TWI730508B - Drug identification method - Google Patents
Drug identification method Download PDFInfo
- Publication number
- TWI730508B TWI730508B TW108142499A TW108142499A TWI730508B TW I730508 B TWI730508 B TW I730508B TW 108142499 A TW108142499 A TW 108142499A TW 108142499 A TW108142499 A TW 108142499A TW I730508 B TWI730508 B TW I730508B
- Authority
- TW
- Taiwan
- Prior art keywords
- drug
- prescription
- medicine
- bag
- identification
- Prior art date
Links
- 239000003814 drug Substances 0.000 title claims abstract description 163
- 229940079593 drug Drugs 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000000955 prescription drug Substances 0.000 claims abstract description 51
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 31
- 238000012377 drug delivery Methods 0.000 claims abstract description 6
- 229940126532 prescription medicine Drugs 0.000 claims description 9
- 239000003086 colorant Substances 0.000 claims 1
- 238000004806 packaging method and process Methods 0.000 description 9
- 238000012790 confirmation Methods 0.000 description 7
- 238000007689 inspection Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 241000282412 Homo Species 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 241000700605 Viruses Species 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 238000009513 drug distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 206010025482 malaise Diseases 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000005022 packaging material Substances 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
本發明係關於一種藥物辨識方法,主要為提升人工智慧學習效率,先在配藥室之人員依據處方箋將處方藥置於藥袋中;再由藥袋辨識系統對藥袋實行藥物辨識,比對該處方箋得到針對該處方藥之確定正確、確定錯誤或無法確認狀態;接著,依據該處方藥之確定錯誤或無法確認狀態,由發藥室之人員再次檢驗該藥袋之各處方藥正確性,並回報人工智慧單元;最後,將該藥袋交付給取藥人員,重複上述步驟。 The present invention relates to a drug identification method. It is mainly to improve the learning efficiency of artificial intelligence. First, the personnel in the dispensing room place the prescription drugs in the drug bag according to the prescription; then the drug bag identification system performs the drug identification on the drug bag, and compares it The prescription note gets the correctness, incorrectness, or unconfirmation status of the prescription drug; then, based on the incorrectness or unconfirmation status of the prescription drug, the staff in the drug delivery room re-checks the correctness of the prescriptions of the medicine bag and reports to the labor Smart unit; finally, deliver the medicine bag to the medicine picker, and repeat the above steps.
Description
本發明係關於一種藥品辨識方法,特別指經由人類驗證回饋資訊,再依此強化人工智慧學習標的,並由重複累積經驗過程來明顯提高機器學習效率。 The present invention relates to a method for identifying medicines, and specifically refers to verifying feedback information by humans, and then strengthening artificial intelligence learning targets based on this, and repetitively accumulating experience processes to significantly improve the efficiency of machine learning.
從人類出生開始必然經歷生老病死四大階段,在初生嬰兒開始會因抗體虛弱及環境因數而導致生病,而成長的過程中則是在人與人的接觸及身體狀況變差等情況下讓病毒有機可乘進而生病,最後因肉體老化除了需要長期照護外,也增加生病的機會。 Human beings must go through the four major stages of birth, old age, sickness and death from birth. Newborn babies will become ill due to weak antibodies and environmental factors, and the growth process will allow the virus to become organic due to human-to-human contact and deterioration of physical conditions. You can take advantage of it and get sick. In the end, besides long-term care due to physical aging, it also increases the chance of getting sick.
其中,醫療人員『發藥錯誤』為常見的醫療糾紛之主因;在臺灣,醫院病房部分常是發藥錯誤的高意外區,而因藥品的錯誤將產生病患的醫療安全問題,嚴重可能導致病患致死;就此,眾多醫院逐漸採用多種方式來改善此類問題。 Among them, medical staff’s "medicine distribution errors" are the main cause of common medical disputes; in Taiwan, hospital wards are often areas of high accidents with drug distribution errors, and medical safety problems for patients due to drug errors will be serious, which may lead to serious problems. The patient died; in this regard, many hospitals have gradually adopted a variety of methods to improve such problems.
