JP7291440B1 - Program, information processing device, method and system - Google Patents

Abstract

[PROBLEMS] To add/modify recorded contents of medical practices such as input electronic medical questionnaires and electronic medical charts by a simple procedure. A program for operating a server (30) having a processor (29) and a memory (25), wherein structured data of an electronic medical chart template are stored in the memory (25), and the structured data are input items of the electronic medical chart. Input content is data associated with the input content, and the program instructs the processor 29 to perform a first step of accepting an input of the input content for the input item from the first user, a first user or a different data from the first user. A second step of receiving input of speech data for correcting the electronic medical chart template from the user 2, and inputting the content of the electronic medical chart template desired to be corrected based on the input items of the electronic medical chart template included in the speech data. and a third step of specifying. [Selection diagram] Fig. 1

Description

The present disclosure relates to programs, information processing apparatuses, methods, and systems.

When visiting a medical facility, the patient fills in a questionnaire in advance about the patient's medical history and the reason for the consultation, and medical professionals such as nurses and doctors provide medical care based on the contents of the questionnaire. It is known to perform deeds. In recent years, a technology called an electronic medical questionnaire has been proposed, in which the content of a patient's interview, which is the patient's answer, can be input via an information processing device such as a tablet, and the input content of the interview can be captured as the input content of an electronic medical record. there is

As a technique related to the technique described above, there is a technique disclosed in Patent Document 1.

Patent Literature 1 discloses a technology related to a medical support device. In the medical support apparatus, the inquiry item display means displays the inquiry items on the display. The inquiry item selection means selects one inquiry item from the plurality of inquiry items. The speech recognition means performs speech recognition of the input speech using the selected dictionary, and extracts word candidates for the speech. The word/phrase candidate display means displays the extracted word/phrase candidates on the display. The selection operation receiving means receives an operation for selecting one word/phrase candidate from the word/phrase candidates. The storage control means causes the storage means to store the selected word/phrase candidate as an answer to the selected medical question item.

JP 2013-156844 A

In the technology described in Patent Literature 1, the user must first select an inquiry item when voice recognition is performed. For this reason, in order to correct the content of the electronic medical questionnaire that has already been input by the patient or the like, it takes time for the medical staff or the like who makes the correction to individually select the medical questionnaire items by manual input or the like.

Such a problem can also arise when correcting the input contents corresponding to the input items defined in the template of the electronic medical record.

Therefore, the present disclosure has been made to solve the above problems, and the purpose thereof is to provide a technique for adding/correcting the recorded contents of medical practices such as input electronic medical questionnaires and electronic medical charts by a simple procedure. It is to be.

A program for operating a computer having a processor and a memory. Structured data of an electronic medical chart template is stored in the memory, and the structured data is data in which input items and input contents of the electronic medical chart are associated with each other. The program instructs the processor to perform a first step of accepting an input of input contents for input items from a first user, and to modify an electronic medical record template from the first user or a second user different from the first user. and a third step of specifying the contents of the electronic medical chart template to be modified based on the input items of the electronic medical chart template included in the utterance data.

According to the present disclosure, it is possible to add/modify recorded contents of medical practices such as input electronic medical questionnaires and electronic medical charts by a simple procedure.

It is a figure showing composition of the whole system concerning one embodiment. It is a figure which shows the functional structure of the terminal device which concerns on one Embodiment. It is a figure which shows the functional structure of the terminal device which concerns on one Embodiment. It is a figure which shows the functional structure of the server which concerns on one Embodiment. It is a figure which shows the data structure of the electronic medical record database which concerns on one Embodiment. It is a figure which shows the data structure of the electronic medical questionnaire database which concerns on one Embodiment. 4 is a flow chart showing an example of a processing flow in the system according to one embodiment; 4 is a flow chart showing another example of the processing flow in the system according to one embodiment; 9 is a flowchart showing still another example of the processing flow in the system according to one embodiment; It is a schematic diagram showing an example of the screen displayed with the terminal device which concerns on one Embodiment. FIG. 5 is a schematic diagram showing another example of a screen displayed on the terminal device according to one embodiment; FIG. 10 is a schematic diagram showing yet another example of a screen displayed on the terminal device according to one embodiment; FIG. 10 is a schematic diagram showing yet another example of a screen displayed on the terminal device according to one embodiment; FIG. 10 is a schematic diagram showing yet another example of a screen displayed on the terminal device according to one embodiment; FIG. 10 is a schematic diagram showing yet another example of a screen displayed on the terminal device according to one embodiment; FIG. 10 is a schematic diagram showing yet another example of a screen displayed on the terminal device according to one embodiment; FIG. 10 is a schematic diagram showing yet another example of a screen displayed on the terminal device according to one embodiment; FIG. 10 is a schematic diagram showing yet another example of a screen displayed on the terminal device according to one embodiment;

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all the drawings for explaining the embodiments, common constituent elements are denoted by the same reference numerals, and repeated explanations are omitted. It should be noted that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Also, not all the components shown in the embodiments are essential components of the present disclosure. Each figure is a schematic diagram and is not necessarily strictly illustrated.

Also, in the following description, a "processor" is one or more processors. The at least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may be another type of processor such as a GPU (Graphics Processing Unit). At least one processor may be single-core or multi-core.

Also, at least one processor may be a broadly defined processor such as a hardware circuit (for example, FPGA (Field-Programmable Gate Array) or ASIC (Application Specific Integrated Circuit)) that performs part or all of the processing.

In the following explanation, the expression "xxx table" may be used to describe information that produces an output for an input. It may be a learning model such as a generated neural network. Therefore, the "xxx table" can be called "xxx information".

Also, in the following description, the configuration of each table is an example, and one table may be divided into two or more tables, or all or part of two or more tables may be one table. good.

Further, in the following description, the processing may be described using the term “program” as the subject. As it is used, the subject of processing may be a processor (or a device, such as a controller, having that processor).

The program may be installed in a device such as a computer, or may be, for example, in a program distribution server or a computer-readable (eg, non-temporary) recording medium. Also, in the following description, two or more programs may be implemented as one program, and one program may be implemented as two or more programs.

In the following description, identification numbers are used as identification information for various objects, but identification information of types other than identification numbers (for example, identifiers including alphabetic characters and symbols) may be employed.

In addition, in the following description, when describing the same type of elements without distinguishing between them, reference symbols (or common symbols among the reference symbols) are used, and when describing the same types of elements with different An identification number (or reference sign) may be used.

Also, in the following description, control lines and information lines indicate those considered necessary for the description, and not all control lines and information lines are necessarily indicated on the product. All configurations may be interconnected.

<0 System Overview>
A system according to the present disclosure is a system that generates an electronic medical chart template and an electronic medical questionnaire template, and adds/corrects input contents of the electronic medical chart and electronic medical questionnaire.

In this specification, the saved contents of the electronic medical chart are generated based on the electronic medical chart template, and similarly, the electronic medical questionnaire data is generated based on the electronic medical questionnaire. In addition, the electronic medical questionnaire is linked to the electronic medical chart template (association between items), and the electronic medical questionnaire is generated from the electronic medical chart template as necessary.

An electronic medical record template is structured data having input items and input content associated with the input items. Here, structured data is data that is pre-defined before being placed in a storage and shaped to have a certain defined structure. In contrast, unstructured data is data that is stored in its native form and not processed until the time of use. Input items for the electronic medical chart are defined based on this electronic medical chart template.

The electronic medical questionnaire is structured data having medical interview items and medical interview questions and medical interview response contents associated with the medical interview items. The questionnaire item is an index of each item of the electronic medical questionnaire, and is a relatively short content using medical terminology in order to specify which item the medical staff is. The inquiry items may be common to the input items of the electronic medical record template, or rather, the fact that the inquiry items and the input items are common is important from the viewpoint of correcting the contents of the inquiry response by the medical staff, which will be described later. preferable. The interview questions are questions that are actually asked to the patient, and are expressed in such a way that the patient can read them and easily understand the contents of the questions. There are various question formats, such as multiple-choice questions and free-response questions. The question response content is the content actually answered by the patient to the question. be. Further, the electronic medical questionnaire data is data in which the contents of the reply to the medical inquiry described above are associated with medical inquiry items. In a system according to the present disclosure, electronic medical questionnaire data is generated based on an electronic medical chart template, and an existing electronic medical questionnaire can be associated with an also existing electronic medical chart template.

The association between the electronic medical chart template and the electronic medical questionnaire means that at least the input items of the electronic medical chart template and the interview items of the electronic medical questionnaire are associated. In other words, on the premise that the input electronic medical questionnaire data is incorporated into the electronic medical record, the items that the patient is required to enter are selected as the medical interview items from the input items of the electronic medical record template, and the inquiry reply contents for the medical questionnaire items are selected. is taken in as the input contents of the electronic medical record, the input items are associated with the medical inquiry items, and further, the medical inquiry reply contents corresponding to the medical inquiry items are associated as the input contents.

Here, the input items and input contents of the electronic medical chart template and the electronic medical chart are input/corrected/added by medical staff, and are prepared on the premise that they are viewed by medical staff. This means that input items and input contents must be based on medical knowledge and must be medically accurate.

On the other hand, the electronic medical questionnaire is based on the assumption that the patient views and inputs the information. In the medical field, it is possible that a medical worker such as a nurse asks a patient questions on a medical questionnaire in a question-and-answer format, and based on the patient's answer, the medical worker records the content of the reply to the inquiry by proxy. However, the work of inputting the electronic medical questionnaire through such a medical staff is a burden on the medical staff, and it takes a lot of time to input the reply contents of the electronic medical questionnaire. It cannot be said that they are fully enjoying the benefits of

In addition, since the electronic medical questionnaire is viewed and recorded by the patient himself/herself, it is preferable that the medical questionnaire is easy for the patient to understand. For this reason, if the input items of the electronic medical record (template) are directly used as the interview questions of the electronic medical questionnaire, the possibility cannot be ruled out that the patient cannot easily and accurately understand the contents of the interview questions. In addition, even if the patient can understand the medical interview questions, it is still possible that the medically incorrect information may not be correct if the contents of responses to the medical interview questions are directly entered into the electronic medical record.

Therefore, in the system according to the present disclosure, in the electronic medical questionnaire based on the electronic medical record template, in order to facilitate the input of the electronic medical questionnaire by the patient, the medical interview questions based on the input items are modified so that the patient can easily answer. etc. In addition, inputting the electronic medical questionnaire is made smoother by making the content of reply to the medical inquiry as options, and the content of the reply to the medical inquiry is approached to be medically accurate.

