JP2018055274A - Finding generation device, finding generation method, finding generation program and recording medium having the same recorded therein - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a finding generation device comprising a user interface suitable for recording of dental findings.SOLUTION: A finding generation device 19 comprises: a speech recognition unit 197 which performs speech recognition on an input voice signal; and a finding generation unit 199 which switches display on a display device from a first screen allowing a character input based on the result of speech recognition to a second screen inhibiting the character input based on the result of speech recognition when receiving a prescribed signal indicating the end of the character input during display of the first screen.SELECTED DRAWING: Figure 1

Description

  The present disclosure relates to a finding creation apparatus, a finding creating method, a finding creating program, and a recording medium on which the program is recorded, capable of inputting a tooth state or a finding by voice recognition.

  Conventionally, as this kind of finding creation device, for example, there is a dental diagnosis information processing device described in Patent Document 1 below. This dental diagnosis information processing apparatus is recognized as a voice input means for inputting voice related to dental diagnosis information, and a voice recognition means for analyzing input voice signals and recognizing predetermined dental diagnosis data. Data storage means for storing the dental diagnosis data, and data display means for displaying the recognized dental diagnosis data.

JP-A-8-71091

  An object of the present disclosure is to provide a finding creation device, a finding creation method, a finding creation program, and a recording medium on which the program is recorded, provided with a user interface that is easy for an operator to use.

The first form of the present disclosure is:
A voice recognition unit that performs at least large vocabulary continuous voice recognition on a voice signal representing the utterance content;
Based on the result of the large vocabulary continuous speech recognition, a predetermined signal indicating the end of the character input is received during the display of the first screen while the first screen allowing the input of the characters representing the utterance content is displayed. A finding creation unit comprising: a finding creating unit that switches the display of the display device to a second screen incapable of character input based on the result of the large vocabulary continuous speech recognition;
Directed to.

The second form of the present disclosure is:
A procedure for causing the display device to display a first screen that allows the input of characters representing the utterance content based on the result of large vocabulary continuous speech recognition;
A procedure for switching the display content of the display device to a second screen in which character input based on the result of the large vocabulary continuous speech recognition is prohibited when a predetermined signal indicating the end of character input is received during display of the first screen And a method of creating findings with
Directed to.

The third form of the present disclosure is:
On the computer,
A procedure for causing the display device to display a first screen that allows the input of characters representing the utterance content based on the result of large vocabulary continuous speech recognition;
A procedure for switching the display content of the display device to a second screen in which character input based on the result of the large vocabulary continuous speech recognition is prohibited when a predetermined signal indicating the end of character input is received during display of the first screen Finding program with
Directed to.

The fourth form of the present disclosure is:
On the computer,
A procedure for causing the display device to display a first screen that allows the input of characters representing the utterance content based on the result of large vocabulary continuous speech recognition;
A procedure for switching the display content of the display device to a second screen in which character input based on the result of the large vocabulary continuous speech recognition is prohibited when a predetermined signal indicating the end of character input is received during display of the first screen And a recording medium on which the finding creation program comprising
Directed to.

  According to the present disclosure, it is possible to provide a finding creation device, a finding creating method, a finding creating program, and a recording medium recording the finding, which have a user interface that is easy for an operator to use.

The figure which shows the structure of the finding creation apparatus which concerns on one Embodiment of this indication. Schematic diagram showing the list screen Schematic diagram showing the findings creation screen Schematic diagram showing the status input screen Schematic diagram showing facial photo screen, intraoral photo screen and denture photo screen Schematic diagram showing the photo editing screen Schematic diagram showing a notebook screen Schematic diagram showing names and other images Schematic diagram showing the setting change screen Schematic diagram showing the edit screen Schematic diagram showing the selection screen Schematic diagram showing the search screen Schematic diagram showing the output screen Schematic diagram showing the data operation screen Schematic diagram showing the findings deletion screen Schematic diagram showing the screen for creating backup data Schematic diagram showing the screen for restoring findings data Main flow diagram showing the processing of the finding creation device First flowchart showing a detailed processing procedure of step S009 in FIG. 7A. FIG. 7A is a second flowchart showing the detailed processing procedure of step S009. FIG. 7A is a third flowchart showing the detailed processing procedure of step S009. Schematic diagram showing a GUI that prompts the operator to click a setting button Schematic diagram showing the transition of the display screen when a tooth-specific speech recognition result is received Schematic diagram showing the display screen when the tooth status is entered in the status input field Schematic diagram showing the display screen when setting the tooth representation Schematic diagram showing the display screen when changing the reading of the tooth Schematic diagram showing the display screen when changing the name of the examining doctor

  Hereinafter, the finding creation apparatus 19 according to an embodiment of the present disclosure will be described in detail with reference to the drawings.

<1. Configuration of Dental Finding System>
In FIG. 1, a dental finding creation system 1 is installed in a police station or the like, and is used, for example, for identity confirmation in a disaster. The dental finding creation system 1 can also be installed in a dental clinic and used for managing a patient's dental chart.

  The dental finding creation system 1 generally includes a voice input device 11, an operation input device 13, a data reading device 15, a communication device 17, a finding creation device 19, a display device 111, and a voice output device. 113. The data reading device 15, the finding creation device 19, the display device 111, and the audio output device 113 may be built in the same casing.

  The voice input device 11 is, for example, a wired or wireless headset or a stationary microphone with a built-in microphone, and is connected to the finding creation device 19 by wire or wireless.

  The voice input device 11 converts voice input by the operator into an electrical signal (hereinafter referred to as a voice signal) and outputs it to the finding creation device 19. Examples of the voice signal include a voice signal representing various voice commands (including a voice signal specifying a tooth, a tooth state, and the like) and a voice signal representing a finding memo. Here, the observation memo is not a voice command but a relatively long sentence representing a finding of a dentist or the like.

  The operation input device 13 is, for example, a mouse and a keyboard, and is connected to the finding creation device 19 by wire or wirelessly.

  The operation input device 13 converts an operation performed by a finger of an operator (for example, a dentist) into a specific electrical signal (hereinafter referred to as an operation signal) and outputs it to the finding creation device 19.

