CN109102809A - A kind of dialogue method and system for intelligent robot - Google Patents
A kind of dialogue method and system for intelligent robot Download PDFInfo
- Publication number
- CN109102809A CN109102809A CN201810650049.XA CN201810650049A CN109102809A CN 109102809 A CN109102809 A CN 109102809A CN 201810650049 A CN201810650049 A CN 201810650049A CN 109102809 A CN109102809 A CN 109102809A
- Authority
- CN
- China
- Prior art keywords
- sentence
- conversation sentence
- standard
- dialog information
- default
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0638—Interactive procedures
Abstract
A kind of dialogue method and system for intelligent robot, wherein this method comprises: Step 1: obtaining the dialog information of user's input;Step 2: calculating separately the semantic similarity of dialog information Yu multiple standard conversation sentences, the standard conversation sentence for corresponding to dialog information is determined according to semantic similarity;Step 3: according to the semantic understanding to standard conversation sentence as a result, generating voice feedback information using default knowledge mapping.This method based on semantic similarity come by user inputted can not the nonstandardized technique conversation sentence used in knowledge mapping be converted to the standardized dialog sentence used in knowledge mapping, human-computer interaction can be carried out with intelligent robot more naturally by also allowing for user in this way, to improve the user experience of intelligent robot.
Description
Technical field
The present invention relates to technical field of voice interaction, specifically, being related to a kind of dialogue method for intelligent robot
And system.
Background technique
With the continuous development of science and technology, the introducing of information technology, computer technology and artificial intelligence technology, machine
Industrial circle is gradually walked out in the research of people, gradually extends to the neck such as medical treatment, health care, family, amusement and service industry
Domain.And requirement of the people for robot also conform to the principle of simplicity single duplicate mechanical action be promoted to have anthropomorphic question and answer, independence and with
The intelligent robot that other robots interact, human-computer interaction also just become an important factor for determining intelligent robot development.
Therefore how to enable intelligent robot more accurately and efficiently interacted with user be robot field urgently
Technical problem to be solved.
Summary of the invention
To solve the above problems, the present invention provides a kind of dialogue methods for intelligent robot, which comprises
Step 1: obtaining the dialog information of user's input;
Step 2: the semantic similarity of the dialog information Yu multiple standard conversation sentences is calculated separately, according to institute's predicate
Adopted similarity determines the standard conversation sentence for corresponding to the dialog information;
Step 3: according to the semantic understanding to the standard conversation sentence as a result, generating voice using default knowledge mapping
Feedback information.
According to one embodiment of present invention, in the step 2, language is chosen from the multiple standard conversation sentence
The adopted maximum sentence of similarity value is as the standard conversation sentence for corresponding to the dialog information.
According to one embodiment of present invention, the multiple standard conversation sentence is stored in default sentence and imports knowledge base
In, in step 2, retrieval in knowledge base is imported from the default sentence according to the semantic similarity and is obtained corresponding to described
The standard conversation sentence of dialog information.
According to one embodiment of present invention, institute is generated according to relationship between the entity and entity of the default knowledge mapping
It states default sentence and imports knowledge base.
According to one embodiment of present invention, the default sentence imports in knowledge base to be also stored with and talk with the standard
The associated similar conversation sentence of sentence calculates separately the dialog information and leads with the default sentence in the step 2
Enter the semantic similarity of each conversation sentence in knowledge base, if it is specific similar for choosing according to the semantic similarity
Conversation sentence then determines its corresponding standard conversation sentence according to the specific similar conversation sentence.
The present invention has also passed through a kind of conversational system for intelligent robot, the system comprises:
Dialog information obtains module, is used to obtain the dialog information of user's input;
Standard conversation sentence generation module obtains module with the dialog information and connect, described right for calculating separately
The semantic similarity for talking about information and multiple standard conversation sentences determines according to the semantic similarity and corresponds to the dialog information
Standard conversation sentence;
Feedback information generation module is connect with the standard conversation sentence generation module, for according to the standard
The semantic understanding of conversation sentence is as a result, generate voice feedback information using default knowledge mapping.
According to one embodiment of present invention, the standard conversation sentence generation module is configured to from the multiple standard pair
The maximum sentence of semantic similarity value is chosen in language sentence as the standard conversation sentence for corresponding to the dialog information.
According to one embodiment of present invention, the multiple standard conversation sentence is stored in default sentence and imports knowledge base
In, the standard conversation sentence generation module is configured to be imported in knowledge base according to the semantic similarity from the default sentence
Retrieval obtains the standard conversation sentence corresponding to the dialog information.
According to one embodiment of present invention, it is according to the default knowledge mapping that the default sentence, which imports knowledge base,
Relationship generates between entity and entity.
According to one embodiment of present invention, the default sentence imports in knowledge base to be also stored with and talk with the standard
The associated similar conversation sentence of sentence, the standard conversation sentence generation module be configured to calculate separately the dialog information with
The default sentence imports the semantic similarity of each conversation sentence in knowledge base, if chosen according to the semantic similarity
Arriving is specific similar conversation sentence, then determines its corresponding standard conversation sentence according to the specific similar conversation sentence.
