Audio recording program and audio recording method

Abstract

To prevent voice recording omissions when creating an electronic medical record using voice recording. [Solution] The audio recording program runs on a web browser of a computer on which the web browser is installed, and provides the computer with the following functions: acquiring page information of a web page accessed by the web browser; determining the start of audio recording when the page information contains specified information; acquiring audio recording data when it is determined that audio recording should start; and transmitting the audio recording data to a generation server and acquiring character data generated based on the audio recording data from the generation server.

Description

[Technical Field]

[0001] The present invention relates to an audio recording program and an audio recording method. [Background technology]

[0002] In recent years, electronic medical records have been used in many medical institutions. To improve the work efficiency of medical professionals, there is a method for creating electronic medical records using voice input. Patent Document 1 describes a highly convenient and operable voice-to-text system that converts voice information into text information in order to reduce the work burden on doctors and other medical professionals. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7689682 Summary of the Invention [Problem to be solved by the invention]

[0004] By creating an electronic medical record using voice recording, medical professionals can concentrate on listening to the patient's story. However, if voice recording is started by operating a recording operation unit as described in Patent Document 1, voice recording may not start if the operator forgets to operate the unit during the examination, resulting in missing voice recordings. In this case, the medical professional is required to perform additional tasks, such as manually entering the information to be entered into the electronic medical record or repeating the same questions to record the voice again, which creates an operational burden.

[0005] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a voice recording program and a voice recording method that prevent voice recording omissions when creating an electronic medical chart using voice recordings. [Means for solving the problem]

[0006] An audio recording program according to one aspect of the present invention is a program that runs on a web browser of a computer on which the web browser is installed, and provides the computer with the following functions: acquiring page information for a web page accessed by the web browser; determining the start of audio recording when the page information contains specified information; acquiring audio recording data when it is determined that audio recording should start; and transmitting the audio recording data to a generation server and acquiring text data generated based on the audio recording data from the generation server.

[0007] According to this aspect, audio recording is started using the page information of the web page as a trigger, so audio recording can be started without any additional operation by the user, thereby preventing any audio recording from being missed.

[0008] In the above aspect, the page information may include at least one of URI information indicating the URI of the web page and rendering information used to render the web page.

[0009] According to this aspect, the start of audio recording can be determined based on the URI information or rendering information required for displaying a web page, so audio recording can be started when a user displays a web page, thereby preventing audio from being missed.

[0010] In the above aspect, the computer may further be configured to realize a function of notifying the user that the voice recording data is being recorded when acquisition of the voice recording data is started.

[0011] According to this aspect, the user is notified that audio data is being recorded, so even if audio recording is started based on page information, the user can be aware of the start of audio recording, thereby increasing user convenience.

[0012] In the above aspect, the computer may further be configured to implement a function of saving the character data acquired from the generating server on a clipboard on the computer.

[0013] According to this aspect, by storing character data on the clipboard, for example, the operational burden on the user when using the character data in other software or the like can be reduced, thereby improving user convenience.

[0014] In the above aspect, the saving function may be configured to automatically save the character data to the clipboard when the character data is acquired.

[0015] According to this aspect, the character data is automatically saved to the clipboard, eliminating the need for additional operations by the user, thereby reducing the operational burden when using the character data in other software, etc., and improving user convenience.

[0016] In the above aspect, the function of saving may be configured to notify the user that the saving has been completed when the saving of the character data to the clipboard has been completed.

[0017] According to this aspect, the user can know that the character data has been automatically saved, and can proceed to the next operation, thereby improving user convenience.

[0018] In the above aspect, the computer may further be configured to realize a function of notifying the user that character data is being generated when the acquired voice recording data is transmitted to the generation server.

[0019] According to this aspect, the user can understand that the character data is generated based on the voice recording data, thereby improving convenience for the user.

