JP2023003649A - Information processing device and program - Google Patents

Abstract

To reduce the risk of inappropriate prescription of medicines.SOLUTION: A prescription confirmation device 3 includes: a character information acquisition unit 311 which acquires medicine character information JP [1] showing a medicine name character string LM [1] and a prescription content character string LN [1] from a prescription reader 1 which recognizes a character string representing a name of a medicine Md [1] described in a prescription as the medicine name character string LM [1] and recognizes a character string representing a prescription content of the medicine Md [1] described in the prescription as the prescription content character string LN [1]; a medicine information acquisition unit 312 which acquires medicine information JY related to the medicine name character string LM [1] as specific medicine information from a medicine database server 7 storing a plurality of pieces of the medicine information JY corresponding to a plurality of medicines which may be described in the prescription; a prescription content determination unit 313 which determines whether or not the prescription content of the medicine Md [1] represented by the prescription content character string LN [1] meets a method of use of the medicine shown by the specific medicine information; and a determination result output unit 314 which outputs information based on a result of determination by the prescription content determination unit 313.SELECTED DRAWING: Figure 2

Description

The present invention relates to an information processing device and a program.

A technique for recognizing a character string written in a prescription by character recognition processing for recognizing characters included in an image has been proposed (see, for example, Patent Document 1).

Japanese Patent Application Laid-Open No. 2006-120020

However, with the conventional technology, there is a risk that the character string written in the prescription is erroneously recognized and a drug is prescribed according to the erroneously recognized character string.

The present invention has been made in view of the circumstances described above, and aims to provide a technique that can reduce the risk of inappropriate prescription of drugs compared to conventional techniques. be one.

In order to solve the above problems, an information processing apparatus according to a first aspect of the present invention provides a character string indicating the name of a first drug described in a prescription by character recognition processing that recognizes characters included in an image. is recognized as a first name character string, and the first name character string and the first From a character information acquisition unit that acquires first character information indicating a content character string, and a storage unit that stores a plurality of drug information corresponding to a plurality of drugs that may be described in the prescription, the first name character A drug information acquisition unit that acquires drug information related to the column as specific drug information, and the prescription content of the first drug indicated by the first content character string matches the usage of the drug indicated by the specific drug information. and an output unit for outputting information based on the result of determination by the determination unit.

Further, an information processing apparatus according to a second aspect of the present invention includes an image information acquisition unit that acquires image information showing an image of a prescription, and a name of the first drug described in the prescription based on the image information. a character string indicating as a first name character string, and a character string indicating the content of the prescription of the first drug described in the prescription as a first content character string; a drug information acquisition unit that acquires, as specific drug information, drug information related to the first name character string from a storage unit that stores a plurality of drug information corresponding to a plurality of drugs that are likely to be used; 1 A determination unit that determines whether or not the prescription content of the first drug indicated by the content character string conforms to the method of use of the drug indicated by the specific drug information, and outputs information based on the result of the determination by the determination unit. and an output unit for outputting.

Further, the program according to the third aspect of the present invention causes the processor to convert a character string indicating the name of the first drug described in the prescription into the first name character string by character recognition processing that recognizes characters included in the image. and recognizes the first name character string and the first content character string from the recognition unit that recognizes the character string indicating the prescription content of the first drug described in the prescription as the first content character string. Drug information related to the first name character string is obtained from a character information acquisition unit that acquires single-character information and a storage unit that stores a plurality of drug information corresponding to a plurality of drugs that may be described in the prescription. as specific drug information, and determines whether or not the prescription content of the first drug indicated by the first content character string conforms to the method of use of the drug indicated by the specific drug information. It is characterized by functioning as a determination unit and an output unit that outputs information based on the result of determination by the determination unit.

Further, a program according to a fourth aspect of the present invention comprises an image information acquisition unit configured to acquire image information showing an image of a prescription, and a name of a first drug described in the prescription based on the image information. a character string indicating as a first name character string, and a character string indicating the content of the prescription of the first drug described in the prescription as a first content character string; a drug information acquisition unit that acquires, as specific drug information, drug information related to the first name character string from a storage unit that stores a plurality of drug information corresponding to a plurality of drugs that are likely to be used; 1 A determination unit that determines whether or not the prescription content of the first drug indicated by the content character string conforms to the method of use of the drug indicated by the specific drug information, and outputs information based on the result of the determination by the determination unit. It is characterized by functioning as an output unit for

ADVANTAGE OF THE INVENTION According to this invention, compared with a conventional technique, it becomes possible to reduce the risk of an inappropriate drug being prescribed.

BRIEF DESCRIPTION OF THE DRAWINGS It is explanatory drawing which shows an example of the outline|summary of the prescription recognition system Sys which concerns on embodiment of this invention. 4 is a sequence chart showing an example of an overview of operations of the prescription recognition system Sys. It is an explanatory view showing an example of an outline of a prescription image GS. FIG. 4 is an explanatory diagram showing an example of an overview of a prescription content display image GH; 1 is a block diagram showing an example of a configuration of a prescription reading device 1; FIG. It is a block diagram which shows an example of the hardware constitutions of the prescription reading device 1. FIG. 2 is a block diagram showing an example of the configuration of a prescription confirmation device 3; FIG. It is a block diagram which shows an example of the hardware constitutions of the prescription confirmation apparatus 3. 2 is a block diagram showing an example of the configuration of a drug database server 7; FIG. 3 is a block diagram showing an example of a hardware configuration of a drug database server 7; FIG. FIG. 4 is a diagram showing an example of the data structure of prescription information JSS; It is a figure which shows an example of a data structure of prescription character information JS. It is a figure which shows an example of a data structure of drug list information table TBL7. 4 is a flow chart showing an example of the operation of the prescription confirmation device 3; 4 is a flow chart showing an example of the operation of the prescription confirmation device 3; 4 is a flow chart showing an example of the operation of the prescription confirmation device 3; 4 is a flow chart showing an example of the operation of the prescription confirmation device 3; FIG. 10 is an explanatory diagram showing an example of an outline of a prescription recognition system Sys-B according to modification 1; It is a block diagram which shows an example of a structure of prescription confirmation apparatus 3B. FIG. 20 is an explanatory diagram showing an example of an overview of a prescription recognition system Sys-C according to Modification 4; 4 is a sequence chart showing an example of the outline of the operation of the prescription recognition system Sys-C; It is a block diagram which shows an example of a structure of 1 C of prescription reading apparatuses. 2 is a block diagram showing an example of the configuration of a character recognition device 9; FIG. 3 is a block diagram showing an example of the hardware configuration of the character recognition device 9; FIG. FIG. 21 is an explanatory diagram showing an example of an outline of a prescription content display image GH according to Modification 7;

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. In each drawing, the dimensions and scale of each part are appropriately different from the actual ones. In addition, since the embodiments described below are preferred specific examples of the present invention, they are subject to various technically preferable limitations. It is not limited to these forms unless stated otherwise.

[A. embodiment]
Embodiments of the present invention will be described below.

<1. Overview of Prescription Recognition System>
FIG. 1 is an explanatory diagram for explaining an example of the configuration of the prescription recognition system Sys according to this embodiment. An overview of the prescription recognition system Sys will be described below with reference to FIG.

As illustrated in FIG. 1, the prescription recognition system Sys includes a prescription reading device 1, a prescription confirmation device 3, a terminal device 5, and a drug database server 7.

Among them, the prescription reading device 1 recognizes the characters written on the prescription issued by the doctor. Also, the prescription confirmation device 3 (an example of an “information processing device”) confirms the recognition result of the prescription reading device 1 . The terminal device 5 also has a display unit 50 on which the confirmation result of the prescription confirmation device 3 is displayed. In this embodiment, as an example, the terminal device 5 is connected to the prescription confirmation device 3 via the network NW, but the present invention is not limited to such an aspect. Absent. The terminal device 5 may be directly connected to the prescription confirmation device 3 . Further, the drug database server 7 can communicate with the prescription confirmation device 3 via the network NW, and provides various information to the prescription confirmation device 3 in response to requests from the prescription confirmation device 3 .

In this way, the prescription recognition system Sys, for example, in the prescription reading device 1, recognizes the content of the prescription issued by the doctor, and in the prescription confirmation device 3, the recognition result of the prescription by the prescription reading device 1 is the appropriate content After confirming whether or not it is, the terminal device 5 presents the recognition result of the description content of the prescription to the pharmacist or the like. Hereinafter, the process of recognizing the written contents of the prescription and confirming the written contents of the prescription by the prescription recognition system Sys is referred to as a prescription confirmation process.

<2. Operation of Prescription Recognition System>
An example of the outline of the operation of the prescription recognition system Sys when the prescription recognition system Sys performs prescription confirmation processing will be described below with reference to FIGS. 2 to 4. FIG.

FIG. 2 is a sequence chart showing an example of the outline of the operation of the prescription recognition system Sys when the prescription recognition system Sys performs prescription confirmation processing.

As illustrated in FIG. 2, when the prescription confirmation process is started, first, the prescription reading device 1 executes a prescription imaging process (S1). Here, the prescription imaging process is a process of imaging a prescription issued by a doctor and generating prescription image information JGS indicating a prescription image GS obtained as a result of the imaging.

FIG. 3 is an explanatory diagram showing an example of a prescription image GS.

