CN108536672A - Intelligent robot Training Methodology, device, computer equipment and storage medium - Google Patents
Intelligent robot Training Methodology, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN108536672A CN108536672A CN201810200486.1A CN201810200486A CN108536672A CN 108536672 A CN108536672 A CN 108536672A CN 201810200486 A CN201810200486 A CN 201810200486A CN 108536672 A CN108536672 A CN 108536672A
- Authority
- CN
- China
- Prior art keywords
- target
- search
- training
- request
- handout
- 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
- 238000012549 training Methods 0.000 title claims abstract description 204
- 238000000034 method Methods 0.000 title claims abstract description 79
- 238000012360 testing method Methods 0.000 claims description 69
- 230000008569 process Effects 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 17
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000002224 dissection Methods 0.000 claims description 4
- 238000013095 identification testing Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 3
- 238000003058 natural language processing Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 238000013473 artificial intelligence Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000011161 development Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 238000006467 substitution reaction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000001737 promoting effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Electrically Operated Instructional Devices (AREA)
- Manipulator (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of intelligent robot Training Methodology, device, computer equipment and storage medium, methods to include：Obtaining mode selection request, if mode selection request is training speech mode request, into training speech interface, obtain searching request, at least one search key is obtained based on searching request, based at least one search key search training data library, obtains be mutually related target PowerPoint and target handout voice data, display target PowerPoint, while playing and being mutually related target handout voice data with target PowerPoint.Technical scheme of the present invention is treated start-up by using intelligent robot Training Methodology and is giveed training, has achieved the effect that treat start-up according to different demands is trained one by one, to effectively meet the individual demand for waiting for start-up.
Description
Technical field
The present invention relates to field of artificial intelligence more particularly to a kind of intelligent robot Training Methodology, device, computers
Equipment and storage medium.
Background technology
With the continuous social and economic development, artificial intelligence plays increasingly important role in we live.People
Work intelligence (Artificial Intelligence, abbreviation AI), refers to the intelligence showed by the system manually manufactured
Can, artificial intelligence is to study how to produce smart machine or intelligence system, to simulate the movable a special kind of skill of human intelligence.
Intelligent robot is the equipment using artificial intelligence, along with the fast development of artificial intelligence the technology, intelligent robot
In fast development.
With the continuous renewal of knowledge, in order to be better adapted to the development of enterprise, it usually needs carry out profession to worker
Training, this professional training carries out generally by the way of being lectured to more people with PowerPoint by training instructor, and knows now
The renewal speed of knowledge is fast, necessarily determines that the frequency giveed training is getting faster.For example, traditional specialty training (such as customer service training)
It often treats start-up by training instructor to be trained face-to-face, but there is task weight, time and ground for this training method
The problems such as personnel of dumb, the training instructor's scarcity of resources of point and guidance training are limited.Moreover, traditional specialty training is mainly by training
Instruction lecturer treats start-up according to its training program and carries out routine training, cannot be satisfied and each waits for start-up to required for it
The requirement that the knowledge of understanding is trained one by one can not meet the individual demand for waiting for start-up.
Invention content
A kind of intelligent robot Training Methodology of offer of the embodiment of the present invention, device, computer equipment and storage medium, with solution
The problem of certainly traditional specialty training cannot be satisfied the individual demand for waiting for start-up.
In a first aspect, the embodiment of the present invention provides a kind of intelligent robot Training Methodology, including：
Obtaining mode selection request is given a lecture if the mode selection request is training speech mode request into training
Interface；
Searching request is obtained, described search request includes at least one search key；
Based at least one described search keyword search training data library, acquisition be mutually related target PowerPoint and
Target handout voice data；
It shows the target PowerPoint, while playing and being mutually related the target handout with the target PowerPoint
Voice data.
Second aspect, the embodiment of the present invention provide a kind of intelligent robot training device, including：
Mode selection module, for obtaining mode selection request, if the mode selection request is training, speech mode is asked
When asking, into training speech interface；
Searching request acquisition module is closed for obtaining searching request based at least one search of described search acquisition request
Keyword；
Target search module is obtained and is mutually closed for being based at least one described search keyword search training data library
The target PowerPoint and target handout voice data of connection；
It shows broadcasting module, for showing the target PowerPoint, while playing mutual with the target PowerPoint
The associated target handout voice data.
The third aspect, the embodiment of the present invention provide a kind of computer equipment, including memory, processor and are stored in institute
The computer program that can be run in memory and on the processor is stated, the processor executes real when the computer program
The step of existing intelligent robot Training Methodology.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, the computer-readable storage medium
Matter is stored with computer program, and the computer program realizes the step of the intelligent robot Training Methodology when being executed by processor
Suddenly.
The embodiment of the present invention has the following advantages that compared with prior art：Training data library is searched for by intelligent robot,
Acquisition is mutually related target PowerPoint and target handout voice data, allows to wait for that start-up needs according to the training of oneself
It asks, personalized acquisition correlation training contents；It is drilled with target by intelligent robot display target PowerPoint and simultaneously broadcasting
Showing that manuscript is mutually related target handout voice data so that training time, place are more flexible, and the start-up of guidance is more,
It realizes and start-up is trained one by one to be waited for different demands, wait for that the personalized of start-up needs to effectively meet
It asks.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is an implementation flow chart of the intelligent robot Training Methodology that the embodiment of the present invention 1 provides；
Fig. 2 is an implementation flow chart of step S20 in Fig. 1；
Fig. 3 is an implementation flow chart of step S30 in Fig. 1；
Fig. 4 is an implementation flow chart of the intelligent robot Training Methodology provided in the embodiment of the present invention 1；
Fig. 5 is another implementation flow chart of the intelligent robot Training Methodology provided in the embodiment of the present invention 1；
Fig. 6 is the another implementation flow chart of the intelligent robot Training Methodology provided in the embodiment of the present invention 1；
Fig. 7 is a schematic diagram of the intelligent robot training device provided in the embodiment of the present invention 2；
Fig. 8 is a schematic diagram of the computer equipment provided in the embodiment of the present invention 4.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained without creative efforts
Example, shall fall within the protection scope of the present invention.
Embodiment 1
Referring to Fig. 1, Fig. 1 shows the implementation process of intelligent robot Training Methodology provided in this embodiment.The intelligence
Robot Training Methodology is applied in intelligent robot, defeated to be based on user for carrying out human-computer interaction with start-up is waited for
The association requests entered treat start-up and carry out individualized training.In the present embodiment, to apply the customer service in insurance financial industry
Training illustrates.Details are as follows：
A kind of intelligent robot Training Methodology includes the following steps executed by intelligent robot：
S10：Obtaining mode selection request is given a lecture if mode selection request is training speech mode request into training
Interface.
Wherein, mode selection request refers to the request for entering corresponding modes for controlling intelligent robot.
In the present embodiment, the demand of business nature and professional training previously according to different industries sets different training moulds
Formula, such as training speech mode, practical operation rehearsal pattern and class-exercise pattern.
Specifically, training speech mode mainly shows related courseware by intelligent robot and treats training by way of speech
Instruction personnel give explanation training, this training pattern theoretical property is strong, and knowledge point is concentrated, with strong points, convenient for waiting for that start-up is quick
Receive itself it should be understood that knowledge.
Practical operation rehearsal pattern is mainly that the scene of simulation relevant issues is provided by intelligent robot, treats start-up's progress
It does simulated exercises, this training pattern scene sense is strong, deepens the memory for waiting for start-up by interaction mode.
Class-exercise pattern is to show related exercise according to curricular advancement by intelligent robot, to treat start-up's progress
Examination or training, consolidation wait for the knowledge that start-up receives.
