CN107122498A - Information retrieval categorizing system and method based on cloud computing - Google Patents
Information retrieval categorizing system and method based on cloud computing Download PDFInfo
- Publication number
- CN107122498A CN107122498A CN201710405522.3A CN201710405522A CN107122498A CN 107122498 A CN107122498 A CN 107122498A CN 201710405522 A CN201710405522 A CN 201710405522A CN 107122498 A CN107122498 A CN 107122498A
- Authority
- CN
- China
- Prior art keywords
- information
- retrieval
- subsystem
- character
- scientific
- 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
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012545 processing Methods 0.000 claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 36
- 230000010365 information processing Effects 0.000 claims abstract description 30
- 230000005540 biological transmission Effects 0.000 claims abstract description 29
- 238000012015 optical character recognition Methods 0.000 claims abstract description 16
- 238000013500 data storage Methods 0.000 claims abstract description 14
- 238000003860 storage Methods 0.000 claims description 8
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000011946 reduction process Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims 2
- 238000005516 engineering process Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 12
- 230000006870 function Effects 0.000 description 7
- 238000012546 transfer Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000010030 laminating Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/56—Information retrieval; Database structures therefor; File system structures therefor of still image data having vectorial format
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to Internet technical field, there is provided a kind of information retrieval categorizing system and method based on cloud computing.The system includes camera, scanner, service terminal, retrieval analysis server and cloud server, service terminal includes image processing subsystem, optical character recognition subsystem, information processing subsystem, data storage subsystem, transmission subsystem and touch display screen, image processing subsystem, optical character recognition subsystem, information processing subsystem and data storage subsystem are sequentially connected, information processing subsystem is also connected with transmission subsystem and touch display screen respectively, camera and scanner are connected with image processing subsystem, transmission subsystem, retrieval analysis server and cloud server are sequentially connected.Information retrieval categorizing system and method for the invention based on cloud computing, can accelerate information and enter to record speed, improve the recall precision of scientific and technical literature.
Description
Technical field
The present invention relates to Internet technical field, and in particular to a kind of information retrieval categorizing system and side based on cloud computing
Method.
Background technology
" cloud computing concept is proposed that narrow sense cloud computing refers to the delivery of IT infrastructure and uses mould by Google
Formula, refer to by network with demand, easy extension way obtain needed for resource.The cloud computing of broad sense refers to the delivery of service and made
With pattern, refer to by network with demand, easy extension way obtain needed for service.Cloud computing will turn using " calculating " from terminal
Service terminal is moved on to, so as to weaken the process demand to mobile terminal device.So mobile terminal mainly undertakes hands over user
Mutual function, complicated computing transfers to cloud server to handle, and terminal does not need powerful operational capability both to have responded user's operation,
And by result presentation to user, so as to realize abundant application.
But, in actual application, it is the pre-stored scientific and technical literature data of retrieval mostly, comparison paper can not be retrieved
Matter document, needs professional that scientific and technical archive is converted into electronic file form, then be retrieved more.Meanwhile, in document
In retrieving, type to be retrieved is not determined, and it is big to retrieve data volume.User, can not after retrieval result is obtained
Enough according to user's request, shown.
How to accelerate information and enter to record speed, improve the recall precision of scientific and technical literature, be those skilled in the art's urgent need to resolve
The problem of.
The content of the invention
For defect of the prior art, the invention provides a kind of information retrieval categorizing system based on cloud computing and side
Method, can accelerate information and enter to record speed, improve the recall precision of scientific and technical literature.
In a first aspect, the present invention provides a kind of information retrieval categorizing system based on cloud computing, the system includes:Lead to successively
Believe terminal, retrieval analysis server and the cloud server of connection, terminal is used to send retrieval request to retrieval analysis server,
Retrieval analysis server is used to analyze retrieval request, and sends to corresponding cloud server, and cloud server is used for
According to retrieval request, based on the retrieval of cloud computing execution information.
The present invention provides another information retrieval categorizing system based on cloud computing, the system include camera, scanner,
Service terminal, retrieval analysis server and cloud server, service terminal include image processing subsystem, optical character identification
System, information processing subsystem, data storage subsystem, transmission subsystem and touch display screen, image processing subsystem, optics
Text region subsystem, information processing subsystem and data storage subsystem are sequentially connected, information processing subsystem also respectively with
Transmission subsystem and touch display screen connection, camera and scanner are connected with image processing subsystem, transmission subsystem, inspection
Rope Analysis server and cloud server are sequentially connected, and camera is used for the image information or video information for gathering scientific and technical archive,
And transmit to image processing subsystem, scanner is used to scan scientific and technical archive, obtains scanning information, and transmit to image procossing
System, image processing subsystem is used for pre-processed image information, video information or scanning information, obtains the image text of object format
Part, optical character recognition subsystem is used to recognize character in image file, obtains the character information of scientific and technical archive, and transmit to
Information processing subsystem, information processing subsystem is used for according to character information, generates retrieval request, and by retrieval request and character
Information is transmitted to retrieval analysis server by transmission subsystem, the retrieval result for being additionally operable to feed back transmission subsystem keep in
Data storage subsystem, and the idsplay order transmitted according to touch display screen, transfer retrieval result from data storage subsystem,
Transmit to touch display screen, retrieval analysis server is used to analyze retrieval request, obtains the retrieval type of retrieval request, it is determined that with
The corresponding target cloud server of type is retrieved, and retrieval request and character information are sent to target cloud server, target
Cloud server is used for according to retrieval request, according to character information, based on the retrieval of cloud computing execution information, obtains retrieval result,
And retrieval result is passed sequentially through into retrieval analysis server, transmission subsystem transmitted to information processing subsystem, data storage
System is used to keep in retrieval result, and touch display screen is used for the idsplay order for receiving user's input, and transmits to information processing
System, is additionally operable to the retrieval result of display information processing subsystem transmission.