  The data reading device 15 reads data stored in a portable recording medium such as a disk or a semiconductor memory, and transfers the data to the working memory 193 of the finding creation device 19.

  The communication device 17 acquires data from a remote server or the like and transfers it to the working memory 193 of the finding creation device 19.

  The finding creation device 19 generally includes various connectors and various interfaces (not shown), a storage device 191, a working memory 193, and a processor 195.

  The storage device 191 is, for example, a hard disk drive or a semiconductor memory, and stores in advance a voice recognition program P1, a voice input dental chart program (shown simply as a dental chart program) P3, and various dictionaries D1 to D11. doing.

  The speech recognition program P1 includes a large vocabulary continuous speech recognition program P11 and a small vocabulary word speech recognition program P13.

  The large vocabulary continuous speech recognition program P11 is a program for realizing speech recognition for a speech signal output from the speech input device 11 without being limited to a speech command in order to enable speech recognition by so-called dictation. . When the large vocabulary continuous speech recognition program P11 is executed, the large vocabulary continuous speech recognition dictionary D1 is used.

  On the other hand, unlike the large vocabulary continuous speech recognition program P1, the small vocabulary word speech recognition program P13 is limited to speech commands and is limited to speech commands for speech signals output from the speech input device 11. It is a program for realizing recognition. When such a small vocabulary word speech recognition program P13 is executed, small vocabulary word speech recognition dictionaries D3 to D11 other than the large vocabulary continuous speech recognition dictionary D1 are used. Details of the small vocabulary word speech recognition dictionaries D3 to D11 are shown in Table 1.

  As described in Table 1 above, the small vocabulary word speech recognition dictionary D3 defines speech commands that can be used on the list screen I01 while the list screen I01 is displayed on the display device 111. Other small vocabulary word speech recognition dictionaries D5 to D11 define speech commands that can be used while the corresponding screen is being displayed on the display device 111.

  The processor 195 executes both programs P1 and P3 while using the working memory 193, and functions as the speech recognition unit 197 and the finding creation unit 199.

  Specifically, the voice recognition unit 197 receives voice data output from the voice input device 11. The voice recognition unit 197 performs voice recognition on the received voice signal, and passes the voice recognition result obtained thereby to the processor 195 functioning as the finding creation unit 199. In the present disclosure, the speech recognition unit 197 displays the large vocabulary continuous speech recognition program P11 and the small vocabulary word speech recognition program P13 as the large vocabulary word speech recognition when the first screen described later (that is, the note screen I15 in FIG. 2F) is displayed. This is executed using the dictionary D1 and the small vocabulary word speech recognition dictionary D9, speech recognition is performed on the received speech signal, and the result is passed to the finding creation unit 199. On the other hand, when the second screen described later (that is, the dental chart screen I05 in FIG. 2B, the facial photo screen I09 in FIG. 2D, the intraoral photo screen I11 and the denture photo screen I13, and the name and other screen I17 in FIG. 2G) are displayed. The small vocabulary word speech recognition program P13 is executed using the corresponding small vocabulary word speech recognition dictionaries D3 to D7, D11, and speech recognition processing is performed on the received speech signal, and the result is generated as a finding creation unit 199. To pass.

  The finding creation unit 199 creates various screens related to creation, editing, and output of finding data based on the voice command that is the voice recognition result of the voice recognition unit 197 and the operation signal from the operation input device 13, and the created screen Is displayed on the display device 111. In addition, while the note creation unit 199 is displaying the note screen I15, the character representing the finding memo, which is the voice recognition result of the voice recognition unit 197, is input to the note input area R11.

  The processor 195 performs various processes in addition to functioning as the voice recognition unit 197 and the finding creation unit 199. These will be described later as appropriate.

  The display device 111 displays various screens (details will be described later) generated by the finding creation device 19.

  The audio output device 113 outputs the audio signal generated by the finding creation device 19 as audio.

<2. Various screens displayed on the display device>
Next, various screens displayed on the finding creation device 19 will be described in detail.
<2-1. List screen>
First, with reference to FIG. 2A, the list screen I01 displayed after starting the dental chart program P3 of FIG. 1 will be described.
2A, the list screen I01 includes a new creation button B01, a setting change button B03, a search button B05, an output button B07, a data operation button B09, an end button B11, and a finding list area R01.

  Each of the buttons B01 to B11 is a button that can be clicked with a mouse or the like constituting the operation input device 13. The functions of the buttons B01 to B11 are as shown in Table 2 below. When the buttons B01 to B11 are clicked on the operation input device 13, the display content of the display device 111 is changed from the list screen I01 as shown in Table 2 below.

  In Table 2 above, the function for switching to the display of the finding creation screen I03 is assigned to the new creation button B01, and the function for switching to the display of the setting change screen I19 is assigned to the setting change button B03. The functions shown in Table 2 are also assigned to the other buttons B01 to B11.

  In the finding list area R01, existing finding data (that is, finding data stored in the storage device 191) is displayed in a list format. Each finding data is opened by double-clicking with the operation input device 13 and displayed on the display device 111.

<2-2. Observation creation screen>
Next, the finding creation screen I03 will be described with reference to FIG. 2B.
In FIG. 2B, the finding creation screen I03 is used when creating finding data of a certain unidentified person or patient (hereinafter referred to as unidentified person, etc.), and includes a plurality of permanent tooth state input fields C01 and a plurality of permanent tooth state selection buttons. B13, a plurality of screen switching tabs T01, a dental chart screen I05, a plurality of milk tooth state input fields C03, a plurality of milk tooth state selection buttons B15, a reproduction button B17, and a close button B19.

  In the center of the finding creation screen I03, any one of the dental chart screen I05, the facial photo screen I09, the intraoral photo screen I11, the denture photo screen I13, the note screen I15, and the other screen I17 can be selected by clicking the screen switching tab T01. Is selectively displayed.

  The permanent tooth state input field C01 is provided for each tooth (specifically, permanent tooth). In the following description, the right means the right from the back of the page toward the front.