It should be noted that due to insurance financial industry customer service training relate generally to its business essential information training and
Seat communication skill training, therefore the pattern configurations of intelligent robot training in the present embodiment illustratively train speech mode
Pattern is drilled with practical operation.
Wherein, training speech interface is to be arranged on intelligent robot for the interface for user's operation, and train and drill
Say the initial program interface of pattern.When intelligent robot obtains the mode selection request of training speech mode of user's selection,
Training speech interface is entered, system starts the initial program of training speech mode.
It is to be appreciated that intelligent robot passes through previously according to the business nature of different industries, professional training or other need
It asks and different training pattern is set, so that each wait for that start-up can be according to the demand combination training progress of oneself from primary input
Corresponding mode selection request waits for start-up's personalization so that intelligent robot enters different training patterns to meet
Demand.
Further, user need to first pass through client and be registered on corresponding training webpage in advance, and succeed in registration
Afterwards, it is based on its corresponding user account and password login intelligent robot, intelligent robot is after user logins successfully every time, base
It is interacted with user in the user information of advance typing.For example, the address extended using the name of user and gender in appellation, is made
Human-computer interaction more has substitution to feel.Also, intelligent robot can be adjusted from its corresponding database for storing user information
It is recorded with the studying history of each user account, and can be recorded based on the last studying history and be pushed away into row information to user
Recommend, different training patterns can be specifically selected with recommended user, can also recommended user select different coursewares or other and training
Relevant information, so that user can efficiently be learnt in training and learning in conjunction with the study schedule of itself.
S20：Searching request is obtained, which includes at least one search key.
In embodiments of the present invention, searching request is the knowledge point that user wants the acquisition that intelligent robot is sent training
Request.Searching request can be that user is asked using the phonetic search of sound pick-up outfit (such as microphone) input or user is using defeated
Enter the text search request of equipment (such as keyboard) input, the input side of element request can be searched according to the autonomous selection of custom of user
Formula.As its name suggests, phonetic search request is voice-based searching request, and text search request is that the search based on word is asked
It asks.
Specifically, it includes at least one and the relevant search key of training contents to search element request.Wherein, search key
It is the keyword of training knowledge point extraction of the user according to desired acquisition.For example, user wants to obtain the electricity for promoting vehicle insurance business
Words training, then the keyword of its extraction can be vehicle insurance sale, vehicle insurance business etc..It is to be appreciated that the search key can be with
It is voluntarily refined by user and is input to intelligent robot to form searching request, can also inputted by user defeated using natural language
The search statement entered carries out keyword extraction by keyword extraction algorithm built in intelligent robot, with obtain it is corresponding extremely
A few search key.
S30：Based at least one search key search training data library, acquisition be mutually related target PowerPoint and
Target handout voice data.
Wherein, training data library is the database for storing material for training, is specifically stored with the phase for prerecording collection
The handout voice data and PowerPoint of mutual correlation.The database can be MySQL database, oracle database or other
Database.In the present embodiment, at least one search key and corresponding search logic connector (such as and, not can be based on
And or) search type is formed, training data library is scanned for based on the search type, to obtain and at least one search key pair
Be mutually related target PowerPoint and the target handout voice data answered.
PowerPoint includes the text that PPT, video and picture etc. can be demonstrated by the display screen of intelligent robot
Original text.Handout voice data may include not only the audio file that explaining illustration is carried out to PPT, video and picture etc., can also wrap
Include the audio file explained to documents such as paper, textbook and exercises.
The target that is mutually related PowerPoint and target handout voice data specifically refer to each of the target PowerPoint
Presentation page is correspondingly configured with the target handout voice data explained to the content of the presentation page.
It is to be appreciated that prestoring be mutually related handout voice data and PowerPoint in training data library, only need
According at least one of searching request input by user search key, using simple search query operation, you can obtain
Corresponding be mutually related target PowerPoint and target handout voice data, operating process is simple and convenient, moreover, interrelated
Handout voice data and PowerPoint start-up's repeat search can be waited for, it can be achieved that primary record repeatedly makes by different
Purpose so that the dependence to training instructor can be greatly decreased in training process, reduce training cost.
S40：Display target PowerPoint, while playing and being mutually related target handout voice number with target PowerPoint
According to.
Specifically, intelligent robot is after acquisition is mutually related target PowerPoint and target handout voice data,
Pass through the player or external playback equipment progress speech play built in intelligent robot；Meanwhile target PowerPoint passes through intelligence
The included screen of energy robot carries out display or by being shown on projector to large screen.It is this in display target
While PowerPoint, the target handout voice data that is mutually related is played, intelligent robot can be made to treat start-up's progress
The process of training is felt with more substitution so that waits for that start-up more easily receives the knowledge to be trained.
In a specific embodiment, by the associated program built in intelligent robot, by PowerPoint and handout language
Sound data are interrelated, and the page iden-tity that a certain page is demonstrated according to the PowerPoint is associated with matched handout voice
Data play the presentation page and are mutually related handout voice data while playing demonstration document a certain presentation page.Example
Such as, if intelligent robot is currently shown in the N pages of a certain target PowerPoint, according to associated program, intelligent robot is same
When play the target handout voice data to match with the N pages presentation page.
In the intelligent robot Training Methodology that the embodiment of the present invention is provided, the search autonomous by controlling intelligent robot
Training data library, according to the target PowerPoint needed for the demand selection of start-up and target handout voice data is waited for, with patch
Close the individual demand for waiting for start-up.And by intelligent robot display target PowerPoint and play target handout voice simultaneously
Data, to realize that treating start-up gives training so that training process is more flexible, and reduces the training pressure of training instructor,
Solves the problems, such as training instructor's scarcity of resources.The intelligent robot Training Methodology to different demands, it can be achieved that wait for trainer
Member carries out one-on-one training, can more easily carry out training, be more suitable for the development of enterprise.
In a specific embodiment, as shown in Fig. 2, in step S20, that is, searching request is obtained, searching request includes extremely
A few search key, specifically comprises the following steps：
S201：Phonetic search request is obtained, phonetic search request includes target voice search data.
As its name suggests, phonetic search request is voice-based searching request, i.e., in the present embodiment, intelligent robot
Data are searched for the target voice for obtaining user by acquiring and identifying the voice of user.Step S201 specifically uses following steps
It obtains target voice and searches for data：
First, intelligent robot searches for data using microphone array acquisition raw tone.Raw tone searches for data
Refer to the intelligent robot voice data collected but untreated by microphone array, which searches comprising voice
The relevant information of rope request.Wherein, microphone array uses distributive array, can be by submatrix member or submatrix Column Layout to bigger
In the range of so that submatrix member or subarray by wired or wirelessly progress data exchanges and are total between each other
It enjoys, and carries out the technologies such as sensu lato auditory localization and Wave beam forming on this basis and realize signal processing.
Then, after microphone array collects raw tone search data, intelligent robot uses dereverberation algorithm
Raw tone search data are further processed, prime number evidence is searched to obtain target voice.
Further, dereverberation algorithm is using method (the Beamforming based based on Wave beam forming
Approach), the signal for data being searched for by the raw tone collected to microphone array is weighted processing, in raw tone
The sense for searching for data forms a pickup wave beam, while the reflected sound from other directions of decaying.Based on Wave beam forming
Method, i.e., by being respectively formed pickup wave beam to the sound source of different directions, and inhibit the sound in other directions, to original
Phonetic search data are extracted or are detached, and data are searched for obtain target voice.
