified, when natural language information is qualified, according to the natural language information
Content automatically update the natural language knowledge data base of electronic equipment, so so that electronic equipment can according to input from
So language message learns automatically, it is not necessary to artificial to update natural language knowledge data base, so as to reduce user operation, improves
The experience of user.
Fig. 2 is the flow chart of step S103 in a kind of natural language knowledge learning according to an exemplary embodiment.
As shown in Fig. 2 in one embodiment, above-mentioned steps S103 include step S201-S204：
In step s 201, whether determine in the content of natural language information includes illegal keyword；
In step S202, when illegal keyword is included in content, determine that natural language information is unqualified；
In step S203, when illegal keyword is not included in content, the semanteme of content is parsed；
In step S204, semantic according to content determines whether natural language information is qualified.
In this embodiment, before the content update natural language knowledge data base according to natural language information, also need
Determine whether natural language information is legal, specifically, it can be determined that whether comprising illegal pass in the content of natural language information
Keyword, such as some political sensitivity words, unhealthy vocabulary etc., determine that natural language information does not conform to if comprising illegal keyword
Lattice, it is impossible to enough that natural language knowledge data base is updated according to the natural language information.It is, of course, also possible to according to natural language information
The semantic of content determine whether natural language information qualified.Natural language information " Li Xiaoming is not people " is such as received, should be certainly
So do not include illegal keyword in the content of language message, but the semanteme of entire content is uncultivated, at this time it is also possible to really
Determine natural language information unqualified.
Fig. 3 is the flow chart of step S104 in a kind of natural language knowledge learning according to an exemplary embodiment.
As shown in figure 3, in one embodiment, above-mentioned steps S104 include step S301-S303：
In step S301, determine in natural language knowledge data base with the presence or absence of related to the content of natural language information
Historical content；
In step s 302, when it is determined that during not history of existence content in natural language knowledge data base, natural language is believed
The Content Transformation of breath is target natural language contents corresponding with electronic equipment, and records target natural language contents；
In step S303, when it is determined that during history of existence content in natural language knowledge data base, using natural language information
Content replace historical content, be in target natural language corresponding with electronic equipment by the Content Transformation of natural language information
Hold, and record target natural language contents.
In this embodiment, in the content update natural language knowledge data base according to natural language information, Ke Nengcun
In two kinds of situations, a kind of is that before presence is related to the content of the natural language information in natural language knowledge data base
Historical content, at this point it is possible to directly by the Content Transformation of the natural language information into the corresponding target natural language of electronic equipment
Content, such as changes person and time, and records the target natural language contents.Another kind is in natural language knowledge data base
There is the historical content related to the content of the natural language information before, now, the content of the natural language information is being turned
Change the corresponding target natural language contents of electronic equipment into, using the target natural language contents natural language knowledge number is replaced
According to the historical content recorded in storehouse, so as to realize the renewal of natural language knowledge data base.
Certainly, the renewal of natural language knowledge data base can also include deleting in addition to above-mentioned addition and replacement operation
Division operation, i.e., according to the delete command for receiving, delete some natural language informations.
For example, user input natural language information：What is your name, and electronic equipment is replied：I is little Bai.Now use
Family is input into natural language information：No, you cry little black, please remember.It is assumed that " please remember " is predetermined keyword, and now, electronics
Equipment is replied：Remember.And electronic equipment can determine whether whether the natural language information " you cry little black " of user input is qualified,
After it is determined that the natural language information is qualified, by the Content Transformation of the natural language information into the corresponding target nature of electronic equipment
Language message, that is, change person, becomes " I cries little black ", and replaces note in natural language knowledge data base with " I cries little black "
" I cries little black " of record, so, when user is input into again natural language information：What you cry, and electronic equipment can be answered：I cries little
It is black.So, according to the natural language information of the user for receiving, learn and update natural language knowledge data base automatically, so as to
Lift the experience of user.
Fig. 4 is the flow chart of another kind of natural language knowledge learning according to an exemplary embodiment.
As shown in figure 4, in one embodiment, said method also includes step S401-S402：
In step S401, the setting command of receiving user's input；
In step S402, according to setting command, following any one is set：Default clause, predetermined keyword, illegal key
Word.