  In the upper right of the finding creation screen I03, the permanent tooth state input fields C01 from the upper right 1 to the upper right 8 in the mouth are arranged in order from top to bottom. On the lower right side of the finding creation screen I03, the lower right first to lower right eighth permanent tooth state input columns C01 in the lower right of the mouth are arranged in order from the bottom to the top. In the upper left and lower left of the finding creation screen I03, a plurality of permanent tooth state input fields C01 in the upper left and lower left are arranged in order.

  In FIG. 2B, for convenience of illustration, the upper right permanent tooth state input field C01 is surrounded by a broken line, and these are collectively denoted by reference numeral C01.

  In each permanent tooth state input field C01, a character string (more specifically, a tooth state) generated based on the voice recognition result can be input. The character input here may be based on an operation signal from a keyboard constituting the operation input device 13. The input character string is displayed in the corresponding permanent tooth state input field C01.

  While a certain tooth is selected by voice or the like, the inside of the corresponding permanent tooth state input field C01 is highlighted with a specific color (for example, red). In the example shown in FIG. 2B, since the upper left C-th deciduous tooth is being selected, none of the permanent tooth state input fields C01 is highlighted.

  The state selection button B13 is provided for each permanent tooth. In the present embodiment, a state selection button B13 for a corresponding permanent tooth is arranged next to each permanent tooth state input field C01.

  In FIG. 2B, for convenience of illustration, the state selection buttons B13 for the upper right permanent teeth are surrounded by a broken line, and these are collectively denoted by reference numeral B13.

  Each state selection button B13 is assigned a function of overlaying the corresponding tooth state input screen I07 (see FIG. 2C) on the finding creation screen I03.

  Here, the state input screen I07 will be described with reference to FIG. 2C. Note that FIG. 2C illustrates a state input screen I07 of the upper left permanent tooth.

  In FIG. 2C, each status input screen I07 includes an input box C05, a clear button B21, a plurality of status buttons B23, and a close button B25.

In the input box C05, a character string indicating a tooth state is input.
A function for clearing the character string in the input box C05 is assigned to the clear button B21.

  Character strings indicating tooth states are individually assigned to the plurality of state buttons B23. Examples of these character strings include healthy teeth, defects (with alveolar fossa), inlay restoration, onlay restoration, and the like. When a certain state button B23 is clicked with the operation input device 13, the character string of the tooth state assigned to the button B23 is input and displayed in the input box C05.

  In FIG. 2C, for the sake of illustration, the all-state button B23 is surrounded by a broken line, and these are collectively denoted by reference sign B23.

  The close button B25 is assigned a function for inputting and displaying the character string displayed in the input box C05 in the corresponding state input field C01 on the finding creation screen I03 and ending the overlay display of the state input screen I07. ing.

Reference is again made to FIG. 2B.
Each of the plurality of screen switching tabs T01 is assigned one of a dental chart screen I05, a facial photo screen I09, an intraoral photo screen I11, a denture photo screen I13, a note screen I15, and a name and other screen I17.

  When a screen switching tab T01 is clicked with the operation input device 13, the display content of the display device 111 is a screen (dental chart screen I05, facial photo screen I09, intraoral photo screen I11 assigned to the clicked tab T01. , Any one of the denture photo screen I13, the note screen I15, and the name and other screen I17).

  The dental chart screen I05 includes an image representing a tooth row of permanent teeth and milk teeth. In the example of FIG. 2B, the tooth row of the upper permanent teeth is represented by a schematic tooth shape as seen in plan view from below, and is shown above the dental chart screen I05. In addition, the lower permanent tooth row is represented by a schematic shape as viewed from above, and is shown below the upper tooth row.

  The tooth row of the upper deciduous tooth is represented by a schematic tooth shape as seen from above, and is shown inside the tooth row of the upper permanent tooth. The tooth row of the lower deciduous tooth is represented by a schematic tooth shape as the tooth row is viewed from above, and is shown inside the tooth row of the lower permanent tooth. Thereby, the space of the dental chart screen I05 is effectively used.

  The milk teeth are grayed out in the initial state. While a certain tooth is selected, the corresponding tooth is surrounded by a circle of a specific color (for example, red).

The milk tooth state input field C03 is provided for each milk tooth.
The state input column C03 of the upper right A to the upper right E of the mouth is from top to bottom between the upper right permanent tooth state input column C01 and the lower right permanent tooth state input column C01 on the finding creation screen I03. Are arranged in order. Below the lower right permanent tooth state input field C01, the lower right A to lower right E milk state input fields C03 in the mouth are arranged in order from top to bottom.

  The upper left and lower left milk tooth status input fields C03 are arranged to face the upper right and lower right milk tooth status input fields C03 across the dental chart screen I05.

  In FIG. 2B, for convenience of illustration, a plurality of state input fields C03 for the upper left deciduous teeth are surrounded by a broken line, and these are collectively denoted by reference numeral C03.

  Similarly to each permanent tooth state input field C01, a tooth state based on a voice recognition result or an operation signal can be input to each milk tooth state input field C03. The tooth status input in the milk tooth status input field C03 is displayed on the screen of the display device 111.

  As in the case of the permanent tooth state input field C01, while a certain milk tooth is selected, the inside of the corresponding milk tooth state input field C03 is highlighted with a specific color (for example, red). In the example of FIG. 2B, it is shown that the upper left C-th deciduous tooth is being selected.

  The milk tooth state selection button B15 is provided for each milk tooth. In the present embodiment, a corresponding state selection button B13 for permanent teeth is arranged next to each milk tooth state input field C03.

  Each state selection button B15 is assigned a function of overlaying the corresponding tooth state input screen I07 (see FIG. 2C) on the finding creation screen I03.

  The milk tooth state input screen I07 has the same configuration as the permanent tooth state input screen I07, and a description thereof will be omitted. In FIG. 2B, for convenience of illustration, the upper left deciduous tooth state selection button B15 is surrounded by a broken line, and these state selection buttons are collectively denoted by reference numeral B15.

A function for starting to read out the character string input on the note screen I15 is assigned to the reproduction button B17.
A function for returning the display content of the display device 111 to the above-described list screen I01 is assigned to the close button B19.