It refers to that intelligent robot is acquired by microphone array that target voice, which searches for data, using dereverberation algorithm from original
The voice data that phonetic search extracting data arrives, target voice search data contain the information that voice searches element request.It can be with
Understand ground, it, can be in a wider context from the original language in multi-faceted acquisition space by the distributive array of microphone array
Sound searches for data so that intelligent robot obtains the range bigger of user speech searching request, more conducively receives phonetic search and asks
It asks.Data are searched for from raw tone search extracting data target voice using dereverberation algorithm, it can be more accurately from original
Phonetic search extracting data goes out target voice search data, obtains the information that more accurate voice searches element request.
S202：Conversion process is carried out to target voice search data using preset speech recognition system, word is obtained and searches
Rope data.
Wherein, speech recognition system is voice to be transformed into using built-in speech recognition algorithm the system of word.At this
In embodiment, intelligent robot calls preset speech recognition system to the mesh after receiving target voice search data
Mark phonetic search data are handled, to obtain text search data.
S203：Dissection process is carried out to text search data using the libraries NLP, obtains at least one search key.
Wherein, NLP (Natural Language Processing, natural language processing) library is one of artificial intelligence
Natural language processing database is for the database by natural language parsing matching for the machine language of computer capacity identification.
The Stanford CoreNLP of Stamford natural-sounding processing team exploitation may be used in the libraries NLP, can quickly be searched to word
Rope data carry out dissection process, to obtain at least one search key.
Based on step S201-S203, intelligent robot will acquire voice input by user by built-in microphone array
Searching request, and using speech recognition system phonetic search is asked in target voice search data be transformed into text search number
According to, and the text search data are uploaded into the libraries NLP and carry out semantic parsing, in order to conveniently and efficiently obtain at least one search
Keyword.Based on the corresponding search key of phonetic search acquisition request, user can be made to select the input of voice input mode
Searching request, operating process are simple and convenient, it is easier to meet the needs of users.
In another specific implementation mode, searching request may include that user passes through the input equipments such as keyboard and/or mouse
The text search data of input.Specifically, intelligent robot obtains what user was inputted by input equipments such as keyboard and/or mouses
Text search data, then the text search data are parsed using the libraries NLP, at least one search key is obtained, is located
Reason process is identical as step S203, to avoid repeating, no longer describes one by one.It is defeated using input equipments such as the keyboard and/or mouses
Enter the mode of searching request, can accurately input searching request, improves search accuracy.
In a specific embodiment, as shown in figure 3, in step S30, that is, it is based on the search training of at least one search key
Database is instructed, be mutually related target PowerPoint and target handout voice data is obtained, specifically comprises the following steps：
S301：Using each search key as search field, at least one search field is carried out using logical relation
Processing forms target search formula.
Specifically, after extracting at least one search key based on searching request, at least one search key,
It is combined using corresponding logical relation (and/or/non-etc.), as target search formula.
Wherein, multiple search keys are scanned for using logical relation combination, the search range smaller determined is searched
The accuracy higher of rope can more quickly search the information of needs.
S302：Based on target search formula search training data library, search result list, search result list are obtained and shown
Including at least one basic courseware-related information, each basis courseware information includes basic courseware ID, be mutually related basis demonstration text
Original text and basic handout voice data.
Wherein, basic courseware-related information is the courseware-related information being stored in advance in training data library.Basic courseware ID is to be used for
The mark of unique identification basis courseware-related information, the mark can be storage location of the basic courseware-related information in training data library.
Each basis courseware ID and corresponding basic courseware information association, corresponding base is quickly found to be based on basis courseware ID
Plinth courseware-related information.In the present embodiment, basic PowerPoint and basic handout voice data are interrelated, so as to subsequently in display base
On the basis of plinth PowerPoint, basic handout data are played, the substitution sense of its training process is improved.
In embodiments of the present invention, the method that fuzzy matching may be used searches for training data library based on target search formula,
To obtain and show search result list, also, the basic courseware-related information that matching degree is higher, priority is bigger, is tied in search
Sequence in fruit list is more forward so that waits for that start-up can be quickly found out the class for oneself most thinking training according to the demand of oneself
Part information.
S303：Search result selection request is obtained, search result selection request includes target courseware ID.
Search result selection request refers to that the selection of one of them is selected to ask from search result list.Target courseware ID
Refer to the corresponding basic courseware ID of basic courseware-related information of user's selection, wherein the basic courseware-related information that user selects is target
Courseware-related information, target courseware ID are the mark of the target courseware-related information.In the present embodiment, search result selection request can be
The selection that the selection request of sound pick-up outfit (such as microphone) typing carried by intelligent robot is either inputted by keyboard
Request can also be using mouse drag or to click the selection request inputted by the way of selection, to choose required target class
Part ID, the above input mode is easy to operate, is easily achieved and operates accuracy height, can meet the different operations for waiting for start-up
Custom is more advantageous to the satisfaction for improving and waiting for start-up.
S304：Corresponding target courseware-related information is found based on target courseware ID, obtains the target demonstration text that is mutually related
Original text and target handout voice data.
Wherein, target courseware ID can be directed toward the storage location of target courseware-related information, associated with the information of target courseware,
Therefore, the storage location of target courseware-related information can be linked to according to target courseware ID, it is corresponding with invocation target courseware-related information
The target that is mutually related PowerPoint and target handout voice data.It specifically, can be when obtaining target PowerPoint, automatically
It calls and is mutually related target handout voice data with target PowerPoint；Can also when obtaining target handout voice data,
Automatic call is mutually related target PowerPoint with target handout voice data.
It further, should if there is no the target courseware-related information needed for user's (waiting for start-up) in search result list
Intelligent robot produces prompting message so that the prompting message is sent to the corresponding mailbox of pre-set administrative staff,
To remind administrative staff to supplement the basic courseware-related information such as corresponding PowerPoint and handout voice data, subsequently to be supplemented
Corresponding basis courseware-related information so that the training contents in training data library are more perfect.
Further, the training data library in intelligent robot networking the case where can real-time update, to extend knowledge
Face, convenient for preferably meeting the needs of waiting for start-up.
In step S301-S304, at least one search key can be based on and obtain target search formula, and searched conducive to the target
Cable-styled search training data library, to obtain and show the search result list for including at least one basic courseware-related information, so as to wait for
Start-up can be by consulting the search result list, and the relevant information in knowledge point of training is more wanted in understanding with oneself, and
Carry out individualized selection.Also, after showing search result list, multiple input modes input search result choosing may be used
Request is selected, to obtain target courseware-related information, so that it is determined that the courseware-related information of individualized selection, operating process is simple and convenient, is easy to
It realizes and accuracy is high.
In a specific embodiment, training data is searched for based at least one search key what step S30 was referred to
Before the step of library, intelligent robot Training Methodology further includes following steps：
S31：Training data library is created, at least one basic courseware-related information, each basis courseware are stored in training data library
Information includes basic course part ID, be mutually related basic PowerPoint and basic handout voice data.
In the present embodiment, it is pre-created training data library, in order to wait for that start-up can be quick by searching request
Corresponding be mutually related target PowerPoint and target handout voice data are selected, subsequently target demonstration is being demonstrated to realize
Manuscript simultaneously plays target handout voice data simultaneously so that its operating process is simple and convenient, it is easier to which satisfaction waits for start-up's
Individual demand.
Further, include the following steps as shown in figure 4, creating training data library (i.e. step S31)：
S311：Obtain at least one basic PowerPoint and at least one basic handout voice data, each basis demonstration
Manuscript includes at least one presentation page.
