TWM583053U - Microscope operated by voice recognition - Google Patents

Abstract

A microscope configured with a memory unit for storing a voice preset value, a sound receiver for receiving a user's language sound, a microprocessor for logically editing a voice signal for receiving a voice signal, and a recognition and analysis voice The preset value and the voice signal are output and the comparison result is output to the voice recognition unit of the microprocessor. In this way, the microscope of the present invention realizes the purpose of performing the action or the operation of the microscope through the structure of the speech recognition, and relatively reduces the time for the manual operation of the user.

Description

Microscope for speech recognition operation

This creation relates to the field of operation of microscopes, and in particular to a microscope that operates by means of speech sound recognition instead of touch elements such as keys.

Conventional microscopes are equipped with touch elements such as buttons, and usually require a user to press the hand to switch the state of use of the microscope. When idle, the user feels very convenient to touch the button with both hands. However, the user concentrates on dealing with something, raising his head or raising his hand may become a luxury, and the manual operation of the microscope becomes a burden.

Therefore, how to reduce the time of manual operation of the microscope has become an urgent problem to be solved in this creation.

In view of this, the creation of the new microscope, the main purpose is to use the structure of speech recognition, allowing the user to command the microscope to perform the required actions or operations in a spoken language, relatively reducing the time of manual operation.

Due to the above object, the microscope of the present invention is configured with a memory unit for storing a voice preset value, a sound receiver for receiving a user's language sound, and a micro-processing for the voice receiver to receive the language sound logically edited into a voice signal. And a speech recognition unit that recognizes, analyzes the voice preset value and the voice signal and outputs the comparison result to the microprocessor.

The voice recognition unit comprises an electrically connected receiving voice signal module for receiving the voice signal, and a voice recognition for distinguishing the feature value of the voice signal embedded instruction. A module, a speech analysis module for comparing the feature values and the voice preset values, and a recognition result output module for notifying the microprocessor of the comparison result.

In this way, the microscope of the present invention realizes the purpose of performing the action or the operation of the microscope through the structure of the speech recognition, and relatively reduces the time for the manual operation of the user.

In order to make the above objects, features and advantages of the present invention more comprehensible, one or more preferred embodiments are described in detail with the accompanying drawings.

10‧‧‧Host

11‧‧‧ pillar

12‧‧‧ Robotic arm

13‧‧‧Active arm

14‧‧‧Users

15‧‧‧Microscope

20‧‧‧ Eyepieces

202‧‧‧Shell

21, 31‧‧‧ circuits

22‧‧‧Microprocessor

23‧‧‧Sound transceiver unit

232‧‧‧Sound Receiver

234‧‧‧Sound transmitter

24‧‧‧Voice recognition unit

242‧‧‧ Receive voice signal module

244‧‧‧Voice recognition module

246‧‧‧Voice Analysis Module

248‧‧‧ Identification result output module

25‧‧‧ memory unit

26‧‧‧Power supply

27‧‧‧Display unit

272‧‧‧ screen

28‧‧‧Wireless communication

29, 32‧‧‧ transceiver

30‧‧‧ objective lens group

302‧‧‧Shell

304‧‧‧Support frame

33‧‧‧Control unit

34‧‧‧ Focus unit

35‧‧‧ lens group

36‧‧‧Subsidiary unit

40‧‧‧Start

41‧‧‧ Receiving the user's voice

42‧‧‧Do you know the voice of the user clearly?

422, 442‧‧‧ is

424, 444‧‧‧ No

43‧‧‧Characteristics of identifying speech

44‧‧‧Compliance with stored voice presets

45‧‧‧Prompt user to make another voice

46‧‧‧Microscope performs actions that are consistent with voice presets

End of 47‧‧

50‧‧‧ Voice presets

52‧‧‧ comparison

54‧‧‧ voice signal

56‧‧‧Characteristic values

Figure 1 is a schematic view showing the use of a preferred embodiment of the present creation microscope.

Figure 2 is a configuration diagram of the microscope.

Figure 3 is a system diagram of the speech recognition unit.

Figure 4 is a schematic diagram of the voice preset value comparison voice signal.

Figure 5 is a flow chart of the speech recognition operating microscope.

Fig. 1 is a view showing the state of use of the preferred embodiment of the microscope 15, which is an electronic device which is used separately by an eyepiece group 20 and an objective lens group 30. In some embodiments, the eyepiece set 20 in combination with the objective lens set 30 constitutes a synchronously actuated microscope 15 and is within the permissible range of this creation. The connection relationship between the eyepiece group 20 and the objective lens group 30 will be described in the following description.