[0020] An audio recording method according to one aspect of the present invention includes the steps of: on a web browser of a computer on which a web browser is installed, the computer acquiring page information of a web page accessed by the web browser; determining to start audio recording when the page information contains specified information; acquiring audio recording data when it has been determined that audio recording should start; transmitting the audio recording data to a generation server; and acquiring text data generated based on the audio recording data from the generation server. [Effects of the Invention]

[0021] According to the present invention, it is possible to provide a voice recording program that prevents missing recordings by automatically starting voice recording. [Brief explanation of the drawings]

[0022] [Figure 1] FIG. 1 is a diagram showing an overview of a voice recording system. [Figure 2] FIG. 2 is a block diagram of each device in the voice recording system. [Figure 3] FIG. 2 is a diagram showing an example of information stored in a medical record DB. [Figure 4] FIG. 1 is a diagram illustrating an outline of processing in a voice recording system. [Figure 5] FIG. 10 is a diagram illustrating a voice recording determination process in a user terminal. [Figure 6] FIG. 10 is a diagram showing an example of a medical record selection screen displayed on a user terminal. [Figure 7] FIG. 10 is a diagram showing an example of a medical record screen displayed on a user terminal. [Figure 8] FIG. 10 is a diagram showing an example of a medical record screen displayed on a user terminal. [Figure 9] FIG. 10 is a diagram showing an example of a medical record screen displayed on a user terminal. [Figure 10] FIG. 10 is a diagram showing an example of a medical record screen displayed on a user terminal. DETAILED DESCRIPTION OF THE INVENTION

[0023] Hereinafter, an embodiment of the voice recording program of the present invention will be described in detail with reference to the drawings. In the drawings, components with the same reference numerals have the same or similar configurations.

[0024] <<Configuration Overview>> An overview of a voice recording system 10 using a voice recording program will be described with reference to Figure 1. The voice recording system 10 includes user terminals 101a to 101n, a voice recording server 201, a medical record management server 301, and a generation server 401. When no distinction is necessary, the user terminals 101a to 101n will be collectively referred to as user terminals 101.

[0025] The user terminal 101 is communicably connected to the voice recording server 201 and the medical record management server 301 via a network N. The voice recording server 201 is communicably connected to the generation server 401 via the network N.

[0026] The user terminal 101 is an information processing terminal operated by a user, and is, for example, a smartphone, a tablet terminal, or a personal computer (for example, a desktop or laptop).

[0027] The voice recording server 201 is a server device that supports input of electronic medical records managed by the medical record management server 301 described below. The voice recording server 201 acquires, for example, voice recording data of a conversation between a user (medical professional) and a patient during a medical interview from the user terminal 101. The voice recording server 201 transfers the voice recording data to the generation server 401 and acquires the character data generated by the generation server 401 for input into the electronic medical record.

[0028] The voice recording server 201 transfers the acquired character data to the user terminal 101. Thereafter, the information in the electronic medical record managed by the medical record management server 301 is updated based on the character data through user operation. The character data is information obtained by converting voice information recorded as voice recording data into character information, or information obtained by converting character information into a predetermined format, for example, a SOAP format (SOAP: Subjective, Objective, Assessment, Plan) that conforms to the electronic medical record.

[0029] The medical record management server 301 is a server device that manages electronic medical records used in medical institutions. A user accesses the patient's electronic medical record stored in the medical record management server 301, for example, during a medical interview.

[0030] The generation server 401 is a server device having a function as a generation AI that generates text information using a language model that can perform natural language processing based on voice recording data or text data.

[0031] 2, the following describes each of the components of the user terminal 101, voice recording server 201, medical record management server 301, and generation server 401 in the voice recording system 10. Each of the components of the user terminal 101, voice recording server 201, medical record management server 301, and generation server 401 in the voice recording system 10 can be realized by a processor executing a program stored in a memory unit in the user terminal 101, voice recording server 201, medical record management server 301, and generation server 401.

[0032] The user terminal 101 includes a communication unit 1011 , a storage unit 1012 , a display unit 1013 , a voice acquisition unit 1014 , an operation acquisition unit 1015 , and a browser unit 1016 .

[0033] The communication unit 1011 controls communication between the user terminal 101 and the voice recording server 201 and the medical record management server 301 .

[0034] The storage unit 1012 stores various types of information used in processing in the user terminal 101 .

[0035] The storage unit 1012 includes a clipboard 10121 managed by the operating system (OS) installed in the user terminal 101 as a temporary information storage area.