Wherein, basic PowerPoint refers to prerecording be collected and stored in training data library training-related to drill
Show that manuscript, basic handout voice data refer to prerecording the training-related voice being collected and stored in training data library
Data.Presentation page refers to constituting the content page of PowerPoint.Basic PowerPoint may include at least one presentation page,
Screen for being carried by intelligent robot carries out display or is shown by external projecting apparatus.
S312：By each presentation page and a basic handout voice data associated configuration, so that each presentation page is shown
When play and be mutually related basic handout voice data.
Specifically, each presentation page is corresponding with the basic handout language that explaining illustration is carried out to the content of its presentation page
Sound data.By the associated program built in intelligent robot, by presentation page and the content of its presentation page is carried out saying explanation
Bright basic handout voice data is associated, in training process, while being shown to a certain presentation page, plays the basis and says
Adopted voice data to the content of presentation page to carry out explaining illustration, conducive to waiting for that start-up preferably learns and understand the demonstration
The knowledge point of the page.
In the present embodiment, by each presentation page and a basic handout voice data associated configuration, in order to wait training
The base that explaining illustration is carried out to the presentation page can be played simultaneously in a certain presentation page of display target PowerPoint in personnel
Plinth handout voice data.In step S311-S312, matched by making each presentation page be associated with a basic handout voice data
It sets, so that subsequently in vision and acoustically cooperation, the knowledge to be trained of more vivid displaying are more conducive to wait training in real time
Personnel learn and understand.
Further, each presentation page and a basic handout voice data associated configuration are specifically included in step S312
Following steps：
S3121：Into associated configuration interface, manuscript selection request is obtained, manuscript selection request includes manuscript mark.
Wherein, associated configuration interface is the intelligence when presentation page and the incidence relation of basic handout voice data is arranged
The interactive interface operated for user shown in robot.Manuscript selection request refers to being associated required for user's selection
The request of the PowerPoint of configuration.Manuscript mark is the mark for determining PowerPoint to be selected, can be demonstration text
The title of original text, can also be storage address of the PowerPoint in training data library or other can be associated with the mark of PowerPoint
Deng.
S3122：According to the corresponding basic PowerPoint of manuscript mark selection, display base PowerPoint corresponding at least one
A presentation page.
Specifically, it after selecting corresponding basic PowerPoint according to the manuscript mark in manuscript selection request, is being associated with
At least one presentation page that the basis PowerPoint is shown on configuration interface, to configure corresponding base for each presentation page
Plinth handout voice data.
S3123：Association selection request is obtained, association selection request includes page iden-tity and voice identifier.
Wherein, association selection request is for saying the corresponding basis of any presentation page in basic PowerPoint
The request that adopted voice data associates.Each presentation page of basic PowerPoint is both provided with page iden-tity (page mark
Know to be identified by manuscript and be formed with the page number), to determine corresponding presentation page based on the page iden-tity.Voice identifier is to use
The mark of basic handout voice data in unique identification training data library.Intelligent robot is receiving association selection request
Afterwards, page iden-tity and voice identifier with incidence relation in association selection request can be obtained, so as to its follow-up each page mark
Know corresponding presentation page basic handout voice data corresponding with its to be associated with.
Further, selection mode is selected to input association selection request, input mode spirit using dragging selection mode or hook
It is living, the more convenient pass relationship for configuring be mutually related basic PowerPoint and basic handout voice data.
S3124：According to page iden-tity and voice identifier, each presentation page is associated with a basic handout voice data and is matched
It sets, so as to play the basic handout voice data that is mutually related when each basis presentation page display.
Specifically, by the way that the page iden-tity of each presentation page and the voice identifier of basic handout voice data to be associated in
Together, when showing a certain presentation page, basic handout voice data is played according to its associated voice identifier.
Based on step S3121-S3124, by each presentation page and the basic handout language for carrying out explaining illustration to its content
Sound data are interrelated so that when showing each demonstration interface, the basic handout voice data of explaining illustration is played simultaneously, it can
It realizes when interface is demonstrated in switching, it is synchronous to automatically switch corresponding basic handout voice data so as to be demonstrated in training process
The content synchronization of content and explanation.
In a specific embodiment, in training process, wait for that start-up may say intelligent robot training process
The knowledge point of solution is not understood, in order to enable result of training is more preferable, the training process of intelligent robot need to be made configured with solution in real time
Answer the function that user's (waiting for start-up) proposes problem.Therefore, after the step s 40, i.e. display target PowerPoint, simultaneously
Play with target PowerPoint be mutually related target handout voice data the step of after, as shown in figure 5, the intelligent robot
Training Methodology further includes following steps：
S411：It obtains and puts question to request, enquirement request includes at least one enquirement keyword.
Wherein, it refers to that user's (waiting for start-up) wants intelligent robot transmission in training process to put question to request
The request putd question to for specific problem.In the present embodiment, it can be that user uses sound pick-up outfit (such as to put question to request
Microphone) input voice put question to request, can also be that user is carried by the word that the input equipments such as keyboard and/or mouse input
Ask request, processing procedure such as step S20 is almost the same, does not repeat one by one herein.
S412：Based at least one enquirement keyword search training data library, obtain and at least one enquirement keyword phase
Corresponding reply data, it includes reply voice data to reply data.
Wherein, it refers to the answer data replied for the enquirement of particular problem user to reply data.Reply voice
Data are the voice data in the answer data replied the enquirement of user.In embodiments of the present invention, it is based at least one
It is a to put question to the process in keyword search training data library and step S30 almost the same, it does not repeat one by one herein.
S413：Based on the broadcasting for puing question to request to suspend target handout voice data, and play reply voice data.
Specifically, intelligent robot is used during display target PowerPoint and broadcasting target handout voice data
Family can propose problem with regard to oneself unapprehended knowledge point, intelligent robot after the enquirement request for receiving user's proposition, according to
After puing question at least one of request that keyword search is putd question to obtain corresponding reply voice data, current target need to be stopped and said
The explanation of adopted voice data, and the reply voice data got are played, user's (waiting for start-up) is replied in real time to realize
The purpose of the problem of proposition improves the substitution sense of training process.
It is to be appreciated that after playing reply voice data in step S413, it need to be temporary from target handout voice data
Stop place to continue to play target handout voice data, to ensure the continuity of training process.
Based on step S411-S413, intelligent robot puts question to keyword by obtaining the enquirement request extraction of user, to search
Rope training data library obtains corresponding reply voice data, suspends the broadcasting of target handout voice data and plays reply voice number
According to the query of Real-time Answer user, encountering unapprehended knowledge point in training process to user and explained in detail, is convenient for
User, which is better understood from, absorbs the knowledge to be trained, and enhances the interactivity in training process.
Further, in step S413 based on put question to ask pause target handout voice data broadcasting, specifically include as
Lower step：
S4131：Whether the currently playing sentence of detection target handout voice data finishes.
Specifically, the program built in intelligent robot is sentenced according to the energy of the currently playing sentence of target handout voice data
Whether the currently playing sentence that breaks finishes.Wherein, each sentence of target handout voice data has accordingly after finishing
Pause, be when pause it is mute, energy less than it is non-stop when the energy that plays of sentence.
S4132：If detecting that currently playing sentence is played to finish, suspend broadcasting for the target handout voice data
It puts.
It after getting reply voice data, detects that currently playing sentence is played to be finished, then suspends the target language
The broadcasting of sound data.
S4133：If detecting, currently playing sentence does not finish, continue play finished to the sentence after,
The operation for the broadcasting for suspending the target handout voice data is executed again.
After getting reply voice data, detects currently playing sentence and do not finish also, then continue to play
Finish the sentence, until when detecting that the energy of currently playing sentence determines that it is pause, then suspend the target handout voice data,
The step of reply voice data being played so as to subsequent execution.