Further, image processing subsystem includes the digital analog converter and DSP Processor that are sequentially connected, camera and sweeps
Retouch instrument to be connected with digital analog converter, DSP Processor is connected with optical character recognition subsystem, digital analog converter is used for will shooting
The video information of head collection is converted to digital information, and DSP Processor is used for real-time pre-processed digital information, image information and scanning
Information, obtains the image file of object format.
Further, optical character recognition subsystem includes arm processor, and DSP Processor passes through at HPI interfaces and ARM
Device connection is managed, the information that HPI interfaces are used between DSP and arm processor is exchanged, arm processor is used to recognize object format
Image file, obtains text information.
Based on above-mentioned any information retrieval categorizing system embodiment based on cloud computing, further, transmission subsystem bag
The couple in router being sequentially connected and hardware firewall are included, information processing subsystem is connected to access route by wireless network
Device, the safe access gateway of hardware firewall is connected to retrieval analysis server.
Second aspect, the present invention provides a kind of information retrieval sorting technique based on cloud computing, and this method includes:
Information input step:The image information or video information of scientific and technical archive, or scanning scientific and technical archive are gathered, scanning is obtained
Information;
Image processing step:Pre-processed image information, video information or scanning information, obtain the image text of object format
Part;
Optical character identification step:The character in image file is recognized, the character information of scientific and technical archive is obtained;
Retrieval request generation step:According to character information, retrieval request is generated;
Retrieval request analytical procedure:Retrieval request is analyzed, the retrieval type of retrieval request is obtained, it is determined that with retrieving type phase
The address for the target cloud server answered;
Record the source address of retrieval request;
According to the address of target cloud server, the source address of retrieval request, character information and retrieval request is sent;
Information retrieval step:According to retrieval request, according to character information, based on the retrieval of cloud computing execution information, inspection is obtained
Hitch fruit, and according to the source address of retrieval request, feedback searching result;
Information display step:The idsplay order of user's input is received, according to idsplay order, the retrieval result of feedback is shown.
Further, pre-processed image information, video information or scanning information, obtain the image file of object format, tool
Body includes:
According to the acquisition time of every two field picture, video information is decomposed into every two field picture;
The every two field picture or scanning information decomposed to image information, video information carries out smooth, noise reduction process;
According to specified storage format, every two field picture that the image information after smooth, noise reduction process, video information are decomposed
Or scanning information enters row format conversion, obtains the image file of object format.
Further, the character in identification image file, obtains the character information of scientific and technical archive, specifically includes:
According to the gray value of image file, the character in image file is recognized, the character information of scientific and technical archive, image is obtained
File is bianry image.
Based on above-mentioned any information retrieval sorting technique embodiment based on cloud computing, further, according to retrieval request,
According to character information, based on the retrieval of cloud computing execution information, retrieval result is obtained, and according to the source address of retrieval request, feedback
Retrieval result, is specifically included:
According to retrieval request, pre-stored scientific and technical archive is transferred;
The keyword or summary info of character information and every scientific and technical archive are compared, contrast is obtained;
By contrast highest scientific and technical archive, as retrieval result, and transmit to the source address of retrieval request.
As shown from the above technical solution, the information retrieval categorizing system and method based on cloud computing that the present embodiment is provided,
The scientific and technical archive of record to be entered can be gathered by camera, image information or video information is formed, or treat by scanner collection
Enter to record the scanning information of scientific and technical archive, complete information gathering.Meanwhile, image processing subsystem is located in advance to the information collected
Reason, in order to which optical character recognition subsystem can recognize that text information, that accelerates scientific and technical literature data enters record process.
Meanwhile, the system determines the type of retrieval request by retrieval analysis server, then is retrieved, in order to improve
The recall precision of scientific and technical literature.Also, the system can also will receive the idsplay order that user clicks, by the retrieval knot of feedback
Fruit is shown, facilitates user to carry out information browse.
Therefore, information retrieval categorizing system and method for the present embodiment based on cloud computing, can accelerate information and enter to record speed,
Improve the recall precision of scientific and technical literature.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art
The accompanying drawing used required in embodiment or description of the prior art is briefly described.In all of the figs, similar element
Or part is general by similar reference mark.In accompanying drawing, each element or part might not be drawn according to actual ratio.
Fig. 1 shows a kind of structural representation of information retrieval categorizing system based on cloud computing provided by the present invention;
Fig. 2 shows the method flow of another information retrieval categorizing system based on cloud computing provided by the present invention
Figure.
