CN208316687U - A kind of capsule image workstation using speech recognition - Google Patents
A kind of capsule image workstation using speech recognition Download PDFInfo
- Publication number
- CN208316687U CN208316687U CN201821021973.3U CN201821021973U CN208316687U CN 208316687 U CN208316687 U CN 208316687U CN 201821021973 U CN201821021973 U CN 201821021973U CN 208316687 U CN208316687 U CN 208316687U
- Authority
- CN
- China
- Prior art keywords
- unit
- speech recognition
- amplifier
- connects
- resistance
- 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.)
- Active
Links
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The utility model proposes a kind of capsule image workstations using speech recognition, including image play unit, voice input unit, speech recognition conversion unit, control unit and text importing unit；Described image broadcast unit plays image information, the voice messaging of the voice input unit acquisition read tablet person, its output end connects the speech recognition conversion unit input terminal, the speech recognition conversion unit identifies voice messaging, obtain text information, its output end connects described control unit corresponding informance input terminal, and described control unit connects the text importing unit, by the voice messaging text importing of read tablet person.The capsule image work station structure is simple, by voice input unit and speech recognition conversion unit in such a way that voice input diagnostic message is converted into textual diagnosis information replace be manually entered diagnostic message in the way of, the both hands for having liberated doctor improve the working efficiency of read tablet.
Description
Technical field
The utility model relates to medical instruments fields, and in particular to a kind of capsule image workstation using speech recognition.
Background technique
Capsule endoscopic system is made of capsule endoscopic and image recorder, before capsule endoscopic is by optics
Lid, rear shell, antenna, radio-frequency module, battery, signal processing module and image capture module composition.Image recorder by antenna array,
Radio-frequency module, control module, signal processing module, memory module, display module, power module, USB transmission module and battery pack
At.
Image workstation access images recorder, reads and downloads the pictorial information of storage, and is shown in the display of PC machine
On screen.Capsule Endoscopy generally requires 6 hours or more, and the picture of storage is usually at 2.5 ten thousand or more, the behaviour of read tablet after inspection
As mode it is that doctor downloads to the picture of storage on PC, then by special software come playing pictures.Doctor is anti-according to picture
The symptom reflected is manually entered inspection diagnostic result, but since Capsule Endoscopy interpreting blueprints amount is also bigger, time-consuming natively long, when
When doctor identifies a certain symptom, needs to suspend interpreting blueprints, corresponding picture is saved, then be manually entered corresponding diagnostic result, most
After summarize diagnostic result, form report.There are many time consumed by such operation, and it is also inconvenient to operate, so that
Tablet reading efficiency is not high.
In order to solve this problem, application No. is a kind of entitled capsule endoscopy auxiliary film reading sides CN2011100829088
Method and its system disclose one kind and control broadcasting speed by the normalized mutual information of picture, improve read tablet speed, reduce
The scoring time of doctor.However this does not solve the problems, such as that the time consumed by read tablet operation is more fundamentally, and improves
After broadcasting speed, be easy to causeing leads to the problem for judging state of an illness inaccuracy because doctor is to the judging that the time is insufficient of pictorial information.
Utility model content
In order to overcome above-mentioned defect existing in the prior art, the purpose of the utility model is to provide a kind of raising read tablet effects
The capsule image workstation of rate.
In order to realize the above-mentioned purpose of the utility model, the utility model provides a kind of capsule figure using speech recognition
As work station, including image play unit, voice input unit, speech recognition conversion unit, control unit and text importing list
Member；
Described image broadcast unit plays image information, and the voice input unit acquires the voice messaging of read tablet person,
Output end connects the speech recognition conversion unit input terminal, and the speech recognition conversion unit identifies voice messaging,
Text information is obtained, output end connects described control unit corresponding informance input terminal, and described control unit connects the text
Display unit, by the voice messaging text importing of read tablet person.
The capsule image work station structure is simple, uses Speech Record using voice input unit and speech recognition conversion unit
Enter diagnostic message and be converted into the mode of textual diagnosis information to replace being manually entered the mode of diagnostic message, liberates the double of doctor
Hand improves the working efficiency of read tablet.
It further, further include signal processing unit, the voice input unit output end connects the signal processing list
First input terminal, the signal processing unit output end connect the speech recognition conversion unit input terminal.Speech recognition is improved to turn
Cell translation is changed into the accuracy rate of text.