What the dialogue method provided by the present invention for intelligent robot was inputted user based on semantic similarity
Can not the nonstandardized technique conversation sentence used in knowledge mapping be converted to the standardized dialog used in knowledge mapping
Sentence, human-computer interaction can be carried out with intelligent robot more naturally by also allowing for user in this way, to improve intelligent machine
The user experience of device people.
Meanwhile method provided by the present invention is due to that can be converted to standardized dialog language for nonstandard conversion conversation sentence
Sentence, therefore compared to existing method, this method is also just without being normalized entity and entity relationship.For example, right
For existing interactive method, may be needed in application process by the entity relationships normalizing such as " wife ", " madam "
" wife " is turned to, and method provided by the present invention is then not necessarily to the process.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by specification, right
Specifically noted structure is achieved and obtained in claim and attached drawing.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is required attached drawing in technical description to do simple introduction:
Fig. 1 is the human-computer interaction schematic diagram of a scenario of intelligent robot according to an embodiment of the invention;
Fig. 2 is the implementation process schematic diagram of the dialogue method according to an embodiment of the invention for intelligent robot;
Fig. 3 is the implementation process signal of the dialogue method in accordance with another embodiment of the present invention for intelligent robot
Figure;
Fig. 4 is the structural schematic diagram of the conversational system according to an embodiment of the invention for intelligent robot.
Specific embodiment
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and examples, how to apply to the present invention whereby
Technological means solves technical problem, and the realization process for reaching technical effect can fully understand and implement.It needs to illustrate
As long as not constituting conflict, each feature in each embodiment and each embodiment in the present invention can be combined with each other,
It is within the scope of the present invention to be formed by technical solution.
Meanwhile in the following description, for illustrative purposes and numerous specific details are set forth, to provide to of the invention real
Apply the thorough understanding of example.It will be apparent, however, to one skilled in the art, that the present invention can not have to tool here
Body details or described ad hoc fashion are implemented.
In addition, step shown in the flowchart of the accompanying drawings can be in the department of computer science of such as a group of computer-executable instructions
It is executed in system, although also, logical order is shown in flow charts, and it in some cases, can be to be different from herein
Sequence execute shown or described step.
Conversational system used in intelligent robot is mostly knowledge based map to realize human-computer interaction at present, however existing
Conversational system using knowledge mapping generate feedback voice when, need user according to specific format come to conversational system carry out
Inquiry.If the voice messaging that user is inputted is to be unsatisfactory for preset format (not being reference format), this
When conversational system will be unable to using generating backchannel sound using knowledge mapping.
For the above problem in the presence of the prior art, the present invention provides a kind of new pairs for intelligent robot
Words method, this method, which is no longer required for user, to be carried out pair according to the format of specific standard conversation sentence with intelligent robot
Words, also just improve the interactive experience of intelligent robot in this way.
As shown in Figure 1, dialogue method provided by the present invention is arranged preferably in intelligent robot, intelligence can be passed through
Can the robot operating system of robot built-in execute.When the operating system built in intelligent robot can be realized institute of the present invention
When the method for offer, user 100 also can input corresponding dialogue letter to intelligent robot 101 according to the habit of oneself
Breath, and intelligent robot 101 then can generate reasonable feedback according to the dialog information that user is inputted come knowledge based map
Information, to realize the human-computer dialogue process more to personalize.
It should be pointed out that in different embodiments of the invention, intelligent robot 101, which can be, various forms of to be had
The system of human-computer dialogue ability.For example, in one embodiment of the invention, intelligent robot 101 can be equipped with intelligence
The class humanoid robot of operating system, and in another embodiment of the present invention, intelligent robot 101, which then can be, to be held
The specific software or application of row interactive method provided by the present invention.
In order to clearly illustrate realization principle, the reality of the dialogue method provided by the present invention for intelligent robot
Existing process and advantage, are further described the particular content of the dialogue method below in conjunction with different embodiments.
Embodiment one:
Fig. 2 shows the implementation process schematic diagrames for the dialogue method that intelligent robot is used for provided by the present embodiment.
As shown in Fig. 2, the dialogue method provided by the present embodiment for intelligent robot preferably can be in step S201
The middle dialog information for obtaining user's input.Specifically, in the present embodiment, the dialog information of user's input can be voice messaging,
The dialogue method preferably passes through voice capture device (such as microphone etc.) provisioned in intelligent robot in step s 201
To obtain the voice messaging that user is inputted.
Certainly, in other embodiments of the invention, according to actual needs, the dialogue method is acquired in step s 201
The dialog information for the user's input arrived can also be the information of other forms, and the invention is not limited thereto.For example, of the invention one
In a embodiment, accessed dialog information can also be text information to the dialogue method in step s 201, wherein this article
This information is either by carrying out optical character identification (Optical Character to the image got
Recognition, abbreviation OCR) obtained text information, be also possible to user by relevant device (such as dummy keyboard or
Physical keyboard etc.) text information that is inputted.
After the dialog information for obtaining user's input, this method can calculate separately the dialog information and more in step S202
The semantic similarity of a standard conversation sentence.In the present embodiment, this method preferably uses in step S202 comprehensively considers word
The multiple features sentence semantic similarity computational algorithms of the factors such as semanteme and sentence structure in sentence of weight, word calculate dialogue
The semantic similarity of information and each standard conversation sentence.