Embodiment
The embodiment of technical solution of the present invention is described in detail below in conjunction with accompanying drawing.Following examples are only used for
Clearly illustrate technical scheme, therefore be intended only as example, and the protection of the present invention can not be limited with this
Scope.
It should be noted that unless otherwise indicated, technical term or scientific terminology used in this application should be this hair
The ordinary meaning that bright one of ordinary skill in the art are understood.
In a first aspect, a kind of information retrieval categorizing system based on cloud computing that the embodiment of the present invention is provided, the system
Including the terminal communicated to connect successively, retrieval analysis server and cloud server, terminal is used to send retrieval request to retrieval
Analysis server, retrieval analysis server is used to analyze retrieval request, and sends to corresponding cloud server, high in the clouds
Server is used for according to retrieval request, based on the retrieval of cloud computing execution information.
Another information retrieval categorizing system based on cloud computing that the embodiment of the present invention is provided, with reference to Fig. 1, the system
Including camera 1, scanner 2, service terminal 3, retrieval analysis server 4 and cloud server 5, service terminal 3 includes image
Processing subsystem 31, optical character recognition subsystem 32, information processing subsystem, data storage subsystem 34, transmission subsystem
35 and touch display screen 36, image processing subsystem 31, optical character recognition subsystem 32, information processing subsystem and data are deposited
Storage subsystem 34 is sequentially connected, and information processing subsystem is also connected with transmission subsystem 35 and touch display screen 36 respectively, shooting
First 1 and scanner 2 be connected with image processing subsystem 31, transmission subsystem 35, retrieval analysis server 4 and cloud server
5 are sequentially connected, and camera 1 is used for the image information or video information for gathering scientific and technical archive, and transmits to image processing subsystem
31, scanner 2 is used to scan scientific and technical archive, obtains scanning information, and transmit to image processing subsystem 31, image procossing subsystem
System 31 is used for pre-processed image information, video information or scanning information, obtains the image file of object format, optical character identification
Subsystem 32 is used to recognize the character in image file, obtains the character information of scientific and technical archive, and transmits to information processing subsystem
System, information processing subsystem is used for according to character information, generates retrieval request, and retrieval request and character information are passed through into transmission
Subsystem 35 is transmitted to retrieval analysis server 4, is additionally operable to keep in the retrieval result that transmission subsystem 35 is fed back to data and is deposited
Subsystem 34, and the idsplay order transmitted according to touch display screen 36 are stored up, retrieval result is transferred from data storage subsystem 34,
Transmit to touch display screen 36, retrieval analysis server 4 is used to analyze retrieval request, obtains the retrieval type of retrieval request, really
Fixed target cloud server 5 corresponding with retrieval type, and retrieval request and character information are sent to target cloud server
5, target cloud server 5 is used for according to retrieval request, according to character information, based on the retrieval of cloud computing execution information, obtains inspection
Hitch fruit, and retrieval result is passed sequentially through into retrieval analysis server 4, transmission subsystem 35 transmitted to information processing subsystem,
Data storage subsystem 34 is used to keep in retrieval result, and touch display screen 36 is used for the idsplay order for receiving user's input, and passes
Information processing subsystem is transported to, the retrieval result of display information processing subsystem transmission is additionally operable to.Wherein, camera is preferred to use
CCD camera, sensitivity is high, and signal conversion is difficult distortion.
As shown from the above technical solution, the information retrieval categorizing system based on cloud computing that the present embodiment is provided, Neng Goutong
The scientific and technical archive that camera 1 gathers record to be entered is crossed, image information or video information is formed, or record to be entered is gathered by scanner 2
The scanning information of scientific and technical archive, completes information gathering.Meanwhile, 31 pairs of information collected of image processing subsystem are located in advance
Reason, in order to which optical character recognition subsystem 32 can recognize that text information, that accelerates scientific and technical literature data enters record process.
Meanwhile, the system determines the type of retrieval request by retrieval analysis server 4, then is retrieved, in order to carry
The recall precision of high-tech document.Also, the system can also will receive the idsplay order that user clicks, by the retrieval of feedback
As a result shown, facilitate user to carry out information browse.
Therefore, information retrieval categorizing system of the present embodiment based on cloud computing, can accelerate information and enter to record speed, raising section
The recall precision of skill document.
It is specifically, right in order to further improve the reliability of information retrieval categorizing system of the present embodiment based on cloud computing
In image processing subsystem, image processing subsystem 31 includes the digital analog converter and DSP Processor being sequentially connected, camera 1
It is connected with scanner 2 with digital analog converter, DSP Processor is connected with optical character recognition subsystem 32, digital analog converter is used
Digital information is converted in the video information for gathering camera 1, DSP Processor is used for real-time pre-processed digital information, image
Information and scanning information, obtain the image file of object format.Here, digital analog converter can be changed video information,
To accelerate the treatment effeciency of DSP Processor.Meanwhile, the system can carry out the image information of big data quantity using DSP Processor
Processing, operation efficiency is fast, and the degree of accuracy is high.In actual application, DSP Processor can use TMS320DM642 cores
Piece is realized.
