CN109359105A - Operation rehearsal visualization system and method based on big data - Google Patents
Operation rehearsal visualization system and method based on big data Download PDFInfo
- Publication number
- CN109359105A CN109359105A CN201811108943.0A CN201811108943A CN109359105A CN 109359105 A CN109359105 A CN 109359105A CN 201811108943 A CN201811108943 A CN 201811108943A CN 109359105 A CN109359105 A CN 109359105A
- Authority
- CN
- China
- Prior art keywords
- data
- face
- user
- rendering
- display
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Processing Or Creating Images (AREA)
Abstract
Operation rehearsal visualization system and method provided by the invention based on big data, in the system, big data acquisition module is used to acquire the rehearsal data during drilling of fighting；The rehearsal data include passing through satellite, radar, sonar, laser, sensor and the collected data of camera；Data processing module is for cleaning the collected data of big data acquisition module, to obtain cleaning data；It is also used to classify to cleaning data；Data display module includes display；The display is equipped with display interface, and dividing on the display interface has multiple display areas, and each display area is for showing a kind of cleaning data；Data memory module is for storing the cleaning data.The system combination big data technology can show a plurality of types of data, preferably displaying operation rehearsal process.
Description
Technical field
The invention belongs to big data technical fields, and in particular to operation rehearsal visualization system and side based on big data
Method.
Background technique
Big data is completely new Industrial form, the important feature for having preceding low to dependence effect and backward pulling production high.
On the one hand, develop big data industry needs a large amount of mating industrial systems and infrastructure as prerequisite item unlike conventional industries
Part.On the other hand, big data is influencing and is changing traditional mode of production mode and economic operational mechanism, promote division of labor in society cooperation and
The intensive and innovation of production organizational mode.
During traditional operation rehearsal, rehearsal video is acquired by camera and is shown, can be realized while aobvious
Show the video that multiple cameras take, but shows that content-form is excessively single.With the development of big data visualization technique
With being constantly progressive for military technology, drilled it is urgent to provide a kind of display content-form diversification, in conjunction with the operation of big data technology
Visualization system.
Summary of the invention
For the defects in the prior art, the present invention provides operation rehearsal visualization system and method based on big data,
In conjunction with big data technology, a plurality of types of data, preferably displaying operation rehearsal process can be shown.
In a first aspect, visualization system is drilled in a kind of operation based on big data, including big data acquisition module, data are deposited
Store up module, data processing module and data display module；
The big data acquisition module is used to acquire the rehearsal data during fighting rehearsal；The rehearsal data include logical
Cross satellite, radar, sonar, laser, sensor and the collected data of camera；
The data processing module is for cleaning the collected data of big data acquisition module, to obtain cleaning number
According to；It is also used to classify to cleaning data；
The data display module includes display；The display is equipped with display interface, draws on the display interface
Dividing has multiple display areas, and each display area is for showing a kind of cleaning data；
The data memory module is for storing the cleaning data.
It preferably, further include enquiry module；
The enquiry module is used to obtain the data inquiry request of legitimate user, obtains inquiry text according to the request of data
This, pre-processes the query text, is segmented to obtain controlled dictionary to the pre-processed results of query text, according to institute
Controlled dictionary building space vector is stated, implements cluster according to the space vector and complete Cluster Evaluation acquisition data query to ask
The keyword asked；
The enquiry module is also used to be parsed according to the keyword and preset processing rule, and inquiry to be carried out
The data presented are visualized, the data display module is transmitted to and is shown.
Preferably, described to be specifically included according to the controlled dictionary building space vector:
It is segmented according to the fields dictionary of query text；
It is trained using the query text after participle, obtains training pattern；
Alternative keywords belonging to each of each query text are substituted into the training pattern of target domain, are obtained every
The term vector of several dimensions of alternative keywords belonging in a query text.
It preferably, further include authorization module；The authorization module includes 3D camera and display terminal；The display terminal
It is equipped with naked eye 3D display screen；
The 3D camera is transferred to the display terminal for obtaining face 3D rendering in real time；
The display terminal is defined as standard header when receiving the register instruction of user, by the face 3D rendering received
Picture is stored in face icon database, is also used to subscriber identity information corresponding with the standard head portrait and is bound；
The display terminal when receive request user face 3D rendering, and in face icon database exist with it is described
When requesting the identical standard head portrait of face 3D rendering of user, the corresponding subscriber identity information of standard head portrait is extracted and shown,
Definition request user is legitimate user；
The display terminal is not present and institute when the face 3D rendering for receiving request user, but in face icon database
When stating the identical standard head portrait of face 3D rendering of request user, definition request user is illegal user.