Existing sentence similarity calculation method is broadly divided into 5 classes, comprising: literal matching process, the reverse document of word frequency-
Frequency (Term Frequency-inverse Document Frequency, abbreviation TF-IDF) vector approach, probabilistic method,
Sentence structure method and semantic extension method.Wherein, literal matching process is mainly according to same words included in two sentences
Number calculate the similarity of sentence.TF-IDF vector approach is then mainly by sentence expression at TF-IDF vector, and by two
The cosine value of a TF-IDF vector is as similarity.Probabilistic method, which mainly passes through, introduces language model frame, utilizes the side of probability
Method obtains the similarity of output sentence.In sentence structure method, usually sentence is divided into the matching way of sentence template
Different component parts then calculates separately similarity by the structure composition of sentence.
Existing above 4 kinds of methods only considered the literal of word in sentence.Due to the case where there are an adopted more words, such as
Fruit relies only on literal, will likely result in the mispairing of sentence similarity.Inventor is by researching and analysing discovery, and sentence is by phrase
At, and the different parts of speech of word and its subsemantic disturbance degree of position distich in sentence are different, concept represented by word is by context
It limits.Meanwhile appearance sequence (i.e. sentence structure) of the word in sentence also has different influences to the meaning of sentence.And it is above-mentioned various
Method, which is all short of, comprehensively considers these factors.For this purpose, the preferably use of method provided by the present embodiment can be integrated and be examined
The multiple features sentence semantic similarity computational algorithm of the factors such as the semanteme and sentence structure of the weight, word of word in sentence is considered to calculate
The semantic similarity of dialog information and each standard conversation sentence.
Different parts of speech and word is different to effect whether distinguishing similar between sentence in the different location in sentence, the area Ci
Significance level in the sub- similitude of subordinate sentence can word weight indicate, the position power of the main frequency occurred in sentence including word, word
Weight and part of speech weight.
Word order also has an important influence semantic expression.For example, S1: flying to the flight in Shanghai from Beijing;S2: from upper
Fly to Pekinese's flight in sea.If using similarity of the literal matched method to determine above-mentioned two sentence, it will
The on all four conclusion of the two sentences out, and the reason of causing this mismatch structures is the structure letter for not considering sentence
Breath.And word order can efficiently differentiate two sentences with identical set of words as a kind of basic structure information.Specifically
Ground, in the present embodiment, this method preferably determines sentence using the word order similarity calculation algorithm of normalized two sentences
Structural similarity.Wherein, when the word order of two sentences is identical, the sentence structure similarity of the two sentences is also just for most
Big value 1.
After the semantic similarity for the weight, word for obtaining word and sentence structure similarity, this method can be by mostly special
The mode of weighting is levied to calculate separately to obtain the language of dialog information and each standard conversation sentence accessed in step S201
Adopted similarity.
Certainly, in other embodiments of the invention, this method can also be calculated above-mentioned right using other rational methods
The semantic similarity of information and each standard conversation sentence is talked about, the invention is not limited thereto.
As shown in Fig. 2, the semanteme of dialog information and each standard conversation sentence accessed in obtaining step S201
After similarity, this method can determine the standard dialogue corresponding to dialog information in step S203 according to above-mentioned semantic similarity
Sentence.
Specifically, in the present embodiment, this method can preferably be chosen in step S203 from multiple standard conversation sentences
The maximum sentence of semantic similarity is as the standard conversation sentence for corresponding to dialog information accessed in step S201.
In the present embodiment, above-mentioned multiple standard conversation sentences are stored preferably in default sentence and import in knowledge base.The party
Method, which can preset sentence from this based on semantic similarity in step S203 and import retrieval in knowledge base, obtains corresponding to that this is right
Talk about the standard conversation sentence of information.
It should be pointed out that above-mentioned default sentence imports knowledge base and is preferably according to default knowledge graph in the present embodiment
Relationship between the entity and entity of spectrum generates.Certainly, in other embodiments of the invention, this method can also use
Other rational methods import knowledge base to generate above-mentioned default sentence, and the invention is not limited thereto.
For example, the dialog information of such as " whom wife of Zhou Jielun is " inputted for user, default sentence importing is known
Knowing the corresponding standard conversation sentence stored in library can be " whom the wife of $ { person } is ".This method is receiving use
After the dialog information of " whom wife of Zhou Jielun is " that family is inputted, it is based on semantic similarity, user can be inputted
Dialog information, which is converted to, can be instructed to standard conversation sentence used in map " whom the wife of Zhou Jielun is ".
And if the dialog information that user is inputted is " who has married Zhou Jielun ", the dialogue of existing knowledge based map
Method due to being merely able to identify a certain standard conversation sentence, existing dialogue method also just can not knowledge based map come just
Really understand that the semanteme of " who has married Zhou Jielun " this dialog information is identical with " whom the wife of Zhou Jielun is " in fact.And this
Embodiment institute's providing method can determine the semantic phase the most with " who has married Zhou Jielun " by the calculating of semantic similarity
As standard conversation sentence be " whom the wife of Zhou Jielun is ", such this method can also convert off-gauge conversation sentence
Can to be standard conversation sentence used in knowledge mapping.
As shown in Fig. 2, this method, can be in step after obtaining the standard conversation sentence of dialog information in the present embodiment
Semantic understanding is carried out to the standard conversation sentence in S204, and utilizes default knowledge mapping to generate phase according to semantic understanding result
The voice feedback information answered simultaneously exports.