Specifically, for optical character recognition subsystem, optical character recognition subsystem 32 is included at arm processor, DSP
Reason device is connected by HPI interfaces with arm processor, and the information that HPI interfaces are used between DSP and arm processor is exchanged, at ARM
Reason device is used for the image file for recognizing object format, obtains text information.Here, the system transmits DSP processing by HPI interfaces
Image file after device processing, and handled by arm processor, low in energy consumption, compatibility is strong, and instruction execution efficiency is high, helps
In the character information for quickly recognizing scientific and technical archive.In actual application, chip signal preferably is S3C6410.
Specifically, for transmission subsystem, transmission subsystem 35 includes the couple in router being sequentially connected and hardware fire prevention
Wall, information processing subsystem is connected to couple in router by wireless network, and the safe access gateway of hardware firewall is connected to
Retrieval analysis server 4.Here, the system is carried out data transmission by couple in router and hardware firewall, it is favorably improved
The safety and reliability of data transfer, it is to avoid data are compromised in transmitting procedure or steal.
Second aspect, the embodiment of the present invention provides a kind of information retrieval sorting technique based on cloud computing, with reference to Fig. 2,
This method includes:
Information input step S1:The image information or video information of scientific and technical archive, or scanning scientific and technical archive are gathered, acquisition is swept
Retouch information;
Image processing step S2:Pre-processed image information, video information or scanning information, obtain the image text of object format
Part;
Optical character identification step S3:The character in image file is recognized, the character information of scientific and technical archive is obtained;
Retrieval request generation step S4:According to character information, retrieval request is generated;
Retrieval request analytical procedure S5:Retrieval request is analyzed, the retrieval type of retrieval request is obtained, it is determined that with retrieving type
The address of corresponding target cloud server;
Record the source address of retrieval request;
According to the address of target cloud server, the source address of retrieval request, character information and retrieval request is sent;
Information retrieval step S6:According to retrieval request, according to character information, based on the retrieval of cloud computing execution information, obtain
Retrieval result, and according to the source address of retrieval request, feedback searching result;
Information display step S7:The idsplay order of user's input is received, according to idsplay order, the retrieval knot of feedback is shown
Really.
As shown from the above technical solution, the information retrieval sorting technique based on cloud computing that the present embodiment is provided, Neng Goutong
The scientific and technical archive that camera gathers record to be entered is crossed, image information or video information is formed, or Dai Rulu sections are gathered by scanner
The scanning information of skill archives, completes information gathering.Meanwhile, image processing sub-method is pre-processed to the information collected, with
It is easy to optical character to recognize that submethod can recognize that text information, that accelerates scientific and technical literature data enters record process.
Meanwhile, this method determines the type of retrieval request by retrieval analysis server, then is retrieved, in order to improve
The recall precision of scientific and technical literature.Also, this method can also will receive the idsplay order that user clicks, by the retrieval knot of feedback
Fruit is shown, facilitates user to carry out information browse.
Therefore, information retrieval sorting technique of the present embodiment based on cloud computing, can accelerate information and enter to record speed, raising section
The recall precision of skill document.
In order to further improve the reliability of information retrieval sorting technique of the present embodiment based on cloud computing, specifically, in advance
Image information, video information or scanning information are handled, the image file of object format is obtained, specifically includes:According to every two field picture
Acquisition time, video information is decomposed into every two field picture, to image information, video information decompose every two field picture or scanning letter
Breath carries out smooth, noise reduction process, according to specified storage format, by the image information after smooth, noise reduction process, video information point
The every two field picture or scanning information of solution enter row format conversion, obtain the image file of object format.Here, this method is using flat
Sliding, noise reduction process mode, is handled the noise in the presence of image, in order to improve image recognition processes accuracy and
The interference that noise in operation efficiency, reduction image is brought.
In actual application, video information is decomposed into by information retrieval sorting technique of the present embodiment based on cloud computing
Before per two field picture, video information can also be carried out transcoding by this method, and detailed process is as follows:
After video information is received, the transcoding processing unit for selecting transcoding multiple to be more than predetermined threshold in resource pool is made
For work disposal unit, wherein, predetermined threshold is associated with playing maximum delay and video segmentation predetermined minimum value.
Judge whether the transcoding multiple summation of T optional work disposal units is less than 1:If T optional work disposal units
Transcoding multiple summation be not less than 1, then video information is split, is that the optional work disposal units of T distribute corresponding lengths
Video-frequency band, to carry out parallel transcoding processing, wherein, video segment length with play maximum delay, work disposal unit itself
Transcoding multiple associated with work disposal unit number T-phase.The transcoding information of T optional work disposal unit outputs is converged
Always, to complete video code conversion, wherein, predetermined threshold=video segmentation predetermined minimum value/(play maximum delay+video segmentation
Predetermined minimum value).If the transcoding multiple summation of T optional work disposal units is less than 1, refuse transcoding task.
Here, this method is constrained by the real-time of the operational capability according to transcoding processing unit and transcoding task, it is right
Video information carries out intelligent scissor, and corresponding transcoding processing unit progress is dispatched to be divided into different size of video-frequency band
Parallel processing, so as to while ensureing that transcoding task is real-time, improve transcoding efficiency, then by the video information after transcoding
It is decomposed into every two field picture.