在改善『發藥錯誤』問題部分,有增設人力來複檢,又或機器配藥,再不然透過習用藥物辨識裝置來輔助改善問題;然而,人力複檢成本高,且改善有限,又機器配藥有其藥品限制,因此未來方向因以藥品辨識為主。 In the part of improving the problem of "dispensing errors", there are additional manpower to recheck, or machine to dispense, otherwise the conventional drug identification device is used to help improve the problem; however, the cost of manpower recheck is high, and the improvement is limited, and there is a problem with machine dispensing. Its medicines are restricted, so the future direction is mainly based on medicine identification.
關於藥品辨識之文獻,多個專利如下: Regarding the literature on drug identification, several patents are as follows:
日本2014-135846揭示一種分藥裝置,其目的在於以簡單且 確實之方式進行包裝前之藥劑的鑑定檢查,其包括有:複數個藥劑盒;手工分配藥劑供給裝置;在包裝紙上印刷在處方資料中所包含的服用資訊的印刷手段;包裝手段,其被供給有包裝紙,根據處方資料而以1包份為單位對從藥劑盒或者上述手工分配藥劑供給裝置所分藥之藥劑進行包裝;使藉由包裝手段而被包裝紙所包裝之前的藥劑產生旋轉的旋轉手段;對藉由旋轉手段而使之旋轉之藥劑與識別部一同進行拍攝的攝像手段;控制手段,其實施鑑定檢查處理,該鑑定檢查處理係從藉由攝像手段所被拍攝的藥劑中讀取識別部,並根據所讀取到的識別部而將藥劑資訊加以抽出,並與在處方資料中所包含的藥劑資訊進行比較。 Japan 2014-135846 disclosed a medicine dispensing device, the purpose of which is to be simple and The authentic method for the identification and inspection of the medicine before packaging includes: a plurality of medicine boxes; manual dispensing medicine supply device; printing means for printing the taking information contained in the prescription information on the packaging paper; packaging means, which are supplied With packaging paper, the medicines dispensed from the medicine box or the above-mentioned manual dispensing medicine supply device are packaged in units of 1 pack according to the prescription information; the medicine before being packaged by the packaging paper by the packaging means is rotated Rotating means; an imaging means that takes pictures of the medicine that is rotated by the rotating means together with the recognition unit; the control means carries out identification inspection processing, which reads from the medicines photographed by the imaging means Take the identification part, extract the medicine information based on the read identification part, and compare it with the medicine information contained in the prescription data.
日本2015-133109揭示一種鑑定檢查支援系統,藉由具備鑑定檢查顯示處理部,而能支援藥劑師關於在藥片分包裝置中被分包的藥片的鑑定檢查業務,該鑑定檢查顯示處理部是以分包單位來顯示當藥片以包裝材料分包之前被攝影而得的前述藥片的攝影圖像,並顯示基於前述藥片的攝影圖像所包含的前述藥片的識別資訊與前述處方資料而實行的鑑定檢查處理的結果,該藥片是在藥片分包裝置中基於處方資料而從藥片藥盒和手動撒藥單元之中的任一方或雙方所配發。 Japan 2015-133109 discloses an identification inspection support system that has an identification inspection display processing unit that can support pharmacists' identification inspections of tablets packaged in a tablet packaging device. The identification inspection display processing unit is The subcontracting unit displays the photographic images of the tablets taken before the tablets are packaged with packaging materials, and displays the identification based on the identification information of the tablets contained in the photographic images of the tablets and the aforementioned prescription data. As a result of the inspection processing, the tablet is dispensed from either or both of the tablet kit and the manual drug dispensing unit based on the prescription data in the tablet packaging device.