Due in knowledge mapping can relationship between storage entity and entity, this method can in step S204
With by carrying out semantic understanding to the standard conversation sentence determined in step S203, to obtain such as entity " Zhou Jielun "
And entity relationship " wife ", isomorphism retrieves knowledge mapping, also can be obtained by and the pass of " Zhou Jielun " this entity
System is the entity " elder brother's icepro " of " wife ".The answer information for also just having obtained the dialog information that user is inputted in this way, according to this
Answer information can also generate the feedback information of such as " being that elder brother insults ".
As can be seen that being based on semanteme for the dialogue method of intelligent robot provided by the present embodiment from foregoing description
The nonstandardized technique conversation sentence used in knowledge mapping that similarity is inputted user is converted to can be by knowledge
Standardized dialog sentence used in map, also allowing for user in this way can be more naturally man-machine with intelligent robot progress
Interaction, to improve the user experience of intelligent robot.
Meanwhile method provided by the present embodiment is due to that can be converted to standardized dialog language for nonstandard conversion conversation sentence
Sentence, therefore compared to existing method, this method is also just without being normalized entity and entity relationship.For example, right
For existing interactive method, may be needed in application process by the entity relationships normalizing such as " wife ", " madam "
" wife " is turned to, and method provided by the present embodiment is then not necessarily to the process.
Embodiment two:
Fig. 3 shows the implementation process schematic diagram provided by the present embodiment for the dialogue method of intelligent robot.
As shown in figure 3, the dialogue method provided by the present embodiment for intelligent robot preferably can be in step S301
The middle dialog information for obtaining user's input.Specifically, in the present embodiment, the dialog information of user's input can be voice messaging,
The dialogue method preferably passes through voice capture device (such as microphone etc.) provisioned in intelligent robot in step S301
To obtain the voice messaging that user is inputted.
Certainly, in other embodiments of the invention, according to actual needs, the dialogue method is acquired in step S301
The dialog information for the user's input arrived can also be the information of other forms, and the invention is not limited thereto.
As shown in figure 3, this method can calculate separately above-mentioned dialog information and default language in step s 302 in the present embodiment
Sentence imports the semantic similarity of each conversation sentence in knowledge base.In the present embodiment, above-mentioned default sentence, which imports in knowledge base, to be removed
It is stored with outside standard conversation sentence, is also stored with similar conversation sentence associated with standard conversation sentence.Such this method
The phase that dialog information imports each standard conversation sentence in knowledge base with default sentence also just can be not only calculated in step s 302
Like degree, the similarity of similarity conversation sentence associated with each standard conversation sentence can be also calculated.
Wherein, if the highest sentence of semantic similarity with dialog information is standard conversation sentence, this method
Default knowledge mapping can be utilized to generate simultaneously output phase based on the identical principle of step S204 in embodiment one and process
The feedback information answered.
And if with the highest sentence of semantic similarity of dialog information be non-standard conversation sentence (i.e. with a certain standard speech
The associated similar conversation sentence of sentence), then party's rule can be in step S303 according to the spy determined in the present embodiment
Fixed similar conversation sentence determines the standard conversation sentence corresponding to it, then again in step s 304 to institute in step S303
The standard conversation sentence determined carries out semantic understanding, and utilizes default knowledge mapping to generate accordingly according to semantic understanding result
Voice feedback information and export.
As can be seen that the dialogue method provided by the present embodiment for intelligent robot is in embodiment from foregoing description
On the basis of method provided by one, is also imported in knowledge base in default sentence and be added to phase associated with standard conversation sentence
Like conversation sentence, (for example, being added to other ways to put questions similar with standard way to put questions, this kind of similar way to put questions may be that user may
The way to put questions of use), the coverage rate of standard conversation sentence is helped to improve in this way, to further increase the user of intelligent robot
Experience.
The present invention also provides a kind of conversational systems for intelligent robot, wherein Fig. 4 is shown should in the present embodiment
The structural schematic diagram of conversational system.
As shown in figure 4, the conversational system provided by the present embodiment for intelligent robot preferably includes: dialog information
Obtain module 401, standard conversation sentence generation module 402 and feedback information generation module 403.Wherein, dialog information obtains
Module 401 is used to obtain the dialog information of user's input.In the present embodiment, dialog information, which obtains module 401, can be intelligent machine
Voice capture device provisioned in device people (such as microphone), the conversational system can also obtain use using voice capture device
The voice messaging that family is inputted.
Certainly, in other embodiments of the invention, according to actual needs, in order to obtain the dialog informations of other forms,
Dialog information, which obtains module 401, can also include other reasonable equipment or be realized using other reasonable equipment, and the present invention is not
It is limited to this.For example, in one embodiment of the invention, dialog information obtains module 401 and can also be to be known with optical character
Other equipment, the equipment can carry out optical character identification to the image got to obtain corresponding text information.
Dialog information obtains module 401 and connect with standard conversation sentence generation module 402, can will be accessed by itself
Dialog information be transmitted to standard conversation sentence generation module 402, to generate correspondence by standard conversation sentence generation module 402
In the standard conversation sentence to utterance information.