Specifically, the character in identification image file, obtains the character information of scientific and technical archive, specifically includes:According to image
Character in the gray value of file, identification image file, obtains the character information of scientific and technical archive, image file is bianry image.
Here, this method recognizes the character in image file, in order to obtain text information, root by the gray value in image file
According to the gray value in image file, character is recognized, accuracy is high, the Wen Yi of the former scientific and technical archive of laminating, without information checkout procedure,
Save human cost.
In actual application, according to the gray value of image file, the character in image file is recognized, scientific and technological shelves are obtained
The character information of case, implements process as follows:
Coloured image in the image file collected is converted to by 8 256 color shade images using maximum value process, used
Maximum variance between clusters choose I values, are the character zone in bianry image, repositioning image by greyscale image transitions, to character
After region is filtered, the closed operation of complex potential after first expanding is carried out, then splits acquisition monocase image.Calculate in monocase image
Comprising hole number.Hole number according to being included in image is classified to character picture, to hole number identical character picture,
Line is assisted in identifying by addition or aspect ratio example is calculated digital identification is carried out to character picture.When the character picture calculated
Hole number when being 2, then the character is digital " 8 ", end of identification;When the hole number of the character picture calculated is not 2, then
Determine whether, when the hole number of the character picture calculated is 1, then the character is digital " 0 ", " 6 " or " 9 ", needs addition
Assist in identifying line or calculate aspect ratio example and digital identification is carried out to character picture, when the hole number of the character picture calculated
Not be 1 when, then determine whether, when the character picture calculated hole number be 0 when, then the character for numeral " 1,2,3,4,
5 " or " 7 ", it need to add to assist in identifying line or calculate aspect ratio example that digital identification is carried out to character picture, when the word calculated
The hole number for according with image is not 0, then nonnumeric character, end of identification, output character information.
Here, this method is classified according to Digital Character Image hole number to Digital Character Image, to hole after classification
Quantity identical character picture, assists in identifying the method that calculates hole number after line again using increase, reduce operand, it is to avoid existing
Have to character picture size normalized in method, recognition accuracy is high, strong robustness.
Specifically, according to retrieval request, according to character information, based on the retrieval of cloud computing execution information, retrieval result is obtained,
And according to the source address of retrieval request, feedback searching result is specifically included:According to retrieval request, pre-stored scientific and technological shelves are transferred
Case, the keyword or summary info of character information and every scientific and technical archive are compared, and contrast are obtained, by contrast highest
Scientific and technical archive, as retrieval result, and transmit to the source address of retrieval request.Here, this method is carried out by character information
Retrieval, improves the degree of accuracy of retrieval.Also, this method is according to retrieval request, transfer corresponding with the type of the retrieval request
Scientific and technical archive, reduces the quantity of scientific and technical archive to be compared, reduces operational data amount.
In actual application, according to retrieval request, transfer before pre-stored scientific and technical archive, this method also includes building
Scientific and technical literature ontology library is found, the process of implementing is:Semantic analysis is carried out to scientific and technical literature, to extract Chinese key and English
Keyword.Identical Chinese key or English keyword are merged, synonymous or near adopted Chinese key and English are closed
Keyword is classified as a class.To each class keywords, a technology literature information body link is set up, meanwhile, set up the science and technology
The index of documentation & info body link sensing source scientific and technical literature.Gather the link of technology literature information body and the technology literature information
The index of body link sensing source scientific and technical literature, forms scientific and technical literature ontology library.Wherein, technology literature information includes:Scientific and technological text
Topic, author, summary, keyword, publication time, the background parts of scientific and technical literature, problematic portion and the solution page offered.
The keyword or summary info of character information and every scientific and technical archive are compared, are specially:The character of reading
Information, searches the technology literature information sheet corresponding to the same class keywords matched with the term in scientific and technical literature ontology library
Body is linked.Pointed to by the link of technology literature information body and technology literature information body link corresponding to same class keywords
The index of source scientific and technical literature, finds out pertinent literature, and be shown to user by predetermined order.
Here, this method by set up have the same class keywords that are stored with scientific and technical literature ontology library, scientific and technical literature ontology library,
With the technology literature information body link corresponding to class keywords and technology literature information body link sensing source scientific and technical literature
Index, be synonymous or nearly adopted Chinese key and English keyword set with class keywords so that user inputs term
Afterwards, the technology literature information sheet corresponding to the same class keywords that the term matches only need to be searched in scientific and technical literature ontology library
Body is linked, and is pointed to by the link of technology literature information body and technology literature information body link corresponding to same class keywords
The index of source scientific and technical literature, finds out pertinent literature, and be shown to user by predetermined order, you can retrieval is realized, compared to existing
Technology, eliminates the original language in retrieving to the translation process of object language, can improve the accuracy of Indexing of Scien. and Tech. Literature.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or the spy that the embodiment or example are described
Point is contained at least one embodiment of the present invention or example.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area
Art personnel can be tied the not be the same as Example or the feature of example and non-be the same as Example or example described in this specification
Close and combine.