As illustrated in FIG. 3, the prescription image GS includes a plurality of writing areas A. As shown in FIG. Specifically, the prescription image GS includes a description area A1 describing information about public expenditure, a description area A2 describing information about insurance, a description area A3 describing information about patients, and a description area A3 describing information about medical institutions. It includes a description area A4 in which information is described and a description area A5 in which information about the drug to be prescribed is described. Each writing area A includes one or more writing fields. Each description column includes an item name KM that is the name of the item described in the description column, and description content KS described in the description column. Here, the description content KS is written by the doctor, for example, at the timing when the doctor prescribes the drug to the patient. Also, the item name KM is a name predetermined by, for example, the Medical Practitioners Act.
In this embodiment, prescriptions that can be handled by the prescription recognition system Sys are not limited to prescriptions having the format represented by the prescription image GS illustrated in FIG. In this embodiment, the prescription recognition system Sys can handle any prescription having a format stipulated by the Medical Practitioners Act or the like.

As exemplified in FIG. 3, in the description area A5, information regarding the drug prescribed by the doctor is described. Specifically, the description area A5 includes the description content KS related to the name of the drug prescribed by the doctor (hereinafter referred to as the description name AM) and the description content KS related to the dose of the drug prescribed by the doctor (hereinafter referred to as the description dose AQ), and description contents KS (hereinafter referred to as description period AR) relating to the period of taking the drug prescribed by the doctor.

Note that when a doctor prescribes a plurality of types of drugs, as shown in FIG. A plurality of described doses AQ corresponding one-to-one with the types of drugs and a plurality of described periods AR corresponding one-to-one with the plurality of types of drugs are described. In this embodiment, it is assumed that there are M types of drugs prescribed by a doctor. Here, the value M is a natural number of 1 or more. Also, hereinafter, the m-th drug among the M types of drugs prescribed by the doctor may be referred to as drug Md[m]. Here, the variable m is a natural number that satisfies 1≤m≤M. Further, hereinafter, the description name AM corresponding to the drug Md[m] is referred to as the description name AM[m], the description dose AQ corresponding to the drug Md[m] is referred to as the description dose AQ[m], and the drug A description period AR corresponding to Md[m] is referred to as a description period AR[m]. Also, hereinafter, the description including the described dose AQ[m] and the described period AR[m] may be referred to as the described usage AN[m].

Note that FIG. 3 illustrates the case of M=3. That is, FIG. 3 illustrates a case where a doctor prescribes three types of drugs. In FIG. 3, among the three drugs Md[1] to Md[3] prescribed by the doctor, the description name AM[1] corresponding to the drug Md[1] is "Vitamin AAA 100 mg", The stated dose AQ[1] corresponding to the drug Md[1] is "three tablets per dose, three times a day", and the stated period AR[1] corresponding to the drug Md[1] is "10 days" and the listed name AM [2] corresponding to the drug Md [2] is "Mineral BBB 150 mg", and the listed dose AQ [2] corresponding to the drug Md [2] is "1 tablet per day 3 times", the description period AR [2] corresponding to the drug Md [2] is "10 days", and the description name AM [3] corresponding to the drug Md [2] is "calcium CCC 50 mg ", the stated dose AQ [3] corresponding to the drug Md [2] is "7 tablets per dose, 7 times a day", and the stated period AR [3] corresponding to the drug Md [2] is " 70 days" is exemplified.

Returning the description to FIG.
As illustrated in FIG. 2, the prescription reading device 1 executes character recognition processing after executing the prescription imaging processing in step S1 (S2). Here, the character recognition process is a process of recognizing characters included in the prescription image GS indicated by the prescription image information JGS generated in the prescription imaging process of step S1 and generating prescription character information JS indicating the recognition result. .

The prescription character information JS consists of drug name character information JM[1] to JM[M], prescription dose character information JQ[1] to JQ[M], and prescription period character information JR[1] to JR[M]. ] and (see FIGS. 4 and 12 to be described later).
Here, the drug name character information JM[m] indicates the drug name character string LM[m], which is the recognition result of the description name AM[m] related to the drug Md[m] prescribed by the doctor in the prescription image GS. Information. Further, the prescribed dose character information JQ[m] is information indicating a prescribed dose character string LQ[m], which is the recognition result of the written dose AQ[m] related to the drug Md[m] prescribed by the doctor in the prescription image GS. is. Further, the prescription period character information JR[m] is information indicating the prescription period character string LR[m], which is the recognition result of the description period AR[m] regarding the drug Md[m] prescribed by the doctor in the prescription image GS. is.
Hereinafter, the information consisting of the prescription amount text information JQ[m] and the prescription period text information JR[m] may be referred to as prescription content text information JN[m]. Moreover, below, the character string which prescription content character information JN[m] shows may be called a prescription content character string LN[m]. Further, hereinafter, the information composed of the drug name text information JM[m] and the prescription content text information JN[m] may be referred to as drug text information JP[m]. As is clear from the above description, the prescription text information JS includes drug text information JP[1] to JP[M].

As illustrated in FIG. 2, the prescription reading device 1 transmits the prescription character information JS generated in step S2 to the prescription checking device 3 (S3).

Next, the prescription confirmation device 3 acquires the prescription text information JS transmitted from the prescription reading device 1 in step S3, and the drug name text information JM[1] to JM[M included in the acquired prescription text information JS. ] is transmitted to the drug database server 7 (S4).

The drug database server 7 stores a plurality of drug information JY corresponding to one-to-one with a plurality of types of drugs that may be described in a prescription. Here, "multiple types of drugs that may be described in a prescription" may be, for example, all types of drugs that actually exist in the world, or all types of drugs available in Japan. It may be a drug or any kind of drug that may be prescribed by the medical institution to which the doctor who issued the prescription belongs.
Then, when the medicine database server 7 acquires the medicine name text information JM[1] to JM[M] read by the prescription reading device 1, one or a plurality of medicines corresponding to each medicine name text information JM[m] is stored. The information JY is transmitted to the prescription confirmation device 3 (S5).

Although the details will be described later with reference to FIG. 13, the drug information JY includes drug name information JYM regarding the name of the drug, drug usage information JYS regarding the method of using the drug, and concomitant drug information JYH regarding contraindicated drugs. ,including.
Here, the drug name information JYM is information indicating the drug name YM, which is the name of the drug corresponding to the drug information JY. The drug usage information JYS is information indicating the usage of a drug corresponding to the drug information JY. and upper limit period information JYR that indicates an upper limit period YR that is the upper limit value of . Further, the concomitant drug information JYH includes contraindicated drug information JYK indicating the drug ID of the contraindicated drug YK for the drug corresponding to the drug information JY, and concomitant drug information JYK indicating the drug ID of the caution drug YC for concomitant use of the drug corresponding to the drug information JY. Including caution drug information JYC.

As illustrated in FIG. 2, the prescription confirmation device 3 acquires one or more pieces of drug information JY transmitted from the drug database server 7 in step S5. In addition, below, the drug information JY transmitted from the drug database server 7 in step S5 may be referred to as "specific drug information".

Then, when the prescription confirmation device 3 acquires one or a plurality of drug information JY corresponding to the drug name text information JM[1] to JM[M] from the drug database server 7, it executes dose determination processing (S6). .
Here, the dose determination process (an example of the "first determination process") means that the prescribed dose of the drug recognized from the prescription in the character recognition process (S2) is stored in the drug information JY acquired from the drug database server 7. This is a process of judging whether or not it is appropriate in light of the indicated upper dose limit YQ. Specifically, in the dose determination process of step S6, the prescription confirmation device 3 determines that the prescription dose character string LQ[m] included in the prescription character information JS generated in the character recognition process (S2) is It is determined whether or not the drug information JY obtained from the above represents a dose equal to or lower than the upper limit dose YQ indicated by the drug information JY.

Further, when the prescription confirmation device 3 acquires one or a plurality of drug information JY corresponding to the drug name text information JM[1] to JM[M] from the drug database server 7, the prescription confirmation device 3 executes period determination processing (S7). .
Here, the period determination process determines whether or not the prescription period of the drug recognized from the prescription in the character recognition process is appropriate in light of the upper limit period YR indicated by the drug information JY acquired from the drug database server 7. processing. Specifically, the prescription confirmation device 3 obtains the prescription period character string LR[m] included in the prescription character information JS generated in the character recognition process from the drug database server 7 in the dose determination process in step S6. It is determined whether or not the period is equal to or less than the upper limit period YR indicated by the drug information JY.

Further, when the prescription confirmation device 3 acquires one or a plurality of drug information JY corresponding to the drug name text information JM[1] to JM[M] from the drug database server 7, the prescription confirmation device 3 executes the combination determination process (S8). .
Here, the combined use determination process (an example of the "second determination process") means that, when a plurality of drugs are described in the prescription, the combination of the multiple drugs described in the prescription is determined by the drug database server. This is a process of judging whether or not it is appropriate in light of the concomitant drug information JYH indicated by the drug information JY acquired from 7. Specifically, in the combination determination process in step S7, the prescription confirmation device 3 confirms that the combination of a plurality of drugs that are contraindicated in combination is not included in the plurality of drugs described in the prescription, and It is determined that a combination of a plurality of drugs that should be used in combination is not included in the plurality of drugs described in the prescription.