It should be pointed out that standard conversation sentence generation module 402, which generates, corresponds to this to utterance information in the present embodiment
Standard conversation sentence can also both be adopted using technical solution disclosed in step S202 to step S203 in embodiment one
The technical solution disclosed in step S302 to step S303 in embodiment two, herein no longer to standard conversation sentence generation module
402 realize that the concrete principle of its function and process are repeated.
Feedback information generation module 403 is connect with standard conversation sentence generation module 402, can be to standard conversation sentence
Generation module 402 transmits the standard conversation sentence come and carries out semantic understanding, and utilizes to preset according to semantic understanding result and know
Know map to generate corresponding voice feedback information and export.Wherein, feedback information generation module 403 realizes the specific original of its function
Reason and process are identical as step S204 disclosure of that in above-described embodiment one, therefore equally no longer raw to feedback information herein
It is repeated at the related content of module 403.
It should be understood that disclosed embodiment of this invention is not limited to specific structure disclosed herein or processing step
Suddenly, the equivalent substitute for these features that those of ordinary skill in the related art are understood should be extended to.It should also be understood that
It is that term as used herein is used only for the purpose of describing specific embodiments, and is not intended to limit.
" one embodiment " or " embodiment " mentioned in specification means the special characteristic described in conjunction with the embodiments, structure
Or characteristic is included at least one embodiment of the present invention.Therefore, the phrase " reality that specification various places throughout occurs
Apply example " or " embodiment " the same embodiment might not be referred both to.
Although above-mentioned example is used to illustrate principle of the present invention in one or more application, for the technology of this field
For personnel, without departing from the principles and ideas of the present invention, hence it is evident that can in form, the details of usage and implementation
It is upper that various modifications may be made and does not have to make the creative labor.Therefore, the present invention is defined by the appended claims.
Claims (10)
1. a kind of dialogue method for intelligent robot, which is characterized in that the described method includes:
Step 1: obtaining the dialog information of user's input;
Step 2: the semantic similarity of the dialog information Yu multiple standard conversation sentences is calculated separately, according to the semantic phase
The standard conversation sentence for corresponding to the dialog information is determined like degree;
Step 3: according to the semantic understanding to the standard conversation sentence for corresponding to the dialog information as a result, utilizing default knowledge
Map generates voice feedback information.
2. dialogue method as described in claim 1, which is characterized in that in the step 2, talk with from the multiple standard
The maximum sentence of semantic similarity value is chosen in sentence as the standard conversation sentence for corresponding to the dialog information.
3. dialogue method as claimed in claim 1 or 2, which is characterized in that the multiple standard conversation sentence is stored in default
Sentence imports in knowledge base, in step 2, is imported in knowledge base and is retrieved from the default sentence according to the semantic similarity
Obtain the standard conversation sentence corresponding to the dialog information.
4. dialogue method as claimed in claim 3, which is characterized in that according to the entity of the default knowledge mapping and entity it
Between relationship generate the default sentence and import knowledge base.
5. dialogue method as described in claim 3 or 4, which is characterized in that the default sentence, which imports in knowledge base, also to be stored
There is similar conversation sentence associated with the standard conversation sentence to calculate separately the dialog information in the step 2
The semantic similarity of each conversation sentence in knowledge base is imported with the default sentence, if chosen according to the semantic similarity
It obtains being specific similar conversation sentence, then its corresponding standard conversation sentence is determined according to the specific similar conversation sentence.
6. a kind of conversational system for intelligent robot, which is characterized in that the system comprises:
Dialog information obtains module, is used to obtain the dialog information of user's input;
Standard conversation sentence generation module obtains module with the dialog information and connect, for calculating separately the dialogue letter
The semantic similarity of breath and multiple standard conversation sentences determines the mark for corresponding to the dialog information according to the semantic similarity
Quasi- conversation sentence;
Feedback information generation module is connect with the standard conversation sentence generation module, for talking with according to the standard
The semantic understanding of sentence is as a result, generate voice feedback information using default knowledge mapping.
7. conversational system as claimed in claim 6, which is characterized in that the standard conversation sentence generation module is configured to from institute
It states and chooses the maximum sentence of semantic similarity value in multiple standard conversation sentences as the standard for corresponding to the dialog information
Conversation sentence.
8. conversational system as claimed in claims 6 or 7, which is characterized in that the multiple standard conversation sentence is stored in default
Sentence imports in knowledge base, and the standard conversation sentence generation module is configured to according to the semantic similarity from the default language
Sentence imports retrieval in knowledge base and obtains the standard conversation sentence corresponding to the dialog information.
9. conversational system as claimed in claim 8, which is characterized in that it is according to described pre- that the default sentence, which imports knowledge base,
If relationship generates between the entity and entity of knowledge mapping.