  By the way, as described above, the display content of the display device 111 is switched not only to the dental chart screen I05 but also to the facial photograph screen I09, the intraoral photograph screen I11, or the denture photograph screen I13 by clicking the screen switching tab T01.

  Hereinafter, the facial photograph screen I09, the intraoral photograph screen I11, and the denture photograph screen I13 will be described with reference to FIG. 2D.

  2D shows a facial photo screen I09, an intraoral photo screen I11, and a denture photo screen I13.

  In the central regions R03, R05, and R07 of the facial photo screen I09, intraoral photo screen I11, and denture photo screen I13, by drag and drop using the operation input device 13, facial photos of the unidentified person, intraoral photos and A denture photo can be pasted. The facial photograph, intraoral photograph, and denture photograph pasted in this way constitute a part of the findings data and are stored in the storage device 191.

  When the stored facial photograph, intraoral photograph, and denture photograph are clicked on the operation input device 13, an edit screen I19 for each photograph as shown in FIG. 2E is displayed as an overlay on the finding creation screen I03.

  In FIG. 2E, each editing screen I19 is a display area R09 of a stored photograph (any one of a facial photograph, intraoral photograph, and denture photograph), a close button B27, a left rotation button B29, an undo button B31, and a right rotation. It consists of a button B33 and a delete button B35.

The close button B27 is assigned a function for ending the overlay display of the editing screen I19.
A function for rotating the photograph displayed in the display area R09 by 90 ° counterclockwise is assigned to the left rotation button B29.

The undo button B31 is assigned a function for returning the photo being edited to the initial state (the state when the editing screen I19 is displayed).
The right rotation button B33 is assigned a function for rotating the photograph displayed in the display region R09 by 90 degrees clockwise.

  By the way, as described above, the display content of the display device 111 is switched not only to the dental chart screen I05 but also to the note screen I15 by clicking the screen switching tab T01.

Hereinafter, the note screen I15 will be described with reference to FIG. 2F.
In FIG. 2F, the note screen I15 includes a note input area R11 and a voice command display area R13.

  In the note input area R11, basically, a character string indicating a voice recognition result by the voice recognition unit 197 is input and displayed. This note screen I15 is mainly used to describe a finding memo by a dentist. Therefore, what is input and displayed in the note input area R11 is typically a character string representing a finding memo.

  In the voice command display area R13, available voice commands are listed and displayed at least during the display of the note screen I15. In the present finding creation device 19, it is assumed that 11 types of voice commands shown in Table 3 below are defined.

  In Table 3 above, the voice command “END” is assigned a function for terminating the input of the voice recognition result by the voice recognition unit 197 to the note input area R11 (ie, dictation input). The voice command “return to the beginning” is assigned a function of moving the cursor in the note input area R11 to the head of the character string already input. The functions described in Table 3 are also assigned to other voice commands.

  By the way, as described above, when the screen switching tab T01 is clicked, the display contents of the display device 111 are switched not only to the dental chart screen I05 but also to the name and other screen I17.

The name and other screen I17 will be described below with reference to FIG. 2G.
In FIG. 2G, the name and other screen I17 is configured so that various item information P01 regarding the finding data can be set. In the present disclosure, as shown in FIG. 2G, the case name, examination date, examination doctor, life and death, sex, estimated age, actual age, discovery date, discovery place, and examination place can be set. Table 4 shows the definition of each item.

  The item information described in Table 4 is basically input or set based on operation information from the operation input device 13.

Among the item information, in particular, the examining doctor can select a doctor registered on a setting change screen I19 described later from the pull-down menu M01.
In addition, as the examination place, the examination place registered on the setting change screen I19 described later is displayed as an initial value.
As the case name, a name for identifying the identity confirmation business is input based on the operation information of the operation input device 13.

<2-3. Setting change screen>
As described above, in FIG. 2A, the setting change button B03 is assigned a function for switching to the display of the setting change screen I19. Hereinafter, the configuration of the setting change screen I19 will be described with reference to FIG. 3A.

  The setting change screen I19 is used to set the reading of each tooth and the state of the tooth to be input. The setting change screen I19 is further used for setting names and other doctor names that can be selected on the screen, and initial values of examination locations. For this purpose, the setting change screen I19 includes a dental chart area R15, a tooth reading list area R17, a tooth status list area R19, an examining doctor list area R21, and an examination area input area R23. Is done.

  The dental chart region R15 is a rightmost region of the setting change screen I19, and is configured such that the tooth row and information for identifying each tooth are visible to the operator.

  The tooth reading list area R17 is an area on the left side of the dental chart area R15, and readings for specifying each tooth by voice are set and displayed for each tooth. Although details will be described later, reading of each tooth can be set in a plurality of ways by using a predetermined delimiter.

  The tooth state list area R19 is an area adjacent to the right of the tooth reading list area R17. In the tooth state list area R19, a setting button B37 is arranged for each tooth state. For convenience of illustration, in FIG. 3A, the setting button at the upper right of the tooth state list region R <b> 19 and the setting button for the tooth state “healthy” is denoted by reference sign B <b> 37.

  Each setting button B37 is assigned a function of displaying the corresponding tooth state editing screen I21 on the setting change screen I19.

  Here, the editing screen I21 will be described with reference to FIG. 3B. FIG. 3B illustrates an editing screen I21 of the tooth state “healthy”.

  3B, each edit screen I21 includes a name input box C07, a reading input box C09, a color button B39, a tooth expression button B41, an OK button B43, and a cancel button B45.

In the name input box C07, a character string indicating the name of the tooth state is input and displayed.
In the reading input box C09, the reading of the character string input in the name input box C07 is input and displayed.

  A function for setting the color of the corresponding setting button B37 is assigned to the color button B39. When this color button B39 is clicked, for example, a color chart (not shown) is further overlaid. The color operated by the operation input device 13 is set as the color of the setting button B37.

  Tooth expression button B41 is assigned a function for setting the expression of the tooth state in dental chart image I05. When the tooth expression button B41 is clicked, a tooth expression image selection screen I23 as shown in FIG. 3C is further displayed in an overlay manner.