Based on step S4131-S4133, by intelligent robot before playing reply voice data, target handout is detected
Whether the currently playing sentence of voice data finishes, to ensure to be returned again after currently playing sentence finishes
The broadcasting of multiple voice data, to ensure that the integrality of currently playing sentence so that currently playing sentence can play
Finish so that user can listen to the complete sentence, be easy to understand the meaning of sentence expression.
Specifically, it can also includes replying PowerPoint to reply data.Wherein, it is the enquirement to user to reply PowerPoint
PowerPoint data in the answer data replied.
Further, the broadcasting of pause target handout voice data is asked based on enquirement in step S413, and play back
Multiple voice data, further includes following steps：
S4134：PowerPoint will be replied and cover the target PowerPoint currently shown, and is complete in reply voice data playback
Cheng Hou returns to the target PowerPoint currently shown, continues the broadcasting of target handout voice data.
Specifically, when reply data include reply voice data and reply PowerPoint, PowerPoint covering will be replied and worked as
The target PowerPoint of preceding display, and reply voice data are played, vividly answer in more detail and intuitively the problem of user proposes.
After obtaining answer the problem of user proposes, intelligent robot returns to the target PowerPoint currently shown, continues target handout
The broadcasting of voice data, to continue current training so that training process is very flexible, adapts to user personalizedly to training
The degree of understanding of knowledge point is instructed, user is helped preferably to grasp trained knowledge.
In the present embodiment, it is carried out in real time by treating the enquirement request of start-up's input in the case where training speech mode
It replys, can obtain in real time and wait for that the difficult of start-up puts question to and provide reply data in real time, training speech mode can be solved in time
In wait for the doubt of start-up, detailed emphasis explanation is carried out to unapprehended problem and knowledge point, enhance intelligent robot with
The interactivity of user so that training process is more flexible.
In a specific embodiment, as shown in fig. 6, the step of obtaining mode that step S10 is referred to selects request it
Afterwards, the intelligent robot Training Methodology is further comprising the steps of：
S111：Obtaining mode selection request is drilled if mode selection request is practical operation rehearsal mode request into practical operation
Interface.
In embodiments of the present invention, practical operation rehearsal pattern is intelligent robot and waits for the pattern of start-up's interaction practice,
Set a question by intelligent robot and treats start-up's progress practical operation examination, this training pattern strong sense of reality, with actual field
It is tightly combined, is conducive to improve the learning interest for waiting for start-up, practical application effect is good, waits for start-up's suitable for examining
Acquisition of knowledge degree.
S112：It obtains rehearsal mode to select to ask, and request search training data library is selected based on rehearsal mode, obtain and survey
Why roll up, test questionnaire includes at least one test problem.
As its name suggests, test questionnaire is specifically referred to according to relevant content is trained, and test waits for the acquisition of knowledge of start-up
The questionnaire of degree.Test problem is specifically referred to according to the relevant curriculum offering of training for testing the knowledge point for waiting for start-up
The problem of.
In this specific embodiment, rehearsal mode may include that scrnario testing mode, random test mode and examination are surveyed
Examination mode.Wherein, scrnario testing mode is to wait for that start-up independently selects certain pre-set scene to practice, this mode
It can be adjusted according to the study schedule of start-up is waited for, in favor of reinforcing remembering.Random test mode is that system is selected at random
Scene, for waiting for that start-up tests, this mode is conducive to the ability of adjusting to changed conditions that training waits for start-up.Examination test side
Formula is to wait for start-up according to a variety of test exercises of the training contents set of records ends of start-up are waited for and tested with taking an exam, this
Mode is conducive to wait for that start-up detects oneself to mastery of knowledge degree.
S113：Test reply message input by user is obtained, test reply message includes and at least one problem identification phase
Corresponding test answers.
Wherein, problem identification is the mark for the corresponding test problem of unique identification, which can be associated with survey
Why inscribe and corresponding model answer.Test reply message can be the language that user uses sound pick-up outfit (such as microphone) input
Sound reply message can also be the word reply message that user is inputted by input equipments such as keyboard and/or mouses, process
Journey such as step S20 is almost the same, does not repeat one by one herein.
Specifically, in nan-machine interrogation's conversational mode, intelligent robot preserves the practical operation rehearsal practice process of user in real time
In voice response information, and by the Content Transformation of voice response information be test reply message.
S114：Corresponding model answer is called based on problem identification, each survey is obtained according to test answers and model answer
The test score value why inscribed.
Further, test answers corresponding at least one problem identification in the test reply message of user are distinguished
Corresponding model answer is matched, and is given a mark to test reply message according to the matching degree of correlation, when matching does not need
Each word is the same, it is only necessary to fuzzy matching success keyword can score, it is higher that higher its of the matching degree of correlation tests score value.
In the present embodiment, user selects practical operation to drill pattern, the rehearsal mode that intelligent robot is selected according to user
In test questionnaire report test problem, each test problem corresponds to a problem identification.Then, user is being obtained based on the survey
Why after the test reply message of topic input, corresponding at least one model answer is searched based on problem identification, each standard is answered
Case corresponds to the test score value of different stage respectively.By test corresponding at least one problem identification in the test reply message
Corresponding model answer is matched respectively for answer.Finally, further according to matching result, judge the corresponding survey of the test answers
Score value is tried, test score value is provided to this test questionnaire, the result based on test score value provides relevant study and suggests.
Wherein, the model answer of the pre-configured all test problems in training data library, a test problem can configure
Multiple standards answer is not unique, as long as the test reply message that user's practical operation is answered when drilling can match pass therein
Keyword, you can score.
In a specific embodiment, for example, in practical operation rehearsal pattern, select rehearsal mode for scrnario testing mode,
Setting is selected as the scene for promoting vehicle insurance, and test problem is directed to for intelligent robot and waits for that the sale call of start-up is refused
Associated analog scene.Wait for that start-up transfers to sale call, intelligence machine human simulation refusal type to reply according to test problem：
" I am now busy, has no time ".If at this point, waiting for that if the reply that start-up provides is：" good, that next time is chatted again ", then it is intelligent
The voice response information is first carried out language conversion by robot
Test answers matched with model answer.Specifically, preset model answer is that requirement waits for trainer in training data library
Member reservation client, inquires next free time, and this waits for that the test answers of start-up are not directed to the pass of the model answer
Key point, then this wait for that the test score value of start-up is relatively low.In another example if waiting at this time, the reply that start-up provides is：" good
, shyly, it may I ask when you have time, I sends a telegram here to you next time again", then the test reply message refers to inquire
The next time, according to fuzzy matching keyword, then this waits for that start-up can obtain relatively high test score value.The present embodiment
In, inquire that there are many next time mode, these needs all configure in the answer in training data library in advance, as long as relevant pass
Keyword can fuzzy matching be obtained with corresponding test score value.
In the present embodiment, in such a way that mode setting difference rehearsal is drilled in practical operation, convenient for for waiting for that start-up selects
Suitable training pattern fully meets the individual demand for waiting for start-up, and according to the progress and content of training, image processor is surveyed
Why roll up, in order to consolidate the knowledge of training, the interaction mode of man-machine answer is conducive to improve and waits for that the study of start-up is emerging
Interest, practical application effect is good, and the test answers for treating start-up carry out the judgement of test score value, wait training convenient for examining
Acquisition of knowledge degree of the personnel after training is given a lecture.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Embodiment 2
Corresponding to the intelligent robot Training Methodology in embodiment 1, Fig. 7 shows the intelligence machine provided with embodiment 1
The one-to-one intelligent robot training device of people's Training Methodology.For convenience of description, it illustrates only and phase of the embodiment of the present invention
The part of pass.