In the figure, the objective lens assembly 30 has a housing 302. The housing 302 is coupled to a robot arm 12 by a support frame 304. The robot arm 12 is rotatably connected to a host 10, and the main assembly 10 is supported by a support 11. It is fixed inside a building (not shown, usually referred to as the ceiling) and can be rotated, allowing any user 14 to manipulate the objective lens group 30 to move back and forth in the horizontal (i.e., horizontal) and longitudinal (i.e., vertical) directions of FIG.

Fig. 2 is a view showing the arrangement of the microscope 15. The objective lens set 30 is in a reasonable position A set of circuits 31 are electrically connected to a transceiver 32, a control unit 33, a focusing unit 34, a lens group 35 and an accessory unit 36.

The reasonable position referred to herein generally refers to the outer casing 302 (see Fig. 1) surrounding the inner space of the objective lens group 30, and the top surface, the bottom surface, the front surface, the back surface and the side surface of the outer casing 302 itself.

The circuit 31 (Electrical Circuit) is also called an electronic circuit, and is a path through which electric wires and/or power sources, resistors, capacitors, inductors, diodes, transistors, integrated circuits, and the like are connected to each other to form a charge flow. For example, an analog circuit, a digital circuit, or a circuit composed of two circuits.

The transceiver 32 (Transceiver) is a device consisting of a transmitter and a receiver, receives an electronic signal (or message) originating from the eyepiece group 20 via the wireless communication 28, or transmits an electronic signal (or message) to the eyepiece group. 20. Of course, the objective lens group 30 receives or transmits electronic signals (or messages) by means of wired communication, which is also an allowable range of the present invention.

The control unit 33 referred to herein generally refers to buttons, knobs and switches, and other manipulation elements for adjusting the scale value scaling, brightness intensity, focus orientation and positioning.

The lens group 35 is a combination of lenses such as a convex lens and a concave lens, and the focal length of the lens is adjusted by the focusing unit 34.

A variety of accessory units 36 are referred to herein, such as a set of Light Emitting Diodes (LEDs) for lighting purposes, and a Charge Coupled Device (CCD) for sensing light and converting images into digital signals. Or other electronic zero (group) parts suitable for the objective lens set 30.

Referring back to Figure 1, the eyepiece set 20 has a housing 202. The back of the housing 202 is pivotally connected to a movable arm 13 that is rotatably coupled to the lower portion of the main unit 10 to facilitate the user 14 The eyepiece group 20 is reciprocally displaced in the lateral and longitudinal directions along the first drawing. In some embodiments, the housing 202 is detached from the movable arm 13 and coupled to the back of the housing 302 by a screw lock to complete the eyepiece assembly 20 and the object. The effect of the mirror group 30 on simultaneous actuation.

In addition, a sound receiver 232, a sound emitter 234 and a screen 272 are disposed on the front surface of the casing 202. The sound receiver 232, such as the microphone, can receive the voice sound emitted by the user 14 mouth. The sound emitter 234, such as a horn, can emit at least one voice preset to notify the user 14 to pay attention to or perform an action. The screen 272 displays at least one image, pattern, symbol, table and color output device (Output Device), or a touch screen (Touchscreen) that receives input signals (including fingers, glue pens, etc.), such as Inductive liquid crystal display, flat screen, etc.

The image referred to herein generally assists the user 14 in understanding the local field of view of the object group 30. As for patterns, symbols, tables, and colors, it refers to the scale value, brightness, focus orientation, and positioning of the observed part.

2, the eyepiece assembly 20 is mounted at a reasonable position with a further set of circuits 21 connected to a microprocessor 22, a voice transceiver unit 23, a voice recognition unit 24, and a memory unit. 25. A display unit 27 and other transceivers 29.

The reasonable position referred to herein generally refers to the housing 202 (see FIG. 1) enclosing the inner space of the eyepiece assembly 20, and the top, bottom, front, back and sides of the housing 202 itself.

Similarly, the circuit 21 (Electrical Circuit) consists of an electric circuit such as a wire and/or a power source 26, an electric device such as a resistor, a capacitor, an inductor, a diode, a transistor, or an integrated circuit, and an element, such as an analog circuit. , a digital circuit, or a circuit composed of two circuits connected. The power source 26 supplies power required by the eyepiece group 20, such as the transceiver 29 receiving an electronic signal (or message) from the objective lens group 30, or transmitting an electronic signal to the objective lens group 30.

The sound transceiving unit 23 referred to herein refers to an electronic device composed of the aforementioned sound receiver and the sound emitter. As for the display unit 27, it is an electronic device including the aforementioned screen.