Then, the prescription confirmation device 3 executes the dosage determination process (S6), the period determination process (S7), and the combination determination process (S8), and then executes the prescription content display process (S9).
Here, the prescription content display processing is processing for displaying a prescription content display image GH on the display unit 50 . Specifically, in the prescription content display process of step S8, the prescription confirmation device 3 performs the prescription character information JS generated in the character recognition process (S2), the determination result in the dose determination process (S6), and the period determination process ( Display image information JGH indicating the prescription content display image GH is generated based on the determination result in S7) and the determination result in the combined use determination process (S8).

FIG. 4 is an explanatory diagram showing an example of the prescription content display image GH.

As illustrated in FIG. 4, the item name KM included in each description area A of the prescription image GS is displayed in the prescription content display image GH.
In the prescription content display image GH, the description content character string KN, which is the recognition result of the description content KS included in each description area A of the prescription image GS by the character recognition processing (S2), is displayed. In this embodiment, as described above, the description content character string KN corresponding to the description name AM is referred to as the drug name character string LM, and the description content character string KN corresponding to the description dose AQ is referred to as the prescription dose character string LQ , and the description content character string KN corresponding to the description period AR is referred to as a prescription period character string LR.

Also, in the prescription content display image GH, a dose caution mark MK1 is displayed according to the determination result of the dose determination process in step S6. Specifically, when the prescription dose character string LQ[m] included in the prescription character information JS represents a dose larger than the upper limit dose YQ indicated by the drug information JY in the dose determination process, the prescription confirmation device 3 , a dose caution mark MK1 is displayed at a position associated with the prescribed dose character string LQ[m] corresponding to the drug Md[m] associated with the drug name character string LM[m]. In addition, FIG. 4 illustrates a case where a dose caution mark MK1 is displayed at a position corresponding to the prescribed dose character string LQ[3].

Also, in the prescription content display image GH, a period caution mark MK2 is displayed according to the determination result in the period determination process in step S7. Specifically, when the prescription period character string LR[m] included in the prescription character information JS represents a period longer than the upper limit period YR indicated by the drug information JY in the dose determination process, the prescription confirmation device 3 , a period caution mark MK2 is displayed at a position associated with the prescription period character string LR[m] corresponding to the drug Md[m] associated with the drug name character string LM[m]. Note that FIG. 4 illustrates a case where a period caution mark MK2 is displayed at a position corresponding to the prescription period character string LR[3].

Further, in the prescription content display image GH, a combination warning mark MK3 is displayed according to the determination result of the combination determination process in step S8. Specifically, in the dose determination process, the prescription confirmation device 3 confirms that the drug corresponding to the drug name character strings LM[1] to LM[M] is contraindicated for the drug corresponding to the drug name character string LM[m]. If the drug YK is included, or if the drugs corresponding to the drug name character strings LM[1] to LM[M] include the drug YC that should be used in combination with the drug corresponding to the drug name character string LM[m], the drug A combination caution mark MK3 is displayed at a position related to the name character string LM[m]. Note that FIG. 4 illustrates a case where the combined use caution mark MK3 is displayed at the position corresponding to the drug name character string LM[1] and the position corresponding to the drug name character string LM[3].

In the prescription content display image GH, a confirmation button KTB for confirming the content displayed in the description content character string KN is displayed.
Although the details will be described later, in this embodiment, the prescription confirmation device 3 includes an input unit 35 for inputting various kinds of information. Then, the operator who operates the prescription confirmation device 3 can use the input unit 35 to correct the content of the description content character string KN. Further, the operator who operates the prescription confirmation device 3 can use the input unit 35 to press the confirmation button KTB to confirm the content of the description content character string KN.

In FIG. 4, the prescription reading device 1 erroneously recognizes the written name AM[1] in the character recognition process, and the written name AM[1] displayed on the prescription image GS is "Vitamin AAA 100 mg". , the drug name character string LM[1] corresponding to the description name AM[1] is "vitamin DDD 100 mg".

As described above, according to the prescription confirmation device 3 according to the present embodiment, misrecognition of characters indicated on the prescription in the character recognition process, errors in the contents of the prescription issued by the doctor, etc. Therefore, when a drug is to be prescribed in a manner that does not conform to the original usage of the drug, the prescription content display image GH displayed on the display unit 50 includes a dosage caution mark MK1, a period caution mark MK2, and a , combined use caution mark MK3, etc., to call attention. For this reason, according to the prescription confirmation device 3 according to the present embodiment, compared with the mode in which the medicine is prescribed based on the recognition result of the prescription image GS by the prescription reading device 1, it is not suitable for the original usage of the medicine. It can reduce the risk of being prescribed a drug in a manner.

<3. Function of Prescription Recognition System>
Hereinafter, functions of the prescription reading device 1, the prescription checking device 3, and the drug database server 7 will be described with reference to FIGS. 5 to 10. FIG.

FIG. 5 is a functional block diagram showing an example of the configuration of the prescription reading device 1. As shown in FIG.

As illustrated in FIG. 5, the prescription reading device 1 includes a control unit 11 that controls each unit of the prescription reading device 1, a storage unit 12 that stores various information, and an external device that exists outside the prescription reading device 1. and an imaging unit 14 for imaging the prescription.

As illustrated in FIG. 5 , the control unit 11 includes an image information acquisition unit 111 and a character recognition unit 112 .
Among these, the image information acquisition unit 111 causes the imaging unit 14 to execute prescription imaging processing (S1). Specifically, the image information acquiring unit 111 controls the image capturing unit 14 to capture an image of the prescription by the image capturing unit 14, and the prescription image information JGS indicating the prescription image GS obtained as a result of the image capturing is sent to the image capturing unit 14. Get from Further, the character recognition unit 112 executes character recognition processing (S2). Specifically, the character recognition unit 112 recognizes characters included in the prescription image GS indicated by the prescription image information JGS, and generates prescription character information JS indicating the recognition result. Various methods can be applied to the character recognition by the character recognition unit 112. As an example, a method based on optical character recognition (OCR) can be applied.

As illustrated in FIG. 5, the storage unit 12 stores the learning model NN, prescription information JSS, prescription image information JGS acquired by the image information acquisition unit 111 from the imaging unit 14, and prescription characters generated by the character recognition unit 112. Information JS and a control program PG1 for controlling each part of the prescription reading device 1 are stored.

Of these, the learning model NN is, for example, a multi-layer neural network, and is a learning model that has learned the relationship between an image containing characters and the characters contained in the image. In this embodiment, the character recognition unit 112 uses the learning model NN to recognize characters included in the prescription image GS. Thus, as an example of the present embodiment, the aforementioned character recognition unit 112 and the storage unit 12 constitute AI (Artificial Intelligence)-OCR.
In the case where there are multiple types of prescriptions that the prescription reading device 1 can target for the prescription imaging process (step S1) and the character recognition process (step S2), the storage unit 12 stores the multiple types of prescriptions. It is assumed that a plurality of prescription information JSS corresponding to each other are stored. The prescription information JSS will be described later.

FIG. 6 is a configuration diagram showing an example of the hardware configuration of the prescription reading device 1. As shown in FIG.

As illustrated in FIG. 6, the prescription reading device 1 includes a processor 1001 that controls each part of the prescription reading device 1, a storage device 1002 that stores various information, and an external device that exists outside the prescription reading device 1. A communication device 1003 for communication and an imaging device 1004 for imaging a prescription are provided.

Among them, the storage device 1002 includes a volatile memory such as a RAM (Random Access Memory) that functions as a work area for the processor 1001, and an EEPROM (Electrically Erasable Programmable Read-Only Memory) that stores various information such as the control program PG1. and one or both of the non-volatile memory of , and provides the function as the storage unit 12 .
Also, the processor 1001 includes, for example, one or more CPUs (Central Processing Units). The processor 1001 functions as the control unit 11 by executing the control program PG1 stored in the storage device 1002 and operating according to the control program PG1. Note that the processor 1001 may be a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), or an FPGA (Field Programmable Gate Array) and other hardware may be included. In this case, part or all of the control unit 11 implemented by the processor 1001 may be implemented by hardware such as a DSP.
Further, the communication device 1003 is hardware for communicating with an external device existing outside the prescription reading device 1 via one or both of a wired network and a wireless network, and functions as the communication unit 13. offer.
Also, the imaging device 1004 is hardware for imaging a prescription by optical means such as a camera or an image scanner, and provides a function as the imaging unit 14 .

FIG. 7 is a functional block diagram showing an example of the configuration of the prescription confirmation device 3. As shown in FIG.

As illustrated in FIG. 7, the prescription confirmation device 3 includes a control unit 31 that controls each unit of the prescription confirmation device 3, a storage unit 32 that stores various information, and an external device that exists outside the prescription confirmation device 3. and an input unit 35 for receiving an operation by the user of the prescription confirmation device 3.

As illustrated in FIG. 7 , the control unit 31 includes a character information acquisition unit 311 , a drug information acquisition unit 312 , a prescription determination unit 313 and a determination result output unit 314 .
Among these, the character information acquisition unit 311 acquires the prescription character information JS from the prescription reading device 1 . Also, the drug information acquisition unit 312 acquires one or more drug information J Y from the drug database server 7 . In addition, the prescription content determination unit 313 (an example of the “determination unit”) executes dose determination processing, period determination processing, and combination determination processing. Further, the determination result output unit 314 (an example of the “output unit”) executes prescription content display processing.