Preferably, the display terminal defines the face 3D rendering received when receiving the register instruction of user
For standard head portrait, it is stored in face icon database and specifically includes:
Display terminal shows the face 3D figure received by naked eye 3D display screen when receiving the register instruction of user
Picture；
Display terminal handles face 3D rendering, extracts facial contour in face 3D rendering, defines in facial contour
Region be human face region；
Display terminal generates acquisition window in the human face region when receiving expression acquisition instructions；It is also used to connect
The dragging instruction for receiving user, drags movement in the facial contour；
Image definition in acquisition window is standard expression, will connect by display terminal when receiving stopping acquisition instructions
The face 3D rendering received is defined as standard head portrait, and standard head portrait is associated with corresponding standard expression, is stored in face head
As in database.
Second aspect, a kind of operation rehearsal method for visualizing based on big data, comprising the following steps:
Rehearsal data during the acquisition operation rehearsal of big data acquisition module；The rehearsal data include by satellite,
Radar, sonar, laser, sensor and the collected data of camera；
Data processing module cleans the collected data of big data acquisition module, to obtain cleaning data, to clear
Data are washed to classify；
Data display module shows sorted cleaning data；
Data memory module stores the cleaning data.
Preferably, this method is after data memory module stores the cleaning data, further includes:
Enquiry module obtains the data inquiry request of legitimate user, query text is obtained according to the request of data, to institute
It states query text to be pre-processed, the pre-processed results of query text is segmented to obtain controlled dictionary, according to described controlled
Dictionary constructs space vector, implements cluster according to the space vector and completes the pass that Cluster Evaluation obtains data inquiry request
Keyword；
Enquiry module is parsed also according to the keyword and preset processing rule, and inquiry to be carried out visualization and be in
Existing data are transmitted to the data display module and are shown.
Preferably, described to be specifically included according to the controlled dictionary building space vector:
It is segmented according to the fields dictionary of query text；
It is trained using the query text after participle, obtains training pattern；
Alternative keywords belonging to each of each query text are substituted into the training pattern of target domain, are obtained every
The term vector of several dimensions of alternative keywords belonging in a query text.
Preferably, this method is before the data inquiry request that enquiry module obtains legitimate user, further includes:
3D camera obtains face 3D rendering in real time, and is transferred to display terminal；
Display terminal is defined as standard head portrait when receiving the register instruction of user, by the face 3D rendering received,
It is stored in face icon database, subscriber identity information also corresponding with the standard head portrait is bound；
Display terminal exists and the request when the face 3D rendering for receiving request user, and in face icon database
When the identical standard head portrait of the face 3D rendering of user, the corresponding subscriber identity information of standard head portrait is extracted and shown, define
Request user is legitimate user；
When the face 3D rendering for receiving request user, but in face icon database, there is no ask display terminal with described
When seeking the identical standard head portrait of the face 3D rendering of user, definition request user is illegal user.
Preferably, the display terminal defines the face 3D rendering received when receiving the register instruction of user
For standard head portrait, it is stored in face icon database and specifically includes:
Display terminal shows the face 3D figure received by naked eye 3D display screen when receiving the register instruction of user
Picture；
Display terminal handles face 3D rendering, extracts facial contour in face 3D rendering, defines in facial contour
Region be human face region；
Display terminal generates acquisition window in the human face region when receiving expression acquisition instructions；It also receives and uses
The dragging at family instructs, and movement is dragged in the facial contour；
Image definition in acquisition window is standard expression, will connect by display terminal when receiving stopping acquisition instructions
The face 3D rendering received is defined as standard head portrait, and standard head portrait is associated with corresponding standard expression, is stored in face head
As in database.
As shown from the above technical solution, the operation rehearsal visualization system and method provided by the invention based on big data,
In conjunction with big data technology, a plurality of types of data, preferably displaying operation rehearsal process can be shown.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art are briefly described.In all the appended drawings, similar element
Or part is generally identified by similar appended drawing reference.In attached drawing, each element or part might not be drawn according to actual ratio.
Fig. 1 is the module frame chart for the system that embodiment one provides.
Fig. 2 is the flow chart for the method that example IV provides.
Specific embodiment
It is described in detail below in conjunction with embodiment of the attached drawing to technical solution of the present invention.Following embodiment is only used for
Clearly illustrate technical solution of the present invention, therefore be only used as example, and cannot be used as a limitation and limit protection model of the invention
It encloses.It should be noted that unless otherwise indicated, technical term or scientific term used in this application are should be belonging to the present invention
The ordinary meaning that field technical staff is understood.