  In FIG. 3C, the selection screen I23 displays a sample image G01 that is prepared in advance and represents a plurality of (14 in the drawing) different tooth expression methods that can be selected. It is not possible to specify a method for expressing a tooth having an occlusal surface with respect to a tooth having no occlusal surface, such as the first to third permanent teeth and the A to C number deciduous teeth.

Reference is again made to FIG. 3B.
The OK button B43 is assigned a function for applying the contents changed on the editing screen I21 and terminating the overlay display of the editing screen I21.
The cancel button B45 is assigned a function of discarding the contents changed on the editing screen I21 without applying them and ending the overlay display of the editing screen I21.

Here, referring to FIG. 3A again.
The examining doctor list area R21 is arranged on the left side of the tooth state list area R19. The name of the examining doctor is added to or deleted from the examining doctor list region R21.
The examination area input area R23 is arranged below the examination doctor list. In the input area R23 of the examination place, the initial value of the examination place of the newly created finding data is entered.

<2-4. Search screen>
As described above, in FIG. 2A, the search button B05 is assigned a function for switching to display of the search screen I25. Hereinafter, the configuration of the search screen I25 will be described with reference to FIG. 4A.

  The search screen I25 is used to search for existing findings data stored in the storage device 191 that include conditions specified by the operator using the operation input device 13. For this purpose, the search screen I25 includes a search condition input area R25 and a search result output area R27.

  The search condition input area R25 is a substantially left half area of the search screen I25. Various search conditions are input and displayed in the search condition input area R25. In the present disclosure, items that can be input and set on the finding creation screen I03 can be input and displayed as search conditions.

  The search result output area R27 is an area in which search results are displayed in response to an operation of the search button B47 arranged in the search condition input area R25.

<2-5. Output screen>
As described above, in FIG. 2A, a function for switching to the display of the output screen I27 is assigned to the output button B07. Hereinafter, the configuration of the output screen I27 will be described with reference to FIG. 5A.

  The output screen I27 is used to output existing finding data in a designated format, and mainly includes an output destination input area R29, an output format selection button B51, a character code selection button B53, and a close button B55. , And an output button B57.

  In the output destination input area R29, the output destination of the existing finding data is input based on the operation information. Note that when a reference button B47 arranged next to the output destination input area R29 is clicked, a dialog for selecting and specifying the output destination input area R29 is displayed in an overlay manner.

  The output format selection button B51 is used to select an output format of finding data by operating the operation input device 13. In the present disclosure, a predetermined word processor format and a csv (comma-separated values) format are selected.

  The character code selection button B53 is used when the csv format is selected, and is used to select a character code and a line feed code by operating the operation input device 13.

  The close button B55 is assigned a function for ending the overlay display on the output screen I27.

  The output button B57 is used when a file is output in the output format specified as the output destination specified on the output screen I27 by the operation of the operation input device 13.

<2-6. Data operation screen>
As described above, in FIG. 2A, a function for switching to the display of the data operation screen I29 is assigned to the data operation button B09. Hereinafter, the configuration of the data operation screen I29 will be described with reference to FIG. 6A.

  The data operation screen I29 is used for deleting any existing finding data, creating a backup, and restoring the finding data from the created backup. For this purpose, the data operation screen I29 includes an existing finding deletion button B59, a backup creation button B61, a backup restoration button B63, and a close button B65.

  A function for switching to the display of the finding deletion screen I31 is assigned to the existing finding deletion button B59. As shown in FIG. 6B, the observation deletion screen I31 includes an observation list area R31, a deletion button B67, and a close button B69.

  The finding list area R31 is configured to list the finding data that can be deleted and to select the finding data to be deleted by the operation of the operation input device 13.

  A function for deleting the selected finding data is assigned to the delete button B67.

  The close button B69 is assigned a function for returning the display of the finding deletion screen I31 to the data operation screen I29.

  Reference is again made to FIG. 6A. The backup creation button B61 is assigned a function for switching to display of a screen I33 for creating backup data of existing finding data. As shown in FIG. 6C, the screen I33 includes an output destination input area R33, a close button B71, and a creation button B73.

  In the output destination input area R33, the output destination of the backup data to be created is input based on the operation information. Note that when a reference button B75 arranged next to the output destination input area R33 is clicked, a dialog (not shown) capable of selecting and specifying the output destination input area R33 is displayed in an overlay manner.

  The close button B71 is assigned a function of ending the display of the screen I33 and returning to the display of the data operation screen I29.

  The creation button B73 is used when the backup data is output in the output format specified as the output destination specified on the screen I33 by the operation of the operation input device 13.

  Reference is again made to FIG. 6A. The backup restoration button B63 is assigned a function of switching to the overlay display of the screen I35 for restoring the backup data as existing finding data. As shown in FIG. 6D, the screen I35 includes a backup folder designation area R35, a close button B77, and a restore button B79.

  In the backup folder designation area R35, the storage location of the backup data is input based on the operation information. Note that a dialog (not shown) that allows the user to select and designate the backup folder designation area R35 is displayed in an overlay manner by clicking a reference button B81 arranged next to the backup folder designation area R35.

  The close button B77 is assigned a function of terminating the display of the screen I35 and returning to the display of the data operation screen I29.

  The restore button B79 is used when restoring the backup data at the storage location designated on this screen I35 to the finding data by operating the operation input device 13.

<3. Processing of Finding Device>
Next, the process of the finding creation device 19 will be described in detail with reference to FIGS. 7A to 7B.
When the operator performs a predetermined operation to activate both programs P1 and P3, the processor 195 functions as the voice recognition unit 197 and is continuously output from the voice input device 11 set to ON. A known small word speech recognition process is always performed on the speech signal, and the speech recognition result (that is, character data) is passed to the finding creation unit 199 through the working memory 193 (step S001 in FIG. 7A).

  The processor 195 also functions as the finding creation unit 199. Immediately after the activation, the processor 195 first generates the list screen I01 shown in FIG. 2A, displays it on the display device 111, and sets the dictionary used for speech recognition as a small vocabulary word speech. Switch to the recognition dictionary (for list screen) D3 (step S003).