Further, the signal processing unit includes filter amplification circuit, and the filter amplification circuit includes the first electricity
Appearance, the second capacitor, third capacitor, first resistor, second resistance, 3rd resistor, the 4th resistance, the 5th resistance, the 6th resistance,
Seven resistance, the first amplifier, the second amplifier, third amplifier, the first triode, the second triode and first diode；
Described first resistor one end connects the voice input unit output end, and the other end connects the one of second capacitor
End, the other end of second capacitor connect the positive terminal of first amplifier, the output end connection of first amplifier
Two branches:
One end of one connection first capacitor, one end of the 4th resistance of the first capacitor other end connection, the described 4th
The other end of resistance connects the base stage of first triode, and the emitter connection third amplifier of first triode is just
Xiang Duan, the collector of first triode connect the cathode of the first diode, the plus earth of the first diode,
The output end of the third amplifier connects the reverse side of first amplifier, the reverse side connection of the third amplifier the
One end of six resistance, the other end of the 6th resistance connect the emitter of second triode, second triode
Emitter is additionally coupled to the reverse side of second amplifier, and the base stage of second triode connects the first diode
Cathode, is also connected with the 7th resistance between the base stage and collector of the second triode, the collector connection of second triode the
One end of three capacitors, the third capacitor other end ground connection, the emitter of second triode connect second amplifier
Reverse side；
One end of another connection second resistance, the other end of the second resistance connect second amplifier
Positive terminal is connected with 3rd resistor, the output of the third amplifier between the output end and positive terminal of second amplifier
One end of the 5th resistance of end connection, the other end of the 5th resistance connect the output end of second amplifier, and described second
The output end of amplifier connects the speech recognition conversion unit input terminal.The filter amplification circuit structure is simple, can be effective
Enhanced processing is filtered to voice messaging.
Further, the voice input unit is microphone array.The interference noise of different directions can be eliminated.
It further, further include fingerprint collecting unit, the fingerprint collecting unit is connect with described control unit, verifying behaviour
The operating right of author ensure that the correctness of diagnostic message typing.
It further, further include relay, coil one end of the relay connects one I/O interface of control unit, another
End connection power supply, the power end of the voice input unit are equipped with the normally opened contact of the relay.It is described after voice authentication success
Control unit I/O interface exports high level, and relay coil obtains electric, normally opened contact closure, and voice input unit obtains electric, beginning work
Make.
The additional aspect and advantage of the utility model will be set forth in part in the description, partially will be from following description
In become obvious, or recognized by the practice of the utility model.
Detailed description of the invention
The above-mentioned and/or additional aspect and advantage of the utility model from the description of the embodiment in conjunction with the following figures will
Become obvious and be readily appreciated that, in which:
Fig. 1 is the structural block diagram of the utility model；
Fig. 2 is filter amplification circuit figure.
Specific embodiment
The embodiments of the present invention are described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning
Same or similar element or element with the same or similar functions are indicated to same or similar label eventually.Below by ginseng
The embodiment for examining attached drawing description is exemplary, and is only used for explaining the utility model, and should not be understood as to the utility model
Limitation.
In the description of the present invention, unless otherwise specified and limited, it should be noted that term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be mechanical connection or electrical connection, the company being also possible to inside two elements
It is logical, it can be directly connected, can also indirectly connected through an intermediary, for the ordinary skill in the art, it can
To understand the concrete meaning of above-mentioned term as the case may be.
As shown in Figure 1, the utility model provides a kind of capsule image workstation using speech recognition, including image is broadcast
Put unit, voice input unit, speech recognition conversion unit, control unit and text importing unit.
Image information obtained by capsule detects is stored in capsule image workstation, described image broadcast unit plays image
Information, the voice messaging of the voice input unit acquisition read tablet person, it is defeated that output end connects the speech recognition conversion unit
Enter end, the speech recognition conversion unit identifies voice messaging, obtains text information, and output end connects the control
Unit corresponding informance input terminal, described control unit connects the text importing unit, by the voice messaging text of read tablet person
Display.
While image play unit plays image, read tablet person passes through diagnosis of the voice input unit typing to current image
Information, the diagnostic message is voice signal at this time, which carries out being converted into text information through speech recognition conversion unit,
Control unit control text importing unit shows the text information.The usual text information is displayed on image play unit broadcasting
On the designated position at interface.Text is formed in report by existing software again.In the present embodiment, speech recognition conversion
Unit uses existing language and characters converter.
Wherein, voice input unit is microphone array, can eliminate the interference noise of different directions, generally include 2,4 or 6
A microphone.
The capsule image workstation further includes signal processing unit, and the voice input unit output end connects the signal
Processing unit input terminal, the signal processing unit output end connect the speech recognition conversion unit input terminal.
The signal processing unit includes filter amplification circuit, and the filter amplification circuit includes first capacitor C1, second
Capacitor C2, third capacitor C3, first resistor R1, second resistance R2,3rd resistor R3, the 4th resistance R4, the 5th resistance R5, the 6th
Resistance R6, the 7th resistance R7, the first amplifier P1, the second amplifier P2, third amplifier P3, the first triode VT1, the two or three
Pole pipe VT2 and first diode D1.