Embodiment one:
A kind of operation rehearsal visualization system based on big data, is deposited referring to Fig. 1, including big data acquisition module, data
Store up module, data processing module and data display module；
The big data acquisition module is used to acquire the rehearsal data during fighting rehearsal；The rehearsal data include logical
Cross satellite, radar, sonar, laser, sensor and the collected data of camera；
Specifically, collected data include video, audio, text, pictorial information etc..The system acquisition operation was drilled
The data of plurality of devices in journey can understand rehearsal situation more fully hereinafter.
The data processing module is for cleaning the collected data of big data acquisition module, to obtain cleaning number
According to；It is also used to classify to cleaning data；
Specifically, can according to cleaning data type classify, such as: according to video, audio, text, picture into
Row classification.It can also classify according to acquisition equipment, such as: according to satellite, radar, sonar, laser, sensor and camera
Classify.
The data display module includes display；The display is equipped with display interface, draws on the display interface
Dividing has multiple display areas, and each display area is for showing a kind of cleaning data；
Specifically, multiple display areas are divided on display interface, are shown different classes of cleaning data, are shown using piecemeal
Method, can it is more intuitive, more clearly show rehearsal situation.Such as: by multiple display areas show respectively video, audio,
Text or picture etc. clean data, or excessively multiple display areas show respectively satellite, radar, sonar, laser, sensor and
The cleaning data of camera acquisition.
The data memory module is for storing the cleaning data.
The system combination big data technology can show a plurality of types of data, preferably displaying operation rehearsal process.
Embodiment two:
Embodiment two on the basis of example 1, increases the following contents:
It further include enquiry module；
The enquiry module is used to obtain the data inquiry request of legitimate user, obtains inquiry text according to the request of data
This, pre-processes the query text, is segmented to obtain controlled dictionary to the pre-processed results of query text, according to institute
Controlled dictionary building space vector is stated, implements cluster according to the space vector and complete Cluster Evaluation acquisition data query to ask
The keyword asked；
The enquiry module is also used to be parsed according to the keyword and preset processing rule, and inquiry to be carried out
The data presented are visualized, the data display module is transmitted to and is shown.
Specifically, wherein directly using text as query text if being text if the data inquiry request that user is input,
If the data inquiry request of user's input is voice, it is converted into after text by voice as query text.Then to described
Query text is pre-processed, and the pretreatment includes: the field for preparing analyzed text, the corresponding fields of the text
Dictionary；Unrelated word denoising carries out word segmentation processing to text according to fields dictionary, finds out text entities, the text after participle
In conjunction with field dictionary, it is filtered and rejects unrelated and word, construct controlled dictionary.
Space vector is constructed according to the controlled dictionary, dimension should be maintained at 10 dimensions hereinafter, to be promoted in subsequent step
The performance of algorithm specifically includes following sub-step:
To each document in the document, segmented according to document fields dictionary；
Using the document training Word2Vec model after participle, the Word2Vec model of fields dictionary is obtained；
The Word2Vec model that alternative keywords belonging to each of each document are substituted into the target domain, obtains
The term vector of several dimensions of alternative keywords belonging in each document, the specific method is as follows:
Since each word corresponds to a term vector, v is dimension, it is assumed that
The similarity of two words is proportional to the product of corresponding term vector, it may be assumed that sin (v1, v2)=v1·v2；
Multiple word v1~vnComposition a fields dictionary indicated with C, wherein Referred to as institute
Belong to the center vector of domain term；
Occurs alternative keywords A in fields dictionary, the probability of A is proportional to energy factors e-E(A,C), whereE=-
AC, therefore:Wherein V is entire lexical space, i.e., document is whole, introducing function: σ (x)=
1/1(1+e-x), show that: P (G/C)=σ (- (H-G) C) then proceedes to the recursive calculating of fractionation lexical space and goes down, last
Need to calculate the vector difference of each keyword similar portion, wherein each child node indicates an alternative keywords, Mei Gezhong
Center of the vector of intermediate node G or H as all subvectors.
Cluster in the present invention is then existed to hyperspace word cluster when there is designated key word number using algorithm
Use the number as clusters number in algorithm；If defaulting keyword number is 5, described without designated key word number
Algorithm description is as follows:
Keyword thesaurus number k and data acquisition system comprising n alternative keywords；Output: meet target function value most
K small clustering algorithm process:
Arbitrarily select k alternative keywords as initial cluster center from n alternative keywords；
Centric keyword is obtained according to the mean value of each cluster alternative keywords, is calculated in each alternative keywords and these
The distance of heart keyword, and according to minimum range, corresponding keyword is divided again again；
The mean value of each cluster keyword, the i.e. mean value of centric keyword are recalculated, repeats the step until target letter
Number no longer changes.