In this embodiment, user or manufacturer can arrange default clause, predetermined keyword, illegal according to demands of individuals
Keyword etc., so that default clause, predetermined keyword, illegal keyword etc. can meet the different demands of different user,
Further lift the experience of user.
It is following for apparatus of the present invention embodiment, can be used for performing the inventive method embodiment.
Fig. 5 is a kind of block diagram of the natural language knowledge device according to an exemplary embodiment, and the device can lead to
Cross software, hardware or both be implemented in combination with become some or all of of electronic equipment.As shown in figure 5, the natural language
Knowledge device includes：
First receiver module 51, for the natural language information of receiving user's input；
Parsing module 52, for when detecting the natural language information and meeting preset requirement, to the natural language
The content of information is parsed；
In one embodiment, the preset requirement includes following any one：
The clause of the natural language information is default clause；
Predetermined keyword is included in the natural language information；
There is context relation between the natural language information that the natural language information and last time receive.
In this embodiment, preset requirement can be the clause of natural language information to preset clause, such as natural language letter
The clause of breath is the declarative sentence of definitional, and such as a is b.Preset requirement can also be and include in natural language information preset critical
Word, such as specific order word, for example, remember.Certainly, preset requirement can also be what natural language information and last time received
There is context relation between natural language information, a question sentence has such as been said before user, current this is precisely returning for problem
Answer.
Determining module 53, for determining whether the natural language information is qualified according to analysis result；
Update module 54, for when it is determined that the natural language information is qualified, according in the natural language information
Hold the natural language knowledge data base for updating the electronic equipment.
In this embodiment, when the natural language information of user input is received, if detect natural language information expiring
Sufficient preset requirement, it is determined that whether natural language information is qualified, when natural language information is qualified, according to the natural language information
Content automatically update the natural language knowledge data base of electronic equipment, so so that electronic equipment can according to input from
So language message learns automatically, it is not necessary to artificial to update natural language knowledge data base, so as to reduce user operation, improves
The experience of user.
Fig. 6 is the block diagram of determining module in a kind of natural language knowledge device according to an exemplary embodiment.
As shown in fig. 6, in one embodiment, the determining module 53 includes：
First determination sub-module 61, for whether including illegal keyword in the content for determining the natural language information；
Second determination sub-module 62, for when illegal keyword is included in the content, determining the natural language letter
Breath is unqualified；
Analyzing sub-module 63, for when illegal keyword is not included in the content, carrying out to the semanteme of the content
Parsing；
3rd determination sub-module 64, for determining whether the natural language information is qualified according to the semanteme of the content.
In this embodiment, before the content update natural language knowledge data base according to natural language information, also need
Determine whether natural language information is legal, specifically, it can be determined that whether comprising illegal pass in the content of natural language information
Keyword, such as some political sensitivity words, unhealthy vocabulary etc., determine that natural language information does not conform to if comprising illegal keyword
Lattice, it is impossible to enough that natural language knowledge data base is updated according to the natural language information.It is, of course, also possible to according to natural language information
The semantic of content determine whether natural language information qualified.Natural language information " Li Xiaoming is not people " is such as received, should be certainly
So do not include illegal keyword in the content of language message, but the semanteme of entire content is uncultivated, at this time it is also possible to really
Determine natural language information unqualified.
Fig. 7 is the block diagram of update module in a kind of natural language knowledge device according to an exemplary embodiment.
As shown in fig. 7, in one embodiment, the update module 54 includes：
4th determination sub-module 71, for determining the natural language knowledge data base in whether there is and the natural language
The related historical content of the content of speech information；
Transform subblock 72, for when it is determined that there is no the historical content in the natural language knowledge data base,
Content Transformation by the natural language information is target natural language contents corresponding with electronic equipment, and records the target
Natural language contents；
Submodule 73 is replaced, for when it is determined that there is the historical content in the natural language knowledge data base, using
The content of the natural language information replaces the historical content, and the Content Transformation by the natural language information is to set with electronics
Standby corresponding target natural language contents, and record the target natural language contents.