Referring to Fig. 7, the intelligent robot training device includes：Mode selection module 10, searching request acquisition module 20,
Target search module 30 and display broadcasting module 40.
Mode selection module 10, for obtaining mode selection request, if mode selection request is training speech mode request
When, into training speech interface.
It is crucial to obtain at least one search for obtaining searching request based on searching request for searching request acquisition module 20
Word.
Target search module 30, for based at least one search key search training data library, obtaining interrelated
Target PowerPoint and target handout voice data.
It shows broadcasting module 40, is used for display target PowerPoint, while playing and being mutually related with target PowerPoint
Target handout voice data.
Preferably, searching request acquisition module 20 includes：Voice searches plain acquisition request unit 201, voice data conversion list
Member 202 and lteral data resolution unit 203.
Voice searches plain acquisition request unit 201, and for obtaining phonetic search request, phonetic search request includes target voice
Search for data.
Voice data converting unit 202, for being carried out to target voice search data using preset speech recognition system
Conversion process obtains text search data.
Lteral data resolution unit 203 obtains at least for carrying out dissection process to text search data using the libraries NLP
One search key.
Preferably, target search module 30 includes：Logical processing unit 301, courseware search unit 302, search result choosing
Select unit 303 and target courseware acquiring unit 304.
Logical processing unit 301 is used for using each search key as search field, using logical relation at least one
A search field is handled, and target search formula is formed.
Courseware search unit 302, for based on target search formula search training data library, obtaining and showing that search result arranges
Table, search result list include at least one basic courseware-related information, and each basis courseware information includes basic courseware ID, mutually closes
The basic PowerPoint of connection and basic handout voice data.
Search result selecting unit 303, for obtaining search result selection request, search result selection request includes target
Courseware ID.
Target courseware acquiring unit 304 finds corresponding target courseware-related information for being based on target courseware ID, obtains phase
The target PowerPoint and target handout voice data of mutual correlation.
Preferably, which further includes：Training data library creation module 31, for creating training number
According to library.
Training data library creation module 31 includes：Data obtain unit 311 and associated configuration unit 312.
Data obtain unit 311, for obtaining at least one basic PowerPoint and at least one basic handout voice data,
Each basis PowerPoint includes at least one presentation page.
Associated configuration unit 312 is used for by each presentation page and a basic handout voice data associated configuration, so that often
The basic handout voice data that is mutually related is played when one presentation page is shown.
Preferably, which further includes puing question to answer module 41.
It includes puing question to acquisition request unit 411, put question to search unit 412 and replying data answering list to put question to answer module 41
Member 413.
Acquisition request unit 411 is putd question to, request is putd question to for obtaining, enquirement request includes that at least one enquirement is crucial
Word.
Search unit 412 is putd question to, for being based at least one enquirement keyword search training data library, is obtained and at least one
A corresponding reply data of enquirement keyword, it includes reply voice data to reply data.
Data answering unit 413 is replied, the broadcasting for asking pause target handout voice data based on enquirement, and play
Reply voice data.
Preferably, which further includes practical operation rehearsal module 11.
Practical operation rehearsal module 11 is obtained including mode selecting unit 111, rehearsal mode selecting unit 112, test reply message
Take unit 113 and test score value acquiring unit 114.
Mode selecting unit 111, for obtaining mode selection request, if mode selection request, which is practical operation, drills mode request
When, drill interface into practical operation.
Rehearsal mode selecting unit 112 selects to ask for obtaining rehearsal mode, and selects request to search based on rehearsal mode
Rope training data library obtains test questionnaire, and test questionnaire includes at least one test problem.
Reply message acquiring unit 113 is tested, for obtaining test reply message input by user, tests reply message packet
Include test answers corresponding at least one problem identification.
Test score value acquiring unit 114, for calling corresponding model answer based on problem identification, according to test answers and
Model answer obtains the test score value of each test problem.
Each module realizes the process of respective function in intelligent robot training device provided in this embodiment, specifically refers to
The description of previous embodiment, details are not described herein again.
Embodiment 3
The present embodiment provides a computer readable storage medium, computer journey is stored on the computer readable storage medium
Sequence realizes intelligent robot Training Methodology in embodiment 1, to avoid repeating, here when the computer program is executed by processor
It repeats no more.Alternatively, realizing in embodiment 2 each list in intelligent robot training device when the computer program is executed by processor
The function of member/module, to avoid repeating, which is not described herein again.
The computer readable storage medium may include：Can carry the computer program code any entity or
Device, recording medium, USB flash disk, mobile hard disk, magnetic disc, CD, computer storage, read-only memory (Read-Only
Memory, ROM), random access memory (Random Access Memory, RAM), electric carrier signal, telecommunication signal and
Software distribution medium etc..
Embodiment 4
Fig. 8 is the schematic diagram for the computer equipment that one embodiment of the invention provides.As shown in figure 8, the calculating of the embodiment
Machine equipment 80 includes：Processor 81, memory 82 and it is stored in the calculating that can be run in memory 82 and on processor 81
Machine program 83.The step of processor 81 realizes intelligent robot Training Methodology in above-described embodiment 1 when executing computer program 83,
Such as step S10 shown in FIG. 1 to step S40.Alternatively, processor 81 realizes above-described embodiment 2 when executing computer program 83
The function of each module/unit of middle intelligent robot training device, such as mode selection module 10 shown in Fig. 2, searching request obtain
Modulus block 20, target search module 30 and the function of showing broadcasting module 40.
Illustratively, computer program 83 can be divided into one or more modules, one or more module is deposited
Storage executes in memory 82, and by processor 81, to complete the present invention.One or more modules can be can complete it is specific
The instruction segment of the series of computation machine program of function, the instruction segment is for describing computer program 83 in computer equipment 80
Implementation procedure.For example, computer program 83 can be divided into mode selection module 10, searching request acquisition module 20, target
Search module 30 and display broadcasting module 40.
Processor 81 can be central processing unit (Central Processing Unit, CPU), can also be other
General processor, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
Memory 82 can be the internal storage unit of computer equipment 80, such as the hard disk of computer equipment 80 or interior
It deposits.Memory 82 can also be the plug-in type being equipped on the External memory equipment of computer equipment 80, such as computer equipment 80
Hard disk.Memory 82 can be used for storing other programs and data needed for computer program and computer equipment 80, may be used also
For temporarily storing the data that has exported or will export.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to aforementioned reality
Applying example, invention is explained in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each
Technical solution recorded in embodiment is modified or equivalent replacement of some of the technical features；And these are changed
Or replace, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of intelligent robot Training Methodology, which is characterized in that including：
Obtaining mode selection is asked, if when the mode selection request is training speech mode request, into training speech interface；
Searching request is obtained, at least one search key of described search acquisition request is based on；
Based at least one described search keyword search training data library, be mutually related target PowerPoint and target are obtained
Handout voice data；
It shows the target PowerPoint, while playing and being mutually related the target handout voice with the target PowerPoint
Data.
2. intelligent robot Training Methodology as described in claim 1, which is characterized in that described search request includes phonetic search
Request；
The acquisition searching request is based at least one search key of described search acquisition request, including：
Phonetic search request is obtained, the phonetic search request includes target voice search data；
Conversion process is carried out to target voice search data using preset speech recognition system, obtains text search number
According to；
Dissection process is carried out to the text search data using the libraries NLP, obtains at least one search key.