As illustrated in FIG. 7, the storage unit 32 stores prescription text information JS that the text information acquisition unit 311 has acquired from the prescription reading device 1, and one or more drugs that the drug information acquisition unit 312 has acquired from the drug database server 7. Information JY and a control program PG3 for controlling each part of the prescription confirmation device 3 are stored.

FIG. 8 is a configuration diagram showing an example of the hardware configuration of the prescription confirmation device 3. As shown in FIG.

As illustrated in FIG. 8, the prescription confirmation device 3 includes a processor 3001 that controls each part of the prescription confirmation device 3, a storage device 3002 that stores various information, and an external device that exists outside the prescription confirmation device 3. It has a communication device 3003 for communication and an input device 3005 for accepting an operation by the user of the prescription confirmation device 3 .

Of these, the storage device 3002 includes one or both of a volatile memory such as a RAM that functions as a work area for the processor 3001 and a nonvolatile memory such as an EEPROM that stores various information such as the control program PG3. It provides the function as the part 32 .
Also, the processor 3001 includes, for example, one or more CPUs. The processor 3001 functions as the control unit 31 by executing the control program PG3 stored in the storage device 3002 and operating according to the control program PG3. Note that the processor 3001 includes hardware such as a GPU, DSP, or FPGA in addition to one or more CPUs, or in place of part or all of one or more CPUs. may be In this case, part or all of the control unit 31 implemented by the processor 3001 may be implemented by hardware such as a DSP.
Further, the communication device 3003 is hardware for communicating with an external device existing outside the prescription confirmation device 3 via one or both of a wired network and a wireless network, and functions as the communication unit 33. offer.
Also, the input device 3005 includes one or more devices such as a keyboard, a touch panel, and a mouse, and provides a function as an input unit 35 that receives user operations of the prescription confirmation device 3 .

FIG. 9 is a functional block diagram showing an example of the configuration of the drug database server 7. As shown in FIG.

As illustrated in FIG. 9, the drug database server 7 includes a control unit 71 that controls each part of the drug database server 7, a storage unit 72 that stores various information, and an external device that exists outside the drug database server 7. and a communication unit 73 that performs communication between.
Among these, the storage unit 72 stores a drug list information table TBL7 in which a plurality of types of drugs that may be described in a prescription and a plurality of drug information JY corresponding one-to-one are stored; A control program PG7 for controlling each section is stored.
Further, the control unit 71 acquires drug information JY from the drug list information table TBL7 in response to a request from the prescription confirmation device 3, and transmits the acquired drug information JY to the prescription confirmation device 3. It controls the communication unit 73 .

FIG. 10 is a configuration diagram showing an example of the hardware configuration of the drug database server 7. As shown in FIG.

As illustrated in FIG. 10, the drug database server 7 includes a processor 7001 that controls each part of the drug database server 7, a storage device 7002 that stores various information, and an external device that exists outside the drug database server 7. and a communication device 7003 for performing communication.

Of these, the storage device 7002 includes one or both of a volatile memory such as a RAM that functions as a work area for the processor 7001 and a nonvolatile memory such as an EEPROM that stores various information such as the control program PG7. The function as the part 72 is provided.
Also, the processor 7001 includes, for example, one or more CPUs. The processor 7001 functions as the control unit 71 by executing the control program PG7 stored in the storage device 7002 and operating according to the control program PG7.
Further, the communication device 7003 is hardware for communicating with an external device existing outside the drug database server 7 via one or both of a wired network and a wireless network, and functions as the communication unit 73. offer.
In addition, the drug database server 7 communicates with an external device or the like via either or both of a wired network and a wireless network using the communication device 7003, acquires the latest drug information JY from the external device and the like, and stores the drug. Update list information table TBL7.

<4. Data Present in Prescription Recognition System>
Various data existing in the prescription recognition system Sys will be described below with reference to FIGS. 11 to 13. FIG.

FIG. 11 is an explanatory diagram showing an example of the data structure of prescription information JSS. Here, the prescription information JSS is information regarding the format of the prescription.

As illustrated in FIG. 11, the prescription information JSS has a plurality of records corresponding one-to-one with a plurality of descriptions KS of the prescription. Each record of the prescription information JSS has an item ID, item name information JKM, item name position information, and description content position information.

Among these items, the item ID is information for identifying each described content KS out of a plurality of described contents KS in the prescription. The item name information JKM is information indicating the item name KM corresponding to the description content KS. The item name position information is information indicating the display position (for example, the coordinates of the start point and the coordinate of the end point) of the item name KM corresponding to the description content KS in the prescription. The description content position information is information indicating the display position (for example, the coordinates of the start point and the coordinates of the end point) of the description content KS in the prescription.

FIG. 12 is an explanatory diagram showing an example of the data structure of the prescription character information JS. The prescription character information JS is, as described above, information indicating the recognition result of the prescription image GS obtained by imaging the prescription.

As illustrated in FIG. 12, the prescription character information JS has a plurality of records corresponding one-to-one with a plurality of description content character strings KN recognized from the prescription by the character recognition process (step S2). Each record of the prescription character information JS has an item ID, item name information JKM, description content information JKN, and similarity information.

Among them, the description content information JKN is information indicating the description content character string KN, which is the result of recognizing the description content KS corresponding to the item ID by character recognition processing. As described above, when the described content character string KN is the drug name character string LM[m], the described content information JKN indicating the described content character string KN is referred to as drug name character information JM[m]. When the description content character string KN is the prescription dose character string LQ[m], the description content information JKN indicating the description content character string KN is referred to as prescription dose character information JQ[m], and the description content character string KN is In the case of the prescription period character string LR[m], the description content information JKN indicating the description content character string KN is referred to as prescription period character information JR[m]. As described above, information including the drug name text information JM[m], prescription dose text information JQ[m], and prescription period text information JR[m] is referred to as drug text information JP[m].
Note that in FIG. 12, the description name AM[1] shown in FIG. The column LM[1] exemplifies the case of "vitamin DDD 100 mg".

The similarity information is information indicating the degree of similarity between the character string represented as the description content KS and the description content character string KN. That is, when the degree of similarity indicated by the similarity information is high, the character string represented by the description content KS and the description content character string KN obtained by recognizing the character string represented by the description content KS by the character recognition process. are more likely to match.

FIG. 13 is an explanatory diagram showing an example of the data configuration of the drug list information table TBL7.

As illustrated in FIG. 13, the drug list information table TBL7 has a plurality of records corresponding one-to-one to a plurality of types of drugs that may be described in a prescription. Each record of the drug list information table TBL7 includes drug ID and drug information JY.

Here, the drug ID is information for specifying each type of drug among multiple types of drugs that may be described in a prescription.
Further, the drug information JY is, as described above, information including drug name information JYM, drug usage information JYS, and concomitant drug information JYH. Further, the drug name information JYM is information indicating the drug name YM as described above. Further, the medicine usage information JYS is, as described above, information including the upper limit dose information JYQ indicating the upper limit dose YQ and the upper limit period information JYR indicating the upper limit period YR. As described above, the concomitant drug information JYH is information including concomitant contraindicated drug information JYK indicating concomitant contraindicated drug YK and concomitant caution drug information JYC indicating concomitant caution drug YC.
The drug information JY may be information provided by a pharmaceutical company that manufactures the drug corresponding to the drug information JY, for example.

In this embodiment, the drug database server 7, in step S5 of FIG. The drug information JY corresponding to the drug name YM is transmitted to the prescription confirmation device 3 as specific drug information. In other words, in step S5, if there is a drug name YM that matches the drug name character string LM[m] indicated by the drug name character information JM[m], the drug information acquisition unit 312 finds the corresponding drug name YM. The drug information JY to be used is acquired as the specific drug information.
On the other hand, if there is no drug name YM that matches the drug name character string LM[m] indicated by the drug name character information JM[m] in step S5, the drug database server 7 selects the drug name among the plurality of drug information JY. One or a plurality of pieces of drug information JY corresponding to a drug name YM whose degree of similarity with the name character string LM[m] is equal to or greater than a predetermined degree of similarity is transmitted to the prescription confirmation device 3 as specific drug information. In other words, in step S5, if there is no drug name YM that matches the drug name character string LM[m] indicated by the drug name character information JM[m], the drug information acquisition unit 312 obtains a plurality of drug information JY. Of these, each of one or a plurality of pieces of drug information JY corresponding to a drug name YM whose degree of similarity with the drug name character string LM[m] is equal to or greater than a predetermined degree of similarity is acquired as specific drug information.
For example, as shown in FIG. 12, the drug name character string LM[1] recognized by the prescription reading device 1 is "vitamin DDD 100 mg", but among the drug names YM shown in FIG. There is no drug name YM that matches "Vitamin DDD 100 mg". The prescription confirmation device 3 selects a plurality of drug names YM whose similarity to the drug name character string LM[1] "vitamin DDD 100 mg" is equal to or higher than a predetermined similarity, for example, the drug name character string LM[1 ] from the drug list information table TBL7 in descending order of similarity to "vitamin DDD 100 mg". In this embodiment, the degree of similarity between "vitamin DDD 100 mg", which is the drug name character string LM[1], and "vitamin AAA 100 mg", which is the drug name YM, is equal to or higher than a predetermined similarity. Further, in the present embodiment, the degree of similarity between "vitamin DDD 100 mg", which is the drug name character string LM[1], and "protein DDD 80 mg", which is the drug name YM, is equal to or greater than a predetermined degree of similarity. . Further, in the present embodiment, in the drug list information table TBL7, the drug name YM whose degree of similarity with "vitamin DDD 100 mg", which is the drug name character string LM[1], is equal to or higher than a predetermined degree of similarity is "vitamin AAA 100 mg" and "Protein DDD 80 mg". As a result, the drug information acquisition unit 312 determines that the drug information JY corresponding to "vitamin AAA 100 mg" and the drug information JY corresponding to "protein DDD 80 mg" whose similarity to "vitamin DDD 100 mg" is equal to or greater than a predetermined similarity Each of the drug information JY is acquired as specific drug information corresponding to the drug name character string LM[1].