It should be noted that the flow chart and block diagram in accompanying drawing show the service of multiple embodiments according to the present invention
Architectural framework in the cards, function and the operation of device, method and computer program product.At this point, flow chart or block diagram
In each square frame can represent a part for a module, program segment or code, the module, one of program segment or code
Subpackage is containing one or more executable instructions for being used to realize defined logic function.It should also be noted that being used as replacement at some
Realization in, the function of being marked in square frame can also with different from the order marked in accompanying drawing occur.For example, two continuous
Square frame can essentially perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is according to involved work(
Depending on energy.It is also noted that each square frame in block diagram and/or flow chart and the square frame in block diagram and/or flow chart
Combination, can be realized with the special hardware based server of function or action as defined in performing, or can be with special
The combination of hardware and computer instruction is realized.
The configuration device that the embodiment of the present invention is provided can be computer program product, including store program code
Computer-readable recording medium, the instruction that described program code includes can be used for performing the side described in previous methods embodiment
Method, implements and can be found in embodiment of the method, will not be repeated here.
It is apparent to those skilled in the art that, for convenience and simplicity of description, the service of foregoing description
The specific work process of device, device and unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
, can in several embodiments provided herein, it should be understood that disclosed server, apparatus and method
To realize by another way.Device embodiment described above is only schematical, for example, stroke of the unit
Point, only a kind of division of logic function can have other dividing mode when actually realizing, in another example, multiple units or group
Part can combine or be desirably integrated into another server, or some features can be ignored, or not perform.It is another, show
Show or the coupling each other discussed or direct-coupling or communication connection can be by some communication interfaces, device or unit
INDIRECT COUPLING or communication connection, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be published to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.
If the function is realized using in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Understood based on such, technical scheme is substantially in other words
The part contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are to cause a computer equipment (can be individual
People's computer, server, or network equipment etc.) perform all or part of step of each of the invention embodiment methods described.
And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
Finally it should be noted that:Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations;To the greatest extent
The present invention is described in detail with reference to foregoing embodiments for pipe, it will be understood by those within the art that:Its according to
The technical scheme described in foregoing embodiments can so be modified, or which part or all technical characteristic are entered
Row equivalent substitution;And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology
The scope of scheme, it all should cover among the claim of the present invention and the scope of specification.
Claims (9)
1. a kind of information retrieval categorizing system based on cloud computing, it is characterised in that including:
Terminal, retrieval analysis server and the cloud server communicated to connect successively,
The terminal, for sending retrieval request to the retrieval analysis server,
The retrieval analysis server, for analyzing the retrieval request, and sends to corresponding cloud server,
The cloud server, for according to the retrieval request, based on the retrieval of cloud computing execution information.
2. a kind of information retrieval categorizing system based on cloud computing, it is characterised in that including:
Camera, scanner, service terminal, retrieval analysis server and cloud server,
The service terminal includes image processing subsystem, optical character recognition subsystem, information processing subsystem, data storage
Subsystem, transmission subsystem and touch display screen,
Described image processing subsystem, the optical character recognition subsystem, described information processing subsystem and the data are deposited
Storage subsystem is sequentially connected, and described information processing subsystem also connects with the transmission subsystem and the touch display screen respectively
Connect,
The camera and the scanner are connected with described image processing subsystem, the transmission subsystem, the retrieval
Analysis server and the cloud server are sequentially connected,
The camera, for gathering the image information or video information of scientific and technical archive, and is transmitted to described image processing subsystem
System,
The scanner, for scanning scientific and technical archive, obtains scanning information, and transmits to described image processing subsystem,
Described image processing subsystem, for pre-processing described image information, the video information or the scanning information, is obtained
The image file of object format,
The optical character recognition subsystem, for recognizing the character in described image file, obtains the character letter of scientific and technical archive
Breath, and transmit to described information processing subsystem,
Described information processing subsystem, for according to the character information, generating retrieval request, and by the retrieval request and institute
State character information to transmit to the retrieval analysis server by the transmission subsystem, be additionally operable to feed back transmission subsystem
Retrieval result is kept in data storage subsystem, and the idsplay order transmitted according to touch display screen, from data storage
Retrieval result is transferred in system, is transmitted to touch display screen,
The retrieval analysis server, for analyzing the retrieval request, obtains the retrieval type of the retrieval request, it is determined that with
The retrieval corresponding target cloud server of type, and the retrieval request and the character information are sent to the target
Cloud server,
The target cloud server, for according to the retrieval request, according to the character information, letter to be performed based on cloud computing
Breath retrieval, obtains retrieval result, and the retrieval result is passed sequentially through into the retrieval analysis server, the transmission subsystem
Transmit to described information processing subsystem,
The data storage subsystem, for keeping in retrieval result,
The touch display screen, for receiving the idsplay order of user's input, and transmits to described information processing subsystem, also uses
In the retrieval result of display described information processing subsystem transmission.
3. the information retrieval categorizing system based on cloud computing according to claim 2, it is characterised in that
Described image processing subsystem includes the digital analog converter and DSP Processor being sequentially connected,
The camera and the scanner are connected with the digital analog converter, the DSP Processor and the optical character
Recognition subsystem is connected,
The digital analog converter, the video information for the camera to be gathered is converted to digital information,
The DSP Processor, for pre-processing the digital information, described image information and the scanning information in real time, is obtained
The image file of object format.