3. intelligent robot Training Methodology as described in claim 1, which is characterized in that described to be based at least one described search
Keyword search training data library obtains be mutually related target PowerPoint and target handout voice data, including：
Using each described search keyword as search field, using logical relation at least one described search field at
Reason forms target search formula；
The training data library is searched for based on the target search formula, obtains and show search result list, described search result
List includes at least one basic courseware-related information, and each basic courseware information includes basic courseware ID, be mutually related base
Plinth PowerPoint and basic handout voice data；
Search result selection request is obtained, the selection request of described search result includes target courseware ID；
Corresponding target courseware-related information is found based on the target courseware ID, obtains the target PowerPoint that is mutually related
With the target handout voice data.
4. intelligent robot Training Methodology as described in claim 1, which is characterized in that described searched based at least one described
Before the step of rope keyword search training data library, intelligent robot Training Methodology further includes：
Training data library is created, at least one basic courseware-related information, each basic courseware are stored in the training data library
Information includes basic course part ID, be mutually related basic PowerPoint and basic handout voice data；
The establishment training data library, including：
At least one basic PowerPoint and at least one basic handout voice data are obtained, each basis is drilled
Show that manuscript includes at least one presentation page；
By each presentation page and a basic handout voice data associated configuration, so that each presentation page is aobvious
The basic handout voice data that is mutually related is played when showing.
5. intelligent robot Training Methodology as described in claim 1, which is characterized in that in the display target demonstration text
Original text, at the same play with the target PowerPoint be mutually related the target handout voice data the step of after, the intelligence
Can robot Training Methodology further include：
It obtains and puts question to request, the enquirement request includes at least one enquirement keyword；
Based on training data library described at least one enquirement keyword search, obtain and at least one enquirement keyword
Corresponding reply data, the reply data include reply voice data；
Based on the broadcasting for puing question to request to suspend the target handout voice data, and play the reply voice data.
6. intelligent robot Training Methodology as claimed in claim 5, which is characterized in that the reply data further include replying to drill
Show manuscript；
It is described to put question to the broadcasting of the request pause target handout voice data based on described, and play the reply voice number
According to further including：
The reply PowerPoint is covered into the target PowerPoint currently shown, and in the reply voice data playback
After the completion, the target PowerPoint currently shown is returned, the broadcasting of the target handout voice data is continued.
7. intelligent robot Training Methodology as described in claim 1, which is characterized in that in obtaining mode selection request
After step, the intelligent robot Training Methodology further includes：
Obtaining mode selection request drills interface if mode selection request is practical operation rehearsal mode request into practical operation；
It obtains rehearsal mode to select to ask, and selects request to search for the training data library based on the rehearsal mode, obtain and survey
Why roll up, the test questionnaire includes at least one test problem；
Test reply message input by user is obtained, the test reply message includes corresponding at least one problem identification
Test answers；
Corresponding model answer is called based on described problem mark, is obtained according to the test answers and the model answer each
The test score value of the test problem.
8. a kind of intelligent robot training device, which is characterized in that including：
Mode selection module, for obtaining mode selection request, if the mode selection request is training speech mode request,
Into training speech interface；
Searching request acquisition module is based at least one search key of described search acquisition request for obtaining searching request；
Target search module, for being based at least one described search keyword search training data library, acquisition is mutually related
Target PowerPoint and target handout voice data；
It shows broadcasting module, for showing the target PowerPoint, while playing interrelated with the target PowerPoint
The target handout voice data.
9. a kind of computer equipment, including memory, processor and it is stored in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
The step of any one of 7 intelligent robot Training Methodology.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, feature to exist
In realization intelligent robot Training Methodology as described in any one of claim 1 to 7 when the computer program is executed by processor
The step of.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810200486.1A CN108536672A (en) | 2018-03-12 | 2018-03-12 | Intelligent robot Training Methodology, device, computer equipment and storage medium |
| PCT/CN2018/081504 WO2019174072A1 (en) | 2018-03-12 | 2018-04-02 | Intelligent robot based training method and apparatus, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810200486.1A CN108536672A (en) | 2018-03-12 | 2018-03-12 | Intelligent robot Training Methodology, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108536672A true CN108536672A (en) | 2018-09-14 |
Family
ID=63483607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810200486.1A Pending CN108536672A (en) | 2018-03-12 | 2018-03-12 | Intelligent robot Training Methodology, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108536672A (en) |
| WO (1) | WO2019174072A1 (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146432A (en) * | 2018-09-26 | 2019-01-04 | 北京城市网邻信息技术有限公司 | It is directed to interview method, apparatus, equipment and the storage medium of application developer |
| CN109262617A (en) * | 2018-11-29 | 2019-01-25 | 北京猎户星空科技有限公司 | Robot control method, device, equipment and storage medium |
| CN109584880A (en) * | 2018-11-26 | 2019-04-05 | 山东弘享机器人有限公司 | A kind of implementation method of robot speech PPT file |
| CN110209957A (en) * | 2019-06-06 | 2019-09-06 | 北京猎户星空科技有限公司 | Explanation method, apparatus, equipment and storage medium based on intelligent robot |
| CN110517688A (en) * | 2019-08-20 | 2019-11-29 | 合肥凌极西雅电子科技有限公司 | A kind of voice association prompt system |
| CN110556028A (en) * | 2019-08-23 | 2019-12-10 | 王英伟 | Human-computer interaction based anesthesiologist training method, equipment and storage medium |
| CN110717020A (en) * | 2019-09-06 | 2020-01-21 | 平安国际智慧城市科技股份有限公司 | Voice question-answering method, device, computer equipment and storage medium |
| CN111553555A (en) * | 2020-03-27 | 2020-08-18 | 深圳追一科技有限公司 | Training method, training device, computer equipment and storage medium |
| CN111696010A (en) * | 2020-05-28 | 2020-09-22 | 深圳市元征科技股份有限公司 | Scene-based training method, server, terminal device and storage medium |
| CN113177126A (en) * | 2021-03-24 | 2021-07-27 | 珠海金山办公软件有限公司 | Method and device for processing presentation, computer storage medium and terminal |
| CN113539267A (en) * | 2021-07-27 | 2021-10-22 | 广东电网有限责任公司 | Metering acquisition operation and maintenance device and method |
| CN113920789A (en) * | 2021-10-21 | 2022-01-11 | 中石化宁波工程有限公司 | Intelligent training method and system for engineering knowledge |
| CN115249359A (en) * | 2021-09-16 | 2022-10-28 | 达闼科技（北京）有限公司 | Teaching method, robot, electronic device, and storage medium |
| CN117033700A (en) * | 2023-10-09 | 2023-11-10 | 南京维赛客网络科技有限公司 | Method, system and storage medium for assisting courseware display based on AI assistant |