  Next, the finding creation unit 199 determines whether or not the new creation button B01 has been operated (step S005). If NO is determined, the process proceeds to step S007 described later.

  On the other hand, if YES is determined in step S005, the finding creation unit 199 generates a finding creation screen I03 to create new finding data, and the display content of the display device 111 is changed from the list screen I01 to the finding creation screen I03. And the finding creation screen I03 is displayed (step S007). At this time, a dental chart screen I05 is displayed at the center of the finding creation screen I03, and the dictionary used for small vocabulary word speech recognition is switched to the small vocabulary word speech recognition dictionary (for dental chart) D5.

  Here, it is also possible for an operator (for example, a dentist) to input characters on the dental chart screen I05 by operating an operation input device. In addition, when the operator speaks a voice representing a predetermined voice command to the voice input device 11, the dental chart screen I 05 is displayed on the dental chart screen 195 based on the small vocabulary word voice recognition result by the voice recognition unit 197. It is also possible to enter the status in characters. In other words, the dental chart screen I05 is an example of a second screen on which characters cannot be input based on the result of large vocabulary continuous speech recognition.

  Therefore, for example, in the process of switching the display from the list screen I01 to the dental chart screen I05, the finding creation unit 199 includes a setting button B83 for setting the input of the voice input device 11 to ON as shown in FIG. 8A. Encourage the operator to click.

Thereafter, the finding creation unit 199 creates finding data (step S009).
Hereinafter, with reference to FIG. 7B, the detailed process of step S009 will be described.

  The operator operates the screen switching tab T01 with the operation input device 13 to select the dental chart screen I05 (step S100), and then opens an unidentified person or the like with his / her finger and observes the oral cavity. On the other hand, a voice command for specifying a tooth as a state input target is uttered toward the voice input device 11. When a voice command for specifying a tooth is input, the voice input device 11 outputs a voice signal representing this to the voice recognition unit 197.

  The speech recognition unit 197 performs a small vocabulary word speech recognition process on the input speech signal while the dental chart screen I05 is displayed on the display device 111, and obtains a speech recognition result (word) for identifying a tooth as a finding creation unit 199.

  When the finding creation unit 199 receives the voice recognition result specifying the tooth (step S101), as shown in FIG. 8B, the dental chart screen I05 surrounds the target tooth with a predetermined color ○ and the state of the target tooth Input fields C01 and C03 are selected, and the inside is highlighted with a specific color (step S103). FIG. 8B illustrates a case where the voice recognition result is “Migiue Ichiban” and the state input fields C01 and C03 are permanent tooth state input fields C01.

  The operator utters a voice command for specifying a tooth while diagnosing the oral cavity of an unidentified person or the like, and then utters a voice command representing the state of the tooth toward the voice input device 11. When the voice representing the tooth state is input, the voice input device 11 outputs a voice signal representing this to the voice recognition unit 197.

  The speech recognition unit 197 performs small vocabulary word speech recognition processing on the input speech data, and passes the speech recognition result representing the tooth state to the finding creation unit 199.

  When the finding creation unit 199 receives a speech recognition result representing the state of the tooth after step S103 (step S105), as shown in FIG. 8C, the state of the tooth is displayed in the state input fields C01 and C03 selected in step S101. Is input and displayed as characters (step S107). FIG. 8C illustrates the case where the voice recognition result is “enjoy”.

At this time, if a tooth expression image is pre-assigned to the received tooth state (YES in step S109), the finding creation unit 199 is circled on the dental chart screen I05 as shown in FIG. 8D. The expression of the tooth is changed to one assigned in advance (step S111).
The operator repeatedly utters the voice specifying the tooth that is the target of state input and the state of the tooth toward the voice input device 11. Each time, the finding creation unit 199 executes steps S101 to S111. When the diagnosis in the oral cavity of the unidentified person is completed, the operator speaks to the voice input device 11 with a voice command “End” set in advance to close the dental chart screen I05. As a result, a voice recognition result representing the voice command “end” is passed from the voice recognition unit 197 to the finding creation unit 199.

  If NO is determined in step S109 or after step S111, the finding creating unit 199 determines whether or not the close button B19 is operated (step S114). If YES is determined, the finding creation unit 199 exits the process of step S009 (the processes of FIGS. 7A to 7B) and performs step S017 of FIG. 7A. On the other hand, when it is determined NO in step S114, the finding creation unit 199 returns to step S100 in FIG. 7B.

  In some cases, the operator may want to correct the state of the input tooth. In this case, the operator speaks to the voice input device 11 a voice that specifies a tooth that is a state input target and a voice command “clear” for deleting the state of the tooth.

  When the finding creation unit 199 receives the voice command “clear”, as shown in FIG. 8D, it clears the state of the tooth already input in the state input fields C01 and C03 selected in step S101. Although the states are inserted in the state input fields C01 and C03 in the order in which they are spoken, the last input image of the tooth on the dental chart screen I05 is given priority.

  Further, when the operator wants to check the state of the tooth input in the state input fields C01 and C03, the operation input device 13 is operated to specify the tooth, and then the reproduction button B17 is operated. In response to this, the finding creating unit 199 reads out the designated tooth state and causes the sound output device 113 to output sound data representing the tooth state.

  As described above, the second screen is a screen incapable of character input based on the result of large vocabulary continuous speech recognition, and an example thereof is a dental chart screen I05. In the present disclosure, among the dental chart screen I05, the facial photo screen I09, the intraoral photo screen I11, the denture photo screen I13, the note screen I15, and the name and other screen I17 that can be switched by the screen switching tab T01, the screens other than the note screen I15 are the first. Predefined as two screens.

  An operator (dentist or his assistant) may take a facial photograph, an intraoral photograph, and a denture photograph of an unidentified person or the like. In this case, these image data are transferred to the finding creation device 19 via the data reading device 15 and the communication device 17.