4. the information retrieval categorizing system based on cloud computing according to claim 3, it is characterised in that the optical character is known
Small pin for the case system includes arm processor,
The DSP Processor is connected by HPI interfaces with the arm processor,
The HPI interfaces, are exchanged for the information between DSP and arm processor,
The arm processor, the image file for recognizing the object format obtains text information.
5. the information retrieval categorizing system based on cloud computing according to claim 2, it is characterised in that
The transmission subsystem includes couple in router and the hardware firewall being sequentially connected,
Described information processing subsystem is connected to the couple in router by wireless network,
The safe access gateway of the hardware firewall is connected to the retrieval analysis server.
6. a kind of information retrieval sorting technique based on cloud computing, it is characterised in that including:
Information input step:The image information or video information of scientific and technical archive, or scanning scientific and technical archive are gathered, scanning letter is obtained
Breath;
Image processing step:Described image information, the video information or the scanning information are pre-processed, object format is obtained
Image file;
Optical character identification step:The character in described image file is recognized, the character information of scientific and technical archive is obtained;
Retrieval request generation step:According to the character information, retrieval request is generated;
Retrieval request analytical procedure:Analyze the retrieval request, obtain the retrieval type of the retrieval request, it is determined that with the inspection
The address of the corresponding target cloud server of rope type;
Record the source address of the retrieval request;
According to the address of the target cloud server, the retrieval request, the character information and the retrieval request are sent
Source address;
Information retrieval step:According to the retrieval request, according to the character information, based on the retrieval of cloud computing execution information, obtain
Retrieval result is taken, and according to the source address of the retrieval request, feedback searching result;
Information display step:The idsplay order of user's input is received, according to the idsplay order, the retrieval result of feedback is shown.
7. the information retrieval sorting technique based on cloud computing according to claim 6, it is characterised in that
Described image information, the video information or the scanning information are pre-processed, the image file of object format is obtained, specifically
Including:
According to the acquisition time of every two field picture, the video information is decomposed into every two field picture;
The every two field picture or scanning information decomposed to described image information, the video information carries out smooth, noise reduction process;
According to specified storage format, every two field picture that the image information after smooth, noise reduction process, the video information are decomposed
Or scanning information enters row format conversion, obtains the image file of object format.
8. the information retrieval sorting technique based on cloud computing according to claim 6, it is characterised in that
The character in described image file is recognized, the character information of scientific and technical archive is obtained, specifically includes:
According to the gray value of described image file, the character in described image file is recognized, the character of the scientific and technical archive is obtained
Information, described image file is bianry image.
9. the information retrieval sorting technique based on cloud computing according to claim 6, it is characterised in that
According to the retrieval request, according to the character information, based on the retrieval of cloud computing execution information, retrieval result is obtained, and
According to the source address of the retrieval request, feedback searching result is specifically included:
According to the retrieval request, pre-stored scientific and technical archive is transferred;
The keyword or summary info of the character information and every scientific and technical archive are compared, contrast is obtained;
By contrast highest scientific and technical archive, as retrieval result, and transmit to the source address of the retrieval request.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710405522.3A CN107122498A (en) | 2017-06-01 | 2017-06-01 | Information retrieval categorizing system and method based on cloud computing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710405522.3A CN107122498A (en) | 2017-06-01 | 2017-06-01 | Information retrieval categorizing system and method based on cloud computing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107122498A true CN107122498A (en) | 2017-09-01 |
Family
ID=59730049
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710405522.3A Pending CN107122498A (en) | 2017-06-01 | 2017-06-01 | Information retrieval categorizing system and method based on cloud computing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107122498A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107943888A (en) * | 2017-11-16 | 2018-04-20 | 长沙瑞晓知识产权服务有限公司 | Information retrieval system based on cloud computing |
CN109784267A (en) * | 2019-01-10 | 2019-05-21 | 济南浪潮高新科技投资发展有限公司 | A kind of mobile terminal multi-source fusion image, semantic content generation system and method |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202486780U (en) * | 2012-03-06 | 2012-10-10 | 郑州航空工业管理学院 | Information retrieval system based on cloud computing |
CN103163155A (en) * | 2013-02-26 | 2013-06-19 | 上海大学 | Device and method for detecting keyboard defects |