The Cluster Evaluation in the present invention, comprising the following steps:
Fuzzy word is rejected, the word point to multiple centroid distance equilibriums can be rejected in treatment process；
In each cluster, according to algorithmic formula:It is calculated.Wherein: Q is that the word exists
The weight of dictionary, n are Spatial Dimension number, XiFor this i-th dimension angle value, XizFor the i-th dimension angle value of center of mass point.L is finally to repair
Final distance after ordering, taking the smallest word of the value is the representative keyword in the classification；
The word nearest from centroid distance is taken out, the word is as final keyword.
Since clustering algorithm will receive the influence of unit scales, the dimension values of the point can be standardized, that is, marked first
In addition value=(value-component mean value before standardization)/component standard deviation after standardization selects the good of clustering algorithm measurement
Place is that this algorithm will not be influenced by dimension, and the distance between two o'clock is unrelated with the measurement unit of initial data；By normalized number
According to identical with centralization data the distance between calculated 2 points of (i.e. the difference of initial data and mean value), while the method measures
Distance can also exclude the interference of the correlation between variable.
Further, Cluster Evaluation specific algorithm is as follows:
It is k to selected keyword number, it is random first that document content is subjected to Preliminary division, then use iteration side
Method is attempted to improve and be divided by constantly moving cluster centre:
Equipment selects keyword set X={ x1,x2,…,xn, K centric keyword is z respectively1,z2,…,zk, with w (iz
=1,2 ..., k) k classification indicating word cluster, just like giving a definition:
Define the Euclidean distance between 1 two alternative keywords are as follows:
Define the arithmetic average for the alternative keywords that 2 belong to same field are as follows:；
Define 3 objective functions are as follows:
Obtain mass center away from formula by defining 1.2.3 are as follows:
The word nearest from centroid distance is taken out, i.e. the smallest word of L value is as final keyword；
Weight of this word in the dictionary of field is promoted, dictionary is optimized.
System provided by the embodiment of the present invention, to briefly describe, embodiment part does not refer to place, can refer to aforementioned system
Corresponding contents in embodiment of uniting.
Embodiment three:
Embodiment three increases the following contents on the basis of other embodiments:
So that guarantee the safety of data, the legitimate user only authorized can be carried out data query.For this purpose, this implementation
Example provides a kind of authorization method of 3D recognition of face.
The system further includes authorization module；The authorization module includes 3D camera and display terminal；The display terminal
It is equipped with naked eye 3D display screen；
The 3D camera is transferred to the display terminal for obtaining face 3D rendering in real time；
Specifically, face 3D rendering increases depth information on the basis of traditional planar information, so that acquisition
The human face image information arrived is more, and recognition of face is more acurrate.
The display terminal is defined as standard header when receiving the register instruction of user, by the face 3D rendering received
Picture is stored in face icon database, is also used to subscriber identity information corresponding with the standard head portrait and is bound；
Specifically, for the first time in use, being registered, the head image information and identity information of typing user.Register instruction
It can be obtained by user's operation display terminal, for example, being clicked in register interface by display terminal Login Register interface by mouse
Registration key is registered.Register instruction can also be issued by back-stage management server, acquire the head image information of user.Display terminal
When receiving register instruction, received face 3D rendering is saved, for comparing when later period recognition of face.Typing people simultaneously
The subscriber identity information of face 3D rendering can know user in this way when identifying the facial image of visiting personnel at the first time
Identity information.
The display terminal when receive request user face 3D rendering, and in face icon database exist with it is described
When requesting the identical standard head portrait of face 3D rendering of user, the corresponding subscriber identity information of standard head portrait is extracted and shown,
Definition request user is legitimate user；
Specifically, in recognition of face, by it is collected request user face 3D rendering and face icon database into
Row comparison, if extracting subscriber identity information there are identical standard head portrait in face icon database, user is identified as
Function, definition request user is legitimate user.
The display terminal is not present and institute when the face 3D rendering for receiving request user, but in face icon database
When stating the identical standard head portrait of face 3D rendering of request user, definition request user is illegal user.
Specifically, in recognition of face, if there is no the face 3D renderings with request user in face icon database
When identical standard head portrait, illustrate that visiting subscriber is not authorized user, user's recognition failures, definition request user is illegal uses
Family.
The system obtains the face 3D rendering of user, recognition of face is carried out to user using 3D rendering, in traditional two dimension
On the basis of image recognition, depth information is introduced, improves the accuracy of recognition of face.