In this embodiment, in the content update natural language knowledge data base according to natural language information, Ke Nengcun
In two kinds of situations, a kind of is that before presence is related to the content of the natural language information in natural language knowledge data base
Historical content, at this point it is possible to directly by the Content Transformation of the natural language information into the corresponding target natural language of electronic equipment
Content, such as changes person and time, and records the target natural language contents.Another kind is in natural language knowledge data base
There is the historical content related to the content of the natural language information before, now, the content of the natural language information is being turned
Change the corresponding target natural language contents of electronic equipment into, using the target natural language contents natural language knowledge number is replaced
According to the historical content recorded in storehouse, so as to realize the renewal of natural language knowledge data base.
For example, user input natural language information：What is your name, and electronic equipment is replied：I is little Bai.Now use
Family is input into natural language information：No, you cry little black, please remember.It is assumed that " please remember " is predetermined keyword, and now, electronics
Equipment is replied：Remember.And electronic equipment can determine whether whether the natural language information " you cry little black " of user input is qualified,
After it is determined that the natural language information is qualified, by the Content Transformation of the natural language information into the corresponding target nature of electronic equipment
Language message, that is, change person, becomes " I cries little black ", and replaces note in natural language knowledge data base with " I cries little black "
" I cries little black " of record, so, when user is input into again natural language information：What you cry, and electronic equipment can be answered：I cries little
It is black.So, according to the natural language information of the user for receiving, learn and update natural language knowledge data base automatically, so as to
Lift the experience of user.
Fig. 8 is the block diagram of another kind of natural language knowledge device according to an exemplary embodiment.
As shown in figure 8, in one embodiment, said apparatus also include：
Second receiver module 81, for the setting command of receiving user's input；
Setup module 82, for according to the setting command, arranging following any one：It is default clause, predetermined keyword, non-
Method keyword.
In this embodiment, user or manufacturer can arrange default clause, predetermined keyword, illegal according to demands of individuals
Keyword etc., so that default clause, predetermined keyword, illegal keyword etc. can meet the different demands of different user,
Further lift the experience of user.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can be using complete hardware embodiment, complete software embodiment or with reference to the reality in terms of software and hardware
Apply the form of example.And, the present invention can be adopted and wherein include the computer of computer usable program code at one or more
The shape of the computer program implemented in usable storage medium (including but not limited to magnetic disc store and optical memory etc.)
Formula.
The present invention is the flow process with reference to method according to embodiments of the present invention, equipment (system) and computer program
Figure and/or block diagram are describing.It should be understood that can be by computer program instructions flowchart and/or each stream in block diagram
The combination of journey and/or square frame and flow chart and/or the flow process in block diagram and/or square frame.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced for reality by the instruction of computer or the computing device of other programmable data processing devices
The device of the function of specifying in present one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or multiple square frames.
These computer program instructions may be alternatively stored in can guide computer or other programmable data processing devices with spy
In determining the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory is produced to be included referring to
Make the manufacture of device, the command device realize in one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or
The function of specifying in multiple square frames.
These computer program instructions also can be loaded in computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented process, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow process of flow chart or multiple flow processs and/or block diagram one
The step of function of specifying in individual square frame or multiple square frames.
Obviously, those skilled in the art can carry out the essence of various changes and modification without deviating from the present invention to the present invention
God and scope.So, if these modifications of the present invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising these changes and modification.
Claims (10)
1. a kind of natural language knowledge learning, for electronic equipment, it is characterised in that include：
The natural language information of receiving user's input；
When detecting the natural language information and meeting preset requirement, the content of the natural language information is parsed；
Determine whether the natural language information is qualified according to analysis result；
When it is determined that the natural language information is qualified, the electronic equipment according to the content update of the natural language information
Natural language knowledge data base.
2. method according to claim 1, it is characterised in that the preset requirement includes following any one：
The clause of the natural language information is default clause；
Predetermined keyword is included in the natural language information；
There is context relation between the natural language information that the natural language information and last time receive.