臺灣I277007揭示一種射頻辨識系統應用於藥品管理之方法,其係包括有下列之步驟:(a)將複數藥品收納於一藥品箱中,該藥品箱設置有一電子控制鎖,以控制該藥品箱之箱門開關;(b)該電子控制鎖係可以人員之識別證加以辨識開啟;(c)經由一人員識別天線發射之一射頻信號藉以辨識人員之識別證,並將人員識別資料傳送至一伺服器資料庫;(d)藥品箱內設置有至少一個以上之藥品識別天線,該藥品識別天線可偵測辨識 藥品上之電子標籤;(e)射頻辨識讀取器經由射頻信號收集藥品之新資料,再經由一伺服器資料庫完成藥品取出或置入之新資料與現有資料比較之工作。 Taiwan I277007 discloses a method for applying radio frequency identification system to medicine management, which includes the following steps: (a) Store a plurality of medicines in a medicine box, and the medicine box is equipped with an electronic control lock to control the medicine box. Box door switch; (b) The electronic control lock can be identified and opened by the identification card of the person; (c) A radio frequency signal is transmitted through a person identification antenna to identify the identification card of the person, and the identification data of the person is sent to a servo (D) At least one medicine identification antenna is installed in the medicine box, and the medicine identification antenna can detect and identify Electronic tags on medicines; (e) The radio frequency identification reader collects new data of medicines through radio frequency signals, and then completes the task of comparing the new data taken out or placed in medicines with existing data through a server database.
但是,單次的影像辨識的確定性略顯不足,而無線訊號則是藥品種類和包裝限制較多,且與臺灣現有醫院流程無法完美融合,因此本發明之目的係在提供一種藥物辨識方法,來改進以上陳述之相關問題。 However, the certainty of a single image recognition is slightly insufficient, and the wireless signal has more restrictions on drug types and packaging, and cannot be perfectly integrated with the existing hospital processes in Taiwan. Therefore, the purpose of the present invention is to provide a drug recognition method. To improve the related issues stated above.
有鑑於以上問題本發明係提供一種藥物辨識方法,是以影像辨識搭配人員再確認來提升學習效果。 In view of the above problems, the present invention provides a drug identification method, which uses image identification and reconfirmation by personnel to enhance the learning effect.
因此,本發明之主要目的係在提供一種藥物辨識方法,由人員回覆可靠狀態來校正人工智慧的不確定性,進而改善下次的確認。 Therefore, the main purpose of the present invention is to provide a drug identification method, which allows personnel to respond to the reliability status to correct the uncertainty of artificial intelligence, thereby improving the next confirmation.
本發明之再一目的係在提供一種藥物辨識方法,利用藥袋搭配特殊紋路表面結構,可保有病患隱私及辨識最佳化。 Another object of the present invention is to provide a medicine identification method, which uses a medicine bag with a special textured surface structure to maintain patient privacy and optimize identification.
本發明之再一目的係在提供一種藥物辨識方法,憑藉一顯示設備呈現處方藥,提醒人員正確處方藥外觀,減少放置錯誤機率。 Another object of the present invention is to provide a medicine identification method that uses a display device to present prescription medicines, remind personnel of the correct appearance of the prescription medicines, and reduce the chance of placing errors.
本發明之再一目的係在提供一種藥物辨識方法,運用藥袋表面之處方標籤來確認處方箋,提高辨識確認性。 Another object of the present invention is to provide a medicine identification method that uses the label on the surface of the medicine bag to confirm the prescription and improve the identification and confirmation.
本發明之再一目的係在提供一種藥物辨識方法,使用藥袋校正辨識系統對該藥袋實行藥物辨識,以回報該人工智慧單元,提升單次處方藥資料收集。 Another object of the present invention is to provide a medicine identification method that uses a medicine bag calibration identification system to perform medicine identification on the medicine bag to report the artificial intelligence unit and improve the collection of single prescription medicine data.