The present embodiment also increases expression identification function.The display terminal will connect when receiving the register instruction of user
The face 3D rendering received is defined as standard head portrait, is stored in face icon database and specifically includes:
Display terminal shows the face 3D figure received by naked eye 3D display screen when receiving the register instruction of user
Picture；
Display terminal handles face 3D rendering, extracts facial contour in face 3D rendering, defines in facial contour
Region be human face region；
Specifically, due to needing to extract expression in the human face region of user, so more accurately being extracted in order to subsequent
The expression of user needs first to mark facial contour in face 3D rendering.
Display terminal generates acquisition window in the human face region when receiving expression acquisition instructions；It is also used to connect
The dragging instruction for receiving user, drags movement in the facial contour；
Image definition in acquisition window is standard expression, will connect by display terminal when receiving stopping acquisition instructions
The face 3D rendering received is defined as standard head portrait, and standard head portrait is associated with corresponding standard expression, is stored in face head
As in database.
Specifically, the expression of user is acquired by acquisition window.In this way, user can increase on the basis of recognition of face
Expression Recognition, then after identifying the face of user, it is also necessary to identify whether it is consistent with expression when user's registration, such as: again
After the face for identifying user, it is also necessary to identify whether user blinks, puts out one's tongue, staring or wapperijaw etc..Face is improved in this way
The accuracy of identification pseudo- can not produce the expression that user specifies, cannot pass through even if the face for having criminal to forge user
Recognition of face.
User needs the face position that acquires in use, acquisition window is dragged to, such as: the expression that user specifies is to blink
Eye, then need acquisition window being dragged to eye, covers entire eye, acquires eye expression.The expression that user specifies is to stuck out one's tongue
Head then needs acquisition window being dragged to oral area, covers entire oral area, acquisition oral area movement.After acquisition, acquisition is extracted
The expression that image in window, as user are specified.The expression and face information that user is specified are bound.
Preferably, the present embodiment also provides the method for following Expression Recognitions.The display terminal, which is worked as, receives request user
Face 3D rendering, and in face icon database exist standard head portrait identical with the request face 3D rendering of user
When, it extracts and shows that the corresponding subscriber identity information of standard head portrait specifically includes:
Display terminal extracts the expression information of face 3D rendering when the face 3D rendering for receiving request user；
When there is standard head portrait identical with the request face 3D rendering of user in face icon database, judgement
In face icon database the associated standard expression of the standard head portrait whether with request user face 3D rendering in expression information
It is identical；
If identical, extract and show the corresponding subscriber identity information of standard head portrait；
If it is not the same, prompt user's recognition failures.
Specifically, display terminal first determines whether face icon database when collecting the face 3D rendering of request user
In whether there is identical standard head portrait；If it does not, user's recognition failures, i.e., do not have this in face icon database
People.If there is, it is also necessary to whether the expression of appointed part is corresponding with standard head portrait in the face 3D rendering of identification request user
Standard expression it is consistent；If inconsistent, illustrate there is no this people in face icon database；If consistent, user is identified as
Function.
Such as: detect request user face 3D rendering when, respectively extract user's face expression, i.e., eyes, eyes,
Eyebrow, nose and mouth.If standard expression is eye expression, the expression for requesting eyes in the face 3D rendering of user is judged
It is whether consistent with standard expression.Unanimously, just illustrate that user identifies successfully.
Preferably, the present embodiment also provides the method for following expression acquisitions.The display terminal, which is worked as, receives stopping acquisition
It is that standard expression specifically includes by the image definition in acquisition window when instruction:
Display terminal judges whether acquisition window includes entire eyes, eyebrow, nose when receiving stopping acquisition instructions
Or mouth；
If comprising being standard expression by the image definition in acquisition window；
If do not included, expression acquisition failure is prompted.
Specifically, it when acquiring expression, needs acquisition window all to cover face to be collected, just can guarantee in this way
Collect the expression of entire face.So when stop acquisition when, first determine whether acquisition window whether include entire eyes, eyebrow,
Nose or mouth；If not, it is believed that this acquisition is invalidated acquisitions, needs to resurvey.
The expression information includes eye expression information, eyebrow expression information, nose expression information and mouth expression information.
System provided by the embodiment of the present invention, to briefly describe, embodiment part does not refer to place, can refer to aforementioned system
Corresponding contents in embodiment of uniting.
Example IV:
A kind of operation rehearsal method for visualizing based on big data, referring to fig. 2, comprising the following steps:
S1: the rehearsal data during the acquisition operation rehearsal of big data acquisition module；The rehearsal data include by defending
Star, radar, sonar, laser, sensor and the collected data of camera；
S2: data processing module cleans the collected data of big data acquisition module, right to obtain cleaning data
Cleaning data are classified；
S3: data display module shows sorted cleaning data；
S4: data memory module stores the cleaning data.