The one end the first resistor R1 connects the voice input unit output end, and the other end connects the second capacitor C2
One end, the other end of the second capacitor C2 connects the positive terminal of the first amplifier P1, the first amplifier P1's
Output end connects two branches.
One end of one connection first capacitor C1, the first capacitor C1 other end connect one end of the 4th resistance R4, institute
The other end for stating the 4th resistance R4 connects the base stage of the first triode VT1, the emitter connection of the first triode VT1
The collector of the positive terminal of third amplifier P3, the first triode VT1 connects the cathode of the first diode D1, described
The plus earth of first diode D1, the output end of the third amplifier P3 connect the reverse side of the first amplifier P1,
The reverse side of the third amplifier P3 connects one end of the 6th resistance R6, the other end connection of the 6th resistance R6 described the
The emitter of two triode VT2, the emitter of the second triode VT2 are additionally coupled to the reverse phase of the second amplifier P2
End, the base stage of the second triode VT2 connect the cathode of the first diode D1, the base stage sum aggregate of the second triode VT2
It is also connected with the 7th resistance R7 between electrode, one end of the collector connection third capacitor C3 of the second triode VT2, described the
Three capacitor C3 other ends ground connection, the emitter of the second triode VT2 connect the reverse side of the second amplifier P2.
One end of another connection second resistance R2, the other end connection of the second resistance R2 second amplification
The positive terminal of device P2 is connected with 3rd resistor R3 between the output end and positive terminal of the second amplifier P2, and the third is put
The output end of big device P3 connects one end of the 5th resistance R5, and the other end of the 5th resistance R5 connects the second amplifier P2
Output end, the output end of the second amplifier P2 connects the speech recognition conversion unit input terminal.
In order to guarantee the correctness of diagnostic message typing, which further includes fingerprint collecting unit, fingerprint collecting unit
It is connect with control unit, the operating right of verification operation person, coil one end of relay connects one I/O interface of control unit, separately
One end connects power supply, and the power end of the voice input unit is equipped with the normally opened contact of the relay.After voice authentication success, institute
State control unit I/O interface output high level, relay coil obtain it is electric, normally opened contact closure, voice input unit obtain it is electric, start
Work.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the utility model.In the present specification, to the schematic table of above-mentioned term
Stating may not refer to the same embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be
It can be combined in any suitable manner in any one or more embodiment or examples.
While there has been shown and described that the embodiments of the present invention, it will be understood by those skilled in the art that:
These embodiments can be carried out with a variety of variations, modification, replacement in the case where not departing from the principles of the present invention and objective
And modification, the scope of the utility model are defined by the claims and their equivalents.
Claims (6)
1. a kind of capsule image workstation using speech recognition, which is characterized in that including image play unit, voice input list
Member, speech recognition conversion unit, control unit and text importing unit；
Described image broadcast unit plays image information；
The voice messaging of the voice input unit acquisition read tablet person, output end connect the speech recognition conversion unit input
End；
The speech recognition conversion unit identifies voice messaging, obtains text information, and output end connects the control
Unit corresponding informance input terminal；
Described control unit connects the text importing unit, by the voice messaging text importing of read tablet person.
2. the capsule image workstation according to claim 1 using speech recognition, which is characterized in that further include at signal
Unit is managed, the voice input unit output end connects the signal processing unit input terminal, the signal processing unit output
End connects the speech recognition conversion unit input terminal.