為達成上述目的,本發明所使用的主要技術手段是採用以下技術方案來實現的。本發明為一種藥物辨識方法,其步驟包括:步驟A:在 一配藥室之一人員依據一處方箋將至少一處方藥置於一藥袋中;步驟B:由一藥袋辨識系統對該藥袋實行藥物辨識,比對該處方箋得到針對該處方藥之確定正確、確定錯誤或無法確認狀態;步驟C:依據該處方藥之確定錯誤或無法確認狀態,由一發藥室之一人員再次檢驗該藥袋之各處方藥正確性,並回報一人工智慧單元;步驟D:將該藥袋交付給一取藥人員,重複該些步驟A到D。 In order to achieve the above objective, the main technical means used in the present invention are achieved by the following technical solutions. The present invention is a drug identification method, the steps of which include: Step A: A person in the dispensing room places at least one prescription drug in a drug bag according to a prescription; Step B: A drug bag identification system performs drug identification on the drug bag, and compares the prescription to obtain the correct determination for the prescription drug , Confirm the error or the status of the unconfirmed; Step C: According to the confirmed error or the unconfirmed status of the prescription drug, a staff of a drug delivery room will re-check the correctness of the prescriptions of the medicine bag and report an artificial intelligence unit; Step D : Deliver the medicine bag to a medicine picker, and repeat these steps A to D.
本發明的目的及解決其技術問題還可採用以下技術措施步驟進一步實現。 The purpose of the present invention and the solution of its technical problems can be further achieved by adopting the following technical measures.
前述的方法,其中該藥袋一側為透明、霧面或特殊紋路表面結構,使該藥袋辨識系統得以實行藥物辨識。 In the aforementioned method, one side of the medicine bag has a transparent, matte or special textured surface structure, so that the medicine bag identification system can perform medicine identification.
前述的方法,其中該步驟A時,由一顯示設備呈現該處方藥外觀。 In the aforementioned method, in step A, the appearance of the prescription drug is presented by a display device.
前述的方法,其中該步驟A後,由該藥袋辨識系統透過該藥袋表面之一處方標籤確認為該處方箋。 In the aforementioned method, after step A, the medicine bag identification system confirms the prescription note through a prescription label on the surface of the medicine bag.
前述的方法,其中該步驟B中,該藥袋辨識系統係透過該人工智慧單元依據該處方藥之數量、該處方藥之表面文字、該處方藥之外形或該處方藥之顏色其一或以上組合為辨識依據。 In the foregoing method, in step B, the medicine bag identification system uses the artificial intelligence unit to identify the basis of one or more combinations of the quantity of the prescription drug, the surface text of the prescription drug, the shape of the prescription drug, or the color of the prescription drug .
前述的方法,其中該步驟C時,由另一顯示設備呈現該處方藥外觀。 In the foregoing method, in step C, another display device presents the appearance of the prescription drug.
前述的方法,其中該步驟C後,再由一藥袋校正辨識系統對該藥袋實行藥物辨識,並回報該人工智慧單元。 In the aforementioned method, after step C, a medicine bag calibration and identification system performs medicine identification on the medicine bag and reports the artificial intelligence unit.
前述的方法,其中該藥袋由一輸送帶設備帶動從該配藥室移 至該發藥室。 The foregoing method, wherein the medicine bag is moved from the dispensing room by a conveyor belt device Go to the medicine room.
前述的方法,其中該人工智慧單元依據該步驟B之該處方藥之狀態及步驟C之再次檢驗該處方藥正確性來訓練判別能力。 In the aforementioned method, the artificial intelligence unit trains the discrimination ability according to the state of the prescription drug in the step B and the correctness of the prescription drug in the step C.
前述的方法,其中該人工智慧單元依據該藥袋校正辨識系統之圖像來訓練判別能力。 In the aforementioned method, the artificial intelligence unit trains the discrimination ability according to the image of the medicine bag correction and identification system.