Preferably, this method is after data memory module stores the cleaning data, further includes:
Enquiry module obtains the data inquiry request of legitimate user, query text is obtained according to the request of data, to institute
It states query text to be pre-processed, the pre-processed results of query text is segmented to obtain controlled dictionary, according to described controlled
Dictionary constructs space vector, implements cluster according to the space vector and completes the pass that Cluster Evaluation obtains data inquiry request
Keyword；
Enquiry module is parsed also according to the keyword and preset processing rule, and inquiry to be carried out visualization and be in
Existing data are transmitted to the data display module and are shown.
Preferably, described to be specifically included according to the controlled dictionary building space vector:
It is segmented according to the fields dictionary of query text；
It is trained using the query text after participle, obtains training pattern；
Alternative keywords belonging to each of each query text are substituted into the training pattern of target domain, are obtained every
The term vector of several dimensions of alternative keywords belonging in a query text.
Preferably, this method is before the data inquiry request that enquiry module obtains legitimate user, further includes:
3D camera obtains face 3D rendering in real time, and is transferred to display terminal；
Display terminal is defined as standard head portrait when receiving the register instruction of user, by the face 3D rendering received,
It is stored in face icon database, subscriber identity information also corresponding with the standard head portrait is bound；
Display terminal exists and the request when the face 3D rendering for receiving request user, and in face icon database
When the identical standard head portrait of the face 3D rendering of user, the corresponding subscriber identity information of standard head portrait is extracted and shown, define
Request user is legitimate user；
When the face 3D rendering for receiving request user, but in face icon database, there is no ask display terminal with described
When seeking the identical standard head portrait of the face 3D rendering of user, definition request user is illegal user.
Preferably, the display terminal defines the face 3D rendering received when receiving the register instruction of user
For standard head portrait, it is stored in face icon database and specifically includes:
Display terminal shows the face 3D figure received by naked eye 3D display screen when receiving the register instruction of user
Picture；
Display terminal handles face 3D rendering, extracts facial contour in face 3D rendering, defines in facial contour
Region be human face region；
Display terminal generates acquisition window in the human face region when receiving expression acquisition instructions；It also receives and uses
The dragging at family instructs, and movement is dragged in the facial contour；
Image definition in acquisition window is standard expression, will connect by display terminal when receiving stopping acquisition instructions
The face 3D rendering received is defined as standard head portrait, and standard head portrait is associated with corresponding standard expression, is stored in face head
As in database.
This method can show a plurality of types of data, preferably displaying operation rehearsal process in conjunction with big data technology.
Method provided by the embodiment of the present invention, to briefly describe, embodiment part does not refer to place, can refer to aforementioned system
Corresponding contents in embodiment of uniting.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme should all cover within the scope of the claims and the description of the invention.
Claims (10)
1. visualization system is drilled in a kind of operation based on big data, which is characterized in that deposited including big data acquisition module, data
Store up module, data processing module and data display module；
The big data acquisition module is used to acquire the rehearsal data during fighting rehearsal；The rehearsal data include by defending
Star, radar, sonar, laser, sensor and the collected data of camera；
The data processing module is for cleaning the collected data of big data acquisition module, to obtain cleaning data；
It is also used to classify to cleaning data；
The data display module includes display；The display is equipped with display interface, and dividing on the display interface has
Multiple display areas, each display area is for showing a kind of cleaning data；
The data memory module is for storing the cleaning data.
2. visualization system is drilled in the operation based on big data according to claim 1, which is characterized in that further include inquiry mould
Block；
The enquiry module is used to obtain the data inquiry request of legitimate user, obtains query text according to the request of data,
The query text is pre-processed, the pre-processed results of query text are segmented to obtain controlled dictionary, according to described
Controlled dictionary constructs space vector, implements cluster according to the space vector and complete Cluster Evaluation to obtain data inquiry request
Keyword；
The enquiry module is also used to be parsed according to the keyword and preset processing rule, and inquiry to be carried out visual
Change the data presented, is transmitted to the data display module and is shown.
3. visualization system is drilled in the operation based on big data according to claim 2, which is characterized in that described according to
Controlled dictionary building space vector specifically includes:
It is segmented according to the fields dictionary of query text；
It is trained using the query text after participle, obtains training pattern；
Alternative keywords belonging to each of each query text are substituted into the training pattern of target domain, each look into is obtained
The term vector of several dimensions of alternative keywords belonging to asking in text.