10. conversational system as claimed in claim 8 or 9, which is characterized in that the default sentence, which imports in knowledge base, also to be stored
There is similar conversation sentence associated with the standard conversation sentence, the standard conversation sentence generation module is configured to count respectively
It calculates the dialog information and the default sentence imports the semantic similarity of each conversation sentence in knowledge base, if according to described
It is specific similar conversation sentence that semantic similarity, which is chosen, then determines its corresponding mark according to the specific similar conversation sentence
Quasi- conversation sentence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810650049.XA CN109102809B (en) | 2018-06-22 | 2018-06-22 | Dialogue method and system for intelligent robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810650049.XA CN109102809B (en) | 2018-06-22 | 2018-06-22 | Dialogue method and system for intelligent robot |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109102809A true CN109102809A (en) | 2018-12-28 |
CN109102809B CN109102809B (en) | 2021-06-15 |
Family
ID=64844889
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810650049.XA Active CN109102809B (en) | 2018-06-22 | 2018-06-22 | Dialogue method and system for intelligent robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109102809B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109887483A (en) * | 2019-01-04 | 2019-06-14 | 平安科技(深圳)有限公司 | Self-Service processing method, device, computer equipment and storage medium |
CN109920414A (en) * | 2019-01-17 | 2019-06-21 | 平安城市建设科技(深圳)有限公司 | Nan-machine interrogation's method, apparatus, equipment and storage medium |
CN110046238A (en) * | 2019-03-29 | 2019-07-23 | 华为技术有限公司 | Talk with exchange method, graphic user interface, terminal device and the network equipment |
CN110473540A (en) * | 2019-08-29 | 2019-11-19 | 京东方科技集团股份有限公司 | Voice interactive method and system, terminal device, computer equipment and medium |
CN110489740A (en) * | 2019-07-12 | 2019-11-22 | 深圳追一科技有限公司 | Semantic analytic method and Related product |
CN110738982A (en) * | 2019-10-22 | 2020-01-31 | 珠海格力电器股份有限公司 | request processing method and device and electronic equipment |
CN110781277A (en) * | 2019-09-23 | 2020-02-11 | 厦门快商通科技股份有限公司 | Text recognition model similarity training method, system, recognition method and terminal |
CN111508488A (en) * | 2020-04-13 | 2020-08-07 | 江苏止芯科技有限公司 | Intelligent robot dialogue system |
CN111563029A (en) * | 2020-03-13 | 2020-08-21 | 深圳市奥拓电子股份有限公司 | Testing method, system, storage medium and computer equipment for conversation robot |
CN111858865A (en) * | 2019-04-30 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Semantic recognition method and device, electronic equipment and computer-readable storage medium |
WO2021051508A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技(深圳)有限公司 | Robot dialogue generating method and apparatus, readable storage medium, and robot |
CN112612877A (en) * | 2020-12-16 | 2021-04-06 | 平安普惠企业管理有限公司 | Multi-type message intelligent reply method, device, computer equipment and storage medium |
CN112911073A (en) * | 2019-04-30 | 2021-06-04 | 五竹科技(北京)有限公司 | Intelligent knowledge graph construction method and device for outbound process conversation content |
CN113448829A (en) * | 2020-03-27 | 2021-09-28 | 北京奔影网络科技有限公司 | Dialogue robot test method, device, equipment and storage medium |
Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101086843A (en) * | 2006-06-07 | 2007-12-12 | 中国科学院自动化研究所 | A sentence similarity recognition method for voice answer system |
CN101520802A (en) * | 2009-04-13 | 2009-09-02 | 腾讯科技(深圳)有限公司 | Question-answer pair quality evaluation method and system |
CN103810218A (en) * | 2012-11-14 | 2014-05-21 | 北京百度网讯科技有限公司 | Problem cluster-based automatic asking and answering method and device |
US20140229163A1 (en) * | 2013-02-12 | 2014-08-14 | International Business Machines Corporation | Latent semantic analysis for application in a question answer system |
CN104462553A (en) * | 2014-12-25 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for recommending question and answer page related questions |
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
CN105335447A (en) * | 2014-08-14 | 2016-02-17 | 北京奇虎科技有限公司 | Computer network-based expert question-answering system and construction method thereof |
CN105373568A (en) * | 2014-09-02 | 2016-03-02 | 联想(北京)有限公司 | Method and device for automatically learning question answers |
CN105550361A (en) * | 2015-12-31 | 2016-05-04 | 上海智臻智能网络科技股份有限公司 | Log processing method and apparatus, and ask-answer information processing method and apparatus |
US20160203412A1 (en) * | 2014-12-12 | 2016-07-14 | International Business Machines Corporation | Inferred Facts Discovered through Knowledge Graph Derived Contextual Overlays |
CN106202038A (en) * | 2016-06-29 | 2016-12-07 | 北京智能管家科技有限公司 | Synonym method for digging based on iteration and device |
US20160378851A1 (en) * | 2015-06-25 | 2016-12-29 | International Business Machines Corporation | Knowledge Canvassing Using a Knowledge Graph and a Question and Answer System |