3. method according to claim 2, it is characterised in that described that the natural language information is determined according to analysis result
It is whether qualified, including：
Whether determine in the content of the natural language information includes illegal keyword；
When illegal keyword is included in the content, determine that the natural language information is unqualified；
When illegal keyword is not included in the content, the semanteme of the content is parsed；
Determine whether the natural language information is qualified according to the semanteme of the content.
4. method according to claim 1, it is characterised in that the content update institute according to the natural language information
The natural language knowledge data base of electronic equipment is stated, including：
Determine in the natural language knowledge data base with the presence or absence of in the history related to the content of the natural language information
Hold；
When it is determined that there is no the historical content in the natural language knowledge data base, by the natural language information
Appearance is converted to target natural language contents corresponding with electronic equipment, and records the target natural language contents；
When it is determined that there is the historical content in the natural language knowledge data base, with the content of the natural language information
The historical content is replaced, the Content Transformation by the natural language information is in target natural language corresponding with electronic equipment
Hold, and record the target natural language contents.
5. method according to claim 3, it is characterised in that methods described also includes：
The setting command of receiving user's input；
According to the setting command, following any one is set：Default clause, predetermined keyword, illegal keyword.
6. a kind of natural language knowledge device, for electronic equipment, it is characterised in that include：
First receiver module, for the natural language information of receiving user's input；
Parsing module, for when detecting the natural language information and meeting preset requirement, to the natural language information
Content is parsed；
Determining module, for determining whether the natural language information is qualified according to analysis result；
Update module, for when it is determined that the natural language information is qualified, according to the content update of the natural language information
The natural language knowledge data base of the electronic equipment.
7. device according to claim 6, it is characterised in that the preset requirement includes following any one：
The clause of the natural language information is default clause；
Predetermined keyword is included in the natural language information；
There is context relation between the natural language information that the natural language information and last time receive.
8. device according to claim 7, it is characterised in that the determining module includes：
First determination sub-module, for whether including illegal keyword in the content for determining the natural language information；
Second determination sub-module, for when illegal keyword is included in the content, determining that the natural language information does not conform to
Lattice；
Analyzing sub-module, for when illegal keyword is not included in the content, parsing to the semanteme of the content；
3rd determination sub-module, for determining whether the natural language information is qualified according to the semanteme of the content.
9. device according to claim 6, it is characterised in that the update module includes：
4th determination sub-module, for determining the natural language knowledge data base in whether there is and the natural language information
The related historical content of content；
Transform subblock, for when it is determined that there is no the historical content in the natural language knowledge data base, will be described
The Content Transformation of natural language information is target natural language contents corresponding with electronic equipment, and records the target nature language
Speech content；
Submodule is replaced, for when it is determined that there is the historical content in the natural language knowledge data base, use to be described certainly
So the content of language message replaces the historical content, and the Content Transformation by the natural language information is corresponding with electronic equipment
Target natural language contents, and record the target natural language contents.
10. device according to claim 8, it is characterised in that described device also includes：
Second receiver module, for the setting command of receiving user's input；
Setup module, for according to the setting command, arranging following any one：Default clause, predetermined keyword, illegal key
Word.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611185192.3A CN106649706A (en) | 2016-12-20 | 2016-12-20 | Natural language knowledge learning method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611185192.3A CN106649706A (en) | 2016-12-20 | 2016-12-20 | Natural language knowledge learning method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106649706A true CN106649706A (en) | 2017-05-10 |