4. visualization system is drilled in the operation based on big data according to claim 2, which is characterized in that further include authorization mould
Block；The authorization module includes 3D camera and display terminal；The display terminal is equipped with naked eye 3D display screen；
The 3D camera is transferred to the display terminal for obtaining face 3D rendering in real time；
The display terminal is defined as standard head portrait when receiving the register instruction of user, by the face 3D rendering received,
It is stored in face icon database, is also used to subscriber identity information corresponding with the standard head portrait and is bound；
The display terminal exists and the request when the face 3D rendering for receiving request user, and in face icon database
When the identical standard head portrait of the face 3D rendering of user, the corresponding subscriber identity information of standard head portrait is extracted and shown, define
Request user is legitimate user；
When the face 3D rendering for receiving request user, but in face icon database, there is no ask the display terminal with described
When seeking the identical standard head portrait of the face 3D rendering of user, definition request user is illegal user.
5. visualization system is drilled in the operation based on big data according to claim 4, which is characterized in that
The display terminal is defined as standard head portrait when receiving the register instruction of user, by the face 3D rendering received,
It is specifically included in deposit face icon database:
Display terminal shows the face 3D rendering received when receiving the register instruction of user, through naked eye 3D display screen；
Display terminal handles face 3D rendering, extracts facial contour in face 3D rendering, defines the area in facial contour
Domain is human face region；
Display terminal generates acquisition window in the human face region when receiving expression acquisition instructions；It is also used to receive use
The dragging at family instructs, and movement is dragged in the facial contour；
Image definition in acquisition window is standard expression, will received by display terminal when receiving stopping acquisition instructions
Face 3D rendering be defined as standard head portrait, standard head portrait is associated with corresponding standard expression, be stored in face head portrait number
According in library.
6. method for visualizing is drilled in a kind of operation based on big data, which comprises the following steps:
Rehearsal data during the acquisition operation rehearsal of big data acquisition module；The rehearsal data include by satellite, radar,
Sonar, laser, sensor and the collected data of camera；
Data processing module cleans the collected data of big data acquisition module, to obtain cleaning data, to cleaning number
According to classifying；
Data display module shows sorted cleaning data；
Data memory module stores the cleaning data.
7. method for visualizing is drilled in the operation based on big data according to claim 6, which is characterized in that this method is in data
Memory module stores after the cleaning data, further includes:
Enquiry module obtains the data inquiry request of legitimate user, obtains query text according to the request of data, looks into described
It askes text to be pre-processed, the pre-processed results of query text is segmented to obtain controlled dictionary, according to the controlled dictionary
Space vector is constructed, implement cluster according to the space vector and completes the key that Cluster Evaluation obtains data inquiry request
Word；
Enquiry module is parsed also according to the keyword and preset processing rule, and inquiry to be carried out visualization presentation
Data are transmitted to the data display module and are shown.
8. method for visualizing is drilled in the operation based on big data according to claim 7, which is characterized in that described according to
Controlled dictionary building space vector specifically includes:
It is segmented according to the fields dictionary of query text；
It is trained using the query text after participle, obtains training pattern；
Alternative keywords belonging to each of each query text are substituted into the training pattern of target domain, each look into is obtained
The term vector of several dimensions of alternative keywords belonging to asking in text.
9. method for visualizing is drilled in the operation based on big data according to claim 7, which is characterized in that this method is being inquired
Module obtains before the data inquiry request of legitimate user, further includes:
3D camera obtains face 3D rendering in real time, and is transferred to display terminal；
Display terminal is defined as standard head portrait when receiving the register instruction of user, by the face 3D rendering received, deposit
In face icon database, subscriber identity information also corresponding with the standard head portrait is bound；
Display terminal exists and the request user when the face 3D rendering for receiving request user, and in face icon database
Face 3D rendering identical standard head portrait when, extract and show the corresponding subscriber identity information of standard head portrait, definition request
User is legitimate user；
There is no use with the request when the face 3D rendering for receiving request user, but in face icon database for display terminal
When the identical standard head portrait of the face 3D rendering at family, definition request user is illegal user.