Hereinafter, the number of pieces of specific drug information corresponding to the drug name character string LM[m] will be referred to as "Qm pieces". Here, the value Qm is a natural number of 1 or more. Also, hereinafter, Qm pieces of specific drug information corresponding to the drug name character string LM[m] are referred to as drug information JY[m][1] to JY[m][Qm]. Also, hereinafter, of the Qm pieces of specific drug information corresponding to the drug name character string LM[m], the qm-th specific drug information is referred to as drug information JY[m][qm]. Here, the value qm is a natural number that satisfies 1≤qm≤Qm. In the following, among various information and various values stored in the drug list information table TBL7, information included in the drug information JY[m][qm] or included in the drug information JY[m][qm] Suffixes [m][qm] are attached to the values indicating the information provided.
For example, in FIGS. 12 and 13, the specific drug information corresponding to the drug name character string LM[1] (=“vitamin DDD 100 mg”) is the drug name YM[1][1] (=“vitamin AAA 100 mg”). If there are two corresponding drug information JY[1][1] and drug name YM[1][2] (= "protein DDD 80 mg", corresponding to drug information JY[1][2], That is, it shows the case of "Qm=2".

<5. Operation of prescription confirmation device>
The operation of the prescription confirmation device 3 will be described below with reference to FIGS. 14 to 17. FIG.

FIG. 14 is a flow chart showing an example of the operation of the prescription confirmation device 3 when the dose determination process shown in step S6 of FIG. 2 is executed.

As illustrated in FIG. 14, when the dose determination process is started, the prescription determination unit 313 sets the variable m to "1" (S101).
Next, the prescription content determination unit 313 sets "1" to the variable qm (S103).

Next, the prescription content determination unit 313 determines whether or not the prescribed dose represented by the prescribed dose character string LQ[m] is equal to or less than the upper limit dose YQ[m][qm] (S105).
If the result of determination in step S105 is affirmative, the prescription content determination unit 313 determines whether or not the variable qm satisfies "qm=Qm" (S107).
Then, if the determination result in step S107 is negative, the prescription content determination unit 313 adds "1" to the variable qm (S109), and advances the process to step S105.
On the other hand, when the result of determination in step S107 is affirmative, the prescription content determination unit 313 advances the process to step S113.
If the result of the determination in step S105 is negative, the determination result output unit 314 outputs improper dose notification information IF1[m] (S111), and advances the process to step S113. Note that the determination result output unit 314 outputs the incorrect dose notification information IF1[m] to display the dose caution mark MK1 at the position corresponding to the prescription dose character string LQ[m] in the prescription content display image GH. . Note that the judgment result output unit 314, when the improper dose notification information IF1[m] is output, compares the number of characters of the prescription dose character string LQ[m] to when the improper dose notification information IF1[m] is not output. You may change the display mode, such as a color and a font.

Next, the prescription content determination unit 313 determines whether or not the variable m satisfies "m=M" (S113).
Then, if the determination result in step S113 is negative, the prescription content determination unit 313 adds "1" to the variable m (S115), and advances the process to step S103.
On the other hand, if the determination result in step S113 is affirmative, the control section 31 terminates the dose determination process.

As described above, according to the dose determination process (step S6) according to the present embodiment, if the recognition accuracy of the written name AM[m] by the character recognition process (step S2) is low and the written name by the prescription reading device 1 When the drug name character string LM[m], which is the recognition result of AM[m], is an inaccurate drug name, analogy is made from the drug name character string LM[m], which is the recognition result of the listed name AM[m]. Using Qm pieces of upper limit dose information JYQ[m][1] to JYQ[m][Qm] corresponding to all possible drug names YM[m][1] to YM[m][Qm], It is determined whether or not the prescribed dose indicated by the prescribed dose character string LQ[m], which is inferred from the stated dose AQ[m] written in the prescription, is appropriate. Therefore, according to the present embodiment, even if there is an error in the drug name character string LM[m], which is the recognition result of the description name AM[m] by the prescription reading device 1, the description name AM[m] It is possible to suppress the excessive prescription of drugs corresponding to
Further, according to the present embodiment, if there is an input error in the prescription by a doctor or the like, the drug Md[m] corresponding to the drug name character string LM[m] is not the name of the drug that should be prescribed to the patient. Qm pieces of upper limit dose information JYQ corresponding to all drug names YM[m][1] to YM[m][Qm] that can be inferred from the drug name character string LM[m] when not represented accurately Using [m][1]~JYQ[m][Qm], whether or not the prescription dose indicated by the prescription dose character string LQ[m], which is inferred from the stated dose AQ[m] written in the prescription, is appropriate judge. Therefore, according to the present embodiment, even if there is an error in the description of the description name AM[m] in the prescription, such as an input error in the prescription by the doctor, the drug corresponding to the description name AM[m] can be suppressed from being excessively prescribed.

FIG. 15 is a flow chart showing an example of the operation of the prescription confirmation device 3 when the period determination process shown in step S7 of FIG. 2 is executed. 15 except that the process of step S205 is executed instead of the process of step S105, and the process of step S211 is executed instead of the process of step S111. 14 is the same as the processing shown in the flowchart of FIG.

As illustrated in FIG. 15, in the period determination process, the prescription content determination unit 313 determines whether the prescription period indicated by the prescription period character string LR[m] is equal to or shorter than the upper limit period YR[m][qm]. Determine (S205).
If the result of determination in step S205 is negative, the determination result output unit 314 outputs period irregularity notification information IF2[m] (S211). Note that the determination result output unit 314 displays the period warning mark MK2 at the position corresponding to the prescription period character string LR[m] in the prescription content display image GH by outputting the period irregularity notification information IF2[m]. . It should be noted that the determination result output unit 314, when the period irregularity notification information IF2[m] is output, compares the number of characters of the prescription period character string LR[m] to the case where the period irregularity notification information IF2[m] is not output. You may change the display mode, such as a color and a font.
Other processes are the same as the dose determination process shown in FIG. 14, so description thereof will be omitted.

As described above, according to the period determination process according to the present embodiment, if the recognition accuracy of the written name AM[m] by the character recognition process is low and the recognition result of the written name AM[m] by the prescription reading device 1 is If a certain drug name character string LM[m] is an inaccurate drug name, all drug names YM[ Using Qm pieces of upper limit period information JYR[m][1] to JYR[m][Qm] corresponding to m][1] to YM[m][Qm], the written dose AQ described in the prescription It is determined whether or not the prescription period indicated by the prescription period character string LR[m] inferred from [m] is appropriate. Therefore, according to the present embodiment, even if there is an error in the drug name character string LM[m], which is the recognition result of the description name AM[m] by the prescription reading device 1, the description name AM[m] It can be suppressed that the drug corresponding to is prescribed beyond the upper limit period.
Further, according to the present embodiment, if there is an input error in the prescription by the doctor or the like, the drug corresponding to the drug name character string LM[m] does not accurately represent the name of the drug that should be prescribed to the patient. Q m pieces of upper limit period information JYR[m][ 1] to JYR[m][Qm] is used to determine whether or not the prescription period indicated by the prescription period character string LR[m] analogized from the stated dose AQ[m] written in the prescription is appropriate. Therefore, according to the present embodiment, even if there is an error in the description of the description name AM[m] in the prescription, such as an input error in the prescription by the doctor, the drug corresponding to the description name AM[m] can be suppressed from being prescribed beyond the upper limit period.

16 and 17 are flowcharts showing an example of the operation of the prescription confirmation device 3 when the combined use determination process shown in step S8 of FIG. 2 is executed.

As illustrated in FIG. 16, when the combined use determination process is started, the prescription content determination unit 313 sets the variable m to "1" (S301). Next, the prescription content determination unit 313 sets "1" to the variable qm (S303). In addition, the prescription content determination unit 313 sets "1" to the variable n (S305). In addition, the prescription content determination unit 313 sets the variable qn to "1" (S307).

Then, the prescription content determination unit 313 determines that all of the contraindicated drugs YK[m][qm] indicated by the contraindicated drug information JYK[m][qm] are the drugs indicated by the drug name character string LM[n][qn]. and is inconsistent (S309).
When the result of determination in step S309 is affirmative, the prescription content determination unit 313 determines that all of the combined caution medicine YC[m][qm] indicated by the combined caution medicine information JYC[m][qm] is the drug name character string LM It is determined whether or not there is a mismatch with the drug represented by [n][qn] (S311).