CN106407198A (en) * | 2015-07-28 | 2017-02-15 | 百度在线网络技术(北京)有限公司 | Question and answer information processing method and device |
CN106776532A (en) * | 2015-11-25 | 2017-05-31 | 中国移动通信集团公司 | A kind of knowledge question answering method and device |
CN106777232A (en) * | 2016-12-26 | 2017-05-31 | 上海智臻智能网络科技股份有限公司 | Question and answer abstracting method, device and terminal |
CN106847279A (en) * | 2017-01-10 | 2017-06-13 | 西安电子科技大学 | Man-machine interaction method based on robot operating system ROS |
CN106919655A (en) * | 2017-01-24 | 2017-07-04 | 网易(杭州)网络有限公司 | A kind of answer provides method and apparatus |
CN107123042A (en) * | 2017-04-26 | 2017-09-01 | 山东浪潮商用系统有限公司 | A kind of intelligent sound does tax method, apparatus and system |
CN107688608A (en) * | 2017-07-28 | 2018-02-13 | 合肥美的智能科技有限公司 | Intelligent sound answering method, device, computer equipment and readable storage medium storing program for executing |
CN107918640A (en) * | 2017-10-20 | 2018-04-17 | 阿里巴巴集团控股有限公司 | Sample determines method and device |
CN107980130A (en) * | 2017-11-02 | 2018-05-01 | 深圳前海达闼云端智能科技有限公司 | It is automatic to answer method, apparatus, storage medium and electronic equipment |
CN107992472A (en) * | 2017-11-23 | 2018-05-04 | 浪潮金融信息技术有限公司 | Sentence similarity computational methods and device, computer-readable storage medium and terminal |
CN108021555A (en) * | 2017-11-21 | 2018-05-11 | 浪潮金融信息技术有限公司 | A kind of Question sentence parsing measure based on depth convolutional neural networks |
CN108053351A (en) * | 2018-02-08 | 2018-05-18 | 南京邮电大学 | Intelligent college entrance will commending system and recommendation method |
-
2018
- 2018-06-22 CN CN201810650049.XA patent/CN109102809B/en active Active
Patent Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101086843A (en) * | 2006-06-07 | 2007-12-12 | 中国科学院自动化研究所 | A sentence similarity recognition method for voice answer system |
CN101520802A (en) * | 2009-04-13 | 2009-09-02 | 腾讯科技(深圳)有限公司 | Question-answer pair quality evaluation method and system |
CN103810218A (en) * | 2012-11-14 | 2014-05-21 | 北京百度网讯科技有限公司 | Problem cluster-based automatic asking and answering method and device |
US20140229163A1 (en) * | 2013-02-12 | 2014-08-14 | International Business Machines Corporation | Latent semantic analysis for application in a question answer system |
CN105335447A (en) * | 2014-08-14 | 2016-02-17 | 北京奇虎科技有限公司 | Computer network-based expert question-answering system and construction method thereof |
CN105373568A (en) * | 2014-09-02 | 2016-03-02 | 联想(北京)有限公司 | Method and device for automatically learning question answers |
US20160203412A1 (en) * | 2014-12-12 | 2016-07-14 | International Business Machines Corporation | Inferred Facts Discovered through Knowledge Graph Derived Contextual Overlays |
CN104462553A (en) * | 2014-12-25 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for recommending question and answer page related questions |
US20160378851A1 (en) * | 2015-06-25 | 2016-12-29 | International Business Machines Corporation | Knowledge Canvassing Using a Knowledge Graph and a Question and Answer System |
CN106407198A (en) * | 2015-07-28 | 2017-02-15 | 百度在线网络技术(北京)有限公司 | Question and answer information processing method and device |
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
CN106776532A (en) * | 2015-11-25 | 2017-05-31 | 中国移动通信集团公司 | A kind of knowledge question answering method and device |
CN105550361A (en) * | 2015-12-31 | 2016-05-04 | 上海智臻智能网络科技股份有限公司 | Log processing method and apparatus, and ask-answer information processing method and apparatus |
CN106202038A (en) * | 2016-06-29 | 2016-12-07 | 北京智能管家科技有限公司 | Synonym method for digging based on iteration and device |
CN106777232A (en) * | 2016-12-26 | 2017-05-31 | 上海智臻智能网络科技股份有限公司 | Question and answer abstracting method, device and terminal |
CN106847279A (en) * | 2017-01-10 | 2017-06-13 | 西安电子科技大学 | Man-machine interaction method based on robot operating system ROS |
CN106919655A (en) * | 2017-01-24 | 2017-07-04 | 网易(杭州)网络有限公司 | A kind of answer provides method and apparatus |
CN107123042A (en) * | 2017-04-26 | 2017-09-01 | 山东浪潮商用系统有限公司 | A kind of intelligent sound does tax method, apparatus and system |
CN107688608A (en) * | 2017-07-28 | 2018-02-13 | 合肥美的智能科技有限公司 | Intelligent sound answering method, device, computer equipment and readable storage medium storing program for executing |
CN107918640A (en) * | 2017-10-20 | 2018-04-17 | 阿里巴巴集团控股有限公司 | Sample determines method and device |
CN107980130A (en) * | 2017-11-02 | 2018-05-01 | 深圳前海达闼云端智能科技有限公司 | It is automatic to answer method, apparatus, storage medium and electronic equipment |
CN108021555A (en) * | 2017-11-21 | 2018-05-11 | 浪潮金融信息技术有限公司 | A kind of Question sentence parsing measure based on depth convolutional neural networks |
CN107992472A (en) * | 2017-11-23 | 2018-05-04 | 浪潮金融信息技术有限公司 | Sentence similarity computational methods and device, computer-readable storage medium and terminal |
CN108053351A (en) * | 2018-02-08 | 2018-05-18 | 南京邮电大学 | Intelligent college entrance will commending system and recommendation method |
Non-Patent Citations (2)
Title |
---|
公安部第三研究所: "《多摄像机协同关注目标检测跟踪技术》", 30 June 2017 * |