  In this case, the operator operates the screen switching tab T01 to display the facial photo screen I09, the intraoral photo screen I11, and the denture photo screen I13, and the respective central regions R03, R05, R07 (see FIG. 2D). ) By drag and drop. In the finding creating apparatus 19, the finding creating unit 199 determines whether or not any of the facial photo screen I09, the intraoral photo screen I11, and the denture photo screen I13 is selected in step S100 (NO in FIG. 7C). Step S115) If YES, the facial photo screen I09, intraoral photo screen I11 and denture photo screen I13 are displayed and the dictionary to be used is switched to the small vocabulary word speech recognition dictionary (for each photo screen) D7 ( Step S116). Thereafter, the finding creation unit 199 stores the image data of the facial photograph, intraoral photograph, and denture photograph in the storage device 191 in accordance with the operation signal of the operation input device 13 (step S117). Thereafter, the finding creation unit 199 returns to Step S100 in FIG. 7B.

  Of course, if a facial photograph, an intraoral photograph, and a denture photograph of an unidentified person or the like cannot be taken, the pasting to the facial photograph screen I09, the intraoral photograph screen I11, and the denture photograph screen I13 is not performed.

  Further, when the operator wants to record a finding memo, the operator operates the screen switching tab T01 with the input operation device 13 to display the note screen I15. Thereafter, the operator utters the voice representing the observation memo to be recorded toward the voice input device 11 and finally utters the voice command “END”. During this time, in the finding creating device 19, the finding creating unit 199 judges whether or not the note screen I15 has been selected after judging NO in step S115 (step S119). Then, the notebook screen I15 as another example of the first screen is displayed, and the dictionary to be used is switched to the small vocabulary word speech recognition dictionary (for notebook) D9 (step S121).

  Next, the finding creation unit 199 determines whether or not the screen is switched from the other screen to the note screen I15, or whether or not the voice command “note” is received from the voice recognition unit 197 (step S122).

  If NO is determined in step S122, the finding creation unit 199 performs step S100 of FIG. 7B.

  In contrast, if YES is determined in step S122, the speech recognition unit 197 starts executing the large-scale continuous speech recognition program P11 using the large-scale continuous speech recognition dictionary D1, and displays the note screen I15 as the first screen. In the middle, large vocabulary continuous speech recognition is performed on the input speech signal from the speech input device 13, and the result is passed to the finding creation unit 199.

  The finding creating unit 199 inputs and displays the large vocabulary continuous speech recognition result received from the speech recognizing unit 197, that is, the character representing the finding memo in the note input area R11 of the note screen I15 (step S123). Upon receiving the voice command “END” (YES in step S125), the finding creation unit 199 stores the contents of the note input area R11 in the storage device 191 (step S127), and displays the display contents of the display device 111 on the note screen. By switching from I15 to the facial picture screen I09 as an example of the second screen, the execution of large vocabulary continuous speech recognition is terminated and character input by so-called dictation to the note screen I15 is disabled (step S129). Thereafter, the finding creation unit 199 returns to Step S100 in FIG. 7B.

  During the creation of the observation memo, the operator can correct the observation memo while using the voice command described in the voice command display area R13.

  Further, while the note screen I15 is displayed, the operator operates the operation input device 13 to operate the playback button B17. In response to this, the finding creation unit 199 performs the reading process of the finding memo described in the note input area R11 and causes the voice output device 113 to output voice data representing the finding memo.

  When the operator wants to set a case name, an examination date, etc., the operator operates the screen switching tab T01 with the input operation device 13 to display the name and other screen I17. Thereafter, the operator operates the input operation device 13 to input a case name, an inspection date, and other necessary items. During this time, when the name and other screen I17 is selected (step S131 in FIG. 7D), the finding creation unit 199 displays the name and other screen I17 and uses a small vocabulary word speech recognition dictionary (for name and other screen). Switching to D11 (step S133), based on the received operation information, necessary items are input and displayed on the name and other screen I17 (step S135). After step S135 or when determining NO in step S131, the finding creation unit 199 returns to step S100 in FIG. 7B.

  The finding data created as described above includes at least a dental chart. In some cases, the findings data includes facial photographs, intraoral photographs and denture photographs, findings notes, and establishment names. Such finding data is stored in the storage device 191.

  Here, FIG. 7A is referred again. If NO in step S005, step S011 is performed. In step S011, the finding creation unit 199 determines whether or not the setting change button B03 has been operated.

  If it is determined YES in step S011, the finding creation unit 199 generates a setting change screen I19 to change various settings, and switches the display content of the display device 111 from the list screen I01 to the setting change screen I19. Then, the setting change screen I19 is displayed (step S013). Thereafter, the finding creation unit 199 changes various settings (step S015).

For example, when the reading of each tooth in the tooth row is individually changed, the operator clicks the reading of the tooth to be changed with the operation input device 13 in the tooth reading list R17. Thereafter, the operator operates the operation input device 13 to input the reading of the target tooth with hiragana (see FIG. 9A). Here, when it is desired to set a plurality of readings, the operator inputs a plurality of readings in hiragana and separates each reading with a delimiter (for example, |).
Further, the operator inputs the tooth state to the edit screen I21 in the same manner as described above.
In response to the operation as described above, the finding creation unit 199 changes the reading of the tooth and the reading of the state of the tooth.

  When the operator registers the name of the dentist, as shown in FIG. 9B, the operator inputs the dentist name by operating the operation input device 13 in the name input box C11 arranged in the examining doctor list region R21. To do. Thereafter, the operator clicks on the operation input device 13 an additional button B85 arranged in the examining doctor list region R21. In response to such an operation, the finding creation unit 199 adds a new dentist to the dentist list region R21.

  After steps S009 and S015, or if NO in step S011, the finding creation unit 199 determines whether or not to end the execution of the programs P1 and P3 (step S017). When it is determined NO, the finding creation unit 199 returns to step S003, but when it is determined YES, the execution of the programs P1 and P3 is terminated.

  In the case of NO in step S011, although not shown in FIG. 7A, retrieval of existing finding data, output, data manipulation, etc. may be performed as necessary (FIGS. 4A, 5A, 6A). See).