If the result of the determination in step S309 is negative, or if the result of the determination in step S311 is negative, the determination result output unit 314 outputs combined fraudulent notification information IF3[m] (S313), and the process proceeds to step S333. proceed to Note that the determination result output unit 314 outputs the combined use fraud notification information IF3[m] to display the combined use caution mark MK3 at the position corresponding to the drug name character string LM[m] in the prescription content display image GH. . It should be noted that the determination result output unit 314, when the combined use fraudulent notification information IF3[m] is output, compares with the case where the combined use fraudulent notification information IF3[m] is not output, the characters of the drug name character string LM[m] You may change the display mode, such as a color and a font.

As illustrated in FIG. 17, when the result of determination in step S311 is affirmative, the prescription content determination unit 313 determines whether or not the variable qn satisfies "qn=Qn" (S321). Here, the value Qn is the number of pieces of specific drug information corresponding to the drug name character string LM[n].
Then, if the determination result in step S321 is negative, the prescription content determination unit 313 adds "1" to the variable qn (S323), and advances the process to step S309.
On the other hand, if the result of determination in step S321 is affirmative, the prescription content determination unit 313 advances the process to step S325.

Next, the prescription content determination unit 313 determines whether or not the variable n satisfies “n=M” (S325).
Then, if the determination result in step S325 is negative, the prescription content determination unit 313 adds "1" to the variable n (S327), and advances the process to step S307.
On the other hand, if the result of determination in step S325 is affirmative, the prescription content determination unit 313 advances the process to step S329.

Next, the prescription content determination unit 313 determines whether or not the variable qm satisfies "qm=Qm" (S329).
Then, if the determination result in step S329 is negative, the prescription content determination unit 313 adds "1" to the variable qm (S331), and advances the process to step S305.
On the other hand, if the result of determination in step S329 is affirmative, the prescription content determination unit 313 advances the process to step S333.

Next, the prescription content determination unit 313 determines whether or not the variable m satisfies "m=M" (S333).
Then, if the determination result in step S333 is negative, the prescription content determination unit 313 adds "1" to the variable m (S335), and advances the process to step S303.
On the other hand, if the determination result in step S333 is affirmative, the control unit 31 terminates the combined use determination process.

As described above, according to the combination determination process according to the present embodiment, if the recognition accuracy of the written name AM[m] by the character recognition process is low, and the recognition result of the written name AM[m] by the prescription reading device 1 is If a certain drug name character string LM[m] is an inaccurate drug name, all drug names YM[ Using Qm pieces of concomitant drug information JYH[m][1] to JYH[m][Qm] corresponding to m][1] to YM[m][Qm], It is determined whether or not the alignment is proper. Therefore, according to the present embodiment, even if there is an error in the drug name character string LM[m], which is the recognition result of the description name AM[m] by the prescription reading device 1, it is possible to prevent inappropriate taking of the drug. Prescription of drugs can be suppressed by combination.
Further, according to the combination determination process according to the present embodiment, if there is an input error in the prescription by the doctor or the like, the drug Md[m] corresponding to the drug name character string LM[m] is not originally prescribed to the patient. Qm corresponding to all drug names YM[m][1] to YM[m][Qm] that can be inferred from the drug name character string LM[m] when the name of the drug to be used is not accurately represented is used to determine whether the combination of drugs described in the prescription is appropriate. For this reason, according to the present embodiment, even if there is an error in the description of the name AM[m] in the prescription, such as an input error in the prescription by the doctor, the drug may be lost due to inappropriate drug combination. Prescription can be suppressed.

<6. Conclusion of Embodiment>
As described above, in the present embodiment, the prescription confirmation device 3 (an example of an “information processing device”) performs character recognition processing for recognizing characters included in an image to determine the medicine Md[1] written in the prescription. (an example of a “first drug”) is replaced with a drug name character string LM[1] (an example of a “first name character string”). example), and the description usage AN[1] (an example of "a character string indicating the prescription content of the first drug") related to the drug Md[1] described in the prescription is converted to a prescription content character string LN[1 ] (an example of a “first content character string”), a drug name character string LM[1] and a prescription content character string LN[ 1] (an example of “first character information”), and a plurality of drug information corresponding to a plurality of drugs that may be described in a prescription. A drug information acquisition unit 312 that acquires drug information JY related to the drug name character string LM[1] as specific drug information from the drug database server 7 having a storage unit 72 that stores JY, and a prescription content character string LN[ 1], a prescription content determination unit 313 (an example of a “determination unit”) that determines whether or not the prescription content of the drug Md[1] indicated by the specific drug information conforms to the usage method of the drug indicated by the specific drug information; and a determination result output unit 314 (an example of an “output unit”) that outputs information based on the determination result of the unit 313 .

That is, according to the present embodiment, the prescription content determination unit 313 determines that the prescription content of the drug Md[1] indicated by the prescription content character string LN[1] recognized by the character recognition process from the prescription is the specific drug information. It is determined whether or not the method of use of the drug indicated by the drug information JY obtained from the database server 7 is suitable. For this reason, according to the present embodiment, compared to the aspect in which a drug is prescribed according to the result recognized by character recognition processing from a prescription, there is an error in character recognition in character recognition processing, or a prescription issued by a doctor. It is possible to suppress the possibility of prescribing a drug in a manner that does not conform to the intended usage of the drug due to an error in the description or the like.

Further, in the present embodiment, the prescription describes the dose AQ[1] related to the drug Md[1] as the content of the prescription of the drug Md[1], and the drug information JY stored in the storage unit 72. Each includes upper limit dose information JYQ (an example of “dosage information”) indicating the upper limit dose YQ of the drug corresponding to the drug information JY, and the prescription content determination unit 313 determines the drug indicated by the prescription content character string LN[1]. performing a dose determination process (an example of a "first determination process") for determining whether or not the prescribed dose of Md[1] is equal to or less than the upper limit dose YQ indicated by the upper limit dose information JYQ included in the specific drug information; If the determination result in the dose determination process is negative, the determination result output unit 314 outputs incorrect dose notification information IF1[1] (an example of "information indicating that there is an error in the prescription content of the first medicine described in the prescription"). ) is output.

That is, according to the present embodiment, the prescription content determination unit 313 determines that the prescription dose of the drug Md[1] indicated by the prescription content character string LN[1] recognized from the prescription by character recognition processing is obtained from the drug database server 7. It is determined whether or not it is equal to or less than the upper limit dose YQ indicated by the acquired drug information JY. For this reason, according to the present embodiment, compared to the aspect in which a drug is prescribed according to the result recognized by character recognition processing from a prescription, there is an error in character recognition in character recognition processing, or a prescription issued by a doctor. It is possible to suppress the possibility that the drug Md[1] is excessively prescribed due to an error in the description.

Further, in the present embodiment, the prescription describes the name AM[2] (an example of the "name of the second drug") related to the drug Md[2] (an example of the "second drug"), and character recognition The unit 112 recognizes the description name AM[2] related to the drug Md[2] described in the prescription as the drug name character string LM[2] (an example of the "second name character string") through character recognition processing. Then, the character information acquisition unit 311 acquires drug character information JP[2] (an example of “second character information”) indicating the drug name character string LM[2] from the prescription reading device 1 including the character recognition unit 112. Each of the plurality of drug information JY stored in the storage unit 72 includes concomitant drug information JYH (an example of "concomitant information") related to contraindicated drug YK and precautionary drug YC for the drug corresponding to the drug information JY. Based on the concomitant drug information JYH included in the specific drug information, the prescription content determination unit 313 determines that the drug having a name related to the drug name character string LM[2] is the drug Md[1] contraindicated drug YK and Performs a combination determination process (an example of a "second determination process") to determine that it is not included in any of the combination caution medicines YC, and the determination result output unit 314 outputs a negative result when the determination result in the combination determination process is negative. , combined use fraudulent notification information IF3[m] (an example of "information to the effect that there is an error in the prescription content of the first medicine described in the prescription") is output.

That is, according to the present embodiment, the prescription content determination unit 313 determines that the drug having the name related to the drug name character string LM[2] is either the contraindicated drug YK or the precautionary drug YC of the drug Md[1]. It is determined that it is not included in For this reason, according to the present embodiment, it is possible to suppress the prescription of drugs due to inappropriate drug combinations, compared to the mode in which drugs are prescribed according to the results recognized by character recognition processing from the prescription. can be done.

In the present embodiment, the drug information acquisition unit 312 determines that the drug information JY including the drug name YM that matches the drug name character string LM[1] exists among the plurality of drug information JY stored in the storage unit 72. In this case, the drug information JY is acquired as the specific drug information, and the drug information JY including the drug name YM that matches the drug name character string LM[1] is included in the plurality of drug information JY stored in the storage unit 72. does not exist, each of one or more pieces of drug information JY containing a drug name YM whose degree of similarity with the drug name character string LM[1] is equal to or greater than a predetermined degree of similarity is acquired as specific drug information. Characterized by

That is, according to this embodiment, the drug information acquisition unit 312 corresponds to one or more drug names YM that can be inferred from the drug name character string LM[1], which is the recognition result of the listed name AM[1]. Acquire one or more drug information JY. Therefore, according to the present embodiment, the recognition accuracy of the written name AM[1] by the character recognition process is low, and the drug name character string LM[1], which is the recognition result of the written name AM[1] by the prescription reading device 1, is low. ] is an inaccurate drug name, it is possible to suppress the possibility of prescribing the drug in a manner that does not conform to the original usage of the drug.