Family
ID=58833622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611185192.3A Pending CN106649706A (en) | 2016-12-20 | 2016-12-20 | Natural language knowledge learning method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106649706A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104118A (en) * | 2018-10-29 | 2020-05-05 | 百度在线网络技术（北京）有限公司 | AIML-based natural language instruction execution method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101097573A (en) * | 2006-06-28 | 2008-01-02 | 腾讯科技（深圳）有限公司 | Automatically request-answering system and method |
| CN101118554A (en) * | 2007-09-14 | 2008-02-06 | 中兴通讯股份有限公司 | Intelligent interactive question answering system and its processing method |
| CN104050256A (en) * | 2014-06-13 | 2014-09-17 | 西安蒜泥电子科技有限责任公司 | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method |
| CN105488164A (en) * | 2015-11-30 | 2016-04-13 | 北京光年无限科技有限公司 | Question and answer (QA) data processing method and device, intelligent robot |
| US20160124937A1 (en) * | 2014-11-03 | 2016-05-05 | Service Paradigm Pty Ltd | Natural language execution system, method and computer readable medium |
| CN105608221A (en) * | 2016-01-11 | 2016-05-25 | 北京光年无限科技有限公司 | Self-learning method and device for question-answering system |
| CN105930374A (en) * | 2016-04-12 | 2016-09-07 | 华南师范大学 | Emotion robot conversation method and system based on recent feedback, and robot |
-
2016
- 2016-12-20 CN CN201611185192.3A patent/CN106649706A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101097573A (en) * | 2006-06-28 | 2008-01-02 | 腾讯科技（深圳）有限公司 | Automatically request-answering system and method |
| CN101118554A (en) * | 2007-09-14 | 2008-02-06 | 中兴通讯股份有限公司 | Intelligent interactive question answering system and its processing method |
| CN104050256A (en) * | 2014-06-13 | 2014-09-17 | 西安蒜泥电子科技有限责任公司 | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method |
| US20160124937A1 (en) * | 2014-11-03 | 2016-05-05 | Service Paradigm Pty Ltd | Natural language execution system, method and computer readable medium |
| CN105488164A (en) * | 2015-11-30 | 2016-04-13 | 北京光年无限科技有限公司 | Question and answer (QA) data processing method and device, intelligent robot |
| CN105608221A (en) * | 2016-01-11 | 2016-05-25 | 北京光年无限科技有限公司 | Self-learning method and device for question-answering system |
| CN105930374A (en) * | 2016-04-12 | 2016-09-07 | 华南师范大学 | Emotion robot conversation method and system based on recent feedback, and robot |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104118A (en) * | 2018-10-29 | 2020-05-05 | 百度在线网络技术（北京）有限公司 | AIML-based natural language instruction execution method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10777207B2 (en) | Method and apparatus for verifying information | |
| CN113590762B (en) | Method and device for recommending test question information, electronic equipment and computer readable medium | |
| US20140074470A1 (en) | Phonetic pronunciation | |
| US11127399B2 (en) | Method and apparatus for pushing information | |
| CN109089172B (en) | Bullet screen display method and device and electronic equipment | |
| US10410655B2 (en) | Estimating experienced emotions | |
| CN108121800A (en) | Information generating method and device based on artificial intelligence | |
| CN111475627B (en) | Method and device for checking solution deduction questions, electronic equipment and storage medium | |
| CN115840796A (en) | Event integration method, device, equipment and computer readable storage medium | |
| US20190325067A1 (en) | Generating descriptive text contemporaneous to visual media | |
| CN111767431A (en) | Method and apparatus for video soundtrack | |
| CN113590772A (en) | Abnormal score detection method, device, equipment and computer readable storage medium | |
| CN109801527A (en) | Method and apparatus for output information | |
| US20250371551A1 (en) | Customer Agent Recording Systems and Methods | |
| CN114065743B (en) | Title generation method, model training method, device, electronic equipment and medium | |
| CN114429141A (en) | Answer determination method and device, computing equipment and storage medium | |
| CN113849723A (en) | Search method and search device | |
| CN112073757A (en) | Emotion fluctuation index acquisition method, emotion fluctuation index display method and multimedia content production method | |
| EP4139784B1 (en) | Hierarchical context specific actions from ambient speech | |
| Shahin et al. | Deaf and hard of hearing in the United Arab Emirates interacting with Alexa, an intelligent personal assistant | |
| CN106649706A (en) | Natural language knowledge learning method and apparatus | |
| CN113241070A (en) | Hot word recall and updating method, device, storage medium and hot word system | |
| US20230197211A1 (en) | Electronic apparatus and control method thereof | |
| CN117556041A (en) | Methods, devices and smart devices for human-computer interaction with smart devices | |
| US12217008B2 (en) | Modifying dynamic conversational responses based on detecting references to socially close people |
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: 20170510 |