In addition, in the system according to the present disclosure, as a pre-work to incorporate the reply contents of the electronic medical questionnaire entered by the patient into the electronic medical record, the reply contents of the inquiry entered by the patient are corrected/added from a medical point of view. At that time, the medical staff utters the correction/addition contents by voice input, speech recognition is performed on this utterance data to obtain voice recognition data, and this voice recognition data is used to correct/addition of the inquiry reply contents. there is At this time, the system according to the present disclosure identifies the question reply content to be corrected/added using the question items included in the voice recognition data as clues, and similarly extracts correction candidates for the question reply content included in the voice recognition data. Then, the medical staff is presented with a correction candidate for the contents of the response to the medical inquiry, and the contents of the reply to the medical inquiry are corrected/added.

<One embodiment>
<1 Configuration diagram of the entire system>
FIG. 1 is a diagram showing the overall configuration of an electronic medical record system 1 of this embodiment. As shown in FIG. 1, an electronic medical record system 1 includes a plurality of terminal devices (terminal device 10 and terminal device 20 are shown in FIG. 1; hereinafter collectively referred to as "terminal device 10"). , and the server 30 . The terminal devices 10 and 20 and the server 30 are connected via a network 80 so as to be able to communicate with each other. Network 80 is configured by a wired or wireless network. In this embodiment, the server 30 is a server that functions as a web server (including a cloud server), and exchanges information with the terminal devices 10 and 20 via web pages. A web page browser for viewing web pages is installed in the terminal devices 10 and 20, and a dedicated application for providing the service of the server 30 is installed so that it can be viewed by the dedicated application. good too.

Since the hardware configuration of the terminal device 10 and the hardware configuration of the terminal device 20 are common, the description of the hardware configuration of the terminal device 20 is omitted by describing the hardware configuration of the terminal device 10 . It should be noted that the components of the terminal device 20 that are the same as the components of the terminal device 10 have the same reference numeral system, with reference numerals beginning with 2. FIG.

The terminal device 10 is a device operated by a patient. The patient browses the interview questions of the electronic medical questionnaire displayed on the output device 14 of the terminal device 10 and inputs the content of the inquiry reply corresponding to the interview questions through the input device 13 . The medical staff may assist the patient in the operation of the terminal device 10, that is, in the input of the contents of the reply to the medical questionnaire in the electronic medical questionnaire. The terminal device 10 is implemented by a stationary PC (Personal Computer), a laptop PC, or the like. In addition, the terminal device 10 may be, for example, a mobile terminal such as a tablet compatible with a mobile communication system or a smart phone.

The terminal device 10 is communicably connected to the server 30 via the network 80 . The terminal device 10 is a wireless base station 81 compatible with communication standards such as 4G, 5G, and LTE (Long Term Evolution), and a wireless LAN (Local Area Network) standard such as IEEE (Institute of Electrical and Electronics Engineers) 802.11. It is connected to the network 80 by communicating with a compatible communication device such as a wireless LAN router 82 . As shown in FIG. 1 , the terminal device 10 includes a communication IF (Interface) 12 , an input device 13 , an output device 14 , a memory 15 , a storage section 16 and a processor 19 .

The communication IF 12 is an interface for inputting and outputting signals so that the terminal device 10 communicates with an external device. The input device 13 is an input device (for example, a keyboard, a touch panel, a touch pad, a pointing device such as a mouse, etc.) for receiving an input operation from a user. The output device 14 is an output device (display, speaker, etc.) for presenting information to the user. The memory 15 temporarily stores programs and data processed by the programs, and is a volatile memory such as a DRAM (Dynamic Random Access Memory). The storage unit 16 is a storage device for storing data, and is, for example, a flash memory or a HDD (Hard Disc Drive). The processor 19 is hardware for executing an instruction set described in a program, and is composed of arithmetic units, registers, peripheral circuits, and the like.

The terminal device 20 is a device operated by a medical staff or an administrator of the electronic medical chart system 1 . Here, the medical staff is a concept including doctors, nurses, laboratory technicians with medical knowledge, and the like. In the following description, the medical staff includes the administrator of the system 1 unless the medical staff and the administrator of the system 1 are described separately.

The medical staff uses the terminal device 20 to perform an operation of associating (linking) the electronic medical chart template with an existing electronic medical questionnaire, and also generates an electronic medical questionnaire from the existing electronic medical chart template. When linking the electronic medical questionnaire and generating a new electronic medical questionnaire, the medical staff corrects/adds/deletes the questionnaire of the electronic medical questionnaire (deleting here means deleting the questionnaire completely) In addition, multiple interview questions are combined into one interview question, including reducing the number of interview questions as a whole), and generation / correction / addition / Delete.

In addition, the medical staff uses the terminal device 10 to view the response contents of the electronic medical questionnaire entered by the patient, and mainly when incorporating the response contents of the electronic medical questionnaire into the input contents of the electronic medical record, For the portion of the question reply content determined to be corrected/added from a medical point of view, the utterance data is input to the terminal device 20, and the correction/addition is instructed. The terminal device 20 acquires speech recognition data by performing voice recognition on the utterance data, and corrects/adds the content of the inquiry reply based on this voice recognition data. Then, the medical staff issues an instruction to import the contents of the response to the medical inquiry that have been corrected/added as the input contents of the electronic medical record.

The server 30 is managed by the administrator of the electronic medical record system 1 of the present embodiment, and the stored contents are appropriately modified/added/deleted by the medical staff who is the user of the terminal device 20 . The server 30 is an electronic medical chart device, and a medical staff at a medical facility views input items and input contents of the electronic chart through a terminal device (not shown), and corrects/additions to the input contents. Also, the electronic medical chart template and the electronic medical questionnaire are edited by the medical staff via the terminal device 20, and the contents are corrected/added/deleted based on the editing operation.

Server 30 is a computer connected to network 80 . The server 30 includes a communication IF 32 , an input/output IF 33 , a memory 35 , a storage 36 and a processor 39 .

The communication IF 32 is an interface for inputting and outputting signals for the server 30 to communicate with an external device. The input/output IF 33 functions as an interface with an input device for receiving input operations from the user and an output device for presenting information to the user. The memory 35 temporarily stores programs and data processed by the programs, and is a volatile memory such as a DRAM (Dynamic Random Access Memory). The storage 36 is a storage device for storing data, such as a flash memory or HDD (Hard Disc Drive). The processor 39 is hardware for executing an instruction set described in a program, and is composed of arithmetic units, registers, peripheral circuits, and the like.

<1.1 Functional Configuration of Terminal Device 10>
FIG. 2 is a block diagram showing an example of the functional configuration of the terminal device 10 shown in FIG. 1. As shown in FIG. The terminal device 10 shown in FIG. 2 is realized by, for example, a PC, a mobile terminal, or a wearable terminal. As shown in FIG. 2, the terminal device 10 includes a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a storage unit 180, and a control unit 190. Prepare. Each block included in the terminal device 10 is electrically connected by, for example, a bus.

The communication unit 120 performs processing such as modulation/demodulation processing for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on the signal generated by the control unit 190 and transmits the signal to the outside (for example, the server 30). Communication unit 120 performs reception processing on a signal received from the outside, and outputs the signal to control unit 190 .

The input device 13 is a device for a user operating the terminal device 10 to input instructions or information. The input device 13 may be implemented by, for example, a keyboard, mouse, reader, or the like. When the terminal device 10 is a mobile terminal or the like, it is realized by a touch sensitive device 131 or the like that inputs an instruction by touching the operation surface. The input device 13 converts an instruction input by the user into an electric signal and outputs the electric signal to the control unit 190 . Note that the input device 13 may include, for example, a receiving port for receiving an electrical signal input from an external input device.

The output device 14 is a device for presenting information to the user who operates the terminal device 10 . The output device 14 is implemented by, for example, the display 141 or the like. The display 141 displays data under the control of the controller 190 . The display 141 is implemented by, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

The audio processing unit 17 performs digital-analog conversion processing of audio signals, for example. The audio processing unit 17 converts the signal supplied from the microphone 171 into a digital signal and supplies the converted signal to the control unit 190 . Also, the audio processing unit 17 provides an audio signal to the speaker 172 . The audio processing unit 17 is realized by, for example, a processor for audio processing. The microphone 171 receives an audio input and provides an audio signal corresponding to the audio input to the audio processing section 17 . The speaker 172 converts the audio signal given from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10 .

The storage unit 180 is implemented by, for example, the memory 15 and the storage unit 16, and stores data and programs used by the terminal device 10. FIG. The storage unit 180 stores electronic medical questionnaire data 182 and image data 183, for example.

The electronic medical questionnaire data 182 is generated based on the electronic medical questionnaire 3027 stored in the server 30, and is data of the electronic medical questionnaire in which the patient operates the terminal device 10 to input the inquiry reply contents.

The image data 183 is image data used when presenting the electronic medical questionnaire to the patient.

Control unit 190 is implemented by processor 19 reading application program 181 stored in storage unit 180 and executing instructions included in application program 181 . The control unit 190 controls operations of the terminal device 10 . By operating according to the application program 181 stored in the storage unit 180, the control unit 190 controls an operation reception unit 191, a transmission/reception unit 192, a data processing unit 193, a presentation control unit 194, and an electronic medical questionnaire input unit 195. , the function as the electronic medical questionnaire data sending unit 196 is exhibited.

The operation reception unit 191 performs processing for receiving instructions or information input from the input device 13 . Specifically, for example, the operation accepting unit 191 accepts information based on instructions input from a keyboard, mouse, or the like.

Further, the operation accepting unit 191 accepts voice instructions input from the microphone 171 . Specifically, for example, the operation reception unit 191 receives an audio signal input from the microphone 171 and converted into a digital signal by the audio processing unit 17 . The operation reception unit 191 acquires an instruction from the user, for example, by analyzing the received audio signal and extracting a predetermined noun.

The transmission/reception unit 192 performs processing for the terminal device 10 to transmit and receive data to and from an external device such as the server 30 according to a communication protocol. Specifically, for example, the transmitting/receiving unit 192 transmits the business content input by the user to the server 30 . The transmitting/receiving unit 192 also receives information about the user from the server 30 .

The data processing unit 193 performs processing according to the application program 181 on the data input by the terminal device 10, and outputs the computation result to the memory 15 or the like.

The presentation control unit 194 controls the output device 14 to present the information provided by the server 30 to the user. Specifically, for example, the presentation control unit 194 causes the display 141 to display information transmitted from the server 30 . The presentation control unit 194 also causes the speaker 172 to output information transmitted from the server 30 .