[0036] The display unit 1013 is a display of the user terminal 101 .

[0037] The voice acquisition unit 1014 is a voice acquisition device such as a microphone provided in the user terminal 101. The voice acquisition unit 1014 may be a voice acquisition device connected to the user terminal 101.

[0038] The operation acquisition unit 1015 acquires operation input from the user. The operation acquisition unit 1015 is, for example, a keyboard, a mouse, or a touch panel.

[0039] The browser unit 1016 is software installed in the user terminal 101 to enable the user terminal 101 to browse the Internet through a network. In the voice recording system 10, in addition to the normal browsing function of the browser unit 1016, a program operable on a web browser having the functions of a page information acquisition unit 10161, a voice recording start determination unit 10162, a voice recording data acquisition unit 10163, a character data acquisition unit 10164, a notification unit 10165, and a storage unit 10166 is installed as an add-in.

[0040] The page information acquisition unit 10161 acquires page information of a web page accessed by a web browser. The page information includes URI information indicating the URI (URL or URN) of the web page or rendering information used to render the web page. URI information is information that identifies the resource of the information displayed as a web page. The URI information is, for example, the address of a website. Rendering information is information about the display content of a web page that is used by the web browser when drawing the web page. The rendering information is, for example, information that includes the identifier of an element displayed on the web page (e.g., a medical record display area) and the text displayed in the element (e.g., the content of the medical record).

[0041] The audio recording start determining unit 10162 determines whether to start audio recording when the page information contains predetermined information.

[0042] For example, when URI information is acquired as page information, the audio recording start determination unit 10162 determines to start audio recording if the string of characters in the URI information contains information indicating that the web page is an input screen for an electronic medical record (for example, an ID that identifies the patient).

[0043] In addition, the audio recording start judgment unit 10162 determines to start audio recording when, for example, rendering information is acquired as page information and the rendering information includes information indicating that the web page is an input screen for an electronic medical record (for example, information indicating the display area for the medical record contents).

[0044] The audio recording start determination unit 10162 may determine to start audio recording when the audio acquisition unit 1014 acquires predetermined audio information indicating the start of audio recording. The predetermined audio information corresponds to a phrase such as "Next person please" when guiding a patient to an examination room, a phrase such as "How are you today?" uttered by a doctor at the start of a medical interview, a phrase such as "Thank you for your help" uttered by a patient at the start of a medical interview, or a phrase such as "This is Mr. / Ms. XX (patient's name)" uttered by a doctor's assistant at the start of a medical interview. The audio recording start determination unit 10162 may input the audio information acquired by the audio acquisition unit 1014 into an AI (e.g., a trained model or a large-scale language model) to determine whether audio recording should be started (i.e., whether an examination is about to begin). The audio recording start determination unit 10162 may have a function to start audio recording based on the predetermined audio information instead of or in addition to the above-described function of starting audio recording based on predetermined information included in page information.

[0045] By determining the start of voice recording based on page information, for example, even if the user has a web page related to an electronic medical record open, voice recording can be prevented from starting if the medical record input screen is not open. Therefore, when the add-in of the browser unit 1016 is running, the user can operate the web browser without being aware of whether the medical record input screen is open, thereby improving user operability when using the add-in.

[0046] When it is determined that audio recording should be started, the audio recording data acquisition unit 10163 acquires the audio recording data. For example, the audio recording data acquisition unit 10163 controls the audio acquisition unit 1014 to a state in which audio recording is performed, and acquires the audio recorded by the audio acquisition unit 1014 as audio recording data.

[0047] The character data acquisition unit 10164 transmits the voice recording data to the generation server 401 and acquires the character data generated based on the voice recording data from the generation server 401. The character data acquisition unit 10164 transmits the voice recording data to the generation server 401, for example, from the user terminal 101 via the voice recording server 201. The voice recording data may be transmitted by streaming the voice recording data in parallel with the recording, or may be transmitted from the user terminal 101 to the voice recording server 201 after the recording is completed. The voice recording server 201 transfers the data acquired from the user terminal 101 to the generation server 401, as described below.