Further, in the present embodiment, when the drug information acquisition unit 312 acquires a plurality of pieces of specific drug information corresponding to a plurality of pieces of drug information JY from the storage unit 72, the prescription content determination unit 313 determines that the prescription content character string LN[1] The determination result output unit 314 determines whether or not the prescription content of the drug Md[1] indicated by is compatible with each of the usage methods of the plurality of drugs indicated by the plurality of specific drug information. , when it is determined that the prescription content of the drug Md[1] does not conform to at least one drug usage method among the plurality of drug usage methods indicated by the plurality of specific drug information, the drug Md[1] described in the prescription 1] is characterized by outputting information to the effect that there is an error in the content of the prescription.

Therefore, according to the present embodiment, the recognition accuracy of the written name AM[1] by the character recognition process is low, and the drug name character string LM[1], which is the recognition result of the written name AM[1] by the prescription reading device 1, is low. ] is an inaccurate drug name, it is possible to suppress the possibility of prescribing the drug in a manner that does not conform to the original usage of the drug.

<7. Variation>
Each of the above forms can be variously modified. Specific modification modes are exemplified below. Two or more aspects arbitrarily selected from the following examples can be combined as appropriate within a mutually consistent range. It should be noted that, in the modifications illustrated below, the reference numerals referred to in the above description will be used for the elements that have the same actions and functions as those of the embodiment, and the detailed description of each will be omitted as appropriate.

<Modification 1>
In the above-described embodiment, the image information acquisition unit 111 and the character recognition unit 112 are provided outside the prescription confirmation device 3, but the present invention is not limited to such an aspect. For example, one or both of the image information acquisition unit 111 and the character recognition unit 112 may be provided in the prescription confirmation device 3 .

FIG. 18 is an explanatory diagram for explaining an example of the outline of the prescription recognition system Sys-B according to this modified example.

As illustrated in FIG. 18 , the prescription recognition system Sys-B includes a prescription confirmation device 3B instead of the prescription confirmation device 3, and does not include the prescription reading device 1. It is configured in the same way as the system Sys.

FIG. 19 is a functional block diagram showing an example of the configuration of the prescription confirmation device 3B.

As illustrated in FIG. 19, the prescription confirmation device 3B includes a control unit 31B instead of the control unit 31, a storage unit 32B instead of the storage unit 32, and an imaging unit 14. Except for this, it is configured in the same manner as the prescription confirmation device 3 according to the embodiment.
Of these, the control unit 31B is configured in the same manner as the control unit 31 according to the embodiment, except that it has an image information acquisition unit 111 instead of the character information acquisition unit 311 and a character recognition unit 112. ing.
In addition, the storage unit 32B stores the learning model NN, the prescription information JSS, and the prescription image information JGS, and stores the control program PG3B instead of the control program PG3. It is configured in the same manner as the storage unit 32 according to the embodiment.
The hardware configuration of the prescription confirmation device 3B is the same as the hardware configuration of the prescription confirmation device 3 according to the embodiment illustrated in FIG. In this modification, the processor 3001 executes the control program PG3B stored in the storage device 3002 and operates according to the control program PG3B, thereby functioning as the control unit 31B.

As described above, in this modified example, the prescription confirmation device 3B (an example of the “information processing device”) receives the prescription image information JGS (an example of the “image information”) indicating the prescription image GS that is the image of the prescription. Based on the image information acquisition unit 111 to acquire and the prescription image information JGS, the description name AM[1] related to the drug Md[1] described in the prescription is changed to the drug name character string LM[1] ("first name character string”), and the description usage AN[1] related to the drug Md[1] described in the prescription is recognized as the prescription content character string LN[1] (an example of the “first content character string”). From the drug database server 7 having a character recognition unit 112 (an example of a “recognition unit”) that recognizes and a storage unit 72 that stores a plurality of drug information JY corresponding to a plurality of drugs that may be described in a prescription, The drug information acquisition unit 312 acquires the drug information JY related to the drug name character string LM[1] as the specific drug information, and the prescription content of the drug Md[1] indicated by the prescription content character string LN[1] is specified. A prescription determination unit 313 (an example of a “determination unit”) that determines whether or not the drug is suitable for the usage method indicated by the drug information, and a determination result output that outputs information based on the determination result of the prescription content determination unit 313 and a unit 314 (an example of an “output unit”).

That is, according to the modified example, the prescription content determination unit 313 determines that the prescription content of the drug Md[1] indicated by the prescription content character string LN[1] recognized from the prescription by character recognition processing is stored in the drug database as the specific drug information. It is determined whether or not the method of use of the drug indicated by the drug information JY obtained from the server 7 is suitable. For this reason, according to the present embodiment, compared to the aspect in which a drug is prescribed according to the result recognized by character recognition processing from a prescription, there is an error in character recognition in character recognition processing, or a prescription issued by a doctor. It is possible to suppress the possibility of prescribing a drug in a manner that does not conform to the intended usage of the drug due to an error in the description or the like.

<Modification 2>
In the above-described embodiment and modification 1, the drug list information table TBL7 is provided outside the prescription confirmation device 3 (or the prescription confirmation device 3B), but the present invention is limited to such an aspect. not something. The drug list information table TBL7 may be stored, for example, in the storage unit 32 (or storage unit 32B) provided in the prescription confirmation device 3 (or prescription confirmation device 3B).

<Modification 3>
In the above-described embodiment and Modifications 1 and 2, the prescription determination unit 313 determines that a combination of multiple drugs that are cautioned for combined use is not included in the multiple drugs described in the prescription. However, the present invention is not limited to such an embodiment. The prescription content determination unit 313 may at least determine that a combination of a plurality of drugs that are contraindicated for combined use is not included in the plurality of drugs described in the prescription.

<Modification 4>
In the above-described embodiment and modified example 3, the case where the character recognition process is executed in the prescription reading device 1 was illustrated, but the present invention is not limited to such an aspect. For example, the character recognition process may be performed in a device different from the prescription reading device 1 .

FIG. 20 is an explanatory diagram for explaining an example of the outline of the prescription recognition system Sys-C according to this modified example.

As exemplified in FIG. 20, the prescription recognition system Sys-C includes a prescription reading device 1C instead of the prescription reading device 1, and a character recognition device 9. It is configured similarly to system Sys.

FIG. 21 is a sequence chart showing an example of an outline of the operation of the prescription recognition system Sys-C when the prescription recognition system Sys-C performs prescription confirmation processing.

As shown in FIG. 21, in the prescription recognition system Sys-C according to this modified example, when the prescription confirmation process is executed, the prescription reading device 1C executes the prescription imaging process (S1).
Next, the prescription reading device 1C transmits the prescription image information JGS generated in the prescription imaging process of step S1 to the character recognition device 9 (S11).
Then, based on the prescription image information JGS supplied from the prescription reading device 1C, the character recognition device 9 executes character recognition processing for recognizing characters included in the prescription image GS indicated by the prescription image information JGS (S2).
After that, the character recognition device 9 transmits the prescription character information JS generated in step S2 to the prescription confirmation device 3 (S3).
In addition, since the process after step S4 is the same as that of the prescription recognition system Sys which concerns on embodiment, description is omitted.

FIG. 22 is a functional block diagram showing an example of the configuration of the prescription reading device 1C.

As illustrated in FIG. 22, the prescription reading device 1C includes a control unit 11C instead of the control unit 11 and a storage unit 12C instead of the storage unit 12. It is configured in the same manner as the reader 1 .
Among them, the control unit 11C is configured in the same manner as the control unit 11 according to the embodiment except that the character recognition unit 112 is not provided.
In addition, the storage unit 12C does not store the network NW, the prescription information JSS, and the prescription text information JS, and stores the control program PG1C instead of the control program PG1. It is configured in the same manner as the storage unit 12 according to the embodiment.
The hardware configuration of the prescription reading device 1C is the same as the hardware configuration of the prescription reading device 1 according to the embodiment illustrated in FIG. In this modification, the processor 1001 executes the control program PG1C stored in the storage device 1002 and operates according to the control program PG1C, thereby functioning as the control unit 11C.

FIG. 23 is a functional block diagram showing an example of the configuration of the character recognition device 9. As shown in FIG.

As illustrated in FIG. 23, the character recognition device 9 includes a control unit 91 that controls each part of the character recognition device 9, a storage unit 92 that stores various information, and an external device that exists outside the character recognition device 9. and a communication unit 93 that performs communication between
Among them, the control unit 91 includes a character recognition unit 112 .
Further, the storage unit 92 controls the learning model NN described above, the prescription information JSS, the prescription image information JGS supplied from the prescription reading device 1C, the prescription character information JS described above, and each unit of the character recognition device 9. and a control program PG9 for

FIG. 24 is a configuration diagram showing an example of the hardware configuration of the character recognition device 9. As shown in FIG.