10. method for visualizing is drilled in the operation based on big data according to claim 9, which is characterized in that the display is eventually
End is defined as standard head portrait when receiving the register instruction of user, by the face 3D rendering received, is stored in face head portrait number
According to being specifically included in library:
Display terminal shows the face 3D rendering received when receiving the register instruction of user, through naked eye 3D display screen；
Display terminal handles face 3D rendering, extracts facial contour in face 3D rendering, defines the area in facial contour
Domain is human face region；
Display terminal generates acquisition window in the human face region when receiving expression acquisition instructions；Also receive user's
Dragging instruction, drags movement in the facial contour；
Image definition in acquisition window is standard expression, will received by display terminal when receiving stopping acquisition instructions
Face 3D rendering be defined as standard head portrait, standard head portrait is associated with corresponding standard expression, be stored in face head portrait number
According in library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811108943.0A CN109359105A (en) | 2018-09-21 | 2018-09-21 | Operation rehearsal visualization system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811108943.0A CN109359105A (en) | 2018-09-21 | 2018-09-21 | Operation rehearsal visualization system and method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109359105A true CN109359105A (en) | 2019-02-19 |
Family
ID=65351253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811108943.0A Pending CN109359105A (en) | 2018-09-21 | 2018-09-21 | Operation rehearsal visualization system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109359105A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101799999A (en) * | 2010-04-06 | 2010-08-11 | 中国石油化工股份有限公司 | Accident emergency drilling system and method |
| CN102222425A (en) * | 2011-07-15 | 2011-10-19 | 西安电子科技大学 | Automatic demonstration system and realizing method for 3-dimensioinal (3D) visual emergency plan |
| CN103578315A (en) * | 2013-10-17 | 2014-02-12 | 中国石油化工股份有限公司 | Three-dimensional firefighting training and drill evaluation method |
| CN107357912A (en) * | 2017-07-18 | 2017-11-17 | 浪潮天元通信信息系统有限公司 | Job scheduling method based on visual presentation |
| CN107911432A (en) * | 2017-11-08 | 2018-04-13 | 中电科新型智慧城市研究院有限公司 | City emergency commading platform |
-
2018
- 2018-09-21 CN CN201811108943.0A patent/CN109359105A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101799999A (en) * | 2010-04-06 | 2010-08-11 | 中国石油化工股份有限公司 | Accident emergency drilling system and method |
| CN102222425A (en) * | 2011-07-15 | 2011-10-19 | 西安电子科技大学 | Automatic demonstration system and realizing method for 3-dimensioinal (3D) visual emergency plan |
| CN103578315A (en) * | 2013-10-17 | 2014-02-12 | 中国石油化工股份有限公司 | Three-dimensional firefighting training and drill evaluation method |
| CN107357912A (en) * | 2017-07-18 | 2017-11-17 | 浪潮天元通信信息系统有限公司 | Job scheduling method based on visual presentation |
| CN107911432A (en) * | 2017-11-08 | 2018-04-13 | 中电科新型智慧城市研究院有限公司 | City emergency commading platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhong et al. | Mapping computer vision research in construction: Developments, knowledge gaps and implications for research | |
| CN105809113B (en) | Three-dimensional face identification method and the data processing equipment for applying it | |
| CN108764018A (en) | A kind of multitask vehicle based on convolutional neural networks recognition methods and device again | |
| Rabiee et al. | Crowd behavior representation: an attribute-based approach | |
| Ajagbe et al. | Investigating the efficiency of deep learning models in bioinspired object detection | |
| CN106537387B (en) | Retrieval/storage image associated with event | |
| WO2019200739A1 (en) | Data fraud identification method, apparatus, computer device, and storage medium | |
| CN107533547B (en) | Product indexing method and system | |
| JP6173754B2 (en) | Image search system, image search apparatus, and image search method | |
| JP2016099835A (en) | Image processor, image processing method, and program | |
| CN106529470A (en) | Gesture recognition method based on multistage depth convolution neural network | |
| Singh | Machine learning in pattern recognition | |
| Taroni et al. | Two items of evidence, no putative source: an inference problem in forensic intelligence | |
| Sarker et al. | Transformer-Based Person Re-Identification: A Comprehensive Review | |
| CN107038593A (en) | A kind of method for processing abnormal data and system based on anti-fake traceability system | |
| Valldor et al. | Firearm detection in social media images | |
| Schutera et al. | Domain is of the essence: Data deployment for city-scale multi-camera vehicle re-identification | |
| CN109359105A (en) | Operation rehearsal visualization system and method based on big data | |
| Gurkan et al. | Evaluation of human and machine face detection using a novel distinctive human appearance dataset | |
| Hassen et al. | Human identification system: A review | |
| CN110472680B (en) | Object classification method, device and computer-readable storage medium | |
| Lalitha et al. | Micro-facial expression recognition in video based on optimal convolutional neural network (MFEOCNN) algorithm | |
| CN112949369A (en) | Mass face gallery retrieval method based on man-machine cooperation | |
| Wang et al. | Facial expression recognition of aerobics athletes based on CNN and HOG dual channel feature fusion | |
| Lakshmi Narayanan et al. | Image classification using gaussian curvature based local tetra pattern descriptor with enhanced feature selection technique |
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 |
Application publication date: 20190219 |
|
| RJ01 | Rejection of invention patent application after publication |