相較於習知技術,本發明具有功效在於:(1)利用人員回覆可靠狀態來校正人工智慧的不確定性,進而改善人工智慧之限制;(2)經由藥袋搭配特殊紋路表面結構,可保有病患隱私及辨識最佳化;(3)憑藉一顯示設備呈現處方藥,提醒人員正確處方藥外觀,減少放置錯誤機率來提昇人員穩定性。 Compared with the conventional technology, the present invention has the following effects: (1) Using the reliable state of the personnel's reply to correct the uncertainty of artificial intelligence, thereby improving the limitation of artificial intelligence; (2) Through the combination of the medicine bag and the special texture surface structure, it can be Maintain patient privacy and optimize identification; (3) Relying on a display device to present prescription drugs, remind personnel of the correct appearance of prescription drugs, reduce the chance of placing errors, and improve personnel stability.
A‧‧‧步驟A A‧‧‧Step A
A1‧‧‧步驟A1 A1‧‧‧Step A1
A2:步驟A2 A2: Step A2
B:步驟B B: Step B
C:步驟C C: Step C
C1:步驟C1 C1: Step C1
C2:步驟C2 C2: Step C2
D:步驟D D: Step D
U:處方箋 U: Prescription
U1:處方標籤 U1: Prescription label
V:處方藥 V: prescription drugs
W:藥袋 W: medicine bag
X:藥袋辨識系統 X: Medicine bag identification system
Y:人工智慧單元 Y: Artificial Intelligence Unit
Z:藥袋校正辨識系統 Z: Medicine bag correction and identification system
10:配藥室 10: Dispensing room
11:人員 11: personnel
12:顯示設備 12: display device
20:發藥室 20: Medicine distribution room
21:人員 21: Staff
22:顯示設備 22: display device
30:取藥人員 30: Medicine picker
40:輸送帶設備 40: Conveyor belt equipment
第1圖:為本發明之第一實施型態之流程圖。 Figure 1: is a flow chart of the first embodiment of the present invention.
第2圖:為本發明之第二實施型態之流程圖。 Figure 2: is a flow chart of the second embodiment of the present invention.
第3圖:為本發明之第三實施型態之流程圖。 Figure 3: A flow chart of the third embodiment of the present invention.
第4a圖:為本發明之最佳實施型態之步驟A示意圖。 Figure 4a: is a schematic diagram of step A of the best embodiment of the present invention.
第4b圖:為本發明之最佳實施型態之步驟B示意圖。 Figure 4b: is a schematic diagram of step B of the best embodiment of the present invention.
第4c圖:為本發明之最佳實施型態之步驟C示意圖。 Figure 4c: is a schematic diagram of step C of the best embodiment of the present invention.
第4d圖:為本發明之最佳實施型態之步驟D示意圖。 Figure 4d: is a schematic diagram of step D of the best embodiment of the present invention.
為了讓本發明之目的、特徵與功效更明顯易懂,以下特別列舉本發明之最佳實施型態:首先,請參考第1圖表述之第一實施型態,本發明為一種藥 物辨識方法,其包含步驟A(A)、步驟B(B)、步驟C(C)及步驟D(D)。 In order to make the purpose, features and effects of the present invention more obvious and understandable, the following specifically lists the best embodiment of the present invention: First, please refer to the first embodiment described in the first diagram. The present invention is a kind of medicine. The object identification method includes step A (A), step B (B), step C (C), and step D (D).
其中,第1圖之步驟A(A)係為在一配藥室(10)之一人員(11)依據一處方箋(U)將至少一處方藥(V)置於一藥袋(W)中。 Among them, step A (A) in Figure 1 is that a person (11) of a dispensing room (10) places at least one prescription medicine (V) in a medicine bag (W) according to a prescription note (U).