[0048] The character data acquisition unit 10164 acquires character data generated by processing the voice recording data in the generation server 401 from the generation server 401. The character data acquisition unit 10164 acquires character data from the generation server 401, for example, via the voice recording server 201. Specifically, the voice recording server 201 sends an instruction (prompt) to the generation server 401 requesting the generation of character data, and the voice recording server 201 transfers the character data acquired from the generation server 401 to the user terminal 101.

[0049] When acquisition of voice recording data begins, the notification unit 10165 notifies the user that the voice recording data is being recorded. Furthermore, when the notification unit 10165 transmits the acquired voice recording data to the generation server 401, the notification unit 10165 notifies the user that character data is being generated in the generation server 401. The notification unit 10165 notifies the user, for example, by updating a screen showing the operating status of the add-in in the web browser or by displaying a pop-up notification on the web browser screen.

[0050] The saving unit 10166 saves the character data acquired from the generation server 401 in the clipboard 10121 of the user terminal 101. When the saving unit 10166 acquires the character data, it may automatically save the character data in the clipboard 10121. Furthermore, when the saving unit 10166 has completed automatic saving of the character data to the clipboard, it may notify the user that the saving has been completed.

[0051] The voice recording server 201 includes a communication unit 2011 , a storage unit 2012 , a voice recording data transfer unit 2013 , and a character data transfer unit 2014 .

[0052] The communication unit 2011 controls communication between the voice recording server 201 and the user terminal 101 and the generation server 401. The storage unit 2012 stores various information used in processing by the voice recording server 201.

[0053] The voice recording data transfer unit 2013 acquires voice recording data acquired by the user terminal 101 from the user terminal 101 and transmits it to the generation server 401. The voice recording data transfer unit 2013 may acquire the voice recording data by streaming, for example, or may acquire the voice recording data after recording is completed from the user terminal 101. The voice recording data transfer unit 2013 may transmit the voice recording data acquired from the user terminal 101 to the generation server 401 by streaming, or may transmit it to the generation server 401 as data after recording is completed.

[0054] The character data transfer unit 2014 transmits an instruction (prompt) requesting the generation of character data to the generation server 401, acquires the character data from the generation server 401, and transmits the character data to the user terminal 101. The prompt transmitted by the character data transfer unit 2014 to the generation server 401 may be, for example, "Please transcribe the voice recording data and organize the character data in SOAP format." The voice recording server 201 may also acquire from the user the settings of a language model for generating character data.

[0055] Furthermore, the voice recording server 201 can accept logins from users via the user terminal 101 and provide voice recording services for each user. The character data transfer unit 2014 may associate the acquired character data with the corresponding voice recording data and store it in the storage unit 2012. The voice recording data transfer unit 2013 may store the transmitted voice recording data in the storage unit 2012. By logging in, users can view the voice recording data and the corresponding character data they have recorded.

[0056] The medical record management server 301 includes a communication unit 3011 , a storage unit 3012 , and a medical record management unit 3013 .

[0057] The communication unit 3011 controls communication between the medical record management server 301 and the user terminal 101. The storage unit 3012 stores various information used in processing by the medical record management server 301. The storage unit 3012 has a medical record management DB 30121.

[0058] The medical record management DB 30121 will be described with reference to Fig. 3. The medical record management DB 30121 stores medical record management information. The medical record management information has the following fields: "Medical Institution ID," "Patient ID," "Patient Name," "Medical Record ID," "Medical Record Information," and "Medical Record Address Information." The medical record management information may also be associated with other information, such as information on the date and time the medical record was created and the date and time the medical record was updated.

[0059] The "Medical Institution ID" field stores information identifying the medical institution. The "Patient ID" field stores information identifying the patient. The "Patient Name" field stores the patient's name. The "Medical Record ID" field stores information identifying the patient's medical record. The "Medical Record Information" field stores the contents of the electronic medical record (initial appearance, diagnosis, treatment, etc.). The medical record information stores, for example, character data for each section in SOAP format and character data for the entire medical record. The "Medical Record Address Information" field stores a URI indicating the address of the medical record. The URI is information that can be arbitrarily designed by the provider of the electronic medical record service. In the audio recording system 10, the URI is described as information that can uniquely identify the medical record, for example, by combining the medical institution ID, patient ID, medical record ID, etc.

[0060] Returning to Figure 2, the medical record management unit 3013 will now be described. The medical record management unit 3013 displays medical record information and updates medical record management information via the medical record management server 301. For example, the medical record management unit 3013 displays an electronic medical record on the user terminal 101 in response to access from the user terminal 101, and accepts input of character data into the electronic medical record from the user terminal 101.

[0061] The generation server 401 includes a communication unit 4011 , a voice analysis model 4012 , a voice recording data input unit 4013 , and a character data transmission unit 4014 .

[0062] The communication unit 4011 controls communication between the generation server 401 and the voice recording server 201 .

[0063] The speech analysis model 4012 is a language model that has been trained to be capable of performing natural language processing based on speech recording data or character data.

[0064] The voice recording data input unit 4013 inputs the voice recording data acquired from the voice recording server 201 into the voice analysis model 4012. At this time, the voice recording data input unit 4013 also inputs a prompt, sent from the voice recording server 201, requesting the generation of character data into the voice analysis model 4012. The voice recording data may be input into the voice analysis model 4012 by streaming the voice recording data from the voice recording server 201, or by inputting the voice recording data acquired from the voice recording server 201 into the voice analysis model 4012 after recording is completed.

[0065] The character data transmission unit 4014 acquires the character data output from the voice analysis model 4012 and transmits it to the user terminal 101 via the voice recording server 201 .

[0066] <<Processing Overview>> The processing in the voice recording system 10 will be described with reference to FIGS.

[0067] In step S401, the web browser of the user terminal 101 and the voice recording add-in installed in the web browser are launched.

[0068] In step S402, login information is transmitted to the voice recording server 201 via the user terminal 101, and the user logs in.

[0069] In step S403, the user terminal 101 transmits login information to the medical record management server 301, and the user logs in. The user can log in to the medical record management server 301 using, for example, the medical institution ID of the medical institution to which the user belongs.

[0070] In step S404, the medical record management unit 3013 generates information for the medical record selection screen.

[0071] In step S405, the user terminal 101 acquires information on the chart selection screen.

[0072] In step S406, the user terminal 101 displays a chart selection screen on the web browser.

[0073] 5 shows an example of a medical record selection screen 501. On the medical record selection screen 501, a list of patients managed by the medical record management server 301 is displayed in list format.

[0074] The medical record selection screen 501 has an address display area 5011 , a list display area 5012 , and a voice recording add-in display area 5021 .

[0075] The address display area 5011 displays the URI currently being accessed by the web browser. The list display area 5012 displays a list of patients acquired from the medical record management server 301. In the example of Figure 5, only the name is displayed, but other information such as the patient ID may also be displayed.

[0076] The audio recording add-in display area 5021 displays information indicating the operation of the add-in installed in the web browser. In the example of FIG. 5, it is displayed that the add-in is an audio recording program. The audio recording add-in display area 5021 has an audio recording status display area 50211. In the audio recording status display area 50211, information indicating the acquisition status of audio recording data, etc. is displayed. In the example of FIG. 5, it is displayed that audio recording is "on hold" and that the audio recording time is "00:00".

[0077] By selecting a patient name on the medical record selection screen 501, the user can obtain page information of the electronic medical record associated with the patient name and display the electronic medical record on the user terminal 101.

[0078] 4, the voice recording determination process is performed in step S407. The voice recording determination process will be described with reference to FIG.

[0079] In step S601, the page information acquisition unit 10161 acquires the URI information of the web page to which the browser is transitioning.

[0080] In step S602, the page information acquisition unit 10161 acquires rendering information used for rendering the web page to be displayed based on the URI information.

[0081] In step S603, the voice recording start determination unit 10162 determines whether the URI information is the URI of the electronic medical record input screen. For example, if the URI contains information indicating a patient ID or a medical record ID, the voice recording start determination unit 10162 determines that the URI is the URI of the electronic medical record input screen.

[0082] If the URI information is the URI of the electronic medical record input screen (step S603: YES), in step S604, the voice recording data acquisition unit 10163 starts recording voice data.

[0083] In step S605, the notification unit 10165 notifies the user that recording of audio data has started. The notification is performed, for example, by displaying a pop-up notification on the user terminal 101.

[0084] Depending on the format of the URI provided by the electronic medical record provider, it may not be possible to determine whether the URI information is the URI of the electronic medical record input screen, and if it is determined that the URI information is not the URI of the electronic medical record input screen (step S603: NO), the audio recording start determination unit 10162 determines whether the rendering information includes information of the electronic medical record input screen. For example, if the rendering information includes information indicating that the web page is an electronic medical record input screen (for example, information indicating the display area of ​​the medical record content), the audio recording start determination unit 10162 determines to start audio recording.

[0085] If the rendering information includes information on the electronic medical record input screen (step S606: YES), the processes of steps S604 and S605 are performed, and audio recording and notification are performed.

[0086] If the determination is negative in both step S603 and step S606, the process ends.

[0087] Furthermore, the processing of steps S603 and S606 does not necessarily have to be performed after the processing of step S603. For example, the start of audio recording may be determined only by the processing of step S603, or the start of audio recording may be determined only by the processing of step S606.

[0088] Returning to FIG. 4, the process when it is determined that audio recording should be started will be described.

[0089] In step S408 , the character data acquisition unit 10164 transmits the voice recording data acquired by the voice recording data acquisition unit 10163 to the voice recording server 201 .

[0090] In step S 409 , the voice recording data transfer unit 2013 transmits the voice recording data to the generating server 401 .

[0091] In step S410, the character data acquisition unit 10164 sends an instruction to end voice recording to the voice recording server 201. The instruction to end voice recording is sent based on an operational input from the user, the content of the voice recording data, or the recording status of the voice recording data. The instruction to end voice recording is sent, for example, by an operational input from the user via a web browser on the user terminal 101. Alternatively, the instruction to end voice recording is sent when it is determined that the recording of the voice recording data has exceeded a predetermined required time for the medical interview. The instruction to end voice recording is sent when a predetermined phrase indicating the end of the medical interview (for example, "take care") appears in the voice recording data. When sending the instruction to end voice recording, the user terminal 101 stops acquiring voice data and updates the acquisition status of the voice recording data.

[0092] In step S411, the character data transfer unit 2014 transmits to the generation server 401 an instruction to analyze the recorded voice data.

[0093] In step S412, the voice recording data input unit 4013 inputs the voice recording data to the generating server 401, and the voice recording data is analyzed.

[0094] In step S413, generated character data is generated by the voice analysis model 4012 and acquired by the character data transmission unit 4014.

[0095] In step S 414 , the character data transfer unit 2014 acquires the character data from the generation server 401 .

[0096] In step S 415 , the character data acquisition unit 10164 acquires character data from the voice recording server 201 .

[0097] In step S 416 , the storage unit 10166 stores the character data in the clipboard 10121 .

[0098] In step S417, the notification unit 10165 notifies the user that the character data has been saved.

[0099] In step S418, character data pasted from the clipboard 10121 into a predetermined input area of ​​the electronic medical record is transmitted from the user terminal 101 to the medical record management server 301 via the electronic medical record input screen.

[0100] In step S419, the medical record management unit 3013 updates the medical record management information stored in the medical record management DB 30121.

[0101] By performing the above process, the voice recording system 10 can start voice recording and acquire text data without any additional operations by the user, thereby preventing voice recording omissions.

[0102] In the example of Figure 4, the end of audio recording is determined by the transmission of an instruction to end audio recording from the user terminal 101, but the end of audio recording may also be determined by the audio recording server 201. The audio recording server 201 may make a determination similar to that made in the user terminal 101 and send an instruction to end audio recording to the user terminal 101. In this case, when the user terminal 101 receives an instruction to end audio recording from the audio recording server 201, it ends audio recording.

[0103] An example of a medical record input screen 701 in the voice recording system 10 will be described with reference to FIGS.

[0104] 7 shows a medical record input screen 701 when "Mr. A" is selected on the medical record selection screen 501. The medical record input screen 701 has a medical record input area 7011 and a patient information display area 70111. At this time, the URI displayed in the address display area 5011 is information indicating that the medical record input screen 701 is an input screen for an electronic medical record. In addition, the voice recording add-in display area 5021 and the voice recording status display area 50211 are superimposed on the medical record input screen 701 or are displayed near the medical record input screen 701.

[0105] The medical record input area 7011 has a patient information display area 70111 and medical record input areas 70112, 70113, 70114, 70115, and 70116. The patient information display area 70111 is an area where the patient name and medical record ID obtained from the medical record management server 301 are displayed. The medical record input areas 70112, 70113, 70114, 70115, and 70116 are areas where information corresponding to the disease name and the Subject, Objective, Assessment, and Plan in SOAP format is entered.

[0106] 7, audio recording has already started, and the user is notified that audio recording has started by displaying "Recording" in audio recording status display area 50211. The recording start time is also updated and displayed.

[0107] When the voice recording is completed, the screen is updated to the medical record input screen 701 shown in Fig. 8. In Fig. 8, the voice recording status display area 50211 displays "analyzing" to notify the user that the voice recording has completed and the voice recording data is currently being analyzed.

[0108] When the analysis of the voice recording data is completed and the character data acquisition unit 10164 acquires the character data from the generation server 401 via the voice recording server 201, the screen is updated to the medical record input screen 701 shown in Fig. 9. In Fig. 9, a completion notice 7021 is displayed to notify the user that the acquisition and storage of the character data has been completed.

[0109] The user operates the user terminal 101 to input information into medical record input areas 70113, 70114, 70115, and 70116. The screen after the information has been input is shown in FIG. 10. Because the character data is recorded in SOAP format, the user can input data into the electronic medical record by pasting the corresponding character data into each of the medical record input areas 70113, 70114, 70115, and 70116. The user can then enter the name of the disease based on the examination. In the voice recording system 10, by storing character data in SOAP format on the clipboard, the operational burden on the user when inputting character data into the electronic medical record can be reduced, for example, thereby improving user convenience.

[0110] The above-described embodiments are intended to facilitate understanding of the present invention and are not intended to limit the present invention. The elements of the embodiments, as well as their arrangement, conditions, shape, size, etc., are not limited to those exemplified and can be modified as appropriate. [Explanation of symbols]

[0111] 10...voice recording system, 101...user terminal, 201...voice recording server, 301...medical record management server, 401...generation server, 1016...browser unit, 10161...page information acquisition unit, 10162...voice recording start determination unit, 10163...voice recording data acquisition unit, 10164...character data acquisition unit, 10165...notification unit, 10166...storage unit

Claims

1. A program that runs on a web browser of a computer on which a web browser is installed, The computer, a function of acquiring page information of a web page accessed by the web browser; a function of determining the start of audio recording when predetermined information is included in the page information; a function of acquiring voice recording data when it is determined that the voice recording has started; a function of transmitting the voice recording data to a generation server and acquiring, from the generation server, character data generated based on the voice recording data; This is an audio recording program that makes this possible.

2. 2. The audio recording program according to claim 1, wherein the page information includes at least one of URI information indicating a URI of the web page and rendering information used to render the web page.

3. The computer, 2. The voice recording program according to claim 1, further realizing a function of notifying the user that the voice recording data is being recorded when acquisition of the voice recording data starts.

4. The computer, 2. The voice recording program according to claim 1, further comprising a function of saving the character data acquired from the generating server on a clipboard on the computer.

5. The function of storing the character data is as follows:

5. The voice recording program according to claim 4, further comprising a function of automatically saving the character data to the clipboard.

6. 6. The audio recording program according to claim 5, wherein the function of saving includes a function of notifying the user that the character data has been saved to the clipboard when the saving is completed.

7. The computer, 2. The voice recording program according to claim 1, further realizing a function of notifying the generation server that the character data is being generated when the acquired voice recording data is transmitted to the generation server.

8. On the web browser of a computer on which a web browser is installed, the computer obtaining page information of a web page accessed by the web browser; determining whether to start audio recording when the page information includes predetermined information; When it is determined that voice recording has started, acquiring voice recording data; transmitting the voice recording data to a generation server, and acquiring character data generated based on the voice recording data from the generation server; 1. A method for recording audio, comprising:

Images