| CN117493531A (en) * | 2023-12-29 | 2024-02-02 | 深圳星网信通科技股份有限公司 | Training material generation method, training material generation equipment and storage medium |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112131743B (en) * | 2020-09-23 | 2024-03-29 | 中广核工程有限公司 | Three-dimensional training method and system for nuclear power plant equipment |
| CN112767199A (en) * | 2020-12-25 | 2021-05-07 | 科讯嘉联信息技术有限公司 | Enterprise employee training system and method |
| CN113630309B (en) * | 2021-08-12 | 2022-11-01 | 深圳追一科技有限公司 | Robot conversation system, method, device, computer equipment and storage medium |
| CN114120740A (en) * | 2021-11-24 | 2022-03-01 | 科大国创云网科技有限公司 | Customer service industry business personnel training method and system based on human-computer interaction |
| CN115860995B (en) * | 2022-12-09 | 2024-02-06 | 广州兴趣岛信息科技有限公司 | Intelligent training supervision method and system based on cloud computing |
| CN116189681B (en) * | 2023-05-04 | 2023-09-26 | 北京水晶石数字科技股份有限公司 | Intelligent voice interaction system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080134038A1 (en) * | 2006-12-05 | 2008-06-05 | Electronics And Telecommunications Research | Interactive information providing service method and apparatus |
| CN202534180U (en) * | 2011-12-30 | 2012-11-14 | 安凯(广州)微电子技术有限公司 | Hand-held autonomous learning machine |
| CN105868419A (en) * | 2016-06-02 | 2016-08-17 | 泉港区奇妙工业设计服务中心 | Robot device for searching and studying of children |
| CN106023693A (en) * | 2016-05-25 | 2016-10-12 | 北京九天翱翔科技有限公司 | Education system and method based on virtual reality technology and pattern recognition technology |
| CN106548773A (en) * | 2016-11-04 | 2017-03-29 | 百度在线网络技术（北京）有限公司 | Child user searching method and device based on artificial intelligence |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150371629A9 (en) * | 2005-01-03 | 2015-12-24 | Luc Julia | System and method for enabling search and retrieval operations to be performed for data items and records using data obtained from associated voice files |
| CN103761261B (en) * | 2013-12-31 | 2017-07-28 | 北京紫冬锐意语音科技有限公司 | A kind of media search method and device based on speech recognition |
| CN104952009A (en) * | 2015-04-23 | 2015-09-30 | 阔地教育科技有限公司 | Resource management method, system and server and interactive teaching terminal |
| CN105895085B (en) * | 2016-03-30 | 2019-10-18 | 讯飞智元信息科技有限公司 | A kind of multimedia transfer method and system |
-
2018
- 2018-03-12 CN CN201810200486.1A patent/CN108536672A/en active Pending
- 2018-04-02 WO PCT/CN2018/081504 patent/WO2019174072A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080134038A1 (en) * | 2006-12-05 | 2008-06-05 | Electronics And Telecommunications Research | Interactive information providing service method and apparatus |
| CN202534180U (en) * | 2011-12-30 | 2012-11-14 | 安凯(广州)微电子技术有限公司 | Hand-held autonomous learning machine |
| CN106023693A (en) * | 2016-05-25 | 2016-10-12 | 北京九天翱翔科技有限公司 | Education system and method based on virtual reality technology and pattern recognition technology |
| CN105868419A (en) * | 2016-06-02 | 2016-08-17 | 泉港区奇妙工业设计服务中心 | Robot device for searching and studying of children |
| CN106548773A (en) * | 2016-11-04 | 2017-03-29 | 百度在线网络技术（北京）有限公司 | Child user searching method and device based on artificial intelligence |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146432A (en) * | 2018-09-26 | 2019-01-04 | 北京城市网邻信息技术有限公司 | It is directed to interview method, apparatus, equipment and the storage medium of application developer |
| CN109584880A (en) * | 2018-11-26 | 2019-04-05 | 山东弘享机器人有限公司 | A kind of implementation method of robot speech PPT file |
| CN109262617A (en) * | 2018-11-29 | 2019-01-25 | 北京猎户星空科技有限公司 | Robot control method, device, equipment and storage medium |
| CN110209957A (en) * | 2019-06-06 | 2019-09-06 | 北京猎户星空科技有限公司 | Explanation method, apparatus, equipment and storage medium based on intelligent robot |
| CN110517688A (en) * | 2019-08-20 | 2019-11-29 | 合肥凌极西雅电子科技有限公司 | A kind of voice association prompt system |
| CN110556028A (en) * | 2019-08-23 | 2019-12-10 | 王英伟 | Human-computer interaction based anesthesiologist training method, equipment and storage medium |
| CN110717020B (en) * | 2019-09-06 | 2022-09-27 | 平安国际智慧城市科技股份有限公司 | Voice question-answering method, device, computer equipment and storage medium |
| CN110717020A (en) * | 2019-09-06 | 2020-01-21 | 平安国际智慧城市科技股份有限公司 | Voice question-answering method, device, computer equipment and storage medium |
| CN111553555A (en) * | 2020-03-27 | 2020-08-18 | 深圳追一科技有限公司 | Training method, training device, computer equipment and storage medium |
| CN111696010A (en) * | 2020-05-28 | 2020-09-22 | 深圳市元征科技股份有限公司 | Scene-based training method, server, terminal device and storage medium |
| CN113177126A (en) * | 2021-03-24 | 2021-07-27 | 珠海金山办公软件有限公司 | Method and device for processing presentation, computer storage medium and terminal |
| CN113539267A (en) * | 2021-07-27 | 2021-10-22 | 广东电网有限责任公司 | Metering acquisition operation and maintenance device and method |
| CN113539267B (en) * | 2021-07-27 | 2023-11-07 | 广东电网有限责任公司 | Metering acquisition operation and maintenance device and method |
| CN115249359A (en) * | 2021-09-16 | 2022-10-28 | 达闼科技（北京）有限公司 | Teaching method, robot, electronic device, and storage medium |
| CN113920789A (en) * | 2021-10-21 | 2022-01-11 | 中石化宁波工程有限公司 | Intelligent training method and system for engineering knowledge |
| CN117033700A (en) * | 2023-10-09 | 2023-11-10 | 南京维赛客网络科技有限公司 | Method, system and storage medium for assisting courseware display based on AI assistant |
| CN117493531A (en) * | 2023-12-29 | 2024-02-02 | 深圳星网信通科技股份有限公司 | Training material generation method, training material generation equipment and storage medium |
| CN117493531B (en) * | 2023-12-29 | 2024-04-09 | 深圳星网信通科技股份有限公司 | Training material generation method, training material generation equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019174072A1 (en) | 2019-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108536672A (en) | Intelligent robot Training Methodology, device, computer equipment and storage medium | |
| Roth | From gesture to scientific language | |
| KR102341752B1 (en) | Method for assisting lectures with avatar of metaverse space and apparatus thereof | |
| CN111290568A (en) | Interaction method and device and computer equipment | |
| EP1986175A2 (en) | Method, interface and system for obtaining user input | |
| CN112073741A (en) | Live broadcast information processing method and device, electronic equipment and storage medium | |
| CN102737536B (en) | Operating method of language experience teaching system | |
| JPH10134028A (en) | Method and device for remote learning using internet | |
| CN104021326B (en) | A kind of Teaching Methods and foreign language teaching aid | |
| Strauss et al. | Proactive spoken dialogue interaction in multi-party environments | |
| CN109147433A (en) | Childrenese assistant teaching method, device and robot | |
| CN109739969A (en) | Answer generation method and intelligent conversational system | |
| CN110111611A (en) | Information processing method, device, medium and electronic equipment | |
| CN110046290B (en) | Personalized autonomous teaching course system | |
| KR20080114100A (en) | Method and apparatus of naturally talking with computer | |
| JP2024507961A (en) | Interactive avatar training system | |
| Abbas et al. | Ready, trainer… one*! discovering the entanglement of adaptive learning with virtual reality in industrial training: a case study | |
| CN113542797A (en) | Interaction method and device in video playing and computer readable storage medium | |
| KR20140145067A (en) | Processing apparatus, processing system, and processing method | |
| Thomaidis | What is new in voice training? | |
| CN116416839A (en) | Training auxiliary teaching method based on Internet of things training system | |
| KR20190070683A (en) | Apparatus and method for constructing and providing lecture contents | |
| KR100447667B1 (en) | Interactive Language Teaching System consisted of Dolls and Voice Recognizing Computer | |
| AU2018102139A4 (en) | Advanced Learning System | |
| Suttor et al. | Implement AI service into VR training |
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: 20180914 |