<3. Action and Effect of Finding Device>
As described above, according to the finding creating apparatus 19, the finding creating screen I03 is obtained by operating a plurality of screen switching tabs T01, a dental chart screen I05, a facial photo screen I09, an intraoral photo screen I11, a denture photo screen I13, Either the note screen I15 or the other screen I17 is selectively displayed. Here, the note screen I15 is defined as the first screen, and the other dental chart screen I05 and the facial photo screen I09 are defined as the second screen. During the display of the first screen, during the execution of step S123, based on the result of the large vocabulary continuous speech recognition from the speech recognition unit 197, it is permitted to input the characters of the observation memo. On the other hand, on the second screen, basically, character input based on the large vocabulary continuous speech recognition result is disabled, and characters are input based on the result of small vocabulary word speech recognition.

  During the display of the note screen I15, the observation creation unit 199 switches the display content of the display device 111 to the facial photo screen I09, which is the second screen, in response to the voice command “end”, and large vocabulary continuous voice recognition And the use of the dictionary D1 is ended (prohibited).

  In the present finding creation device 19, while the note screen I15 is being displayed and step S123 is being executed, the speech recognition unit 197 performs large-scale continuous speech recognition on the speech signal from the speech input device 11, so If the unit 199 automatically switches from the note screen I15 (first screen) to the second screen and does not switch to a state in which only the small-scale word speech recognition is performed by terminating the large-scale continuous speech recognition, the display screen Unnecessary character input may be performed above. However, according to the finding creation apparatus 19, the note screen I15 (that is, the first screen) is not capable of large-scale continuous speech recognition such as the facial photo screen I09 in response to the input of the voice command “end”. Since the screen is switched to two screens, unnecessary character input as described above is not performed.

  As described above, the main finding creation device 19 switches from large-scale continuous speech recognition to small-scale word speech recognition in order to make it possible to create finding memos completely hands-free while the note screen I15 is displayed. Switching from the screen to the second screen. As a result, a finding memo can be created by completely hands-free, and a finding creating device 19 having a user interface that is easy for the operator to use and a program for creating a dental finding can be provided.

  Further, according to the present finding creation device 19, as described above, the dental chart and the finding memo can be created completely hands-free, so the dentist can create the dental chart without an assistant. .

  Further, according to the present disclosure, it is possible to input commands with natural utterances as in normal diagnosis by changing readings of teeth and dentition (customizing a dictionary).

<4. Addendum>
In the above embodiment, as a preferred mode, switching from the first screen to the second screen is performed using the voice command “end” as a trigger. However, the present invention is not limited to this, and the operator operates the plurality of screen switching tabs T01 on the operation input device 13, and switching from the first screen to the second screen is performed using an operation signal generated thereby as a trigger. It doesn't matter.

  In the above embodiment, the storage device 191 has been described as storing the voice recognition program P1 and the voice input dental chart program P3. However, the present invention is not limited thereto, and the programs P1 and P3 may be provided by being stored in a computer-readable recording medium (for example, a DVD). In addition, the program may be stored in the server device so that various terminal devices can be downloaded.

  In addition, the voice recognition program P1 and the voice input dental chart program P3 may be provided separately stored in a recording medium, and may be provided to the server device so that various terminal devices can be individually downloaded. It may be stored.

  Further, the dental chart screen I05 included a tooth row image viewed in plan from the up-down direction. However, the present invention is not limited to this, and the dental chart screen I05 may include a tooth row image viewed in plan from the front, and a tooth row image viewed in plan from the top and bottom and a tooth row image viewed in plan from the front are It may be switched according to user settings.

  The finding creation device of the present disclosure, a program for creating a dental finding, and a recording medium on which the program is recorded have a user interface suitable for recording a dental finding, and are suitable for being mounted on a personal computer or the like. It is.

19 Finding Device 191 Storage Device 197 Speech Recognition Unit 199 Finding Creation Unit P1 Speech Recognition Program P3 Speech Input Dental Chart Program

Claims (9)

A voice recognition unit that performs at least large vocabulary continuous voice recognition on a voice signal representing the utterance content;
Based on the result of the large vocabulary continuous speech recognition, a predetermined signal indicating the end of the character input is received during the display of the first screen while the first screen allowing the input of the characters representing the utterance content is displayed. And a finding creation unit that switches the display of the display device to a second screen on which characters cannot be input based on the result of the large vocabulary continuous speech recognition.   The finding creation apparatus according to claim 1, wherein the predetermined signal is a voice signal representing a predetermined voice command. An operation input device that outputs an operation signal in response to an operation with a finger is connected to the finding creation device,
The finding creation apparatus according to claim 1, wherein the predetermined signal is an operation signal transmitted from an operation input device when a predetermined operation is performed on the first screen. The voice recognition unit further performs small vocabulary word voice recognition,
The finding creation apparatus according to claim 1, wherein character input based on a result of the small vocabulary word speech recognition is permitted on the second screen. The second screen includes a tooth row image representing a tooth row,
The finding creation apparatus according to any one of claims 1 to 4, wherein expression of each tooth in the tooth row image is selectable. The second screen includes a tooth row image representing a tooth row,
The finding creation apparatus according to claim 1, wherein a state of each tooth in the tooth row image is represented by a specific color. A procedure for causing the display device to display a first screen that allows the input of characters representing the utterance content based on the result of large vocabulary continuous speech recognition;
A procedure for switching the display content of the display device to a second screen in which character input based on the result of the large vocabulary continuous speech recognition is prohibited when a predetermined signal indicating the end of character input is received during display of the first screen And a method for creating findings. On the computer,
A procedure for causing the display device to display a first screen that allows the input of characters representing the utterance content based on the result of large vocabulary continuous speech recognition;
A procedure for switching the display content of the display device to a second screen in which character input based on the result of the large vocabulary continuous speech recognition is prohibited when a predetermined signal indicating the end of character input is received during display of the first screen And a finding creation program. On the computer,
A procedure for causing the display device to display a first screen that allows the input of characters representing the utterance content based on the result of large vocabulary continuous speech recognition;
A procedure for switching the display content of the display device to a second screen in which character input based on the result of the large vocabulary continuous speech recognition is prohibited when a predetermined signal indicating the end of character input is received during display of the first screen And a recording medium recording the finding creation program.