CN103995904A (en) * | 2014-06-13 | 2014-08-20 | 上海珉智信息科技有限公司 | Recognition system for image file electronic data |
CN104142955A (en) * | 2013-05-08 | 2014-11-12 | ***通信集团浙江有限公司 | Method and terminal for recommending learning courses |
CN104883591A (en) * | 2015-06-06 | 2015-09-02 | 孔华 | Network communication based video file retrieval method |
CN205281495U (en) * | 2016-01-05 | 2016-06-01 | 长春职业技术学院(长春市职业技术教育中心长春市财政学校) | Information retrieval system based on cloud calculates |
CN105893404A (en) * | 2015-11-11 | 2016-08-24 | 乐视云计算有限公司 | Natural information identification based pushing system and method, and client |
CN205540723U (en) * | 2016-01-22 | 2016-08-31 | 宿州学院 | Information retrieval system based on cloud calculates |
CN105956186A (en) * | 2016-06-03 | 2016-09-21 | 捷开通讯科技(上海)有限公司 | Picture search system and method |
CN106503199A (en) * | 2016-11-02 | 2017-03-15 | 河南理工大学 | A kind of network machine information retrieval system |
CN106682665A (en) * | 2016-12-27 | 2017-05-17 | 陕西科技大学 | Digital recognition method for seven-segment digital indicator |
CN106686406A (en) * | 2015-11-05 | 2017-05-17 | 中国电信股份有限公司 | Method and apparatus for realizing video real-time code-converting pre-processing |
CN106709050A (en) * | 2017-01-05 | 2017-05-24 | 黑河学院 | Environment law case storage inquiring system |
-
2017
- 2017-06-01 CN CN201710405522.3A patent/CN107122498A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202486780U (en) * | 2012-03-06 | 2012-10-10 | 郑州航空工业管理学院 | Information retrieval system based on cloud computing |
CN103163155A (en) * | 2013-02-26 | 2013-06-19 | 上海大学 | Device and method for detecting keyboard defects |
CN104142955A (en) * | 2013-05-08 | 2014-11-12 | ***通信集团浙江有限公司 | Method and terminal for recommending learning courses |
CN103995904A (en) * | 2014-06-13 | 2014-08-20 | 上海珉智信息科技有限公司 | Recognition system for image file electronic data |
CN104883591A (en) * | 2015-06-06 | 2015-09-02 | 孔华 | Network communication based video file retrieval method |
CN106686406A (en) * | 2015-11-05 | 2017-05-17 | 中国电信股份有限公司 | Method and apparatus for realizing video real-time code-converting pre-processing |
CN105893404A (en) * | 2015-11-11 | 2016-08-24 | 乐视云计算有限公司 | Natural information identification based pushing system and method, and client |
CN205281495U (en) * | 2016-01-05 | 2016-06-01 | 长春职业技术学院(长春市职业技术教育中心长春市财政学校) | Information retrieval system based on cloud calculates |
CN205540723U (en) * | 2016-01-22 | 2016-08-31 | 宿州学院 | Information retrieval system based on cloud calculates |
CN105956186A (en) * | 2016-06-03 | 2016-09-21 | 捷开通讯科技(上海)有限公司 | Picture search system and method |
CN106503199A (en) * | 2016-11-02 | 2017-03-15 | 河南理工大学 | A kind of network machine information retrieval system |
CN106682665A (en) * | 2016-12-27 | 2017-05-17 | 陕西科技大学 | Digital recognition method for seven-segment digital indicator |
CN106709050A (en) * | 2017-01-05 | 2017-05-24 | 黑河学院 | Environment law case storage inquiring system |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107943888A (en) * | 2017-11-16 | 2018-04-20 | 长沙瑞晓知识产权服务有限公司 | Information retrieval system based on cloud computing |
CN109784267A (en) * | 2019-01-10 | 2019-05-21 | 济南浪潮高新科技投资发展有限公司 | A kind of mobile terminal multi-source fusion image, semantic content generation system and method |
CN109784267B (en) * | 2019-01-10 | 2021-10-15 | 山东浪潮科学研究院有限公司 | Mobile terminal multi-source fusion image semantic content generation system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10191650B2 (en) | Actionable content displayed on a touch screen | |
JP4395176B2 (en) | Future technology trend prediction support apparatus, method, program, and method for providing future technology trend prediction support service | |
US7877706B2 (en) | Controlling a document based on user behavioral signals detected from a 3D captured image stream | |
US20120232987A1 (en) | Image-based search interface | |
WO2020005731A1 (en) | Text entity detection and recognition from images | |
CN110362714A (en) | The searching method and device of video content | |
CN103942268B (en) | Search for method, equipment and the application interface being combined with application | |
CN102663138A (en) | Method and device for inputting formula query terms | |
CN112507090B (en) | Method, apparatus, device and storage medium for outputting information | |
CN113365147A (en) | Video editing method, device, equipment and storage medium based on music card point | |
WO2021184026A1 (en) | Audio-visual fusion with cross-modal attention for video action recognition | |
CN113486833A (en) | Multi-modal feature extraction model training method and device and electronic equipment | |
CN207051898U (en) | Information retrieval categorizing system based on cloud computing | |
CN114238573A (en) | Information pushing method and device based on text countermeasure sample | |
CN107122498A (en) | Information retrieval categorizing system and method based on cloud computing | |
CN109408658A (en) | Expression picture reminding method, device, computer equipment and storage medium | |
CN114241501A (en) | Image document processing method and device and electronic equipment | |
CN109391836B (en) | Supplementing a media stream with additional information | |
EP3564833B1 (en) | Method and device for identifying main picture in web page | |
CN116011447B (en) | E-commerce comment analysis method, system and computer readable storage medium | |
Belhi et al. | Deep learning and cultural heritage: the CEPROQHA project case study | |
CN116758558A (en) | Cross-modal generation countermeasure network-based image-text emotion classification method and system | |
CN110069691A (en) | For handling the method and apparatus for clicking behavioral data | |
CN116090450A (en) | Text processing method and computing device | |
CN106777124B (en) | Semantic knowledge method, apparatus and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170901 |