The electronic medical questionnaire input unit 195 is used for inputting inquiry reply contents that the patient has entered in response to the inquiry questions of the electronic medical questionnaire displayed on the display 141 by the presentation control unit 194 (the input of the inquiry reply contents is set in advance). (including a selection input for any of the options of the medical interview question) is accepted, and the accepted input of the reply content of the medical inquiry is stored in the electronic medical questionnaire data 182 in association with the medical inquiry item associated with the reply content of the medical inquiry.

The electronic medical questionnaire data sending unit 196 receives the reply contents of the medical questionnaire from the electronic medical questionnaire input unit 195 , and sends the electronic medical questionnaire data 182 stored as the electronic medical questionnaire data 182 in the storage unit 180 to the server 30 .

<1.2 Functional Configuration of Terminal Device 20>
FIG. 3 is a block diagram showing an example of the functional configuration of the terminal device 20 shown in FIG. 1. As shown in FIG. The terminal device 10 shown in FIG. 3 is realized by, for example, a PC, a mobile terminal, or a wearable terminal.

Since the functional configuration of the terminal device 20 has many things in common with the functional configuration of the terminal device 10, the functional configuration different from that of the terminal device 10 will be mainly described.

The storage unit 280 is realized by, for example, the memory 25 and the storage 26, and stores data and programs used by the terminal device 20. FIG. The storage unit 180 stores electronic medical questionnaire data 282, speech recognition data 283, technical term data 284, teacher data 285, and learning models 286, for example.

The electronic medical questionnaire data 282 is electronic medical questionnaire data in which the patient operates the terminal device 10 to input the content of the reply to the medical questionnaire, and is obtained from the storage unit 302 of the server 30 by the electronic medical questionnaire data acquisition unit 295 described later. electronic medical questionnaire data 3026. The electronic medical questionnaire data 282 may be part of the electronic medical questionnaire data 3026 . In other words, although the details will be described later, the electronic medical questionnaire data 3026 stored in the storage unit 302 of the server 30 is all the electronic medical questionnaire data managed by the server 30 (that is, the electronic medical record device). This is because the electronic medical questionnaire data to be corrected/added as will be described later may be data relating to a specific electronic medical questionnaire input by a specific patient.

The speech recognition data 283 is speech recognition data obtained as a result of speech recognition performed by the speech recognition section 296 of the control section 290 . The speech recognition data 283 is, for example, data in which kanji and hiragana are mixed, or may be data in pairs of kanji and hiragana, which is the reading of the kanji.

The terminology data 284 is used to correct/add the response contents of the electronic medical questionnaire based on the speech recognition data 283 by the correction item specifying unit 297 of the control unit 290. This is technical term data used to specify such interview items. The technical terms here include at least so-called medical terms, and further include technical terms used in medical interview items. Preferably, terminology data 284 includes a synonym dictionary for these medical terms and the like.

The learning model 286 is a learning model used when the speech recognition unit 296 performs speech recognition based on speech data uttered by a medical worker or the like and acquired by the microphone 271 to generate the speech recognition data 283 . That is, the learning model 286 uses the speech data temporarily stored in the storage unit 280 as input data, and outputs the speech recognition data 283 .

The learning model 286 is obtained by causing the machine learning model to perform machine learning according to a model learning program (not shown) based on the teacher data 285 . The training data 285 consists of pairs of utterance data of many speakers and correctly recognized text data corresponding to the utterance data, which is generally used for speech recognition by machine learning. . At this time, the terminal device 20 may have a plurality of learning models 286 and teacher data 285 . In particular, since it is preferable to appropriately select the learning model 286 (and the teacher data 285 that is the premise thereof) according to the interview items of the electronic medical questionnaire, the storage unit 280 stores a plurality of learning models 286 and the teacher data corresponding to the learning model 286. 285 is preferred.

The learning model 286 according to this embodiment is, for example, a synthetic function with parameters that is a combination of multiple functions. A parameterized composite function is defined by a combination of multiple adjustable functions and parameters. The prediction model according to the present embodiment may be any parameterized composite function that satisfies the above requirements, but is assumed to be a multi-layered network model (hereinafter referred to as a multi-layered network). A prediction model using a multi-layered network has an input layer, an output layer, and at least one intermediate layer or hidden layer provided between the input layer and the output layer. Predictive models are envisioned for use as program modules that are part of artificial intelligence software.

As the multi-layered network according to the present embodiment, for example, a deep neural network (DNN), which is a multi-layered neural network targeted for deep learning, can be used. As the DNN, for example, a convolution neural network (CNN) targeting images may be used.

Moreover, the above is merely an example of the prediction model, and the prediction model may have other configurations. For example, the predictive model may be a rule-based model described by a function in which hunting information and environment information are variables, and coefficients derived from past performance are attached to each variable.

Preferably, teacher data 285 includes previously accumulated speech data and electronic chart template 3024 . In other words, it is preferable to use actual data suitable for voice recognition of the electronic medical questionnaire data 282, which has already been captured as an electronic medical chart, as well as general teacher data for voice recognition. However, the electronic medical record template 3024 accumulated in the past naturally includes personal information such as the patient's name, date of birth, contact information, and very rare diseases. The Personal Information Protection Law strictly stipulates management methods for such personal information. Therefore, using the electronic medical record template 3024 with such restrictions for speech recognition processing requires strict handling and carries the risk of personal information leakage. Therefore, in the system 1 according to the present disclosure, at least a part of the actual electronic medical record template 3024 is anonymized or modified to protect personal information and improve the convenience of data utilization. there is

Specifically, as the teacher data 285, part of the numbers in the actual electronic medical chart template 3024 is increased or decreased by a predetermined value, or the question reply content is replaced with the same question item as the electronic medical chart template 3024 of another patient. By modifying, the actual electronic medical chart data 3023 is modified. In addition, personal information is anonymized by masking proper nouns. At the same time, morphological analysis is performed as words, and very rare words are masked from display.

In addition, it is preferable that the training data 285 include data on the relationship between kanji characters and their readings. By using the learning model 286 that has been machine-learned using such training data 285, when specifying correction contents by the correction item specifying unit 297, which will be described later, if reading kana is input as utterance data, other similar words can be obtained from reading kana. It is possible to instruct replacement to kanji with the sound of .

Control unit 290 is implemented by processor 29 reading application program 281 stored in storage unit 280 and executing instructions included in application program 281 . The control unit 290 controls operations of the terminal device 20 . By operating according to the application program 281 stored in the storage unit 280, the control unit 290 includes an operation reception unit 291, a transmission/reception unit 292, a data processing unit 293, a presentation control unit 294, and an electronic medical questionnaire data acquisition unit. 295 , voice recognition section 296 , correction item identification section 297 , correction content input section 298 , and electronic medical questionnaire data transmission section 299 .

Operations of the operation reception unit 291, the transmission/reception unit 292, the data processing unit 293, and the presentation control unit 294 are the same as those of the operation reception unit 191, the transmission/reception unit 192, the data processing unit 193, and the presentation control unit 194 of the terminal device 10. Therefore, description of these is omitted.

The electronic medical questionnaire data acquisition unit 295 acquires the electronic medical questionnaire data 3026 stored in the storage unit 302 of the server 30 and stores it in the storage unit 280 as the electronic medical questionnaire data 282 .

The speech recognition unit 296 acquires speech recognition data 283 as an output result by inputting the speech data into the learning model 286 based on the speech data input by the medical staff via the microphone 271 .

At this time, the speech recognition unit 296 performs speech recognition on the speech data corresponding to the interview items of the electronic medical questionnaire included in the speech data, and determines which interview item the speech data pertains to. Based on this, it is preferable to select a learning model 286 that is suitable for the interview item, which is the determination result, from a plurality of learning models 286 stored in the storage unit 280, and perform speech recognition processing based on the selected learning model 286.

The correction item identification unit 297 refers to the speech recognition data 283 that is the output result of the speech recognition unit 296, compares the speech recognition data 283 with the technical term data 284, and prepares the electronic medical questionnaire included in the speech recognition data 283. identify the questionnaire items of Then, the correction item identification unit 297 identifies inquiry reply content to be corrected/added from the voice recognition data 283 based on the speech data uttered by the medical staff subsequent to the identified inquiry item. In other words, in the utterance data (and thus the voice recognition data 283), the question items and the content of the reply to the question are continuous ("continuous" here means that the medical staff who is the speaker responds to the question item and this question item, It means a time interval that can be objectively recognized as a series of utterances between the contents of the reply to the inquiry, which are the corrected/added contents. If it can be objectively recognized as being present, it can fall into the category of continuous). The instructed inquiry reply content is extracted from the voice recognition data 283, and based on this speech recognition data 283, candidates for correction/addition of the inquiry reply content are extracted.

Furthermore, based on the above-described continuity, the correction item specifying unit 297 extracts a plurality of candidate medical question items included in the utterance data (speech recognition data 283), and determines which medical question item is the correction/addition instruction. may be presented to the operator of the terminal device 20 (that is, the medical worker). After that, the correction content input unit 298 accepts an inquiry item selection instruction from the operator of the terminal device 20, and confirms the correction/addition content.

Here, the utterance data of the medical staff who is the utterer is an interview item that is a noun, a particle such as "ha" that connects to this interview item, and a correction/addition target that is uttered following this particle. It is considered to have a series of unity with the content of reply to inquiry. Therefore, the correction item identification unit 297 uses a predetermined particle (for example, "ha") as a key, and presumes that the utterance data uttered before this particle corresponds to the medical inquiry item. In addition to specifying, the utterance data uttered after the particle (for example, "ha") uttered consecutively to the identified questionnaire item is the inquiry reply content associated with this inquiry item, and the speaker can modify/modify it. It is determined that the content of the inquiry reply is uttered for additional writing, and based on the speech recognition data 283, the inquiry reply content to be corrected/added is specified.

Furthermore, since the correction item identification unit 297 can identify the content of the reply to the inquiry based on the continuity between the inquiry item and the particle, if the content of the reply to the inquiry can be expressed by certain options, candidates (options) for the content of the inquiry reply can be selected. Candidates for inquiry reply content may be prepared in advance and presented to the operator (medical worker who is the speaker) to request selection of the inquiry reply content candidate. After that, the correction content input unit 298 accepts a selection instruction of inquiry reply content from the operator of the terminal device 20, and confirms the correction/addition content.

Note that the operation of the correction item identification unit 297 described above is performed by providing patterns in the teacher data 285 (for example, associations between inquiry items, particles, and inquiry reply contents, and candidates for inquiry reply contents). It is also possible to implement it as an operation of the speech recognition unit 296 by making the learning model 286 learn based on it.

In addition, an identifier, such as a number, for specifying each medical interview item is attached to the medical questionnaire items of the electronic medical questionnaire 3027 stored in the storage unit 302 of the server 30, and this identifier is attached to the electronic medical questionnaire data 282. is also included, if the correction item identifying unit 297 determines that the voice recognition data 283 includes the identifier of the medical inquiry item, it identifies the medical inquiry item to be corrected/added based on this identifier, Further, it may be determined that the voice recognition data 283 includes the correction/additional contents of the medical inquiry reply corresponding to the identified medical inquiry item, and the correction/additional contents of the medical inquiry reply may be specified.

Further, the storage unit 280 may store information (not shown) that specifies and limits types of words and/or characters that can be input as inquiry reply contents. In this case, the correction item specifying unit 297 determines whether or not the text data included in the voice recognition data 283 matches the specified and limited information when specifying the question reply contents from the voice recognition data 283. , if it matches, it may be identified as input of the inquiry reply content to be corrected/added. As an example, if the inquiry item is "patient's contact information", the contents of the inquiry reply must be a numeric string. Therefore, the part where the speech recognition data 283 is a numeric string may be specified as the question reply content. Alternatively, based on this information, the speech recognition unit 296 determines that, if the inquiry item is "patient's contact information," then the question reply content uttered following this inquiry item must be a numeric string. Recognition processing may be performed.

Furthermore, if the inquiry reply content is an option, the correction item specifying unit 297, if any of the options is included in the voice recognition data 283, the medical staff who is the speaker instructs correction/addition. The speech recognition data 283 uttered in the speech may represent this option, and the question reply content to be corrected/added may be specified. Further, after identifying the medical inquiry item based on the speech recognition data 283, the correction item identification unit 297 may present options for inquiry reply content associated with the identified medical inquiry item. After that, the correction content input unit 298 accepts a selection input from a medical worker or the like who is an operator, and confirms the correction/addition of the medical inquiry reply content based on the accepted selection input.

Here, the medical staff who is the utterer utters a predetermined word, such as "line feed", that indicates the delimitation of the medical question item and the content of the reply to the medical question. is included in the speech recognition data 283, the correction item specifying unit 297 determines that this word is used to delimit the inquiry item and inquiry reply content. Further, the correction item identification unit 297 identifies the inquiry item and inquiry reply content also for the speech recognition data 283 after the delimiting word. In this way, even if the speaker utters a series of utterances, it is possible to reliably identify the question items and the contents of the reply to the question.

For example, an anamnesis item, which is an example of an interview item, can be further filled with information such as the year of onset, disease name, treatment method, treatment medical institution, etc. to further add a plurality of related items, and eventually the input items of the electronic medical chart template 3023. is required to be entered. As voice recognition processing for the speech data, "History is colorectal cancer at the age of 34. Operated at Nagoya Hospital. Cured. Line feed. Prostate cancer since 2002. Prostate cancer resection at our hospital. Cured." , first check the related item "previous history", then check the sentences up to another related item or the word "new line", from among them, the disease name "prostate cancer", the treatment name "Prostate cancer resection surgery, surgery, cure", "34 years old", "since 2002", and "Nagoya Hospital" and "our hospital", which mean the time, and the year of onset The period, disease name can identify the disease name, treatment method can identify the treatment, and treatment medical institution can identify the name of the medical institution, and the items of the medical history can be structured more finely. For this reason, the correction item specifying unit 297 has each sub-item name and a list of words that are allowed to be input to each sub-item, and makes determination based on the word list.

The correction content input unit 298 receives (including selection input and consent/cancel input) from the operator the inquiry items and inquiry reply content specified by the correction item specifying unit 297 and presented to the operator of the terminal device 20. ) Accepts the input, corrects/adds the inquiry items and inquiry reply contents based on the accepted input, and confirms the input of these inquiry items. Then, the correction content input unit 298 corrects/additions to the electronic medical questionnaire data 282 using the confirmed medical inquiry items and medical inquiry reply contents.

At this time, the correction content input unit 298 presents the operator with a selection as to whether to correct or add to each of the inquiry items and/or inquiry reply contents specified by the correction item specifying unit 297. You may correct/add an inquiry item and an inquiry reply content based on the selection instruction of .

Further, when the inquiry item/inquiry reply content specified by the correction item specifying unit 297 is not intended by the operator, the correction content input unit 298 refers to the voice recognition data 283 stored in the storage unit 280. Then, the correction item specifying unit 297 may be instructed to redo the specified action. In addition, if the inquiry reply content specified by the correction item specifying unit 297 is intended, but the inquiry item associated with this inquiry reply content is different from the operator's intention, the correction content input unit 298 can be used for voice recognition. Input may be received from the operator with reference to data 283 to associate the identified inquiry reply with a different inquiry item.

The electronic medical questionnaire data sending unit 299 sends the electronic medical questionnaire data 282 confirmed by the correction content input unit 298 to the server 30 .

<1.3 Functional Configuration of Server 30>
FIG. 4 is a diagram showing an example of a functional configuration of the server 30. As shown in FIG. As shown in FIG. 4 , the server 30 functions as a communication section 301 , a storage section 302 and a control section 303 .

The communication unit 301 performs processing for the server 30 to communicate with an external device.

The storage unit 302 has, for example, an electronic medical record DB 3022, electronic medical record data 3023, an electronic medical record template 3024, an electronic medical questionnaire DB 3025, electronic medical questionnaire data 3026, an electronic medical questionnaire 3027, association data 3028, and the like. .

The electronic medical record DB 3022 is a database for managing electronic medical record data 3023 on patients who have visited medical facilities using the server 30 . The electronic medical record DB 3022 may manage electronic medical record data 3023 in multiple medical facilities. Details will be described later.

The electronic medical chart data 3023 is electronic medical chart data managed by the electronic medical chart DB 3022 , and is electronic medical chart data 3023 about patients who have visited a medical facility using the server 30 . Since the electronic medical chart data 3023 itself is known, its details are omitted, but the electronic medical chart data 3023 has input items and input contents associated with the input items. Although the data format of the electronic medical record data 3023 is not particularly limited, the electronic medical record data 3023 of this embodiment uses data described in XAML (Extensible Application Markup Language) as JSON (JavaScript Object Notation) (JavaScript is a registered trademark). ) format. The electronic medical chart data 3023 preferably has an identifier such as a number string attached to the input item, and this identifier also constitutes the electronic medical chart data 3023 .

The electronic medical chart template 3024 is template data for generating the electronic medical chart data 3023 . The electronic medical chart template 3024 is structured data that defines input items and input content associated with the input items. Although the data format of the electronic medical chart template 3024 is not particularly limited, the electronic medical chart template 3024 of this embodiment is data described in XAML converted into JSON format, like the electronic medical chart data 3023 . Similar to the electronic medical chart data 3023 , the electronic medical chart template 3024 preferably has identifiers such as numeric strings attached to its input items, and this identifier also constitutes the electronic medical chart template 3024 .

Each electronic medical chart template 3024 is associated with an identifier for identifying each electronic medical chart template 3024 . As an example, the identifier of the electronic medical chart template 3024 is a numeric string of predetermined digits. The identifier of the electronic medical record template 3024 is assigned by an electronic medical questionnaire creation module 3033, which will be described later.

The electronic medical questionnaire DB 3025 is a database for managing the electronic medical questionnaire data 3026 on patients who have visited medical facilities using the server 30 . The electronic medical questionnaire DB 3025 may manage electronic medical questionnaire data 3026 in a plurality of medical facilities. Details will be described later.

The electronic medical questionnaire data 3026 is electronic medical questionnaire data managed by the electronic medical questionnaire DB 3025 , and is electronic medical questionnaire data 3026 for patients who have undergone a medical examination at a medical facility using the server 30 . The electronic medical questionnaire data 3026 of the present embodiment is generated by the terminal device 10 and stored in the storage unit 180 as the electronic medical questionnaire data 182. Further, the electronic medical questionnaire data 3026 is corrected/added in the terminal device 20 and It is stored in the storage unit 280 as the data 282 .

The electronic medical questionnaire data 3026 has medical inquiry items and medical inquiry questions and inquiry reply contents associated with the medical inquiry items. Although the data format of the electronic medical questionnaire data 3026 is not particularly limited, the electronic medical questionnaire data 3026 of this embodiment is data described in XAML converted into JSON format, similar to the electronic medical record data 3023. be. The electronic medical questionnaire data 3026 preferably has identifiers such as numeric strings attached to the medical questionnaire items.

The electronic medical questionnaire 3027 is template data for generating the electronic medical questionnaire data 3026 . The electronic medical questionnaire 3027 is structured data that defines medical interview items, medical interview questions associated with the medical interview items, and medical interview contents. Although the data format of the electronic medical questionnaire 3027 is not particularly limited, the electronic medical questionnaire 3027 of the present embodiment is data described in XAML converted into JSON format, similar to the electronic medical questionnaire data 3026. . Similar to the electronic medical questionnaire data 3026 , the electronic medical questionnaire 3027 preferably has identifiers such as numeric strings attached to its input items.

Each electronic medical questionnaire 3027 is associated with an identifier for identifying each electronic medical questionnaire 3027 . As an example, the identifier of the electronic medical questionnaire 3027 is a numeric string of predetermined digits. An identifier for the electronic medical questionnaire 3027 is assigned by an electronic medical questionnaire creation module 3033, which will be described later.

The association data 3028 is data describing the association between the electronic medical record template 3024 and the electronic medical questionnaire 3027 . The association data 3028 is, for example, data describing the association between the identifier of the electronic medical chart template 3024 and the identifier of the electronic medical questionnaire 3027 . The association data 3028 is generated by the electronic medical questionnaire creation module 3033 .

Control unit 303 is implemented by processor 29 reading application program 3021 stored in storage unit 302 and executing instructions included in application program 3021 . By operating according to the application program 3021 , the control unit 303 exhibits the functions of a reception control module 3031 , a transmission control module 3032 , an electronic medical questionnaire creation module 3033 and an electronic medical record data generation module 3034 .

The reception control module 3031 controls processing for the server 30 to receive a signal from an external device according to a communication protocol.

The transmission control module 3032 controls the processing by which the server 30 transmits signals to external devices according to a communication protocol.

The electronic medical questionnaire creation module 3033 generates an electronic medical questionnaire 3027 . The procedures for generating the electronic medical questionnaire 3027 by the electronic medical questionnaire creation module 3033 are roughly classified into two types.

First, the first procedure is a procedure for generating a new electronic medical questionnaire 3027 based on the existing electronic medical chart template 3024 . In this case, the input items and input contents of the existing electronic medical record template 3024 are generated as inquiry items and inquiry reply contents of a new electronic medical questionnaire 3027, respectively.

At this time, the electronic medical questionnaire creation module 3033 gives a unique identifier to the newly created electronic medical questionnaire 3027 . As an example, when the electronic medical questionnaire 3027 is shared by multiple medical facilities, the first digit (first digit) of the identifier is a unique number indicating that it is shared by multiple medical facilities. For the subsequent digits, there is a method of assigning serial number strings in the order in which the electronic medical questionnaire 3027 is created. In addition, when the electronic medical questionnaire 3027 is used only at a single medical facility, the first digit of the identifier is a number other than a unique number indicating that it is shared by multiple medical facilities, and the subsequent digits are , a method of assigning serial number strings in the order in which the electronic medical questionnaire 3027 is created. Furthermore, after assigning an identifier to the electronic medical questionnaire 3027 that is used only at a single medical facility, an identifier that does not conflict with the already assigned identifier may be assigned again.

The second procedure is to associate the existing electronic medical questionnaire 3027 with the electronic medical record template 3024, which is also existing. In this case, the inquiry items and inquiry reply contents of the electronic medical questionnaire 3027 are overwritten with the input items and input contents of the associated electronic medical record template 3024 . In this case as well, the electronic medical questionnaire creation module 3033 assigns an identifier to the associated electronic medical questionnaire 3027 as in the case described above.

Next, the electronic medical questionnaire creation module 3033 corrects the medical interview questions of the electronic medical questionnaire 3027 that has been created (hereafter, the act of “creating” will include the fact that it is associated with the existing electronic medical record template 3024). This electronic medical questionnaire is input by the patient using the terminal device 10 at the medical facility (including the case where the medical staff supports it), and the patient who does not necessarily have accurate medical knowledge can smoothly perform the medical interview. This is because, in some cases, it is preferable to use expressions that are different from the input items and input contents of the electronic medical record template 3024 in order to input the inquiry reply contents after looking at the questions.

Further, in the present embodiment, it is assumed that a plurality of medical inquiry question answer candidates (inquiry reply content candidates) may be associated with medical inquiry items. In other words, the question reply content can be one answer candidate selected from a plurality of answer candidates.

Therefore, as an example, the electronic medical questionnaire creation module 3033 changes a plurality of answer candidates for the medical interview questions to open-ended medical interview questions. In other words, the electronic medical questionnaire creation module 3033 aggregates a plurality of answer candidates into a free-form medical interview question for one medical interview question.

Also/or, the electronic medical questionnaire creation module 3033 changes each of the plurality of answer candidates for the medical interview question to the medical interview question, and associates the changed medical interview question with the answer candidates such as "yes" and "no". That is, the electronic medical questionnaire creation module 3033 divides each of the plurality of answer candidates into interview questions, and changes the answer candidates to the interview questions to easy answers such as "yes" and "no."

Corrections to the medical interview questions of these electronic medical questionnaires 3027 are performed according to instructions from the medical staff who operates the terminal device 20 connected to the server 30 .

Then, the electronic medical questionnaire creation module 3033 presents (candidates for) the medical interview question and the contents of the reply to the medical interview corrected by the above-described procedure to the medical staff via the terminal device 20, and asks the medical staff to input whether or not the correction is possible. demand. Then, the electronic medical questionnaire creation module 3033 corrects the electronic medical questionnaire 3027 based on the input as to whether or not correction is possible. The corrected electronic medical questionnaire 3027 is stored in the storage unit 302 .

The electronic medical chart data generation module 3034 generates electronic medical chart data 3023 based on the electronic medical questionnaire data 3026 acquired from the terminal device 10 .

<2 Data structure>
5 and 6 are diagrams showing the data structure of the database stored by the server 30. FIG. Note that FIGS. 5 and 6 are examples, and do not exclude data not described.

The databases shown in FIGS. 5 and 6 refer to relational databases, and are for managing data sets called tabular tables structurally defined by rows and columns in association with each other. In a database, a table is called a table, columns of a table are called columns, and rows of a table are called records. Relational databases allow you to establish and associate relationships between tables.

Each table usually has a primary key column to uniquely identify a record, but setting a primary key to a column is not essential. The control unit 303 of the server 30 can cause the processor 29 to add, delete, and update records in a specific table stored in the storage unit 302 according to various programs.

FIG. 5 is a diagram showing the data structure of the electronic medical record DB 3022. As shown in FIG. As shown in FIG. 5, each record of the electronic medical chart DB 3022 includes, for example, the item "electronic medical chart ID", the item "patient ID", the item "medical department ID", and the item "electronic medical chart data". Each item of the electronic medical record DB 3022 is input by the electronic medical record data generation module 3034 when the electronic medical record data generation module 3034 generates the electronic medical record data 3023 . Information stored in the electronic medical chart DB 3022 can be changed or updated as appropriate.

The item "electronic medical record ID" is an ID for specifying an electronic medical record managed by the system 1 (especially the server 30) of the present embodiment. The item "patient ID" is an ID for identifying a patient related to the medical information managed by the electronic medical record specified by the item "electronic medical record ID". The item "medical department ID" is an ID for specifying the medical department related to the medical information managed by the electronic medical chart specified by the item "electronic medical chart ID". The item "electronic medical chart data" is information on the file name of the electronic medical chart data 3023 related to the electronic medical chart specified by the item "electronic medical chart ID".

FIG. 6 is a diagram showing the data structure of the electronic medical questionnaire DB 3025. As shown in FIG. As shown in FIG. 7, each record of the electronic medical questionnaire DB 3025 includes, for example, an item “electronic medical questionnaire ID”, an item “patient ID”, an item “medical department ID”, an item “input date and time”, The item "electronic medical questionnaire data" is included. Each item of the electronic medical questionnaire DB 3025 is input by the electronic medical questionnaire preparation module 3033 when the electronic medical questionnaire preparation module 3033 generates the electronic medical questionnaire data 3026 . Information stored in the electronic medical questionnaire DB 3025 can be changed or updated as appropriate.

The item "electronic medical questionnaire ID" is an ID for specifying an electronic medical chart managed by the system 1 (particularly the server 30) of this embodiment. The item "patient ID" is an ID for specifying a patient, and is common with the item "patient ID" of the electronic medical record DB 3022. The item “medical department ID” is an ID for specifying the medical department, and is common with the item “medical department ID” of the electronic medical record DB 3022 . The item "input date and time" is information indicating the date and time when the electronic medical questionnaire data 3026 specified by the item "electronic medical questionnaire data" was input. The item "electronic medical questionnaire data" is information on the file name of the electronic medical questionnaire data 3026 related to the electronic medical questionnaire specified by the item "electronic medical questionnaire ID".

<3 Operation example>
An example of the operation of the server 30 will be described below.

FIG. 7 is a flow chart showing an example of the operation of the server 30. As shown in FIG. FIG. 7 is a flow chart showing an example of the operation when a new electronic medical questionnaire 3027 is generated from the electronic medical record template 3024 in response to a request from the operator of the terminal device 20 (that is, a medical worker who uses the system 1). be.

In step S<b>700 , the control unit 303 calls the electronic medical record template 3024 stored in the storage unit 302 in response to a request from the terminal device 20 . Specifically, for example, the control unit 303 calls the electronic medical record template 3024 by the electronic medical questionnaire creation module 3033 .

Next, in step S701, the control unit 303 newly generates an electronic medical questionnaire 3027 based on the electronic medical record template 3024 called in step S700. Specifically, for example, the control unit 303 causes the electronic medical questionnaire creation module 3033 to newly generate an electronic medical questionnaire 3027 based on the electronic medical record template 3024 .

Then, in step S702, the control unit 303 sets the name, ID, etc. of the electronic medical questionnaire 3027 generated in step S701, and stores them in the storage unit 302. FIG. Specifically, for example, the control unit 303 registers the electronic medical questionnaire 3027 generated by the electronic medical questionnaire creation module 3033 in the storage unit 302 .

FIG. 8 is a flow chart showing an example of the operation of the server 30. As shown in FIG. FIG. 8 shows editing of interview questions and inquiry reply contents of the electronic medical questionnaire 3027 stored in the storage unit 302 at the request of the operator of the terminal device 20 (that is, the medical staff who uses the system 1). 10 is a flow chart showing an example of an operation at a time;

In step S<b>800 , the control unit 303 selects the electronic medical questionnaire 3027 to be edited from the electronic medical questionnaire 3027 stored in the storage unit 302 and calls it from the storage unit 302 . Specifically, for example, the control unit 303 causes the electronic medical questionnaire creation module 3033 to select the electronic medical questionnaire 3027 to be edited from among the electronic medical questionnaires 3027 stored in the storage unit 302 , and call from Next, the electronic medical questionnaire creation module 3033 causes the display 241 of the terminal device 20 to display information for specifying the electronic medical questionnaire 3027 such as the name of the electronic medical questionnaire 3027 that has been called.

Next, in step S801, the control unit 303 accepts an edit instruction input from the terminal device 20 for the electronic medical questionnaire 3027 called in step S800. Specifically, for example, the control unit 303 causes the display 241 of the terminal device 20 to display an "edit" button using the electronic medical questionnaire creation module 3033, and inputs an instruction for the "edit" button through the input device 23 of the terminal device 20. accept.

Next, in step S802, the control unit 303 causes the display 241 of the terminal device 20 to display the interview questions and the reply contents of the electronic medical questionnaire 3027 for which the editing instruction was input in step S801. Accept selection prompt input. Specifically, for example, the control unit 303 causes the electronic medical questionnaire creation module 3033 to display on the display 241 the contents of the medical questionnaire and the reply to the medical questionnaire of the electronic medical questionnaire 3027 for which the instruction input of the "edit" button is accepted in step S801. , the operator of the terminal device 20 accepts the input of selection instructions such as interview questions that the operator wishes to edit.

Next, in step S803, the control unit 303 receives from the terminal device 20 input of specific edit content for the medical interview question or the like for which selection instruction input was received in step S802. Specifically, for example, the control unit 303 causes the electronic medical questionnaire creation module 3033 to display a pull-down menu for presenting a menu of specific editing contents of the medical interview question for which the selection instruction input is received in step S802. is displayed on the display 241 of the terminal device 20, and a selection instruction input for specific editing contents by the input device 23 of the terminal device 20 is accepted.

Further, in step S804, the control unit 303 performs editing work such as medical interview questions based on the editing content accepted as input in step S803. Specifically, for example, the control unit 303 causes the electronic medical questionnaire creation module 3033 to perform editing work based on the specific editing content for which the selection instruction input was received in step S803.

Furthermore, in step S805, the control unit 303 presents the terminal device 20 with the edited content, which is the result of the editing work performed in step S804. Specifically, for example, the control unit 303 causes the electronic medical questionnaire creation module 3033 to display the result of the editing work performed in step S804 on the display 241 of the terminal device 20 . After that, the electronic medical questionnaire creation module 3033 accepts input of approval of the edited content from the operator of the terminal device 20 via the input device 23 .

Then, in step S806, the control unit 303 corrects the electronic medical questionnaire 3027 according to the edited contents presented in step S805, and stores the corrected electronic medical questionnaire 3027 in the storage unit 302. FIG. Specifically, for example, the control unit 303 causes the electronic medical questionnaire creation module 3033 to modify the electronic medical questionnaire 3027 according to the edited contents of the acceptance input, and stores the corrected electronic medical questionnaire 3027 in the storage unit 302 .

FIG. 9 is a flow chart showing an example of the operation of the terminal device 20. As shown in FIG. FIG. 9 shows an example of the operation of the electronic medical questionnaire data 3026 stored in the storage unit 302 of the server 30 when the operator of the terminal device 20 corrects/adds mainly the contents of the reply to the medical questionnaire by voice input. It is a flow chart.

In step S 900 , the control unit 290 calls the electronic medical questionnaire data 3026 to be corrected/added from the electronic medical questionnaire data 3026 stored in the storage unit 302 of the server 30 . Specifically, for example, the control unit 290 corrects/adds the electronic medical questionnaire data 3026 stored in the storage unit 302 of the server 30 through the electronic medical questionnaire data acquisition unit 295. The electronic medical questionnaire data 3026 is called, and the called electronic medical questionnaire data 3026 is stored in the storage unit 280 as the electronic medical questionnaire data 282 .

Next, in step S901, the control unit 290 causes the display 241 to display the input contents of the electronic medical questionnaire data 282 called up in step S900. Specifically, for example, the control unit 290 causes the electronic medical questionnaire data acquisition unit 295 to display on the display 241 the inquiry items and inquiry reply content, which are the input contents of the electronic medical questionnaire data 282 called in step S900.

Next, in step S902, the control unit 290 accepts from the operator of the terminal device 20 a selection input of a portion to be corrected/added in the input contents of the electronic medical questionnaire data 282 displayed in step S901. Specifically, for example, the control unit 290 causes the correction item specifying unit 297 to select an item desired to be corrected/added from among the input contents of the electronic medical questionnaire data 282 displayed on the display 241 of the terminal device 20. Instruction input is accepted via the input device 23 .

Next, in step S<b>903 , the control unit 290 receives through the microphone 271 of the voice input unit 27 voice input of correction content for the portion to be corrected/added. Specifically, for example, the control unit 290 receives the voice input of the correction content of the portion to be corrected/added by the voice recognition unit 296 via the microphone 271 of the voice input unit 27, and stores it as speech data. Stored in section 280 .

Next, in step S904, the control unit 290 performs speech recognition processing on the utterance data received in step S903, and specifies contents to be corrected/added from the speech recognition result. Specifically, for example, the control unit 290 obtains the speech recognition data 283 by subjecting the speech data received in step S903 to speech recognition processing by the speech recognition unit 296 . Next, based on the speech recognition data 283, the correction item identification unit 297 identifies the contents of the electronic medical questionnaire data 282 to be corrected/added.

In step S905, the control unit 290 presents on the display 241 the speech recognition content, which is the correction content specified in step S904. Specifically, for example, the control unit 290 causes the correction item specifying unit 297 to present the voice recognition content, which is the correction content specified in step S904, on the display 241 .

Then, in step S906, the control unit 290 accepts an input of approval or disapproval from the operator of the terminal device 20 for the correction content (speech recognition content) presented in step S905, and the accepted approval or disapproval input indicates that the approval is accepted. Determines whether it is the input content of Specifically, for example, the control unit 290 causes the correction item specifying unit 297 to confirm the acceptance of the correction content (speech recognition content) presented in step S905 by the operator of the terminal device 20 via the input device 23. It accepts the approval/disapproval input and determines whether or not the accepted approval/disapproval input is the input content to the effect that the approval is accepted. If it is determined that the input is to accept the consent (YES in step S906), the program proceeds to step S907, and if it is determined that the input is not to accept the consent (NO in step S906), the program returns to step S903. , accepts voice input from the operator of the terminal device 20 again.

In step S907, the control unit 290 corrects the content of the electronic medical questionnaire data 282 with the speech recognition content specified in step S904. Specifically, for example, the control unit 290 causes the correction content input unit 298 to correct the content of the electronic medical questionnaire data 282 with the speech recognition content specified in step S904. Thereafter, the electronic medical questionnaire data sending unit 299 sends the corrected electronic medical questionnaire data 282 to the server 30, and the electronic medical questionnaire creation module 3033 of the server 30 receives the electronic medical questionnaire data 282 sent from the terminal device 20. Stored in the storage unit 302 .

After that, in step S908, the control unit 303 of the server 30 imports the electronic medical questionnaire data 3026 corrected and input in step S907 into the electronic medical chart data 3023. FIG. Specifically, for example, the control unit 303 causes the electronic medical record data generation module 3034 to import the electronic medical questionnaire data 3026 sent from the terminal device 20 into the electronic medical record data 3023 .

<4 Screen example>
An example of a screen output to the terminal device 20 will be described below with reference to FIGS. 10 to 18. FIG.

FIG. 10 is a diagram showing an example of a screen displayed on the display 241 of the terminal device 20 when the operator of the terminal device 20 corrects the input items of the electronic medical questionnaire 3027. As shown in FIG.

On the screen 1000 of the display 241 of the terminal device 20, the names 1001 of the electronic medical questionnaires 3027 stored in the storage unit 302 of the server 30 are displayed. Buttons 1002 and 1003 for input are displayed respectively.

The operator of the terminal device 20 performs an operation input such as clicking these buttons 1002 and 1003 using the input device 23 to give an instruction to edit or delete the displayed electronic medical questionnaire 3027 . The screen 1000 also displays a button 1004 for instructing to generate a new electronic medical questionnaire 3027 based on the electronic medical chart template 3024 .

FIG. 11 is a diagram showing an example of a screen displayed on the display 241 of the terminal device 20 when the operator of the terminal device 20 issues an editing instruction in FIG.

On the screen 1100 of the display 241 of the terminal device 20 are displayed the interview questions 1101 of the electronic medical questionnaire 3027 for which the editing instruction has been input in FIG. A check box 1103 is displayed on the left side of the screen of the medical interview question 1101 to instruct selection input of the medical interview question 1101 . Furthermore, buttons 1104 and 1105 for inputting an edit instruction and a deletion instruction for the medical interview question 1101 are displayed on the right side of the screen of the medical interview question 1101, respectively.

The operator of the terminal device 20 inputs a selection instruction by performing an operation input such as clicking a check box 1103 via the input device 23 for the interview question 1101 to be edited, and then presses buttons 1104 and 1105 using the input device 23. By performing an operation input such as clicking , an instruction to edit or delete the selected medical interview question 1101 is given.

FIG. 12 is a diagram showing an example of a screen displayed on the display 241 of the terminal device 20 when the operator of the terminal device 20 issues an editing instruction in FIG.

A screen 1200 of the display 241 of the terminal device 20 displays a pull-down menu 1201 for instructing the specific contents of the editing instruction when the editing instruction is issued. The operator of the terminal device 20 operates the pull-down menu 1201 via the input device 23 to input specific contents of the editing instruction. In FIG. 12, the operator of the terminal device 20 has issued an editing instruction to collect the medical inquiry reply contents associated with the selected medical inquiry question 1101 into a single question answer.

FIG. 13 is a diagram showing an example of a screen displayed on the display 241 of the terminal device 20 when the operator of the terminal device 20 issues an editing instruction in FIG.

On the screen 1300 of the display 241 of the terminal device 20, the inquiry reply content associated with the selected medical inquiry question 1101 has been changed to a free description format due to the editing instruction, and the options for the inquiry reply content have been deleted. is displayed.

FIG. 14 is a diagram showing another example of a screen displayed on the display 241 of the terminal device 20 when the operator of the terminal device 20 issues an editing instruction in FIG.

On the screen 1400 of the display 241 of the terminal device 20, the operator of the terminal device 20 operates the pull-down menu 1401 to set the options of the inquiry reply content associated with the selected medical inquiry question 1101 to the question (interview item). I am giving instructions to edit.

FIG. 15 is a diagram showing an example of a screen displayed on the display 241 of the terminal device 20 when the operator of the terminal device 20 issues an editing instruction in FIG.

On the screen 1500 of the display 241 of the terminal device 20, the inquiry reply contents associated with the selected inquiry question 1101 are changed to the inquiry question by the editing instruction, and the inquiry reply contents are "yes" and "no". is displayed.

FIG. 16 shows a screen when the operator of the terminal device 20 calls the electronic medical questionnaire data 3026 stored in the storage unit 302 of the server 30, and the called content is displayed on the display 241 of the terminal device 20. It is a figure which shows an example.

On the screen 1600 of the display 241 of the terminal device 20, the name 1601 of the called electronic medical questionnaire data 3026, the medical inquiry items 1602, and the medical inquiry reply contents 1603 are displayed.

FIG. 17 shows that the operator of the terminal device 20 inputs voice to the terminal device 20 in order to correct the contents of the electronic medical questionnaire data 3026 shown in FIG. 283 is a diagram showing an example of a screen displayed on the display 241 of the terminal device 20. FIG.

On the screen 1700 of the display 241 of the terminal device 20, an inquiry item 1701 that is the voice recognition data 283 and an inquiry reply content 1702 associated with this inquiry item 1701 are displayed. A number string 1703 for identifying this medical inquiry item 1701 is also displayed in the medical inquiry item 1701 . As shown in FIG. 17, the speech recognition unit 296 and the correction item identification unit 297 have identified from the speech recognition data 283 the portion to be input as the inquiry reply content 1702, and the portion specified as the inquiry reply content 1702 is underlined 1704 .

FIG. 18 is a diagram showing an example of a screen in which the electronic medical questionnaire data 282 corrected/added based on the voice recognition result shown in FIG. 17 is displayed on the display 241 of the terminal device 20. FIG.

On the screen 1600 of the display 241 of the terminal device 20, the identifier 1801 of the medical inquiry item 1802, the medical inquiry item 1802, and the corrected medical inquiry reply content 1803 are displayed.

<5 Effect of one embodiment>
As described in detail above, according to the system 1 of the present embodiment, it is possible to add/modify recorded contents of medical practices such as input electronic medical questionnaires and electronic medical charts by a simple procedure. This point will be described in detail below.

The medical industry is an industry in which mistakes are not tolerated. And in the medical industry, the need for structured data with templates is very high. Structured data can reduce medical errors. It is possible to unify the work flow by using electronic medical record templates.

However, entering structured data into electronic medical records is very time-consuming. For example, at the hospital admission and discharge support center of a certain medical facility, there were about 6 pages of input content, and it took about 20 minutes per patient to instruct which item to enter the content and enter it there. . According to the system 1 according to this embodiment, this task could be reduced to about 5 minutes.

There are three reasons why, until now, inputting structured data using speech recognition has not been used in the field. The first is that the accuracy of speech recognition is not sufficient, the second is that there are easier input methods than voice recognition, and the third is that it is difficult to correct mistakes.

In the system 1 according to the present embodiment, the first problem, that is, the accuracy of speech recognition, is solved by restricting usage scenes, and at the same time, displaying template item names and candidates for the item contents, and inputting I solved it by narrowing down the voice pattern. In the system 1 according to the present disclosure, WER (Word Error Rate) associated with speech recognition is reduced from 6% to approximately 1%.

The second problem is that input by multiple choice questions, which is easier than voice recognition, is performed before voice recognition, and the results are displayed, so that voice recognition can fill in the insufficient parts of the input. Resolved by modifying or adding.

The problem that makes it difficult to correct the third mistake is to display other candidates after input, allow other candidates to be selected, and what kind of voice this input is based on. It is solved by making it easier to check whether the

Furthermore, in order to make the second question more efficient, the input of multiple-choice questions can be reduced by having the patient enter the multiple-choice questions as an electronic medical questionnaire. We were able to reduce the 20 minutes it took for nurses to interview patients to about 15 minutes.

As a result of the above, we were able to halve the time taken from 40 minutes (20 minutes for listening and 20 minutes for input) to 20 minutes. Assuming that a nurse's hourly wage is 2,000 yen, this will double the productivity per person and reduce the cost of one medical facility by about 10 million yen.

Unlike regular questionnaires, the electronic questionnaire is communication with different levels of knowledge, and it is often necessary for people with little medical knowledge to enter medical information in the questionnaire, so we converted it into medical terms. It is necessary to write it in the medical record in the form, and there are many misunderstandings by the patient, and the input is often corrected. Therefore, correcting the initial input of the electronic medical questionnaire by using voice recognition is more effective.

<6 Notes>
It should be noted that the above-described embodiments describe the configurations in detail in order to explain the present disclosure in an easy-to-understand manner, and are not necessarily limited to those having all the described configurations. Also, part of the configuration of each embodiment can be added, deleted, or replaced with another configuration.

As an example, in the above-described embodiment, the electronic medical questionnaire data was corrected/added by voice recognition. good.

Further, each of the above configurations, functions, processing units, processing means, and the like may be realized by hardware, for example, by designing them in an integrated circuit. The present invention can also be implemented by software program code that implements the functions of the embodiments. In this case, a computer is provided with a storage medium recording the program code, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiments, and the program code itself and the storage medium storing it constitute the present invention. Storage media for supplying such program codes include, for example, flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tapes, and non-volatile memory cards. , ROM, etc. are used.

Also, the program code that implements the functions described in this embodiment can be implemented in a wide range of programs or script languages, such as assembler, C/C++, perl, Shell, PHP, and Java (registered trademark).

Furthermore, by distributing the program code of the software that implements the functions of the embodiment via a network, it can be stored in storage means such as a hard disk or memory of a computer, or in a storage medium such as a CD-RW or CD-R. Alternatively, a processor provided in the computer may read and execute the program code stored in the storage means or the storage medium.

The items described in the above embodiments will be added below.

(Appendix 1)
A program for operating a computer comprising a processor and a memory, wherein structured data of an electronic medical chart template is stored in the memory, and the structured data is associated with input items and input contents of the electronic medical chart template. The program is data, and the program instructs the processor to perform a first step of accepting an input of input contents for an input item from a first user; A second step of receiving input of speech data for correcting the structured data of , and a third step of specifying the content of the electronic medical chart template that is desired to be corrected based on the input items of the electronic medical chart template included in the speech data. A program that causes a step to be performed.
(Appendix 2)
A program for operating a computer comprising a processor and a memory, wherein structured data of an electronic medical questionnaire is stored in the memory, and the structured data includes questionnaire items, questionnaire response contents, and questionnaire questions of the electronic medical questionnaire. a fourth step of receiving input of questionnaire responses to the questionnaire items using the questionnaire from the first user; a fifth step of accepting input of utterance data for correcting the content of the response to the inquiry received from the first user; A program for executing a sixth step of specifying an interview item.
(Appendix 3)
2. The program according to appendix 1 or appendix 2, wherein a plurality of words are associated with one inquiry item or input item.
(Appendix 4)
The program according to appendix 3, wherein the memory stores a synonym dictionary of technical terms, and in the third step or the sixth step, the synonym dictionary is used to specify the content of the interview item or the electronic medical record template that you want to modify. .
(Appendix 5)
The program further instructs the processor to accept the input of speech data for the content of the electronic medical record template specified in the third step or the sixth step, or the inquiry response content corresponding to the inquiry item, and perform voice recognition of the accepted speech data. A seventh step of acquiring voice recognition data and specifying correction content desired to be corrected or added based on the voice recognition data; The program according to appendix 1 or appendix 2, causing execution of the eighth step of performing at least one of
(Appendix 6)
In a fifth step, accepting a selection input as to whether to correct or add the content of the electronic medical record template or the content of the response to the medical inquiry, and based on the accepted selection input, the addition of either the correction or the addition of the content of the medical inquiry response. 5. The program according to 5.
(Appendix 7)
In a seventh step, based on the utterance data from the second user, from the continuity of the utterance data, one candidate for the response to the inquiry is specified from among the candidates for the input item or the inquiry item, and the input item or the inquiry item is specified. The program according to Supplementary Note 5, for inputting data for performing and inputting data for specifying the content of the electronic medical record template or the content of the correction of the response to the medical inquiry.
(Appendix 8)
In step 7, a combination of an input item that is a noun and a particle connected to this input item, or a combination of an inquiry item that is a noun and a particle that is connected to this inquiry item is specified from the speech recognition data, and these inputs are specified. Supplementary notes for inputting data for specifying input items or interview items and for specifying correction contents of electronic medical record templates or interview response contents based on combinations of items or interview items and particles 7. The program according to 7.
(Appendix 9)
In a seventh step, storing utterance data or speech recognition data in a memory, and accepting input for associating the correction of the input item or question reply content with a different input item or question reply candidate based on the speech recognition data; 6. The program of Claim 5 that accepts input specifying the content of the electronic medical record template or the content of the questionnaire response from the candidates.
(Appendix 10)
The speech recognition data includes notations and readings associated with them, and in a seventh step, based on the readings, candidate answers to the questionnaire associated with the inquiry item are searched to obtain candidates for notations, and among the candidates 7. The program of Claim 6 that accepts input of specific input or inquiry selected from.
(Appendix 11)
In the structured data of the electronic medical questionnaire, each questionnaire item is associated with an identifier for identifying each individual questionnaire item. 5. The program according to appendix 5, for specifying a candidate for reply content to medical inquiry, inputting data for specifying a question item, and inputting data for specifying correction content of reply content for medical inquiry.
(Appendix 12)
The structured data of the electronic medical questionnaire has information on the types of words and/or characters that can be entered in the medical questionnaire response content. 6. The program of Claim 5 for data entry.
(Appendix 13)
In the structured data of the electronic medical questionnaire, the question reply content corresponding to the question item includes options, and in the seventh step, if the question reply content is an option, the speech recognition data corresponding to the question reply content is a character representing the choice In the case of data, the program according to appendix 5 for inputting data for specifying correction contents of inquiry response contents by options corresponding to character data.
(Appendix 14)
The structured data of the electronic medical questionnaire includes candidates for the interview response content corresponding to the interview item, and presents the candidate for the interview response content based on the candidate for the interview response content specified in the sixth step. program as described.
(Appendix 15)
The memory stores a plurality of speech recognition engines corresponding to the inquiry items, and in the seventh step, at least one voice of the speech recognition engines is recognized based on the candidates for the inquiry reply content specified in the sixth step. 6. The program of Clause 5 for selecting a recognition engine.
(Appendix 16)
If the utterance data contains at least one of a plurality of inquiry items and inquiry response contents, and in the seventh step, if the voice recognition data contains a word indicating the delimitation of the inquiry item and inquiry response contents, this word is 6. The program according to Supplementary Note 5, which recognizes and specifies correction contents for at least one of a plurality of inquiry items and inquiry response contents.
(Appendix 17)
In the seventh step, having a plurality of input items related to the inquiry item, an evaluation function for evaluating whether it is possible to input to each input item, and a word or character using morphological analysis or maximum length match etc. 5. The program according to appendix 5, having a function of identifying a string and determining a word or character string determined to be possible by the evaluation function as the input content of each item.
(Appendix 18)
3. The program according to appendix 1, wherein in the third step, the content or question items are specified by the input content obtained by anonymizing or modifying the personal information included in the input content.
(Appendix 19)
The memory stores the input contents associated with the input items, and in the seventh step, the personal information included in the input contents is anonymized or modified to generate inquiry reply contents, and the generated inquiry reply contents are also included. 16. The program according to Supplementary Note 15, which creates speech data and performs speech recognition using a learning model learned based on the speech data and the content of the response to the inquiry.
(Appendix 20)
6. The program according to appendix 5, wherein the inquiry items are associated with the input items of the electronic medical record.
(Appendix 21)
16. The program according to appendix 15, wherein the program further causes the processor to execute a ninth step of incorporating, into the input contents of the electronic medical record, the contents of the response to the inquiry that have been corrected and/or added in the eighth step.
(Appendix 22)
An information processing device comprising a processor and a memory, wherein structured data of an electronic medical chart template is stored in the memory, the structured data being data in which input items and input contents of the electronic medical chart are associated, The program instructs the processor to perform a first step of accepting an input of input content for an input item from a first user, and input structured data of an electronic medical record template from the first user or a second user different from the first user. and a third step of specifying the content of the electronic medical record template to be corrected based on the input items of the electronic medical record template included in the utterance data. information processing device.
(Appendix 23)
An information processing device comprising a processor and a memory, wherein structured data of an electronic medical questionnaire is stored in the memory, and the structured data is data in which the questionnaire items of the electronic medical questionnaire and the questionnaire contents are associated with each other. , the processor performs a first step of receiving input from a first user of an inquiry response content for an inquiry item, and a second user different from the first user, receiving an inquiry response content received from the first user. information for performing a second step of accepting input of speech data for correction and a third step of identifying interview items that the second user wishes to correct based on technical terms contained in the speech data; processing equipment.
(Appendix 24)
A computer-implemented method comprising a processor and memory, wherein the memory stores structured data of an electronic medical record template, the structured data being data associated with electronic medical record entries and entries. and the program instructs the processor to perform a first step of accepting an input of input content for an input item from a first user, and input of an electronic medical record template from the first user or a second user different from the first user. A second step of receiving an input of speech data for modifying structured data; a third step of specifying the contents of an electronic medical record template to be modified based on input items of the electronic medical record template included in the speech data. How to perform and
(Appendix 25)
A computer-implemented method comprising a processor and memory, wherein structured data of an electronic medical questionnaire is stored in the memory, and the structured data is associated with questionnaire items and questionnaire contents of the electronic medical questionnaire. The processor performs a first step of receiving input from a first user of an inquiry response content to an inquiry item, and a second user different from the first user, receiving an inquiry from the first user. Execute a second step of receiving input of speech data for correcting the content of the reply, and a third step of specifying the interview item that the second user wishes to correct based on the technical terms included in the speech data. how to.
(Appendix 26)
A memory storing structured data of an electronic medical chart template, wherein the structured data is data in which input items and input contents of the electronic medical chart are associated with each other; means for receiving input of content; means for receiving input of speech data for modifying structured data of the electronic medical record template from the first user or a second user different from the first user; and means for specifying the content of the electronic medical chart template that is desired to be modified based on the electronic medical chart template input items included.
(Appendix 27)
A memory in which structured data of an electronic medical questionnaire is stored, wherein the structured data is data in which questionnaire items and questionnaire contents of the electronic medical questionnaire are associated with each other; Means for accepting input of inquiry response content, means for accepting input of utterance data for correcting the inquiry response content received from the first user from a second user different from the first user, and utterance data and means for identifying questionnaires that the second user wishes to modify based on the terminology contained therein.

DESCRIPTION OF SYMBOLS 1... Electronic chart system 10, 20... Terminal device 15... Memory 16... Storage part 19... Processor 25... Memory 26... Storage 29... Processor 30... Server 35... Memory 36... Storage 39... Processor 180, 280, 302... Storage part 181, 281, 3021... Application program 182, 282, 3026... Electronic medical questionnaire data 190, 290, 303... Control unit 195... Electronic medical questionnaire input unit 196... Electronic medical questionnaire data sending unit 283... Voice recognition data 284... Technical terms Data 285: Teacher data 286: Learning model 295: Electronic medical questionnaire data acquisition unit 296: Voice recognition unit 297: Correction item identification unit 298: Correction content input unit 299: Electronic medical questionnaire data transmission unit 3022: Electronic medical record DB 3023: Electronic Chart data 3024 Electronic chart template 3025 Electronic medical questionnaire DB 3027 Electronic medical questionnaire 3033 Electronic medical questionnaire creation module 3034 Electronic medical chart data generation module

Claims (20)

A program for operating a computer comprising a processor and a memory,
Structured data of an electronic medical questionnaire is stored in the memory, and the structured data is data in which questionnaire items, questionnaire responses, and questionnaires of the electronic medical questionnaire are associated,
The program causes the processor to:
a fourth step of accepting an input of the inquiry response content for the inquiry item using the inquiry question from the first user;
Input of utterance data is received from the first user or a second user different from the first user , and the utterance data contains corrections or additions to the inquiry/response content received from the first user. a fifth step including the contents and the interview items ;
a sixth step of specifying the inquiry item that the first user or the second user wishes to modify, based on the inquiry item included in the speech recognition data obtained by recognizing the speech data ;
6. Identifying correction content for which correction or addition is desired for the inquiry response content corresponding to the inquiry item specified in the sixth step, based on the voice recognition data; 7 steps and
an eighth step of performing at least one of correction and addition of the inquiry response content with the correction content specified in the seventh step;
The program that causes the to run. 2. The program according to claim 1 , wherein a plurality of words are associated with one medical question item . The memory stores a synonym dictionary of technical terms,
3. The program according to claim 2, wherein, in said sixth step , the content of said inquiry item desired to be corrected is specified using said synonym dictionary. 2. In the fifth step, receiving a selection input as to whether to correct or add the content of the reply to the inquiry, and based on the accepted selection input, correct or add the content of the reply to the inquiry . program described in . In the seventh step, based on the utterance data from the first user or the second user, one candidate for the inquiry reply content is specified from the plurality of candidates for the inquiry item from the continuity of the utterance data. 2. The program according to claim 1 , further comprising inputting data for specifying the question item and inputting data for specifying the correction content of the response to the question. In the sixth step and the seventh step, from the speech recognition data , identify a combination of the interview item that is a noun and a particle connected to the interview item, and based on the combination of the interview item and the particle, 6. The program according to claim 5 , for inputting data for specifying the inquiry item and inputting data for specifying the correction content of the response to the inquiry. In the seventh step, storing the utterance data or the speech recognition data in the memory, and receiving an input for associating the modified content of the inquiry response with a different candidate for the inquiry response based on the speech recognition data. 2. The program according to claim 1 , accepting an input specifying said inquiry response content from said candidates. the speech recognition data includes notations and associated readings;
In the sixth step and the seventh step, based on the reading, candidates for the inquiry reply content associated with the inquiry item are searched to acquire candidates for the notation, and a selection is made from among the candidates. 5. The program according to claim 4 , which accepts input of the question reply content specified by the In the structured data of the electronic medical questionnaire, the medical questionnaire items are associated with identifiers for identifying individual medical questionnaire items,
In the sixth step and the seventh step, by using the identifier included in the speech recognition data, one candidate for the inquiry response content is specified from a plurality of candidates for the inquiry item, and the inquiry item is specified. 2. The program according to claim 1 , for inputting data and inputting data for specifying correction contents of said inquiry reply contents. The structured data of the electronic medical questionnaire has information on the types of words and/or characters that can be entered in the medical questionnaire response content,
2. The program according to claim 1 , wherein, in said seventh step, data input for specifying said correction contents of said inquiry response contents is performed based on said information. In the structured data of the electronic medical questionnaire, the questionnaire response content corresponding to the questionnaire item includes options,
In the seventh step, when the inquiry response content is the option, and if the voice recognition data corresponding to the inquiry response content is character data representing the option, the inquiry is performed by the option corresponding to the character data. 2. The program according to claim 1 , which performs data input for specifying the content of correction of the reply content. In the structured data of the electronic medical questionnaire, including candidates for the interview response content corresponding to the interview item,
2. The program according to claim 1 , wherein, in said seventh step, the candidates for the reply contents to the inquiry are presented based on the specified candidates for the reply contents to the inquiry. the memory stores a plurality of speech recognition engines corresponding to the medical inquiry items;
2. The program according to claim 1 , wherein at least one speech recognition engine is selected from among the speech recognition engines based on the candidates for the question reply contents specified in the seventh step. The utterance data includes at least one of a plurality of the inquiry items and the inquiry response contents, and
In the sixth step and the seventh step, if the speech recognition data includes a word indicating the delimitation of the inquiry item and the reply contents of the inquiry, the word is recognized and a plurality of the inquiry items and the inquiry are obtained. 2. The program according to claim 1 , wherein said correction content is specified for at least one of the reply content. In the sixth step, having a plurality of input items related to the inquiry item, an evaluation function for evaluating whether or not each input item can be input, and the inquiry response content using morphological analysis or maximum length matching. 2. The program according to claim 1 , having a function of identifying a word or character string by using the evaluation function, and determining the word or character string determined to be possible by the evaluation function as the input content of each item. 2. The program according to claim 1 , wherein said inquiry items are associated with input items of an electronic medical chart. The program further instructs the processor to:
17. The program according to claim 16 , causing execution of a ninth step of importing into the input contents of the electronic medical record the contents of the reply to the medical inquiry that have been corrected and/or added in the eighth step. An information processing device comprising a processor and a memory,
Structured data of an electronic medical questionnaire is stored in the memory, and the structured data is data in which questionnaire items, questionnaire responses , and questionnaires of the electronic medical questionnaire are associated,
The processor
a fourth step of accepting an input of the inquiry response content for the inquiry item using the inquiry question from the first user;
Input of utterance data is received from the first user or a second user different from the first user , and the utterance data contains corrections or additions to the inquiry/response content received from the first user. a fifth step including the contents and the interview items ;
a sixth step of specifying the inquiry item that the first user or the second user wishes to modify, based on the inquiry item included in the speech recognition data obtained by recognizing the speech data ;
6. Identifying correction content for which correction or addition is desired for the inquiry response content corresponding to the inquiry item specified in the sixth step, based on the voice recognition data; 7 steps and
an eighth step of performing at least one of correction and addition of the inquiry response content with the correction content specified in the seventh step;
An information processing device that executes A computer implemented method comprising a processor and memory, comprising:
Structured data of an electronic medical questionnaire is stored in the memory, and the structured data is data in which questionnaire items, questionnaire responses , and questionnaires of the electronic medical questionnaire are associated,
The processor
a fourth step of accepting an input of the inquiry response content for the inquiry item using the inquiry question from the first user;
Input of utterance data is received from the first user or a second user different from the first user , and the utterance data contains corrections or additions to the inquiry/response content received from the first user. a fifth step including the contents and the interview items ;
a sixth step of specifying the inquiry item that the first user or the second user wishes to modify, based on the inquiry item included in the speech recognition data obtained by recognizing the speech data ;
6. Identifying correction content for which correction or addition is desired for the inquiry response content corresponding to the inquiry item specified in the sixth step, based on the voice recognition data; 7 steps and
an eighth step of performing at least one of correction and addition of the inquiry response content with the correction content specified in the seventh step;
how to run a memory storing structured data of an electronic medical questionnaire, wherein the structured data is data in which questionnaire items, questionnaire responses , and questionnaires of the electronic medical questionnaire are associated;
means for receiving an input of the inquiry response content to the inquiry item using the inquiry question from the first user;
Input of utterance data is received from the first user or a second user different from the first user , and the utterance data contains corrections or additions to the inquiry/response content received from the first user. a means including the content and the interview items ;
means for specifying the inquiry item that the first user or the second user wishes to modify, based on the inquiry item included in the speech recognition data obtained by recognizing the speech data ;
With regard to the inquiry response content corresponding to the inquiry item specified by the inquiry item specifying means, correction content desired to be corrected or added to the inquiry response content corresponding to the inquiry item based on the voice recognition data. a means to identify;
means for at least one of correcting and adding to the inquiry response content with the correction content specified by the correction content specifying means;
A system comprising:

Images