3. the capsule image workstation according to claim 2 using speech recognition, which is characterized in that the signal processing
Unit includes filter amplification circuit, and the filter amplification circuit includes first capacitor (C1), the second capacitor (C2), third capacitor
(C3), first resistor (R1), second resistance (R2), 3rd resistor (R3), the 4th resistance (R4), the 5th resistance (R5), the 6th electricity
Hinder (R6), the 7th resistance (R7), the first amplifier (P1), the second amplifier (P2), third amplifier (P3), the first triode
(VT1), the second triode (VT2) and first diode (D1)；
Described first resistor one end (R1) connects the voice input unit output end, and the other end connects second capacitor (C2)
One end, the other end of second capacitor (C2) connects the positive terminal of first amplifier (P1), first amplifier
(P1) output end connects two branches:
One end of one connection first capacitor (C1), first capacitor (C1) other end connect one end of the 4th resistance (R4),
The other end of 4th resistance (R4) connects the base stage of first triode (VT1), the hair of first triode (VT1)
Emitter-base bandgap grading connects the positive terminal of third amplifier (P3), and the collector of first triode (VT1) connects the first diode
(D1) cathode, the plus earth of the first diode (D1), the output end connection described the of the third amplifier (P3)
The reverse side of one amplifier (P1), the reverse side of the third amplifier (P3) connect one end of the 6th resistance (R6), and described the
The other end of six resistance (R6) connects the emitter of second triode (VT2), the emitter of second triode (VT2)
It is additionally coupled to the reverse side of second amplifier (P2), the base stage of second triode (VT2) connects the one or two pole
The cathode for managing (D1), is also connected with the 7th resistance (R7), the two or three pole between the base stage and collector of the second triode (VT2)
Manage one end of collector connection third capacitor (C) 3 of (VT2), third capacitor (C3) other end ground connection, the two or three pole
The emitter for managing (VT2) connects the reverse side of second amplifier (P2)；
One end of another connection second resistance (R2), the other end connection of the second resistance (R2) second amplification
The positive terminal of device (P2) is connected with 3rd resistor (R3) between the output end and positive terminal of second amplifier (P2), described
The output end of third amplifier (P3) connects one end of the 5th resistance (R5), described in the other end connection of the 5th resistance (R5)
The output end of second amplifier (P2), the output end of second amplifier (P2) connect the speech recognition conversion unit input
End.
4. the capsule image workstation according to claim 1 using speech recognition, which is characterized in that the voice input
Unit is microphone array.
5. the capsule image workstation according to claim 1 using speech recognition, which is characterized in that further include that fingerprint is adopted
Collect unit, the fingerprint collecting unit is connect with described control unit, the operating right of verification operation person.
6. the capsule image workstation according to claim 5 using speech recognition, which is characterized in that further include relay
Device, coil one end of the relay connect one I/O interface of control unit, and the other end connects power supply, the voice input unit
Power end be equipped with the relay normally opened contact.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201821021973.3U CN208316687U (en) | 2018-06-29 | 2018-06-29 | A kind of capsule image workstation using speech recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201821021973.3U CN208316687U (en) | 2018-06-29 | 2018-06-29 | A kind of capsule image workstation using speech recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN208316687U true CN208316687U (en) | 2019-01-01 |
Family
ID=64717718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201821021973.3U Active CN208316687U (en) | 2018-06-29 | 2018-06-29 | A kind of capsule image workstation using speech recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN208316687U (en) |
-
2018
- 2018-06-29 CN CN201821021973.3U patent/CN208316687U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110111787A (en) | A kind of semanteme analytic method and server | |
| CN103400592A (en) | Recording method, playing method, device, terminal and system | |
| CN105874448A (en) | Method and apparatus for outputting digital content | |
| CN112087657B (en) | Data processing method and device | |
| CN104679430A (en) | Credible electronic handwriting generation method and system and electronic signature pen | |
| CN104717467A (en) | Wireless field teaching system | |
| CN208316687U (en) | A kind of capsule image workstation using speech recognition | |
| CN203338371U (en) | Multifunctional scanning pen | |
| KR20160001359A (en) | Method for managing data and an electronic device thereof | |
| CN207096409U (en) | The detection means of electric cooking pot and wherein battery electric quantity | |
| CN105721837A (en) | Student self-adaptive learning system and method | |
| CN110225274A (en) | A kind of digital business card methods of exhibiting, device and storage medium based on video | |
| CN109377798A (en) | A kind of english teaching auxiliary device | |
| CN203070318U (en) | Audio reading machine | |
| CN105677010A (en) | Method and system for automatically recording characters and converting characters into electronic documents | |
| CN209641352U (en) | A kind of recording pen | |
| CN107967060A (en) | Multi-freedom parallel connection vivid platform data real-time collecting system and method | |
| CN110211612A (en) | A kind of recording pen and the way of recording | |
| CN213338767U (en) | Identity identification information acquisition equipment | |
| CN109982041A (en) | A kind of image procossing tracking system and its image tracking method | |
| CN201514760U (en) | Digital photo frame having voice recognition function | |
| JP5381133B2 (en) | Playback device, imaging device, and program | |
| CN211207206U (en) | Electronic diary | |
| CN110531831A (en) | A kind of electronic diary | |
| CN202334671U (en) | Mobile phone with translation function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211105 Address after: 401120 1-1, 2-1, 3-1, building 5, No. 18, Cuiping Lane 2, Huixing street, Yubei District, Chongqing Patentee after: Chongqing Jinshan Medical Technology Research Institute Co.,Ltd. Address before: 401120 1 office buildings, Jinshan International Industrial City, 18 of Nei sang Road, Hui Xing street, Yubei District, Chongqing. Patentee before: CHONGQING JINSHAN MEDICAL APPLIANCE Co.,Ltd. |