As exemplified in FIG. 24, the character recognition device 9 includes a processor 9001 that controls each part of the character recognition device 9, a storage device 9002 that stores various information, and an external device that exists outside the character recognition device 9. and a communication device 9003 for performing communication.

Of these, the storage device 9002 includes one or both of a volatile memory such as a RAM that functions as a work area for the processor 9001 and a nonvolatile memory such as an EEPROM that stores various information such as the control program PG9. The function as the part 92 is provided.
Also, the processor 9001 includes, for example, one or more CPUs. The processor 9001 functions as the control unit 91 by executing the control program PG9 stored in the storage device 9002 and operating according to the control program PG9. Note that the processor 9001 includes hardware such as a GPU, DSP, or FPGA in addition to one or more CPUs, or in place of part or all of one or more CPUs. may be In this case, part or all of the control unit 91 implemented by the processor 9001 may be implemented by hardware such as a DSP.
Further, the communication device 9003 is hardware for communicating with an external device existing outside the character recognition device 9 via one or both of a wired network and a wireless network, and functions as the communication unit 93. offer.

In addition, in this modification, 1 C of prescription reading devices and the terminal device 5 may be installed in a pharmacy, for example. Moreover, in this modification, for example, the prescription reading device 1C may be directly connected to the terminal device 5 without going through the network NW. Further, in this modification, for example, the character recognition device 9, the prescription confirmation device 3, and the drug database server 7 are server devices capable of communicating with the terminal device 5 via the Internet (an example of the network NW). good too. Moreover, in this modification, part or all of the character recognition device 9, the prescription confirmation device 3, and the drug database server 7 may be integrally configured as the same server device.

<Modification 5>
In the embodiment and Modifications 1 to 4 described above, the drug usage information JYS may include lower limit dose information JYQ2 indicating a lower limit dose YQ2, which is the lower limit of the dose of the drug corresponding to the drug information JY. In this case, in step S105 of the dose determination process, the prescription content determination unit 313 determines that the prescribed dose represented by the prescribed dose character string LQ[m] is equal to or lower than the upper limit dose YQ[m][qm] and the lower limit dose YQ2 It may be determined whether or not it is greater than or equal to [m][qm]. Then, in step S111, the determination result output unit 314 may output inappropriate dose notification information IF1[m] when the determination result in step S105 is negative.

<Modification 6>
In the embodiment and Modifications 1 to 5 described above, the drug usage information JYS may include lower limit period information JYR2 indicating a lower limit period YR2, which is the lower limit of the use period of the drug corresponding to the drug information JY. In this case, in step S205 of the period determination process, the prescription content determination unit 313 determines that the prescription period represented by the prescription period character string LR[m] is equal to or shorter than the upper limit period YR[m][qm] and that the lower limit period YR2 It may be determined whether or not it is greater than or equal to [m][qm]. Then, in step S211, the determination result output unit 314 may output period irregularity notification information IF2[m] when the result of determination in step S205 is negative.

<Modification 7>
In the embodiment and Modifications 1 to 6 described above, the determination result output unit 314 determines that the drug name character string LM[m] indicated by the prescription character information JS that the character information acquisition unit 311 acquires from the prescription reading device 1 is a drug If it does not exist in the list information table TBL7, incorrect name notification information IF4[m] may be output indicating that the drug name character string LM[m] is an incorrect name. Specifically, the determination result output unit 314 converts the drug name character string LM[m] indicated by the prescription character information JS obtained by the character information obtaining unit 311 from the prescription reading device 1 into the drug name character string LM[m]. If the drug information acquisition unit 312 does not match any of the drug names YM indicated by the drug information JY acquired from the drug list information table TBL7 in response to , the invalid name notification information IF4[m] may be output. Then, when the incorrect name notification information IF4[m] is output, the determination result output unit 314 puts , a name non-existence mark MK4 may be displayed.

DESCRIPTION OF SYMBOLS 1... Prescription reading apparatus 3... Prescription confirmation apparatus 5... Terminal device 7... Drug database server 11... Control part 31... Control part 111... Image information acquisition part 112... Character recognition part 311... Text information Acquisition unit 312... Drug information acquisition unit 313... Prescription determination unit 314... Determination result output unit Sys... Prescription recognition system.

Claims (8)

A character string indicating the name of the first medicine described in the prescription is recognized as a first name character string by character recognition processing for recognizing characters included in the image, and prescription content of the first medicine described in the prescription. a character information acquisition unit that acquires first character information indicating the first name character string and the first content character string from a recognition unit that recognizes the character string indicating as the first content character string;
A drug information acquisition unit that acquires drug information related to the first name character string as specific drug information from a storage unit that stores a plurality of drug information corresponding to a plurality of drugs that may be described in the prescription. When,
a determination unit that determines whether or not the prescription content of the first drug indicated by the first content character string is compatible with the usage method of the drug indicated by the specific drug information;
an output unit that outputs information based on the result of determination by the determination unit;
comprising
An information processing device characterized by: In the prescription, the dose of the first drug is described as the content of the prescription of the first drug,
each of the plurality of drug information stored in the storage unit includes dose information indicating an upper limit of the dose of the drug corresponding to the drug information;
The determination unit determines whether or not the dose of the first drug indicated by the first content character string is equal to or less than the upper limit of the dose indicated by the dose information included in the specific drug information. and
When the determination result in the first determination process is negative, the output unit outputs information indicating that there is an error in the prescription content of the first medicine described in the prescription.
2. The information processing apparatus according to claim 1, characterized by: The prescription includes the name of the second drug,
The recognition unit recognizes a character string indicating the name of the second medicine described in the prescription as a second name character string by the character recognition process,
The character information acquisition unit acquires second character information indicating the second name character string from the recognition unit,
each of the plurality of drug information stored in the storage unit includes concomitant information regarding a contraindicated drug and a cautionary drug for concomitant use of the drug corresponding to the drug information;
Based on the concomitant information included in the specific drug information, the determining unit determines that the drug having the name related to the second name character string is a drug contraindicated for co-administration of the first drug and a caution drug for co-administration of the first drug. Perform a second determination process for determining whether or not it is included in any of
When the determination result in the second determination process by the determination unit is negative, the output unit outputs information indicating that there is an error in the prescription content of the first drug described in the prescription.
3. The information processing apparatus according to claim 1, wherein: The drug information acquisition unit
when there is drug information including a name that matches the first name character string among the plurality of drug information stored in the storage unit, acquiring the drug information as the specific drug information,
When there is no drug information including a name that matches the first name character string among the plurality of drug information stored in the storage unit, a name whose similarity to the first name character string is equal to or greater than a predetermined similarity Obtaining each of one or more drug information containing as the specific drug information,
4. The information processing apparatus according to any one of claims 1 to 3, characterized by: The determination unit is
When the drug information acquisition unit acquires a plurality of pieces of specific drug information corresponding to a plurality of pieces of drug information from the storage unit, the prescription content of the first drug indicated by the first content character string corresponds to the plurality of specific drug information. Determining whether it is compatible with each of the usage methods of a plurality of drugs indicated by the information,
The output unit
When the determination unit determines that the prescription content of the first drug does not conform to the usage method of at least one drug among the plurality of drug usage methods indicated by the plurality of specific drug information, it is described in the prescription. outputting information to the effect that there is an error in the prescription content of the first drug that has been received;
5. The information processing apparatus according to claim 4, characterized by: an image information acquisition unit that acquires image information representing an image of the prescription;
A character string indicating the name of the first drug described in the prescription is recognized as a first name character string based on the image information, and a character string indicating the prescription content of the first drug described in the prescription. as a first content character string; and
A drug information acquisition unit that acquires drug information related to the first name character string as specific drug information from a storage unit that stores a plurality of drug information corresponding to a plurality of drugs that may be described in the prescription. When,
a determination unit that determines whether or not the prescription content of the first drug indicated by the first content character string is compatible with the usage method of the drug indicated by the specific drug information;
an output unit that outputs information based on the result of determination by the determination unit;
comprising
An information processing device characterized by: the processor,
A character string indicating the name of the first medicine described in the prescription is recognized as a first name character string by character recognition processing for recognizing characters included in the image, and prescription content of the first medicine described in the prescription. a character information acquisition unit that acquires first character information indicating the first name character string and the first content character string from a recognition unit that recognizes the character string indicating as the first content character string;
A drug information acquisition unit that acquires drug information related to the first name character string as specific drug information from a storage unit that stores a plurality of drug information corresponding to a plurality of drugs that may be described in the prescription. When,
a determination unit that determines whether or not the prescription content of the first drug indicated by the first content character string is compatible with the usage method of the drug indicated by the specific drug information;
an output unit that outputs information based on the result of determination by the determination unit;
function as
A program characterized by an image information acquisition unit for acquiring image information indicating an image of a prescription;
A character string indicating the name of the first drug described in the prescription is recognized as a first name character string based on the image information, and a character string indicating the prescription content of the first drug described in the prescription. as a first content character string; and
A drug information acquisition unit that acquires drug information related to the first name character string as specific drug information from a storage unit that stores a plurality of drug information corresponding to a plurality of drugs that may be described in the prescription. When,
a determination unit that determines whether or not the prescription content of the first drug indicated by the first content character string is compatible with the usage method of the drug indicated by the specific drug information;
an output unit that outputs information based on the result of determination by the determination unit;
to function as
A program characterized by

Images