吕学强: "句子相似模型和最相似句子查找算法", 《东北大学学报(自然科学版)》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109887483A (en) * | 2019-01-04 | 2019-06-14 | 平安科技(深圳)有限公司 | Self-Service processing method, device, computer equipment and storage medium |
CN109920414A (en) * | 2019-01-17 | 2019-06-21 | 平安城市建设科技(深圳)有限公司 | Nan-machine interrogation's method, apparatus, equipment and storage medium |
CN110046238A (en) * | 2019-03-29 | 2019-07-23 | 华为技术有限公司 | Talk with exchange method, graphic user interface, terminal device and the network equipment |
CN110046238B (en) * | 2019-03-29 | 2024-03-26 | 华为技术有限公司 | Dialogue interaction method, graphic user interface, terminal equipment and network equipment |
CN111858865A (en) * | 2019-04-30 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Semantic recognition method and device, electronic equipment and computer-readable storage medium |
CN112911073A (en) * | 2019-04-30 | 2021-06-04 | 五竹科技(北京)有限公司 | Intelligent knowledge graph construction method and device for outbound process conversation content |
CN110489740A (en) * | 2019-07-12 | 2019-11-22 | 深圳追一科技有限公司 | Semantic analytic method and Related product |
CN110489740B (en) * | 2019-07-12 | 2023-10-24 | 深圳追一科技有限公司 | Semantic analysis method and related product |
CN110473540B (en) * | 2019-08-29 | 2022-05-31 | 京东方科技集团股份有限公司 | Voice interaction method and system, terminal device, computer device and medium |
US11373642B2 (en) | 2019-08-29 | 2022-06-28 | Boe Technology Group Co., Ltd. | Voice interaction method, system, terminal device and medium |
CN110473540A (en) * | 2019-08-29 | 2019-11-19 | 京东方科技集团股份有限公司 | Voice interactive method and system, terminal device, computer equipment and medium |
WO2021051508A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技(深圳)有限公司 | Robot dialogue generating method and apparatus, readable storage medium, and robot |
CN110781277A (en) * | 2019-09-23 | 2020-02-11 | 厦门快商通科技股份有限公司 | Text recognition model similarity training method, system, recognition method and terminal |
CN110738982A (en) * | 2019-10-22 | 2020-01-31 | 珠海格力电器股份有限公司 | request processing method and device and electronic equipment |
CN110738982B (en) * | 2019-10-22 | 2022-01-28 | 珠海格力电器股份有限公司 | Request processing method and device and electronic equipment |
CN111563029A (en) * | 2020-03-13 | 2020-08-21 | 深圳市奥拓电子股份有限公司 | Testing method, system, storage medium and computer equipment for conversation robot |
CN113448829A (en) * | 2020-03-27 | 2021-09-28 | 北京奔影网络科技有限公司 | Dialogue robot test method, device, equipment and storage medium |
CN111508488A (en) * | 2020-04-13 | 2020-08-07 | 江苏止芯科技有限公司 | Intelligent robot dialogue system |
CN112612877A (en) * | 2020-12-16 | 2021-04-06 | 平安普惠企业管理有限公司 | Multi-type message intelligent reply method, device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109102809B (en) | 2021-06-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109102809A (en) | A kind of dialogue method and system for intelligent robot | |
US9747895B1 (en) | Building language models for a user in a social network from linguistic information | |
WO2023273170A1 (en) | Welcoming robot conversation method | |
US9047868B1 (en) | Language model data collection | |
CN106959839A (en) | A kind of human-computer interaction device and method | |
CN108000526A (en) | Dialogue exchange method and system for intelligent robot | |
CN107728780A (en) | A kind of man-machine interaction method and device based on virtual robot | |
CN107315766A (en) | A kind of voice response method and its device for gathering intelligence and artificial question and answer | |
CN107273477A (en) | A kind of man-machine interaction method and device for robot | |
CN109887484A (en) | A kind of speech recognition based on paired-associate learning and phoneme synthesizing method and device | |
CN106844587B (en) | It is a kind of for talking with the data processing method and device of interactive system | |
WO2020253128A1 (en) | Voice recognition-based communication service method, apparatus, computer device, and storage medium | |
CN106356057A (en) | Speech recognition system based on semantic understanding of computer application scenario | |
CN108536670A (en) | Output statement generating means, methods and procedures | |
WO2022252636A1 (en) | Artificial intelligence-based answer generation method and apparatus, device, and storage medium | |
CN111694940A (en) | User report generation method and terminal equipment | |
CN110795542A (en) | Dialogue method and related device and equipment | |
CN109036467A (en) | CFFD extracting method, speech-emotion recognition method and system based on TF-LSTM | |
JP2022006173A (en) | Knowledge pre-training model training method, device and electronic equipment | |
CN103076893A (en) | Method and equipment for realizing voice input | |
CN106548777A (en) | A kind of data processing method and device for intelligent robot | |
CN111128175B (en) | Spoken language dialogue management method and system | |
Mian Qaisar | Isolated speech recognition and its transformation in visual signs | |
CN110347901A (en) | A kind of searching method and a kind of electronic device using this method | |
CN104679733B (en) | A kind of voice dialogue interpretation method, apparatus and system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |