JP7753752B2 - Voice recording management system, voice recording management device, voice recording management method and program - Google Patents

Description

The present invention relates to an audio recording management system, an audio recording management device, an audio recording management method, and a program.

Technology for recognizing voice data based on recognition patterns and converting it into text has been known for some time.

For example, there is known technology that converts voice data indicating the content of a task spoken by a user into text and manages it as a work record (see, for example, Patent Document 1).

However, with conventional technology, when registering voice recording information from voice information based on spoken voice, the spoken voice must be provided using limited recognition patterns regardless of the tenant, group, etc. to which the user belongs, resulting in a lack of flexibility for the user.

In order to solve the above-mentioned problems, the invention of claim 1 is a voice recording management system including a registration management terminal that registers one or more recognition patterns for recognizing uttered voices, and a voice recording management device that manages voice recording information obtained based on the one or more recognition patterns input to the registration management terminal, wherein the registration management terminal has a transmission means that transmits the one or more recognition patterns so that a voice analysis server that analyzes voice information based on the uttered voice and converts it into text information can analyze the voice information, and the voice recording management device receives, as a voice analysis request for requesting analysis of the voice information, tenant identification information of a tenant to which a user who uttered the uttered voice belongs and group identification information of a group to which the user belongs. The present invention provides a voice recording management system comprising: a transmitting means for transmitting to the voice analysis server one or more recognition pattern identification information that identifies the one or more recognition patterns associated with at least one of the identification information, and the voice information; a receiving means for receiving, in response to the voice analysis request , a voice analysis response that includes voice analysis result information that indicates the voice analysis result analyzed by the voice analysis server using a specific recognition pattern from among the one or more recognition patterns, and specific recognition pattern identification information that indicates the specific recognition pattern; and a registration means for registering voice recording information corresponding to the voice information based on the voice analysis result information and the specific recognition pattern identification information that indicates the specific recognition pattern included in the received voice analysis response.

As described above, according to the present invention, when registering voice recording information from voice information based on spoken voice, the spoken voice can be provided using a recognition pattern corresponding to the tenant, group, etc. to which the user belongs, thereby achieving the effect of improving flexibility for users.

FIG. 1 is a diagram illustrating an example of the overall configuration of a communication system. 2 is a diagram illustrating an example of the hardware configuration of a registration management terminal, a voice recording management device, a voice analysis server, and a voice communication management device. FIG. FIG. 2 is a diagram illustrating an example of the hardware configuration of an input terminal and a viewing terminal. FIG. 1 illustrates an example of a functional configuration of a communication system. FIG. 1 illustrates an example of a functional configuration of a communication system. FIG. 1 illustrates an example of a functional configuration of a communication system. FIG. 10 is a conceptual diagram illustrating an example of a recognition pattern item management table. FIG. 10 is a conceptual diagram illustrating an example of a recognition pattern identification management table. FIG. 10 is a conceptual diagram illustrating an example of a synonym management table. FIG. 10 is a conceptual diagram illustrating an example of a tenant group management table. FIG. 10 is a conceptual diagram illustrating an example of a voice recording management table. FIG. 10 is a conceptual diagram illustrating an example of an analysis result management table. FIG. 10 is a conceptual diagram illustrating an example of a notification information management table. FIG. 10 is a conceptual diagram illustrating an example of a recognition pattern. FIG. 10 is a conceptual diagram illustrating an example of a user information management table. FIG. 10 is a conceptual diagram illustrating an example of a voice information management table. FIG. 10 is a sequence diagram illustrating an example of a process for registering a recognition pattern. FIG. 10 is a sequence diagram illustrating an example of a synonym registration process. FIG. 10 is a sequence diagram showing an example of processing up to storage of voice information (data). FIG. 10 is a sequence diagram illustrating an example of a voice analysis process when there is no matching recognition pattern. FIG. 10 is a sequence diagram illustrating an example of a voice analysis process when a matching recognition pattern is present. 10A is an example of a screen display in the input terminal notifying the user that an instruction has been input unsuccessfully, and FIG. 10B is an example of a screen display in the input terminal notifying the user that an instruction has been input successfully. 10 is an example of a screen display of a nursing care record confirmation notification on a viewing terminal. 10 is an example of a screen display of a transfer confirmation notice on a viewing terminal. FIG. 10 is a sequence diagram illustrating an example of a search process and a voice recording process. 10A is an example of a screen display at the time of transfer search on the viewing terminal, and FIG. 10B is another example of a screen display at the viewing terminal for transfer confirmation notification. 10A is an example of a screen display at the time of a transfer search at another viewing terminal, and FIG. 10B is another example of a screen display at the other viewing terminal for a transfer confirmation notice.

The following describes the embodiments of the invention using the drawings. Note that identical elements in the description of the drawings are given the same reference numerals, and any overlapping parts will be omitted.

[Embodiment]
The embodiment will be described with reference to FIGS. 1 to 25. FIG.

[Overall configuration of communication system]
<<System configuration example>>
FIG. 1 is a diagram illustrating an example of the overall configuration of a communication system. As shown in FIG. 1, the communication system 1 includes various devices and servers, including a registration management terminal 2, a voice recording management device 3, a voice analysis server 4, a voice communication management device 5, a user terminal 6, a telephone 7, and a viewing terminal 9. The registration management terminal 2, the voice recording management device 3, the voice analysis server 4, the voice communication management device 5, the user terminal 6, the telephone 7, and the viewing terminal 9 are connected to each other via a communication network 100. Here, the communication network 100 is a communication network through which an unspecified number of communications are conducted, and is constructed using the Internet, an intranet, a local area network (LAN), or the like. Note that the communication network 100 may include not only wired communication, but also wireless communication networks such as 3G (3rd Generation), 4G (4th Generation), 5G (5th Generation), WiMAX (Worldwide Interoperability for Microwave Access), and LTE (Long Term Evolution).

The communication system 1 has a voice recording management system 10 constructed by a registration management terminal 2 and a voice recording management device 3. The registration management terminal 2 and the voice recording management device 3 may be connected to each other via a dedicated local area network, or may be connected to each other via a firewall inside the communication network 100.

The communication system 1 may further comprise a voice input/viewing management system 20, which adds an input terminal 8 and a viewing terminal 9 to the voice recording management system 10, which is comprised of the registration management terminal 2 and the voice recording management device 3. In this embodiment, the user terminal 6 and the telephone 7 are collectively referred to as the input terminal 8. The basic functions of each device and server are explained in detail below.

<Registration management terminal>
The registration management terminal 2 is realized by one or more information processing devices (computer systems) equipped with a general server OS or the like. The registration management terminal 2 is one of the devices that constitute the voice recording management system 10. The registration management terminal 2 registers one or more recognition patterns for recognizing spoken voice. The registration management terminal 2 accepts a registration instruction for a recognition pattern input by an administrator managing the registration management terminal 2 and transmits the accepted recognition pattern to the voice recording management device 3 via the network 100. The registration management terminal 2 may be a communication terminal with communication functions, such as a commonly used personal computer (PC), portable notebook PC, mobile phone, smartphone, tablet terminal, or wearable terminal (sunglasses-type, wristwatch-type, etc.). The registration management terminal 2 may also be a communication device or communication terminal capable of running software such as browser software.

<Audio Recording Management Device>
The voice recording management device 3 is realized by one or more information processing devices (computer systems) equipped with a general server OS or the like. The voice recording management device 3 is one of the devices that make up the voice recording management system 10. The voice recording management device 3 also manages voice recording information obtained based on one or more recognition patterns input to the registration management terminal 2. The voice recording information is managed in the analysis result management DB 3006 described below, and includes voice analysis result information corresponding to item names defined for each recognition pattern. The voice recording management device 3 also stores a voice communication app in a storage means.

The audio recording management device 3 may be constructed using a single computer, or may be constructed using multiple computers to which each section (function or means) such as storage is divided and arbitrarily assigned. Furthermore, all or part of the functions of the audio recording management device 3 may be performed by a server computer in a cloud environment, or a server computer in an on-premise environment.

<Speech analysis server>
The voice analysis server 4 is realized by one or more information processing devices (computer systems) equipped with a general server OS or the like. The voice analysis server 4 registers one or more recognition patterns associated with at least one of the tenant and the group transmitted by the voice recording management device 3. The voice analysis server 4 also analyzes voice data (voice information) based on the speech uttered by the user using a voice recognition engine, converts it into text data (text information), and responds to the voice recording management device 3. That is, in the communication system according to this embodiment, the voice analysis server 4 has a cloud service function for converting voice information into text information. Specifically, the voice analysis server may use a third-party service that enables voice recognition, and may be provided, for example, by a general-purpose voice recognition engine service.

<Voice communication management device>
The voice communication management device 5 is realized by one or more information processing devices (computer systems) equipped with a general server OS or the like. The voice communication management device 5 stores voice data transmitted from the input terminal in a predetermined storage means, and transmits the voice data stored in the predetermined storage means to the voice recording management device 3 in response to an inquiry about the voice data transmitted from the voice recording management device 3. The voice communication management device 5 also stores a voice communication application in a storage means, and transmits voice data (voice information) transmitted from the input terminal 8 to the voice recording management device 3. The voice communication management device 5 also functions as an intermediary device that acts as an intermediary between the input terminal 8 and the voice recording management device 3, transmitting various notification information, screen data (screen information), etc. transmitted by the voice recording management device 3 to the input terminal 8. The voice communication management device 5 is provided by a third-party service.

The voice communication management device 5 may also notify (send) data (information) to the input terminal 8 (described below) via push notification (transmission). In this case, the voice communication management device 5 can achieve this by using, for example, FCM (Firebase Cloud Messaging), an example of a push notification server, to send push notifications. The voice communication management device 5 may also be a commonly used PC (Personal Computer). The voice communication management device 5 may also be a communication device or communication terminal capable of running software such as browser software.

<User terminal>
The user terminal 6 is realized by one or more information processing devices (computer systems) for communication, equipped with a general OS or the like. The user terminal 6 converts the user's speech into audio information and transmits it to the voice communication management device 5. The user terminal 6 also receives various notification information and screen data (screen information) generated by the voice recording management device 3 and transmitted (transferred) by the voice communication management device 5, displays them on the display of the user terminal 6, and plays the notification audio through a speaker. The user terminal 6 may be a communication terminal with communication functions, such as a commonly used PC (Personal Computer), portable notebook PC, mobile phone, smartphone, tablet device, or wearable device (sunglasses-type, wristwatch-type, etc.). The user terminal 6 may also be a communication device or communication terminal capable of running software such as browser software.

<Telephone>
The handset 7 is equipped with a microphone and has a function of converting the speech of a user using the handset into an electrical signal and transmitting it to the communication network 100. The handset 7 also converts voice data transmitted via the communication network 100 into an audio signal and plays it back through a speaker. The handset 7 is a communication device, an example of which is a commonly known intercom.

In this embodiment, the user terminal 6 and the telephone 7 function as an input terminal 8 that transmits voice data (voice signals) provided by the speech of users belonging to a specific tenant, group, etc., and displays various notification information and screen data transmitted by the voice communication management device 5, or plays back the voice.

<Viewing terminal>
The viewing terminal 9 is realized by one or more information processing devices (computer systems) for communication, equipped with a general OS or the like. The viewing terminal 9 displays various notification information and screen data generated by the voice recording management device 3 and transmitted (transferred) by the voice communication management device 5 on a display in response to a viewer's operation, and plays notification audio through a speaker. The viewing terminal 9 may also be a communication terminal with communication functions, such as a commonly used personal computer (PC), portable notebook PC, mobile phone, smartphone, tablet device, or wearable device (sunglasses, wristwatch, etc.). The viewing terminal 9 may also be a communication device or communication terminal capable of running software such as browser software.

●About terminology●
In this embodiment, a user refers to any of the following: For example, users include workers who speak during specific events, tasks, medical procedures, etc., viewers who view various information using viewing terminals, machines equipped with AI that can generate human-spoken language, humanoid robots, etc. In this embodiment, the term "user" is used for the sake of convenience.

Furthermore, in this embodiment, audio information includes care records or handover information related to handovers in care and nursing. Furthermore, one or more pieces of recognition pattern information include recognition pattern identification information for identifying one or more recognition patterns and one or more items included in the recognition pattern.

Furthermore, in this embodiment, text (text information) refers to various information that has been converted from audio information related to the voice spoken by the user into words, phrases, numbers, symbols, sentences, etc. expressed in visible characters based on the results of recognition using a specified dictionary, etc.

Furthermore, in this embodiment, an audio recording refers to a record consisting of text information (data), images, minutes including audio, etc. obtained based on audio information (data) related to the audio spoken by one or more event participants (users) at a specified event such as a conference.

The audio recording information is managed in the analysis result management table described below, and indicates analysis result information corresponding to the item names defined for each recognition pattern.

[Hardware configuration]
Next, the hardware configuration of the device or terminal constituting the communication system according to the embodiment will be described with reference to Figures 2 and 3. Note that components may be added or deleted from the hardware configuration of the device or terminal shown in Figures 2 and 3 as needed.

<Hardware configuration of registration management terminal, voice recording management device, voice analysis server, and voice communication management device>
2 is a diagram showing an example of the hardware configuration of a registration management terminal, a voice recording management device, a voice analysis server, and a voice communication management device. As shown in FIG. 2, the registration management terminal 2 is constructed, for example, by a computer, and includes a CPU 201, a ROM 202, a RAM 203, an EEPROM 204, a HD 205, a HDD (Hard Disk Drive) controller 206, a display 207, a short-range communication I/F 208, a CMOS sensor 209, an image sensor I/F 210, a network I/F 211, a keyboard 212, a pointing device 213, a media I/F 215, an external device connection I/F 216, an audio input/output I/F 217, a microphone 218, a speaker 219, and a bus line 220.

Of these, the CPU 201 controls the overall operation of the registration management terminal 2. The ROM 202 stores programs used to drive the CPU 201. The RAM 203 is used as a work area for the CPU 201. The EEPROM 204 reads and writes various data such as apps under the control of the CPU 201. The HD 205 stores various data such as programs. The HDD controller 206 controls the reading and writing of various data from and to the HD 205 under the control of the CPU 201. The display 207 displays various information such as a cursor, menus, windows, text, or images. The near-field communication I/F 208 is a communication circuit for performing data communication with a communication device or communication terminal equipped with a wireless communication interface such as NFC (Near Field Communication), Bluetooth (registered trademark, omitted below), or Wi-Fi (registered trademark, omitted below). The CMOS sensor 209 is a type of built-in imaging device that captures an image of a subject under the control of the CPU 201 to obtain image data or video data. Note that the imaging device may not be a CMOS sensor, but may instead be an imaging device configured as a CCD (Charge Coupled Device) sensor or the like. The imaging element I/F 210 is a circuit that controls the driving of the CMOS sensor 209.

The network I/F 211 is an interface for data communication using the communication network 100. The keyboard 212 is a type of input means equipped with multiple keys for inputting characters, numbers, various instructions, etc. The pointing device 213 is a type of input means for selecting and executing various instructions, selecting processing targets, moving the cursor, etc. The media I/F 215 controls the reading and writing (storage) of data from the recording medium 214, such as a flash memory. The external device connection I/F 216 is an interface for connecting various external devices. In this case, the external device is, for example, a USB (Universal Serial Bus) memory. The sound input/output I/F 217 is a circuit that processes the input and output of sound signals between the microphone 218 and speaker 219 under the control of the CPU 201. The microphone 218 is a built-in circuit that converts sound into an electrical signal, capturing voices and sound waves emitted from an external speaker, etc., and acquiring information using the electrical signal. The speaker 219 is a built-in circuit that converts electrical signals into physical vibrations to produce sounds such as music and voice. The bus line 220 is an address bus, data bus, etc. that electrically connects the CPU 201 and other components.

The audio recording management device 3 is constructed, for example, by a computer, and includes a CPU 301, ROM 302, RAM 303, EEPROM 304, HD 305, HDD (Hard Disk Drive) controller 306, display 307, short-range communication I/F 308, CMOS sensor 309, image sensor I/F 310, network I/F 311, keyboard 312, pointing device 313, media I/F 315, external device connection I/F 316, sound input/output I/F 317, microphone 318, speaker 319 and bus line 320. These hardware resources are similar to the respective hardware resources of the registration management terminal 2, including the CPU 201, ROM 202, RAM 203, EEPROM 204, HD 205, HDD (Hard Disk Drive) controller 206, display 207, short-range communication I/F 208, CMOS sensor 209, image sensor I/F 210, network I/F 211, keyboard 212, pointing device 213, media I/F 215, external device connection I/F 216, sound input/output I/F 217, microphone 218, speaker 219, and bus line 220, and therefore will not be described here.

The voice analysis server 4 is constructed, for example, by a computer, and includes a CPU 401, ROM 402, RAM 403, EEPROM 404, HD 405, HDD (Hard Disk Drive) controller 406, display 407, near-field communication I/F 408, CMOS sensor 409, image sensor I/F 410, network I/F 411, keyboard 412, pointing device 413, media I/F 415, external device connection I/F 416, sound input/output I/F 417, microphone 418, speaker 419 and bus line 420. These hardware resources are similar to the respective hardware resources of the registration management terminal 2, including the CPU 201, ROM 202, RAM 203, EEPROM 204, HD 205, HDD (Hard Disk Drive) controller 206, display 207, short-range communication I/F 208, CMOS sensor 209, image sensor I/F 210, network I/F 211, keyboard 212, pointing device 213, media I/F 215, external device connection I/F 216, sound input/output I/F 217, microphone 218, speaker 219, and bus line 220, and therefore will not be described here.

The voice communication management device 5 is constructed, for example, by a computer, and includes a CPU 501, ROM 502, RAM 503, EEPROM 504, HD 505, HDD (Hard Disk Drive) controller 506, display 507, short-range communication I/F 508, CMOS sensor 509, image sensor I/F 510, network I/F 511, keyboard 512, pointing device 513, media I/F 515, external device connection I/F 516, sound input/output I/F 517, microphone 518, speaker 519 and bus line 520. These hardware resources are similar to the respective hardware resources of the registration management terminal 2, including the CPU 201, ROM 202, RAM 203, EEPROM 204, HD 205, HDD (Hard Disk Drive) controller 206, display 207, short-range communication I/F 208, CMOS sensor 209, image sensor I/F 210, network I/F 211, keyboard 212, pointing device 213, media I/F 215, external device connection I/F 216, sound input/output I/F 217, microphone 218, speaker 219, and bus line 220, and therefore will not be described here.

<Hardware configuration of input terminal and viewing terminal>
3 is a diagram showing an example of the hardware configuration of an input terminal and a viewing terminal. As shown in Fig. 3, the input terminal 8 is constructed by, for example, a computer, and includes a CPU 801, a ROM 802, a RAM 803, an EEPROM 804, a display 807, a short-range communication I/F 808, a CMOS sensor 809, an image sensor I/F 810, a network I/F 811, a pointing device 813, a media I/F 815, an external device connection I/F 816, an audio input/output I/F 817, a microphone 818, a speaker 819, and a bus line 820. These hardware resources are similar to the respective hardware resources of the registration management terminal 2 shown in Fig. 2, namely, the CPU 201, ROM 202, RAM 203, EEPROM 204, display 207, short-range communication I/F 208, CMOS sensor 209, image sensor I/F 210, network I/F 211, pointing device 213, media I/F 215, external device connection I/F 216, sound input/output I/F 217, microphone 218, speaker 219, and bus line 220, and therefore will not be described here. Note that the input terminal 8 may be a communication device or communication terminal capable of running a program such as browser software.

The viewing terminal 9 is constructed, for example, by a computer, and includes a CPU 901, ROM 902, RAM 903, EEPROM 904, display 907, short-range communication I/F 908, CMOS sensor 909, image sensor I/F 910, network I/F 911, pointing device 913, media I/F 915, external device connection I/F 916, sound input/output I/F 917, microphone 918, speaker 919, and bus line 920. These hardware resources are similar to the respective hardware resources of the registration management terminal 2 shown in FIG. 2 , including the CPU 201, ROM 202, RAM 203, EEPROM 204, display 207, short-range communication I/F 208, CMOS sensor 209, image sensor I/F 210, network I/F 211, pointing device 213, media I/F 215, external device connection I/F 216, sound input/output I/F 217, microphone 218, speaker 219, and bus line 220, and therefore will not be described here. The viewing terminal 9 may be a communication device or terminal capable of running programs such as browser software.

Furthermore, the above program may be recorded on a computer-readable recording medium as an installable or executable file, or may be distributed by downloading via a network. Examples of recording media include CD-Rs (Compact Disc Recordables), DVDs (Digital Versatile Disks), Blu-ray Discs, SD cards, and USB memory. Furthermore, the recording media may be provided domestically or internationally as a program product. For example, the audio recording management device 3 realizes the audio recording management method of the present invention by executing the program of the present invention.

[Functional configuration of communication system]
Next, the functional configuration of this embodiment will be described with reference to Figures 4 to 14. Figure 4 is a diagram showing an example of the functional configuration of a communication system.

<Functional configuration of the registration management terminal>
As shown in Fig. 4A, the registration management terminal 2 includes a transmission/reception unit 21, an operation reception unit 22, a display control unit 24, a registration unit 26, an application launch unit 28, and a storage/readout unit 29. Each of these functional units is a function or means realized when any of the hardware resources shown in Fig. 2 operates in response to commands from the CPU 201 in accordance with a program for the registration management terminal 2 that is loaded from at least one of the ROM 202, EEPROM 204, and HD 205 to the RAM 203. The registration management terminal 2 also includes a memory unit 2000 constructed from at least one of the ROM 202, EEPROM 204, and HD 205 shown in Fig. 2. The memory unit 2000 also stores a communication program (communication application), a browser application, and the like for communicating with each device and each terminal via the communication network 100.

<<Functional configuration of the registration management terminal>>
Next, each functional component of the registration management terminal 2 will be described in detail. The transmission/reception unit 21 of the registration management terminal 2 shown in Fig. 4A is mainly realized by processing by the CPU 201 on the network I/F 211 and the short-range communication I/F 208, and transmits and receives various data (or information) between each terminal and each device via the communication network 100. The transmission/reception unit 21 also transmits one or more recognition patterns input to the registration management terminal 2 so that the voice analysis server 4 can analyze voice information. In this embodiment, the transmission/reception unit 21 functions as an example of at least one of a transmitting means and a receiving means.

The operation reception unit 22 is realized mainly by the CPU 201 processing signals generated by various operations received by the keyboard 212 and pointing device 213. Note that the operation reception unit 22 may use input means such as a touch panel 321 instead of the keyboard 212 and pointing device 213. In this embodiment, the operation reception unit 22 functions as an example of a reception means.

The display control unit 24 is mainly realized by the processing of the CPU 201 on the display 207, and controls the display of various screens and information (data) on the registration management terminal 2. The display control unit 24 also uses, for example, a browser to display a display screen created using HTML or the like on the display 207. In this embodiment, the display control unit 24 functions as an example of a display control means.

The registration unit 26 is realized mainly by processing of the CPU 201, and stores and registers various information, such as recognition patterns, input to the registration management terminal 2 in a predetermined area of the storage unit 2000. In this embodiment, the registration unit 26 functions as an example of a registration means.

The application launch unit 28 is mainly realized by the processing of the CPU 201, and launches various applications between each device and each terminal via the communication network 100. The application launch unit 28 also runs an application for uploading various text information to the voice communication management device 5 in a predetermined working area of the RAM 303. In this embodiment, the application launch unit 28 functions as an example of a launching means.

The memory/read unit 29 is mainly realized by the processing of the CPU 201 on at least one of the ROM 202, EEPROM 204, and HD 205 shown in FIG. 2, and stores various data (or information) in the memory unit 2000 and reads various data (or information) from the memory unit 2000. In this embodiment, the memory/read unit 29 functions as an example of a memory/reading means.

<Functional configuration of input terminal>
As shown in Fig. 4A, the input terminal 8 includes a transmission/reception unit 81, an operation reception unit 82, a sound/image acquisition unit 83, a display control unit 84, an audio playback unit 86, an application launch unit 88, and a storage/readout unit 89. Each of these functional units is a function or means realized when any of the hardware resources shown in Fig. 3 operates in response to an instruction from the CPU 801 in accordance with a program for the input terminal 8 that is loaded from at least one of the ROM 802 and the EEPROM 804 to the RAM 803. The input terminal 8 also includes a storage unit 8000 constructed from at least one of the ROM 802 and the EEPROM 804 shown in Fig. 3. The storage unit 8000 further stores a communication program (communication application), a browser application, and the like for communicating with each device and each terminal via the communication network 100.

<<Functional configuration of the input device>>
Next, a detailed description will be given of each functional configuration of the input terminal 8. The transmission/reception unit 81 of the input terminal 8 shown in Fig. 4A is mainly realized by processing of the CPU 801 on the network I/F 811 and the short-range communication I/F 808, and transmits and receives various data (or information) between each terminal and each device via the communication network 100. In this embodiment, the transmission/reception unit 81 functions as an example of at least one of a transmitting means and a receiving means.

The operation reception unit 82 is realized mainly by the CPU 801 processing signals generated by various operations received by the pointing device 813. Note that the operation reception unit 82 may use input means such as a keyboard or touch panel instead of the pointing device 813. In this embodiment, the operation reception unit 82 functions as an example of a reception means.

The sound/image acquisition unit 83 is mainly realized by the CPU 801's processing of the microphone 818, sound input/output I/F 817, CMOS sensor 809, and image sensor I/F 810, and collects voice (sound) related to speech, etc., uttered by a user using the input terminal 8 to acquire voice information (voice data) or sound information (sound data). The sound/image acquisition unit 83 also captures images related to images of the user's face, etc., to acquire image information (image data). In this embodiment, the sound/image acquisition unit 83 functions as an example of an acquisition means.

The display control unit 84 is mainly realized by the processing of the CPU 801 on the display 807, and controls the display of various screens and information (data) on the input terminal 8. The display control unit 84 also uses, for example, a browser to display a display screen created using HTML or the like on the display 807. In this embodiment, the display control unit 84 functions as an example of a display control means.

The audio playback unit 86 is mainly realized by the CPU 801's processing of the speaker 819 and the audio input/output I/F 817, and outputs (plays) audio (sound) related to various notification information generated by the audio recording management device 3 to the user using the input terminal 8 via the speaker 819. In this embodiment, the audio playback unit 86 functions as an example of playback means.

The application launch unit 88 is mainly realized by the processing of the CPU 801, and launches various applications between each device and each terminal via the communication network 100. The application launch unit 88 also runs an application for uploading various text information to the voice communication management device 5 in a specified work area of the RAM 803. In this embodiment, the application launch unit 88 functions as an example of a launching means.

The memory/read unit 89 is mainly realized by the processing of the CPU 801 on at least one of the ROM 802 and EEPROM 804 shown in FIG. 3, and stores various data (or information) in the memory unit 8000 and reads various data (or information) from the memory unit 8000. In this embodiment, the memory/read unit 89 functions as an example of a memory/reading means.

<Functional configuration of viewing terminal>
As shown in Fig. 4A, the viewing terminal 9 has a transmission/reception unit 91, an operation reception unit 92, a display control unit 94, an audio playback unit 96, an application launch unit 98, and a storage/readout unit 99. Each of these functional units is a function or means realized when any of the hardware resources shown in Fig. 3 operates in response to an instruction from the CPU 901 in accordance with a program for the viewing terminal 9 that is loaded from at least one of the ROM 902 and the EEPROM 904 to the RAM 903. The viewing terminal 9 also has a storage unit 9000 constructed from at least one of the ROM 902 and the EEPROM 904 shown in Fig. 3. Furthermore, the storage unit 9000 stores a communication program (communication application), a browser application, and the like for communicating with each device and each terminal via the communication network 100.

<<Functional configuration of the viewing device>>
Next, a detailed description will be given of each functional configuration of the viewing terminal 9. The transmitting/receiving unit 91 of the viewing terminal 9 shown in Fig. 4A is mainly realized by processing of the CPU 901 on the network I/F 911 and the short-range communication I/F 908, and transmits and receives various data (or information) between each terminal and each device via the communication network 100. In this embodiment, the transmitting/receiving unit 91 functions as an example of at least one of a transmitting means and a receiving means.

The operation reception unit 92 is realized mainly by the CPU 901 processing signals generated by various operations received by the pointing device 913. Note that the operation reception unit 92 may use input means such as a keyboard or touch panel instead of the pointing device 913. In this embodiment, the operation reception unit 92 functions as an example of a reception means.

The display control unit 94 is mainly realized by the processing of the CPU 901 on the display 907, and controls the display of various screens and information (data) on the viewing terminal 9. The display control unit 94 also uses, for example, a browser to display a display screen created using HTML or the like on the display 907. In this embodiment, the display control unit 94 functions as an example of a display control means.

The audio playback unit 96 is mainly realized by the processing of the CPU 901 on the speaker 919 and the audio input/output I/F 917, and outputs (plays) audio (sound) related to various notification information generated by the audio recording management device 3 to the user using the viewing terminal 9 via the speaker 919. In this embodiment, the audio playback unit 96 functions as an example of playback means.

The application launch unit 98 is mainly realized by the processing of the CPU 901, and launches various applications between each device and each terminal via the communication network 100. The application launch unit 98 also runs an application for uploading various text information to the voice communication management device 5 in a specified work area of the RAM 903. In this embodiment, the application launch unit 98 functions as an example of a launching means.

The memory/read unit 99 is mainly realized by the processing of the CPU 901 on at least one of the ROM 902 and EEPROM 904 shown in FIG. 3, and stores various data (or information) in the memory unit 9000 and reads various data (or information) from the memory unit 9000. In this embodiment, the memory/read unit 99 functions as an example of a memory/reading means.

<Functional configuration of the voice recording management device>
As shown in FIG. 4B, the voice recording management device 3 includes a transmission/reception unit 31, a display control unit 34, a judgment unit 35, a registration unit 36, a search unit 37, a generation unit 38, and a storage/readout unit 39. Each of these functional units is a function or means realized by the operation of any of the hardware resources shown in FIG. 2 in response to commands from the CPU 301 in accordance with a program for the voice recording management device 3 that is loaded from at least one of the ROM 302, EEPROM 304, and HD 305 to the RAM 303. The voice recording management device 3 also includes a memory unit 3000 constructed from at least one of the ROM 302, EEPROM 304, and HD 305 shown in FIG. 2. The memory unit 3000 further stores a communication program (communication application) for communicating with the core device and each terminal via the communication network 100, a browser application, a recording management application, and the like.

●Recognition Pattern Item Management Table●
Fig. 5 is a conceptual diagram showing an example of a recognition pattern item management table. A recognition pattern item management DB 3001 configured by the recognition pattern item management table shown in Fig. 5 is constructed in the storage unit 3000. In the recognition pattern item management table, a registration order and an item name are associated with each piece of recognition pattern identification information described later, and are stored and managed.

Of these, the recognition pattern identification information represents identification information for identifying the recognition pattern used by the voice analysis server 4 to perform voice recognition on the voice information sent by the input terminal 8 and convert it into text information, and is given as, for example, "R0001", "R0002", etc. The registration order is order information that indicates which of the items constituting one authentication pattern -- "record type", "task target", "task item", and "task result" -- are to be registered in what order. This table allows the administrator to register multiple recognition patterns for a specific tenant or group. The item names are the names of the items constituting one authentication pattern described above. In this embodiment, the recognition pattern item management DB 3001 is an example of a recognition pattern item management means that manages one or more recognition patterns in association with the recognition pattern identification information that identifies the recognition pattern.

●Recognition pattern identification management table●
Fig. 6 is a conceptual diagram showing an example of a recognition pattern identification management table. A recognition pattern item management DB 3001 configured by the recognition pattern item management table as shown in Fig. 5 is constructed in the storage unit 3000. In the recognition pattern identification management table, group identification information and recognition pattern identification information are associated with each other and stored and managed for each tenant identification information.

Of these, tenant identification information is identification information used to identify tenants to which users, administrators, viewers, etc. using communication system 1 belong. Examples of tenants include organizations and groups such as companies and schools. Here, tenant identification information is given as, for example, "T0001" or "T0115." Group identification information is identification information used to identify specific groups assigned to specific tenants. Here, group identification information is given as, for example, "G0001" or "G0002." The recognition pattern identification management table manages which recognition pattern identification information indicates which recognition pattern is associated with tenant identification information and group identification information. For example, two recognition patterns ("R0001" and "R0002") are associated with tenant identification information "T0001" and group identification information "G0001," while three recognition patterns ("R1234," "R1235," and "R1236") are associated with tenant identification information "T0001" and group identification information "G0001." In this embodiment, the recognition pattern identification management DB 3002 is an example of a recognition pattern identification management means that manages each piece of recognition pattern identification information indicating one or more recognition patterns in association with tenant identification information that identifies a specific tenant to which the user who uttered the speech belongs, and group identification information that identifies a specific group to which the user belongs.

●Synonym Management Table●
Fig. 7 is a conceptual diagram showing an example of a synonym management table. A synonym management DB 3003 configured by the synonym management table shown in Fig. 7 is constructed in the storage unit 3000. In the synonym management table, an item name keyword, synonym 1, synonym 2, ... are associated with each item identification information, stored, and managed.

Of these, item identification information is identification information (e.g., a serial number) for identifying items as synonyms. Item name keywords are managed as keywords for each item that makes up the recognition pattern, and are given as, for example, "body temperature," "taking medication," and "administering medication." Synonym 1, synonym 2, ... are managed as words similar to the item name keywords; for example, "fever" and "fever" are managed as words similar to "body temperature." This allows users (workers) to relax restrictions on the words they use when speaking in caregiving and nursing settings. In this embodiment, the synonym management DB 3003 is an example of a synonym management means that manages synonyms for each item that makes up the recognition pattern, included in the spoken voice, in association with keywords indicating each item.

●Tenant Group Management Table●
Fig. 8 is a conceptual diagram showing an example of a tenant group management table. A tenant group management DB 3004 configured by the tenant group management table shown in Fig. 8 is constructed in the storage unit 3000. In the tenant group management table, group identification information is stored and managed in association with tenant identification information. In this way, the tenant group management table is a table for associating tenants with groups.

●Audio Recording Management Table●
Fig. 9 is a conceptual diagram showing an example of a voice recording management table. A voice recording management DB 3005 configured by the voice recording management table shown in Fig. 9 is constructed in the storage unit 3000. In the voice recording management table, for each voice recording identification information separated by tabs, each set of tabs being tenant identification information and group identification information, the path of the voice data, user identification information, and registration date and time are associated with each other and stored and managed.

Of these, the audio recording identification information is identification information used to manage audio recordings, and is given as, for example, "V0001", "V0002", etc. The audio data path indicates the destination and path information for the saved audio data. This audio data path is given as, for example, "https://aaa/0001.wav". Note that the content managed by the audio data path may be the same as the audio data path managed in the audio information management table described above. The user identification information is information used to identify the user (worker), and is given as, for example, "User001", "User002", etc. The registration date and time is the date and time when the audio recording was registered, and is given as date information, for example, "2021/08/06 15:00:39".

●Analysis results management table●
Fig. 10 is a conceptual diagram showing an example of an analysis result management table. An analysis result management DB 3006 configured by the analysis result management table shown in Fig. 10 is constructed in the storage unit 3000. In the analysis result management table, the recording type, task target, task item, task date and time, and user identification information are associated with each piece of voice recording identification information, and are stored and managed.

Of these, the specific details of the record type, task target, task item, and task target corresponding to each item name described in the recognition pattern item management table above are managed in association with each voice recording identification information. Furthermore, the task date and time and user identification information are also managed in association with the voice recording identification information. The analysis result management table manages each component that makes up the voice analysis result information, which is the result of analysis by the voice analysis server 4, described below. In this embodiment, the analysis result management DB 3006 is an example of an analysis result management means that associates each value included in the voice analysis result information with each item managed in the recognition pattern item management DB 3001 (see Figure 5), and then manages the values in association with the voice recording identification information that identifies the voice recording information.

●Notification Information Management Table●
FIG. 11 is a conceptual diagram showing an example of a notification information management table. A notification information management DB 3007 configured by the notification information management table shown in FIG. 11 is constructed in the storage unit 3000. In the notification information management table, audio data of the notification information is managed in association with a record type. Here, the record types are given as "care record" and "handover," but are not limited to these. The audio data of the notification information is associated with each record type, and a path ("https://aaa.notice01.wav, etc.") of the audio data of the notification information to be notified to the input terminal 8 and the viewing terminal 9 is given.

<<Functional configuration of the voice recording management device>>
Next, each functional component of the voice recording management device 3 will be described in detail. The transmission/reception unit 31 of the voice recording management device 3 shown in FIG. 4B is mainly realized by processing by the CPU 301 on the network I/F 311 and the short-range communication I/F 308, and transmits and receives various data (or information) between the voice analysis server 4 and the voice communication management device 5 via the communication network 100. The transmission/reception unit 31 also transmits, as a voice analysis request for requesting analysis of the voice information, one or more recognition pattern identification information identifying one or more recognition patterns associated with at least one of the tenant identification information of the tenant to which the user who uttered the uttered voice belongs and the group identification information of the group to which the user belongs, and voice information to the voice analysis server 4. The transmission/reception unit 31 also transmits, to the voice communication management device 5, at least one of registration completion notification information indicating that the voice recording information has been registered and registration completion voice information obtained by vocalizing the registration completion notification information, so that the input terminal 8 can receive it. The transmitting/receiving unit 31 further transmits a registration failure notification indicating that the voice analysis server 4 was unable to analyze the voice information to the voice communication management device 5 so that the notification can be received by the input terminal 8. In this embodiment, the transmitting/receiving unit 31 functions as an example of at least one of a transmitting means and a receiving means.

The display control unit 34 is mainly realized by the processing of the CPU 301 on the display 307, and controls the display of various screens and information (data) in the audio recording management device 3. The display control unit 34 may also use a browser, for example, to control the display of a display screen created using HTML or the like on the display 807 of the input terminal 8 via the communication network 100. In this embodiment, the display control unit 34 functions as an example of a display control means.

The judgment unit 35 is mainly realized by the processing of the CPU 301, and makes various judgments in the voice recording management device 3. The judgment unit 35 also determines whether there is a recognition pattern that matches the voice analysis result information sent by the voice analysis server 4. In this embodiment, the judgment unit 35 functions as an example of a judgment means that determines whether given predetermined conditions are met. Note that the judgment made by the judgment unit may be changed to determine whether given predetermined conditions are met, in addition to determining whether given predetermined conditions are met.

The registration unit 36 is mainly realized by processing of the CPU 301, and stores and registers various data (information) such as recognition patterns, synonyms, voice data, analysis results, and voice records transmitted to the voice recording management device 3 in various databases or in a specified area of the memory unit 3000. The registration unit 36 also registers voice recording information corresponding to spoken voice information in response to a voice analysis request transmitted to the voice analysis server 4. Specifically, the registration unit 36 registers voice recording information based on voice analysis result information and specific recognition pattern identification information contained in a voice analysis response analyzed by the voice analysis server 4 using a specific recognition pattern from one or more recognition patterns. The specific recognition pattern identification information is identification information that indicates a specific recognition pattern. The registration unit 36 also registers one or more recognition patterns, including the specific recognition pattern transmitted by the registration management terminal 2, in the recognition pattern item management DB 3001 (see Figure 5). The registration unit 36 also registers each piece of recognition pattern identification information indicating one or more recognition patterns transmitted by the registration management terminal 2 in a recognition pattern identification management DB 3002 (see FIG. 6). The registration unit 36 also registers synonyms for each item included in the spoken voice that constitutes the recognition pattern in a synonym management DB 3003 (see FIG. 7). The registration unit 36 also registers voice recording information including the voice data path, user identification information, and registration date and time in a voice recording management DB 3005 (see FIG. 9). The registration unit 36 also registers each value included in the voice analysis result information in an analysis result management DB 3006 (see FIG. 10). In this embodiment, the registration unit 36 functions as an example of a registration means.

The search unit 37 is mainly realized by the processing of the CPU 301, and searches various data (information) registered and managed by the voice recording management device 3, for example, based on a search request for voice recording information requested by the viewing terminal 9. In this embodiment, the search unit 37 functions as an example of a search means.

The generation unit 38 is mainly realized by the processing of the CPU 301, and generates screen data and voice recording data (voice recording information) to be displayed on the input terminal 8 and the viewing terminal 9 based on the voice analysis result information transmitted by the voice analysis server. In this embodiment, the generation unit 38 functions as an example of a generation means.

The memory/read unit 39 is mainly realized by the processing of the CPU 301 on at least one of the ROM 302, EEPROM 304, and HD 305, and stores various data (or information) in the memory unit 3000 and reads various data (or information) from the memory unit 3000. In this embodiment, the memory/read unit 39 functions as an example of a memory/reading means.

<Functional configuration of the voice analysis server>
As shown in Figure 4C, the voice analysis server 4 has a transmission/reception unit 41, an analysis unit 45, a registration unit 46, and a storage/readout unit 49. Each of these functional units is a function or means realized by any of the hardware resources shown in Figure 2 operating in response to an instruction from the CPU 401 in accordance with a program for the voice analysis server 4 that is loaded from at least one of the ROM 402, EEPROM 404, and HD 405 to the RAM 403. The voice analysis server 4 also has a memory unit 4000 constructed from at least one of the ROM 402, EEPROM 404, and HD 405 shown in Figure 2. Furthermore, the memory unit 4000 stores a communication program (communication application) and the like for communicating with the voice recording management device 3 via the communication network 100.

●Recognition pattern●
FIG. 12 is a conceptual diagram showing an example of a recognition pattern. One or more recognition patterns as shown in FIG. 12 are stored and managed in the storage unit 4000. In this embodiment, the recognition pattern has the following data structure. For example, for each recognition pattern identification information "R0001", "R0002", etc., (1) record type, (2) work target, (3) work item, and (4) work result are associated and managed. Specifically,
・When the recognition pattern identification information is "R0001",
(1) Record type: [Transfer/care record]
(2) Work target: <Name> [san/sama]
(3) Work item... [item name]
(4) Work result... [item value]
・When the recognition pattern identification information is "R0002",
(1) Record type: <Name> [san/sama]
(2) Work target... [item name]
(3) Work item...[Item value]
(4) Work results: [Handover/Care Record]
The data is managed by associating each of these.

Here, an example of a processing image when the analysis server 4 analyzes predetermined voice information using a recognition pattern is shown below. For example, a caregiver (worker) uses a communication device 7 (intercom) to
"Nursing record: Rikiko, blood pressure 114/60"
The process performed by the analysis server 4 when the user utters the following will be described below.
- Detect the keyword "care record" from the spoken audio information.
Next, the analysis server 4 confirms that the keyword "care record" matches the (1) record type of the registered recognition pattern.
・Detects the next keyword, "Rikou-san," and recognizes "Rikou" as (2) the name of the work target.
・Furthermore, the next keyword, "blood pressure," is detected, and "blood pressure" is recognized as the <item name> of the work result (3).
・Furthermore, the next keyword, “60 of 114”, is detected, and “60 of 114” is recognized as the <item value> of the work result (4).

In this way, the analysis server 4 converts the spoken voice information into text, then analyzes each of the converted keywords (components) one by one, evaluates the analysis results, and each item in the registered recognition pattern, to obtain voice analysis result information.

<<Functional configuration of the voice analysis server>>
Next, a detailed description will be given of each functional configuration of the voice analysis server 4. The transmission/reception unit 41 of the voice analysis server 4 shown in Fig. 4C is mainly realized by processing of the CPU 401 on the network I/F 411 and the short-range communication I/F 408, and transmits and receives various data (or information) to and from the voice recording management device 3 via the communication network 100. In this embodiment, the transmission/reception unit 41 functions as an example of at least one of a transmitting means and a receiving means.

The analysis unit 45 is mainly realized by the processing of the CPU 401, and converts a voice analysis request sent by the voice recording management device 3 into text information using recognition patterns registered and managed in a specified area of the storage unit 4000. In this embodiment, the analysis unit 45 functions as an example of analysis means.

The registration unit 46 is realized mainly by processing by the CPU 401, and stores and registers various data (information) such as one or more recognition patterns and voice analysis results transmitted to the voice analysis server 4 in a predetermined area of the storage unit 4000. In this embodiment, the registration unit 46 functions as an example of a registration means.

The memory/read unit 49 is mainly realized by the CPU 401's processing of at least one of the ROM 402, EEPROM 404, and HD 405, and stores various data (or information) in the memory unit 4000 and reads various data (or information) from the memory unit 4000. In this embodiment, the memory/read unit 49 functions as an example of a memory/reading means.

<Functional configuration of the voice communication management device>
As shown in Figure 4C, the voice communication management device 5 has a transceiver unit 51, an acquisition unit 53, an information management unit 56, and a storage/readout unit 59. Each of these functional units is a function or means realized when any of the hardware resources shown in Figure 2 operates in response to commands from the CPU 401 in accordance with a program for the voice communication management device 5 that is loaded from at least one of the ROM 502, EEPROM 504, and HD 505 to the RAM 503. The voice communication management device 5 also has a memory unit 5000 constructed from at least one of the ROM 502, EEPROM 504, and HD 505 shown in Figure 2. Furthermore, the memory unit 5000 stores communication programs (communication applications) and the like for communicating with the voice recording management device 3, the input terminal 8, and the viewing terminal 9 via the communication network 100.

●User information management table●
Fig. 13 is a conceptual diagram showing an example of a user information management table. A user information management DB 5001 configured by the user information management table shown in Fig. 13 is constructed in the storage unit 5000. In the user information management table, each item including a password and an email address is associated with and stored and managed for each user identification information grouped by tabs, each tab consisting of tenant identification information and group identification information.

Of these, the password is a password that can be used by a user who has user identification information, and the email address is the email address information of a user who has user identification information, and is given as, for example, "u01@aaa.com".

●Audio information management table●
Fig. 14 is a conceptual diagram showing an example of a voice information management table. A voice information management DB 5002 configured by the voice information management table shown in Fig. 14 is constructed in the storage unit 5000. In the voice information management table, the path of the voice data and the date and time of the speech are stored and managed in association with each piece of user identification information.

Among these, the voice data path indicates the data (file) path for managing the contents of the user's speech in the voice communication management device 5, and for example, "<filepath>●●●.wav
The utterance date and time is managed as the date and time when the user (worker) made an utterance, and is given as date information.

<<Functional configuration of the voice communication management device>>
Next, a detailed description will be given of each functional configuration of the voice communication management device 5. The transmission/reception unit 51 of the voice communication management device 5 shown in Fig. 4C is mainly realized by the processing of the CPU 501 on the network I/F 511 and the short-range communication I/F 508, and transmits and receives various data (or information) between the voice recording management device 3, the input terminal 8, and the viewing terminal 9 via the communication network 100. In this embodiment, the transmission/reception unit 51 functions as an example of at least one of a transmitting means and a receiving means.

The acquisition unit 53 is mainly realized by the processing of the CPU 501, and acquires audio data transmitted by the input terminal 8 and stored in a specified area of the storage unit 5000 in response to periodic inquiries (acquisition requests) for audio data from the audio recording management device 3. In this embodiment, the acquisition unit 53 functions as an example of an acquisition means.

The information management unit 56 is primarily realized by the processing of the CPU 501, and manages and checks the user information registered and managed in the user information management DB 5001 based on the user identification information transmitted by the input terminal 8. In this embodiment, the information management unit 56 functions as an example of a management means.

The memory/read unit 59 is mainly realized by the CPU 501's processing of at least one of the ROM 502, EEPROM 504, and HD 505, and stores various data (or information) in the memory unit 5000 and reads various data (or information) from the memory unit 5000. In this embodiment, the memory/read unit 59 functions as an example of a memory/reading means.

[Processing or Operation of the Embodiment]
Next, each process or operation in the voice recording management system according to the embodiment will be described using Figures 15 to 25. Note that in each sequence diagram described below, communication between each device is assumed to be in a state where communication is possible with each other after various authentication processes according to predetermined procedures, processes for establishing a session, etc. have been successfully completed. Furthermore, it is assumed that each device has already executed processes such as launching a browser and launching a predetermined application for communication via the communication network 100.

<Recognition pattern registration process>
First, the recognition pattern registration process will be described. FIG. 15 is a sequence diagram showing an example of the recognition pattern registration process. The operation reception unit 22 of the registration management terminal 2 receives a recognition pattern registration instruction, for example, input by an administrator using at least one of the keyboard 212 and the pointing device 213 (step S11). Specifically, the operation reception unit 22 receives an operation to upload a recognition pattern registration file given a file format such as xml or csv by the administrator, and receives an operation such as input of a predetermined URL. The above-mentioned recognition pattern registration file includes the item names listed in the recognition pattern item management table shown in FIG. 5, and the contents of the item names with their registration order changed are managed in association with the respective written pattern identification information. Note that the recognition pattern registration file is not limited to the above-mentioned file format and may be saved and managed in the form of a data table, for example, as shown in FIG. 5.

Next, the transmitter/receiver 21 transmits the recognition pattern received in step S11 to the voice recording management device 3 (step S12). As a result, the transmitter/receiver 31 of the voice recording management device 3 receives the recognition pattern as the contents of the recognition pattern registration file transmitted by the registration management terminal 2. At this time, the recognition pattern includes recognition pattern identification information, as well as the record type, task target, task item, and task result that constitute the recognition pattern. The contents of these recognition patterns include content related to various actions performed in the field of nursing care, medical care, etc., such as care records and handovers.

Next, the transmission/reception unit 31 of the voice recording management device 3 transmits a recognition pattern registration request to the voice analysis server 4 (step S13). As a result, the transmission/reception unit 41 of the voice analysis server 4 receives the recognition pattern registration request transmitted by the voice recording management device 3. At this time, the recognition pattern registration request includes the recording type, task target, task item, and task result that constitute the recognition pattern received in step S12.

Next, the registration unit 46 of the voice analysis server 4 registers the recognition pattern received in step S13 in a predetermined area of the memory unit 4000 (step S14).

Next, the transmitter/receiver 41 transmits a recognition pattern registration response to the voice recording management device 3 in response to the recognition pattern registration request (step S15). As a result, the voice recording management device 3 receives the recognition pattern registration response transmitted by the voice analysis server 4. This recognition pattern registration response includes commonly used response messages, response flags, etc., and there are no particular restrictions on the information as long as it indicates that the recognition pattern registration request has been successfully processed.

Next, the registration unit 36 of the voice recording management device 3 registers recognition pattern items based on the recognition patterns received in step S12 (step S16). Specifically, the registration unit 36 registers the received recognition patterns in the recognition pattern item management DB 3001 (see Figure 5) by separating them into item names in the order of registration, corresponding to the recognition pattern identification information. The recognition pattern items registered in step S16 are synonymous with keyword definitions used when the voice analysis server 4 executes the analysis results.

The registration unit 36 then registers the recognition pattern identification information (step S17). Specifically, the registration unit 36 registers the recognition pattern identification information associated with the registered recognition pattern in the recognition pattern identification management DB 3002 (see FIG. 6) in association with the tenant identification information and group identification information. For example, in the recognition pattern identification management DB 3002, two pieces of recognition pattern identification information, "R0001" and "R0002," are registered in association with tenant identification information "T0001" and group identification information "G0001." This means that users belonging to a tenant with tenant identification information "T0001" and a group with group identification information "G0001," can use either of the recognition patterns with the two recognition pattern identification information "R0001" and "R0002" to analyze speech in caregiving, nursing, and other settings and register audio recording information.

Next, the transmitter/receiver unit 31 sends a completion notification to the registration management terminal 2 as a notification in response to step S12 (step S18). As a result, the transmitter/receiver unit 21 of the registration management terminal 2 receives the completion notification sent by the voice recording management device 3.

In the communication system according to this embodiment, for example, when the processing of steps S12 and S18 described above is performed, other devices may exist between the registration management terminal 2 and the voice recording management device 3. In other words, each piece of information (data) sent and received between the registration management terminal 2 and the voice recording management device 3 may be configured to be sent and received once via another device. The above-described configuration is applicable even if other processing steps exist between the registration management terminal 2 and the voice recording management device 3.

Furthermore, in the communication system according to this embodiment, for example, when the processing of steps S13 and S15 described above is performed, other devices may exist between the voice recording management device 3 and the voice analysis server 4. In other words, each piece of information (data) sent and received between the voice recording management device 3 and the voice analysis server 4 may be configured to be sent and received once via another device. The above-described configuration is applicable even if other processing steps exist between the voice recording management device 3 and the voice analysis server 4.

<Synonym registration process>
Next, the synonym registration process will be described. FIG. 16 is a sequence diagram showing an example of the synonym registration process. Similar to the recognition pattern registration process, the operation reception unit 22 of the registration management terminal 2 receives a synonym registration instruction input by, for example, an administrator using at least one of the keyboard 212 and the pointing device 213 (step S21). Specifically, the operation reception unit 22 receives an operation to upload a synonym registration file given a file format such as xml or csv by the administrator, and an operation such as input of a predetermined URL. The synonym registration file described above includes multiple synonyms similar to the item name keywords associated with each item identification information listed in the synonym item management table shown in FIG. 7. Note that the synonym registration file is not limited to the file format described above and may be stored and managed in the format of a data table, for example, as shown in FIG. 7.

Next, the transmitter/receiver 21 transmits synonym information relating to the synonyms received in step S21 to the voice recording management device 3 (step S22). As a result, the transmitter/receiver 31 of the voice recording management device 3 receives the synonym information transmitted by the registration management terminal 2. At this time, the synonym information includes multiple synonyms similar to each item name keyword. The content of these synonyms relates to various actions performed in the field of care, medical care, etc., such as nursing records and handovers, and includes content similar to the item names that make up the recognition patterns described above.

Next, the transmission/reception unit 31 of the voice recording management device 3 transmits a synonym registration request to the voice analysis server 4 (step S23). As a result, the transmission/reception unit 41 of the voice analysis server 4 receives the synonym registration request transmitted by the voice recording management device 3. At this time, the synonym information registration request includes the synonym information received in step S22.

Next, the registration unit 46 of the voice analysis server 4 registers the synonyms received in step S23 in a specified area of the memory unit 4000 (step S24).

Next, the transmitter/receiver 41 transmits a synonym information registration response to the voice recording management device 3 as a response to the synonym information registration request (step S25). As a result, the voice recording management device 3 receives the synonym information registration response transmitted by the voice analysis server 4. This synonym information registration response includes commonly used response messages, response flags, etc., and there are no particular restrictions on the information as long as it indicates that the recognition pattern registration request has been successfully processed.

Next, the registration unit 36 of the voice recording management device 3 registers synonyms based on the synonyms received in step S22 (step S26). Specifically, the registration unit 36 registers the received multiple synonyms in the synonym management DB 3003 (see Figure 7) in association with the item name keywords assigned to each item identification information. The reason for executing this process in step S26 is that the voice recording management device 3 itself will use the synonyms when searching for the analysis results, which will be described later.

Next, the transmitter/receiver unit 31 sends a completion notification to the registration management terminal 2 as a notification in response to step S22 (step S27). As a result, the transmitter/receiver unit 21 of the registration management terminal 2 receives the completion notification sent by the voice recording management device 3.

<Audio analysis processing>
Next, the voice analysis process will be described. FIG. 17 is a sequence diagram showing an example of the process up to the storage of voice information (data). First, the operation reception unit 82 of the input terminal 8 receives a voice instruction from the user (step S101). Specifically, the operation reception unit 82 receives a voice instruction (command) by speech uttered by the user to the user terminal 6 or the intercom or other communication device 7 constituting the input terminal 8. Note that in this embodiment, the user must speak in a pattern that conforms to the registered recognition pattern. If the user makes an utterance that does not conform to the recognition pattern, an error notification will be sent to the input terminal used by the user in the process that does not match the recognition pattern, as described below. However, in this embodiment, to resolve such inconvenience, a system is constructed that allows various recognition patterns corresponding to tenants, groups, etc. to be registered in advance.

Next, the transmitter/receiver 81 transmits voice data (also referred to as voice information) representing the received voice instruction to the voice communication management device 5 (step S102). As a result, the transmitter/receiver 51 of the voice communication management device 5 receives the voice data (voice information) transmitted by the input terminal 8. At this time, the voice data (voice information) includes tenant identification information of the tenant to which the user belongs, group identification information of the group to which the user belongs, user identification information identifying the user, and voice data (voice information) related to the voice spoken by the user. Here, it is assumed that the tenant identification information, group identification information, and user identification information have been registered in advance in the voice communication app installed on the input terminal 8 (entered during login authentication). Note that the input terminal 8 may transmit all user identification information of the group (room) including the user identification information logged in to the voice communication app to the voice recording management device 3, or may transmit group identification information.

Next, the information management unit 56 of the voice communication management device 5 confirms the user information (step S103). Specifically, the information management unit 56 searches the user information management DB 5001 (see FIG. 13) using the tenant identification information and group identification information received in step S102 as search keys, and reads information such as the password and email address for each corresponding user identification information.

Next, the storage/reading unit 59 associates the voice data received in step S102 with the user identification information and stores it in the voice information management DB 5002 (see Figure 14) (step S104). At this time, the transmission/reception unit 51 of the voice communication management device 5 may transmit the user identification information received in step S102 to the voice recording management device 3 with which a session has been established.

Here, the storage/reading unit 39 of the voice recording management device 3 reads the tenant identification information and group identification information from the tenant group management DB 3004 (see Figure 8) to obtain the voice data stored in the voice communication management device 5 (step S105).

Next, we will explain the process of acquiring voice data by the voice recording management device 3. The process from step S106 to S108, which will be described below, involves loop processing between the voice recording management device 3 and the voice communication management device 5, and polling of the voice communication management device 5 by the voice recording management device 3. In other words, the voice recording management device 3 periodically requests voice data from the voice communication management device 5.

First, the transmitter/receiver unit 31 of the voice recording management device 3 transmits inquiry information related to the inquiry about the voice data to the voice communication management device 5 (step S106). As a result, the transmitter/receiver unit 51 of the voice communication management device 5 receives the inquiry information related to the inquiry about the voice data transmitted by the voice recording management device 3. At this time, the inquiry information related to the inquiry about the voice data includes the tenant identification information, group identification information, and user identification information read in step S105.

Next, the acquisition unit 53 of the voice communication management device 5 acquires the voice data stored in the voice information management DB 5002 (see FIG. 14) (step S107). Specifically, the acquisition unit 53, in cooperation with the storage and reading unit 59, searches the voice information management DB 5002 (see FIG. 14) using the user identification information as a search key, thereby reading the path and speech date and time of the corresponding voice data.

Next, the transmitter/receiver unit 51 transmits the voice data to the voice recording management device 3 as a response to the voice data inquiry (step S108). As a result, the transmitter/receiver unit 31 of the voice recording management device 3 receives the voice data transmitted by the voice communication management device 5. At this time, the inquiry response information relating to the voice data inquiry response includes user record identification information, the date and time of the speech, and the voice data or path information for the voice data.

Furthermore, in the processing of steps S106-S108 described above, the voice recording management device 3 may be configured to send a query for the next voice data to the voice communication management device 5 immediately upon receiving the voice data. At this time, a processing method may be used in which a search is performed using either tenant identification information or group identification information included in the query information related to the voice data query described in step S106. Furthermore, rather than the voice recording management device 3 querying for voice data as in step S106, upon receiving voice data, the voice communication management device 5 may be configured to send the received voice data to the voice recording management device 3 before receiving the query for voice data.

Next, the storage/readout unit 39 of the voice recording management device 3 stores (preserves) the voice data received in step S108 in a specified area of the memory unit 3000 (step S109).

In the communication system according to this embodiment, for example, when the processing of steps S106 and S108 described above is performed, other devices may exist between the voice communication management device 5 and the voice recording management device 3. In other words, each piece of information (data) sent and received between the voice communication management device 5 and the voice recording management device 3 may be configured to be sent and received once via another device. The above-described configuration is applicable even if other processing steps exist between the voice communication management device 5 and the voice recording management device 3.

<Speech analysis process when there is no matching recognition pattern>
Next, we will explain what happens when there is no recognition pattern that matches the analysis results in the analysis of voice data by the voice analysis server 4. Figure 18 is a sequence diagram showing an example of voice analysis processing when there is no matching recognition pattern. First, the registration unit 36 of the voice recording management device 3 registers the voice data or the path of the voice data received in step S108 in association with the user identification information managed in the voice recording management DB 3005 (see Figure 9) (step S111).

Next, the storage and reading unit 39 searches the recognition pattern identification management DB 3002 (see FIG. 6) using the tenant identification information or group identification information as a search key to read out one or more corresponding recognition pattern identification information (step S112). This process is performed because the voice recording management device 3 needs to read out the recognition pattern identification information that corresponds to the tenant identification information.

Next, the transmitting/receiving unit 31 transmits a voice analysis request to the voice analysis server 4 (step S113). As a result, the transmitting/receiving unit 41 of the voice analysis server 4 receives the voice analysis request transmitted by the voice recording management device 3. At this time, the voice analysis request includes recognition pattern identification information associated with at least one of the tenant identification information of the tenant to which the user who uttered the uttered voice belongs and the group identification information of the group to which the user belongs, and the voice data (voice information based on the uttered voice) received in step S108 and stored in step S109. At this time, the voice data (voice information based on the uttered voice) transmitted by the voice recording management device 3 to the voice analysis server 4 may be, for example,
"Nursing record: Rikiko's blood pressure 114/60"
is.

Next, the analysis unit 45 of the voice analysis server 4 performs voice analysis of the received voice data by referencing the recognition pattern corresponding to the recognition pattern identification information stored in the processing of step S14 for the recognition pattern identification information and voice data received in step S113 (step S114). Specifically, for example, the analysis unit 45 converts each piece of voice information constituting the input speech voice into text information, and analyzes each piece of voice information to determine which of the registered recognition patterns it matches.

Next, the transmitting/receiving unit 41 transmits the voice analysis response to the voice recording management device 3 (step S115). As a result, the transmitting/receiving unit 31 of the voice recording management device 3 receives the voice analysis response transmitted by the voice analysis server 4. At this time, the voice analysis response includes voice analysis result information indicating the voice analysis result, and recognition pattern identification information. Furthermore, the voice analysis response includes text data and a set of keywords extracted from pre-registered recognition patterns and assigned with order information. However, the voice analysis result information does not include the "item name" managed in the recognition pattern item management DB 3001 (see FIG. 5), but includes words or simple character strings. Here, the voice analysis result information transmitted by the voice analysis server 4 to the voice recording management device 3 may be, for example,
{Nursing record, Riko, Blood pressure, 114 of 60}
is.

The voice recording management device 3 may store the recognition pattern identification information when sending a voice analysis request, and perform the association based on the recognition pattern (recognition pattern item management DB 3001 (see Figure 5)) associated with the stored recognition pattern identification information when receiving a voice analysis response to the voice analysis request. In this case, the recognition pattern identification information used by the voice analysis server 4 for analysis does not need to be included in the voice analysis response.

Next, the judgment unit 35 of the voice recording management device 3 determines whether there is a matching recognition pattern for the voice analysis result information received in step S115 (step S116). If there is no matching recognition pattern (step S116: NO), the transmission/reception unit 31 sends a registration failure notification to the voice communication management device 5 (step S117). As a result, the voice communication management device 5 receives the registration failure notification sent by the voice recording management device 3. At this time, the registration failure notification includes tenant identification information, group identification information, user identification information, and registration failure notification information indicating that registration has failed. The content of the registration failure notification may be a pre-prepared message, etc.

Next, the transmitter/receiver 51 of the voice communication management device 5 transmits (transfers) the voice data (voice information) included in the registration failure notification received in step S117 to the input terminal 8 (step S118). As a result, the transmitter/receiver 81 of the input terminal 8 receives the voice data transmitted by the voice communication management device 5. At this time, the voice communication management device 5 may notify (transmit) the data (information) to the input terminal 8 by push notification. In this case, the voice communication management device 5 can achieve this by using, for example, FCM (Firebase Cloud Messaging), which is an example of a push notification server, to transmit the push notification.

Next, the display control unit 84 of the input terminal 8 displays registration failure notification information on the display 807. Furthermore, the audio playback unit 86 of the input terminal 8 may play the registration failure notification aloud via the speaker 819 (step S119). Note that if an error notification is displayed on the input terminal 8, the user of the input terminal 8 may re-input speech into the input terminal 8 that conforms to a different recognition pattern.

In the communication system according to this embodiment, for example, when the processing of steps S102 and S119 described above is executed, other devices may exist between the input terminal 8 and the voice communication management device 5. In other words, each piece of information (data) sent and received between the input terminal 8 and the voice communication management device 5 may be configured to be sent and received once via another device. The above-described configuration is applicable even if other processing steps exist between the input terminal 8 and the voice communication management device 5.

Furthermore, in the communication system according to this embodiment, for example, when the processing of steps S113 and S115 described above is executed, other devices may be present between the voice recording management device 3 and the voice analysis server 4. In other words, each piece of information (data) sent and received between the voice recording management device 3 and the voice analysis server 4 may be configured to be sent and received once via another device. The above-described configuration is applicable even if other processing steps exist between the voice recording management device 3 and the voice analysis server 4.

●Screen display example●
Next, an example of a screen display displayed on the input terminal 8 will be described. Fig. 20(a) is an example of a screen display for notifying the user that an instruction has been successfully input on the input terminal, and Fig. 20(b) is an example of a screen display for notifying the user that an instruction has been successfully input on the input terminal. As shown in Fig. 20(a), a registration failure notification screen 8101 is displayed on the display 807 of the input terminal 8 by the display control unit 84. The registration failure notification screen 8101 displays, for example, the recording type of the voice recording, "care record," and text information of "input error notification" indicating that analysis of the input voice information failed. Furthermore, a message indicating that no matching recognition pattern was found and a message prompting the user to give instructions using a different recognition pattern or to re-register a new recognition pattern are displayed.

<Speech analysis process when a matching recognition pattern exists>
Next, a case will be described in which, in the analysis of voice data by the voice analysis server 4, there is a recognition pattern that matches the analysis result. FIG. 19 is a sequence diagram showing an example of voice analysis processing when there is a matching recognition pattern. In the determination processing of step S116 described above, if the determination unit 35 determines that there is a matching recognition pattern (step S116: YES), the search unit 37 executes the following processing. Specifically, the search unit 37 searches the recognition pattern item management DB 3001 (see FIG. 5 ) for the voice analysis result information included in the voice analysis response received in step S115 using the received recognition pattern identification information as a search key. Thereafter, the search unit 37 associates each item name and item value of the received voice analysis result information with each other by referring to the item name and registration order corresponding to the recognition pattern identification information (step S121). Specifically, the voice recording management device 3 associates the results managed in the analysis result management DB 3006 (see FIG. 10) with the recognition pattern item management DB 3001 (see FIG. 5) and the speech data (speech information) corresponding to the user's speech. Specifically, the search unit 37 performs the following process. That is, the search unit 37 performs the following process on the basis of the recognition pattern item management DB 3001 (see FIG. 5) and the speech data (speech information) corresponding to the user's speech.
{Nursing record, Riko, Blood pressure, 114 of 60}
For the voice analysis result information,
First, the first item "care record" is associated with the first item name "record type" associated with the recognition pattern identification information: "R0001." In other words, the association is made as "record type" → "care record."
Next, the second item "Riko" is associated with the second item name "Work object" associated with the recognition pattern identification information: "R0001." In other words, the association is made between "Work object" and "Riko."
Next, the third item, "blood pressure," is associated with the third item name, "work item," associated with the recognition pattern identification information: "R0001." In other words, the association is made between "work item" and "blood pressure."
Finally, the fourth item, "60 of 114," is associated with the fourth item, "Work result," associated with the recognition pattern identification information: "R0001." In other words, the association is made between "Work result" and "60 of 114."

In this way, the search unit 37 can match the voice analysis result information sent by the voice analysis server 4 with the recognition patterns registered and managed by the voice recording management device 3. However, the above-mentioned matching process is just one example, and the order of matching may be changed depending on the system specifications, program configuration, etc.

The registration unit 36 then associates the analysis results associated in step S121 with the "recording type," "task target," "task item," and "task result" managed in the analysis result management DB 3006 (see FIG. 10), and finally assigns and registers the voice recording identification information (step S122). The registration unit 36 also registers the user identification information, which indicates the date and time of the work and the worker, and which is managed in association with the voice recording identification information. Note that the voice recording identification information may be assigned after the date and time of the work and the user identification information have been associated.

Next, the storage and reading unit 39 reads the notification information (step S123). Specifically, the storage and reading unit 39 searches the voice recording management DB 3005 (see FIG. 9) using the voice recording identification information as a search key, and reads the notification information including the voice data path, user identification information, and registration date and time, which is managed under the tabs for the tenant identification information and group identification information in which the voice recording identification information is registered. Next, the storage and reading unit 39 searches the notification information management DB 3007 (see FIG. 11) using the recording type as a search key, and reads the voice data of the corresponding notification information.

Next, the generation unit 38 generates a display screen to be displayed on the input terminal 8 (step S124). Specifically, the generation unit 38 works in cooperation with the storage and reading unit 39 to search the analysis result management DB 3006 (see FIG. 10) using the voice recording identification information as a search key, and reads out the corresponding content indicated by "record type," "task target," "task item," "task result," "task date and time," and "user identification information." The generation unit 38 then generates a display screen by associating each of the read-out items with each content. At this time, a display screen template prepared in advance in a specified area of the storage unit 3000 may be used.

Next, the transmitter/receiver 31 transmits a registration completion notification to the voice communication management device 5 (step S125). As a result, the transmitter/receiver 51 of the voice communication management device 5 receives the registration completion notification transmitted by the voice recording management device 3. At this time, the registration completion notification includes registration completion notification information indicating that the tenant identification information, group identification information, user identification information, and voice recording information have been registered, as well as screen data for the screen to be displayed on the input terminal 8 generated in step S124. Furthermore, the registration completion notification may include the voice data of the notification information read in step S123.

Next, the transmitter/receiver unit 51 of the voice communication management device 5 transmits the voice data and screen data to the input terminal 8 (step S126).

Next, the audio playback unit 86 of the input terminal 8 outputs (plays) the audio data received in step S126 via the speaker 819. The display control unit 84 also displays the screen data received in step S126 on the display 807 (step S127). Note that the input terminal 8 may either play the audio data or display the screen data. Furthermore, when playing back the audio data, an answerback function may be used, such as sounding the same number of sounds as the number of keywords spoken by the user (worker).

●Screen display example●
Next, an example of a screen display displayed on the input terminal 8 will be described. Fig. 20(b) is an example of a screen display for notifying the success of instruction input on the input terminal. As shown in Fig. 20(b), a registration completion notification screen 8102 is displayed on the display 807 of the input terminal 8 by the display control unit 84. The registration completion notification screen 8102 displays, for example, the recording type of the voice recording, "care record," and text information of "input completion notification" indicating that analysis of the input voice information has been completed. Furthermore, a message indicating that registration of the care record has been completed using the specified recognition pattern is displayed.

●Screen display example●
Next, an example of a screen display displayed on the viewing terminal 9 will be described. FIG. 21 illustrates an example of a screen display of a care record confirmation notification on the viewing terminal. As shown in FIG. 21 , a care record confirmation notification screen 9101 is displayed by the display control unit 94 on the display 907 of the viewing terminal 9. The care record confirmation notification screen 9101 displays, for example, the name of "Rikou" indicating the "work target" of the care, the date indicating the "work date and time,""bloodpressure" indicating the "work item," and blood pressure values indicating the "work result." In this case, two sets of data, 7:00 a.m. and 6:00 p.m., are displayed. A copy button 9151 is displayed in the display field for the morning data, and a copy button 9152 is displayed in the display field for the evening data. A viewer viewing the viewing terminal 9 can operate each of these copy buttons to execute a process indicated as "transcribe to care record software," thereby saving the spoken voice of the worker (user) regarding the care record as voice recording information in the care record software.

●Screen display example●
Next, an example of a screen display displayed on the viewing terminal 9 will be described. FIG. 22 is an example of a screen display of a handover confirmation notice on the viewing terminal. As shown in FIG. 22 , a handover confirmation notice screen 9111 is displayed by the display control unit 94 on the display 907 of the viewing terminal 9. The handover confirmation notice screen 9111 displays, for example, the name of "Rikou" indicating the "work target" and the handover content as the handover content. In this case, the content that a shower will be performed after an IV drip is displayed, along with a copy button 9161. A viewer viewing the viewing terminal 9 can operate this copy button 9161 to execute a process displayed as "transcribe to nursing care record software," and the spoken voice of the worker (user) regarding the handover can be saved in the nursing care record software as audio recording information.

<Search processing>
Next, a search process for searching the voice analysis results will be described. Fig. 23 is a sequence diagram showing an example of the search process and the voice recording process. First, the operation accepting unit 92 of the browsing terminal 9 accepts search condition input by operation of the user (browser) (step S131).

Next, the transmitter/receiver 91 transmits a search request to the audio recording management device 3 (step S132). As a result, the transmitter/receiver 31 of the audio recording management device 3 receives the search request. At this time, the search request includes the search conditions "recording type," "task target," "task item," and "task date and time."

Next, the search unit 37 of the audio recording management device 3 performs a search (step S133). Specifically, the search unit 37 searches the analysis result management DB 3006 (see FIG. 10) using the search conditions received in step S132 as a search key, thereby searching for and reading out the corresponding analysis results. At this time, the search unit 37 may also use the synonym management DB 3003 (see FIG. 7) to broaden the range of search conditions.

Next, the transmission/reception unit 31 transmits the search response to the viewing terminal 9 (step S134). As a result, the viewing terminal 9 receives the search response transmitted by the audio recording management device 3. At this time, the search response includes search result screen data as the search results related to the search performed in step S133. In other words, the search unit 37 cooperates with the generation unit 38 to generate search result screen data including the search results.

Next, the display control unit 94 of the viewing terminal 9 displays the search result screen on the display 907 based on the search result screen data received in step S134 (step S135).

Next, the operation acceptance unit 92 accepts an audio recording selection (step S141). For example, this process may be performed by the operation acceptance unit 22 accepting the selection of a specific audio recording selected by the viewer from among the audio recordings displayed on the display 907.

Next, the transmitter/receiver 91 transmits a voice data acquisition request to the voice recording management device 3 (step S142). As a result, the transmitter/receiver 31 of the voice recording management device 3 receives the voice data acquisition request transmitted by the viewing terminal 9. At this time, the voice data acquisition request includes voice recording identification information corresponding to the recorded voice data.

Next, the storage and reading unit 39 of the voice recording management device 3 reads the voice data (step S143). Specifically, the storage and reading unit 39 searches the analysis result management DB 3006 (see FIG. 10) using the voice recording identification information received in step S142 as a search key to read the corresponding user identification information. Next, the storage and reading unit 39 searches the voice recording management DB 3005 (see FIG. 9) using the user identification information as a search key to read the path of the corresponding voice data. This allows the storage and reading unit 39 to search for desired voice data based on the path of the voice data. Note that the storage and reading unit 39 may also directly read the path of the corresponding voice data by searching the voice recording management DB 3005 (see FIG. 9) using the voice recording identification information as a search key.

Next, the transmitter/receiver 31 transmits a voice data acquisition response to the viewing terminal 9 (step S144). As a result, the transmitter/receiver 91 of the viewing terminal 9 receives the voice data acquisition response transmitted by the voice recording management device 3.

Next, the display control unit 94 of the viewing terminal 9 outputs (plays) the audio data received in step S144 via the speaker 919 (step S145). At this time, the display control unit 94 may display text information corresponding to the audio output (played) via the speaker 919 on the display 907. By performing the processing of steps S131-S145 described above, the viewer can check, on the viewing terminal 9, the audio and corresponding text information indicating the audio recording searched based on the search criteria entered into the viewing terminal 9. As a result, if the viewer is the user who made the spoken audio, they can check the work content they spoke using the audio and text information.

Furthermore, in the communication system according to this embodiment, for example, when the processes of steps S132 and S134, and steps S142 and S144 described above are executed, other devices may be present between the voice recording management device 3 and the viewing terminal 9. In other words, each piece of information (data) transmitted and received between the voice recording management device 3 and the viewing terminal 9 may be transmitted and received once via another device. The above-described configuration is applicable even if other processing steps exist between the voice recording management device 3 and the viewing terminal 9.

●Screen display example●
Next, an example of a search screen display displayed on the viewing terminal 9 will be described. FIG. 24(a) is an example of a screen display during a handover search on the viewing terminal. As shown in FIG. 24(a), a search key input screen 9121 is displayed on the display 907 of the viewing terminal 9 by the display control unit 94. The search key input screen 9121 has multiple input fields. The viewer can input period information for searching for "work date and time,""worktarget,""recordingtype," and "work item" into these input fields. The information input into these input fields is sent to the voice recording management device 3, and search results are returned by referring to various data tables managed by the voice recording management device 3.

24(b) is another example of a screen display of a handover confirmation notice on a viewing terminal. As shown in FIG. 24(b), a search result display screen 9122 is displayed on the display 907 of the viewing terminal 9 by the display control unit 94. The search result display screen 9122 displays the name "Rikou" indicating the "work object" as a search result, and two handover contents for May 22nd at 7:00 and 18:00 as handover contents for the "work object" in the searched period information.
●Screen display example●
Next, an example of a screen display displayed on another viewing terminal 9 will be described. FIG. 25(a) is an example of a screen display during a handover search on another viewing terminal. As shown in FIG. 25(a), a search key input screen 9131 is displayed on the display 907 of the viewing terminal 9 by the display control unit 94. While the viewing terminal 9 shown in the search key input screen 9121 of FIG. 24 is an example of a tablet terminal, the search key input screen 9131 shows an example of a screen displayed on a communication terminal, an example of which is a smartphone. Therefore, the content of FIG. 25(a) is the same as the content shown in FIG. 24(a), and therefore detailed description will be omitted.

Figure 25(b) is another example of the screen display of the handover confirmation notification on another viewing terminal. As shown in Figure 25(b), the display control unit 94 displays a search result display screen 9132 on the display 907 of the viewing terminal 9. In addition to the handover content shown in Figure 24(b), the search result display screen 9132 also displays information on the procedure performed by the user (worker) on the "work target," Mr. Riko, on the display 907. Furthermore, the audio playback unit 96 plays the text information displayed on the search result display screen 9132 as audio information via the speaker 919.

[Major Effects of the Embodiments]
As described above, according to this embodiment, the voice recording management device 3 transmits to the voice analysis server 4 voice information based on the user's voice utterance and recognition pattern identification information that identifies a recognition pattern for analyzing the voice information associated with at least one of the tenant identification information of the tenant to which the user who uttered the voice belongs and the group identification information of the group to which the user belongs (S113), and the analysis server 4 analyzes the voice information and the recognition pattern identification information, and registers the analysis results in association with the "recording type,""tasktarget,""taskitem," and "task result" managed in the analysis result management DB 3006 (S122). As a result, when registering voice recording information from voice information based on the voice utterance, the voice can be given using a recognition pattern that corresponds to the tenant, group, etc. to which the user belongs, thereby achieving the effect of improving flexibility for users.

Furthermore, according to this embodiment, synonym information is pre-registered in addition to multiple recognition patterns corresponding to the tenant, group, etc. to which the user belongs, and the synonym information is also sent to the analysis server 4 for analysis. This means that users (workers) in caregiving, nursing, and other settings can speak the words they normally use without worrying about their place of origin, accent, etc., and can report on tasks (jobs) such as care records and handovers. This has the effect of further improving the work efficiency of users (workers).

[Supplementary explanation of the embodiment]
In this embodiment, work performed by a caregiver (worker) on a care recipient (work target) in a nursing facility and work performed by a nurse (worker) on a patient (work target) in a hospital have been described as examples, but the above-mentioned embodiment may also be applied to other work performed by one or more workers on one or more work targets, such as work performed by a worker (worker) on a construction project (work target) at a construction site, work performed by a mechanic (worker) on an automobile (work target) at an automobile repair shop, or work performed by staff (worker) on documents (work target) in an office.

Furthermore, while this embodiment has been described using recognition patterns using Japanese as an example, it is also possible to apply the recognition patterns to foreign languages and build a system using an external server that can analyze speech information in foreign languages.

Furthermore, each function of the above-described embodiments can be realized by one or more processing circuits. Here, the term "processing circuit" as used herein includes devices programmed to perform each function by software, such as a processor implemented as an electronic circuit. Examples of such devices include processors, ASICs (Application Specific Integrated Circuits) designed to perform the functions described above, DSPs (Digital Signal Processors), FPGAs (Field Programmable Gate Arrays), SOCs (Systems on a Chip), GPUs (Graphics Processing Units), and conventional circuit modules.

Furthermore, the various texts and text information obtained by the above-described embodiments may be obtained through the learning effects of machine learning using artificial intelligence (AI). In this case, the voice analysis server may use machine learning to obtain the various texts and text information from the voice information, or a database or the like different from the voice analysis server may use machine learning to obtain the various texts and text information from the voice information. Here, machine learning is a technology that enables a computer to acquire human-like learning capabilities, and refers to a technology in which a computer autonomously creates algorithms necessary for judgments such as data identification from previously acquired learning data, and applies these to new data to make predictions. The learning method for machine learning may be any of supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, and deep learning. Furthermore, the learning method for machine learning may be a combination of these learning methods, and any learning method for machine learning is acceptable.

So far, we have described an audio recording management system, audio recording management device, audio recording management method, and program according to one embodiment of the present invention. However, the present invention is not limited to the above-described embodiment, and other modifications, such as additions, changes, or deletions, can be made within the scope of what one skilled in the art can conceive. Any modification that achieves the functions and effects of the present invention is within the scope of the present invention.

1 Communication system 2 Registration management terminal 3 Voice recording management device 4 Voice analysis server (cloud service)
5. Voice communication management device (cloud service)
6. User terminal (an example of a user terminal)
7. Talking device 8. Input terminal 9. Viewing terminal 10. Voice recording management system 21. Transmitting/receiving unit (an example of a transmitting means, an example of a receiving means)
31 Transmitting/receiving unit (an example of a receiving means, an example of a transmitting means)
3001 Recognition pattern item management DB (an example of a recognition pattern item management means)
3002 Recognition pattern identification management DB (an example of recognition pattern identification management means)
3003 Synonym management DB (an example of a synonym management means)
3006 Analysis result management DB (an example of an analysis result management means)
35 Determination unit (an example of a determination means)
36 Registration unit (an example of a registration means)

JP 2015-049254 A

Claims (12)

A voice recording management system including a registration management terminal that registers one or more recognition patterns for recognizing spoken voices, and a voice recording management device that manages voice recording information obtained based on the one or more recognition patterns input to the registration management terminal,
The registration management terminal
a transmitting means for transmitting the one or more recognition patterns so that a voice analysis server that analyzes voice information based on the uttered voice and converts the voice information into text information can analyze the voice information;
and
The voice recording management device
a transmitting means for transmitting, as a voice analysis request for requesting analysis of the voice information, to the voice analysis server, one or more recognition pattern identification information for identifying the one or more recognition patterns associated with at least one of tenant identification information of a tenant to which the user who uttered the uttered voice belongs and group identification information of a group to which the user belongs; and the voice information;
a receiving means for receiving a voice analysis response in response to the voice analysis request, the voice analysis response including voice analysis result information indicating a voice analysis result obtained by the voice analysis server using a specific recognition pattern among the one or more recognition patterns , and specific recognition pattern identification information indicating the specific recognition pattern;
a registration means for registering voice recording information corresponding to the voice information based on the voice analysis result information and specific recognition pattern identification information indicating the specific recognition pattern included in the received voice analysis response ;
having
1. A voice recording management system comprising: The transmitting means of the voice recording management device
and transmitting at least one of registration completion notification information indicating that the voice recording information has been registered and registration completion voice information obtained by vocalizing the registration completion notification information to the voice communication management device so that the input terminal to which the uttered voice is input can receive the information.
2. The voice recording management system according to claim 1. The registration means
registering the one or more recognition patterns including the specific recognition pattern transmitted by the registration management terminal in a recognition pattern item management means that manages the recognition patterns in association with recognition pattern identification information that identifies the recognition patterns;
having
3. The voice recording management system according to claim 1 or 2. The registration means
registering each of the recognition pattern identification information indicating the one or more recognition patterns in a recognition pattern identification management means that manages the recognition pattern identification information in association with tenant identification information that identifies a predetermined tenant to which the user who uttered the speech voice belongs and group identification information that identifies a predetermined group to which the user belongs;
4. The voice recording management system according to claim 1, wherein the voice recording management system is a voice recording management system. The registration means
registering synonyms of each item included in the speech and constituting the recognition pattern in a synonym management means that manages the synonyms in association with keywords representing the items;
5. The voice recording management system according to claim 1, wherein the voice recording management system is a voice recording management system. The registration means
each value included in the voice analysis result information is associated with each item managed by the recognition pattern item management means, and then the associated value is registered in an analysis result management means that manages the voice recording information in association with voice recording identification information that identifies the voice recording information;
4. The voice recording management system according to claim 3 . 7. The voice recording management system according to claim 1,
The voice recording management device further comprises:
a determination means for determining whether there is a recognition pattern that matches the voice analysis result information transmitted by the voice analysis server;
1. A voice recording management system. When the determination means determines that there is no recognition pattern that matches the voice analysis result information, the transmission means of the voice recording management device:
a registration failure notification indicating that the voice analysis server was unable to analyze the voice information is transmitted to the voice recording management device so that the notification can be received by the input terminal to which the uttered voice is input ;
8. The voice recording management system according to claim 7. The voice information includes a care record or handover information related to handover in care and nursing, and the one or more recognition pattern information includes recognition pattern identification information for identifying the one or more recognition patterns and one or more items included in the recognition pattern.
9. The voice recording management system according to claim 1, wherein the voice recording management system is a voice recording management system. A voice recording management device connectable to a voice analysis server that manages voice recording information obtained based on one or more recognition patterns input to a registration management terminal that registers one or more recognition patterns for recognizing uttered voices, and analyzes the voice information based on the uttered voices and converts it into text information ,
a receiving means for receiving a voice analysis response including voice analysis result information indicating a voice analysis result obtained by analyzing using a specific recognition pattern among the one or more recognition patterns transmitted by the registration management terminal, and specific recognition pattern identification information indicating the specific recognition pattern;
a transmitting means for transmitting, as a voice analysis request for requesting analysis of the voice information, to the voice analysis server, one or more recognition pattern identification information for identifying the one or more recognition patterns associated with at least one of tenant identification information of a tenant to which the user who uttered the uttered voice belongs and group identification information of a group to which the user belongs; and the voice information;
a registration means for registering voice recording information corresponding to the voice information based on voice analysis result information included in a voice analysis response obtained by the voice analysis server analyzing the voice analysis request using a specific recognition pattern among the one or more recognition patterns and specific recognition pattern identification information indicating the specific recognition pattern;
having
1. A voice recording management device comprising: A voice recording management method executed by a voice recording management device connectable to a voice analysis server that manages voice recording information obtained based on one or more recognition patterns input to a registration management terminal that registers one or more recognition patterns for recognizing uttered voices, and analyzes the voice information based on the uttered voices and converts it into text information , comprising:
a receiving step of receiving a voice analysis response including voice analysis result information indicating a voice analysis result analyzed using a specific recognition pattern among the one or more recognition patterns transmitted by the registration management terminal, and specific recognition pattern identification information indicating the specific recognition pattern ;
a transmission step of transmitting, to the voice analysis server, one or more recognition pattern identification information identifying the one or more recognition patterns associated with at least one of tenant identification information of a tenant to which the user who uttered the uttered voice belongs and group identification information of a group to which the user belongs, as a voice analysis request for requesting analysis of the voice information;
a registration step of registering voice recording information corresponding to the voice information based on voice analysis result information included in a voice analysis response analyzed by the voice analysis server using a specific recognition pattern among the one or more recognition patterns in response to the voice analysis request and specific recognition pattern identification information indicating the specific recognition pattern;
A voice recording management method comprising the steps of: A voice recording management device connectable to a voice analysis server that manages voice recording information obtained based on voice information, analyzes the voice information based on uttered voices, and converts it into text information,
a voice recording management device that manages voice recording information obtained based on one or more recognition patterns input to a registration management terminal that registers one or more recognition patterns for recognizing the spoken voice,
a receiving step of receiving the one or more recognition patterns transmitted by the registration management terminal;
a transmission step of transmitting, to the voice analysis server, one or more recognition pattern identification information identifying the one or more recognition patterns associated with at least one of tenant identification information of a tenant to which the user who uttered the uttered voice belongs and group identification information of a group to which the user belongs, as a voice analysis request for requesting analysis of the voice information;
a receiving step of receiving a voice analysis response in response to the voice analysis request, the voice analysis response including voice analysis result information indicating a voice analysis result analyzed by the voice analysis server using a specific recognition pattern among the one or more recognition patterns , and specific recognition pattern identification information indicating the specific recognition pattern;
a registration step of registering voice recording information corresponding to the voice information based on the voice analysis result information and specific recognition pattern identification information indicating the specific recognition pattern included in the received voice analysis response ;
A program that executes processing including