The microprocessor 22 (microprocessor, abbreviated as uP) is also called a central processing unit (CPU), and is a programmable integrated circuit for processing image data, audio data and general data according to a preset mode and an operation mode. .

In the preset mode, the memory unit 25 stores a voice signal, which is an electronic signal that the microprocessor 22 logically edits the language sound (from the user), and functions as a scaling value, brightness, and focus. The preset value of one of the items such as orientation and positioning. Of course, according to personal preference, the user has to change the preset value arbitrarily.

When switching to the operation mode, the voice transceiver unit 23 receives the user's password and edits it into an instructional voice signal via the microprocessor 22. At this moment, the voice signal represents the user's instruction, which is different from the preset value of the preset mode, but commands the objective lens group 30 to automatically perform a certain preset action.

As shown in FIG. 3, the voice recognition unit 24 is composed of a received voice signal module 242, a voice recognition module 244, a voice analysis module 246, and a recognition result output module 248. The received voice signal module 242 receives the aforementioned command voice signal. The speech recognition module 244 discriminates at least one feature value containing the instruction from the instructional speech signal. The speech analysis module 246 compares the feature value with the preset value to know the user's instruction, and notifies the microprocessor by the recognition result output module 248.

It is not difficult to understand from Fig. 4 that a piece of speech signal 54 is discerned by the speech recognition module for a single feature value 56. After the comparison 52, the feature value 56 conforms to one of the plurality of voice preset values 50, and the comparison result output module notifies the microprocessor of the comparison result (usually the voice preset value 50).

Figure 5 is a brief introduction to the flow of the speech recognition operation microscope. From "Start 40" to "End 47", after "Receiving the user's voice 41", "Is it clear the user's voice 42", "Characteristics of recognizing speech" The value is 43", "Is it compatible with the stored voice preset value 44", "Prompt the user to re-send the voice 45", and "The microscope performs the action 46 with the voice preset value".

In the "Start 40" step, it is determined that the microscope is powered, and the "voice operation" control mode is activated. As for the "End 47" step, the "voice operation" control mode is exited, and the microscope returns to the user's "manual manipulation" control mode.

In the step of "receiving the user's speech sound 41", the user performs one of the operations of scaling, brightness, focus orientation, or positioning by the voice command microscope.

In the step of "whether or not the user's voice 42 is clearly recognized", if the discrimination cannot be clearly made, the conclusion is no 424, and the process returns to the previous step, and the user is asked to re-send the voice that can be clearly discerned; The conclusion is 422, taking the next step.

In the step of "identifying the feature value 43 of the voice", the feature value is a correct command, and belongs to a command that the user requests the microscope to perform an action or a job. Other languages or sounds are redundant and should be omitted.

In the step of "whether the stored voice preset value 44 is met", the feature value does not match the plurality of voice preset values stored in the memory unit, and the comparison result is no 444, and the message "prompts the user to voice 45 again" Steps, returning to the "Receive User's Language Sound 41" step again; if the feature value meets one of the plurality of voice preset values, the representative comparison result is 442, and proceeds to the next step.

In the step of "microscope performing action 46 corresponding to the voice preset value", the microprocessor transmits an electronic signal to the objective lens group according to the voice preset value corresponding to the feature value, and the objective lens group performs the action or job requested by the user. For example, scaling, brightness, focus orientation, or positioning.

Claims (5)

A microscope for voice recognition operation, the microscope (15) is provided with a memory unit (25) for storing a voice preset value (50), a sound receiver (232) for receiving a user language sound, and a sound receiver (232). a microprocessor (22) that receives the speech sound logically edited into a voice signal (54) and an identification, analysis voice preset value (50) and voice signal (54) and output comparison (52) results to the microprocessor (22) Speech recognition unit (24). The microscope for voice recognition operation according to claim 1, wherein the voice recognition unit (24) comprises an electrically connected receiving voice signal module (242) for receiving the voice signal (54), The speech signal (54) includes a speech recognition module (244) of the feature value (56) of the command, a comparison (52) feature value (56), and a voice analysis module (46) of the voice preset value (50). And an output module (248) that notifies the microprocessor (22) of the result of the comparison. A microscope for speech recognition operation according to claim 1, wherein the microscope (15) comprises: an eyepiece group (20) and an objective lens group (30), the eyepiece group (20) and the objective lens group (30) Used separately or in combination. A microscope for voice recognition operation according to claim 3, wherein the eyepiece group (20) and the objective lens group (30) each have a transceiver (29, 32) for intercommunicating electronic signals. A microscope for voice recognition operation as claimed in claim 3, wherein the sound receiver (232) is mounted on the eyepiece set (20).