該步驟A(A)目的係如第4a圖所示,由人員(11)根據處方箋(U)上陳述之各處方藥(V),人工將各處方藥(V)放置於藥袋(W);其中,配藥室(10)係具有保管處方藥(V)及分配處方藥(V)之場所;而,該人員(11)係為配置於配藥室(10)協助將處方藥(V)分配者;再,處方箋(U)是醫師針對病人病症所開具之醫療處置,標示病人資料、藥名、劑量、數量、醫師姓名等內容;其中,處方藥(V)是藥品管理上的界定,指須憑執業醫師、執業助理醫師處方或藥房工作人員同意即可調配、購買和使用的藥品;該藥袋(W)係交付之藥劑容器或包裝除應標示病人資料、藥名、劑量、數量、用法、作用、警語或副作用外,另應包含機構名稱地點、醫師姓名、調劑者姓名及調劑時間等內容。 The purpose of this step A (A) is to manually place each prescription (V) in the medicine bag (W) according to the prescriptions (V) stated on the prescription sheet (U) as shown in Figure 4a. Among them, the dispensing room (10) is a place for storing prescription drugs (V) and dispensing prescription drugs (V); and the person (11) is a person who is deployed in the dispensing room (10) to assist in dispensing prescription drugs (V); further, Prescription (U) is a medical treatment prescribed by a physician for a patient’s symptoms, indicating patient information, drug name, dosage, quantity, and physician’s name; among them, prescription drug (V) is a definition of drug management, which means that it requires a licensed physician , Medicines that can be dispensed, purchased, and used with the prescription of a practicing assistant physician or the consent of the pharmacy staff; the medicine bag (W) is the delivered medicine container or package except that the patient information, the name of the medicine, the dosage, the quantity, the usage, and the function In addition to warnings or side effects, it should also include the name of the institution and place, the name of the physician, the name of the person who made the adjustment, and the time of the adjustment.
其中,第1圖之步驟B(B)係為由一藥袋辨識系統(X)對該藥袋(W)實行藥物辨識,比對該處方箋(U)得到針對該處方藥(V)之確定正確、確定錯誤或無法確認狀態。 Among them, step B (B) in Figure 1 is to perform drug identification on the medicine bag (W) by a medicine bag identification system (X), and compare the prescription note (U) to obtain a determination for the prescription medicine (V) Correct, incorrect, or unable to confirm the status.
該步驟B(B)作用為如第4b圖表示,藥袋辨識系統(X)透過藥袋(W)針對內容之該處方藥(V)與該處方箋(U)做出比對;較佳者,該藥袋(W)一側為透明、霧面或特殊紋路表面結構,使該藥袋辨識系統(X)得以針對該藥袋(W)實行處方藥(V)辨識;其中,該藥袋辨識系統(X)係透過人工智慧單元(Y)依據處方藥(V)之數量、處方藥(V)之表面文字、處方藥(V)之外形或處方藥(V)之顏色其一或以上組合為辨識依據,依此可得到針對該處方藥(V)之確定正確、確定錯誤或無法確認狀態。 The function of this step B (B) is as shown in Figure 4b, the medicine bag identification system (X) compares the content of the prescription medicine (V) with the prescription note (U) through the medicine bag (W); better , The medicine bag (W) has a transparent, matte or special texture surface structure on one side, so that the medicine bag identification system (X) can perform prescription medicine (V) identification for the medicine bag (W); among them, the medicine bag identification The system (X) is based on one or more combinations of the number of prescription drugs (V), the surface text of the prescription drugs (V), the shape of the prescription drugs (V), or the color of the prescription drugs (V) through the artificial intelligence unit (Y). According to this, the correctness, incorrectness, or unconfirmation status of the prescription drug (V) can be obtained.
其中,第1圖之步驟C(C)係為依據該處方藥(V)之確定錯誤或無法確認狀態,由一發藥室(20)之一人員(21)再次檢驗該藥袋(W)之各處方藥(V)正確性,並回報一人工智慧單元(Y)。 Among them, step C (C) in Figure 1 is based on the prescription drug (V) determination error or unrecognizable status, a staff (21) of a drug delivery room (20) re-examines the drug bag (W) Each prescription drug (V) is correct, and an artificial intelligence unit (Y) is reported.
該步驟C(C)如第4C圖呈現,目標為由人員(21)人工再確認藥袋(W)之各處方藥(V)正確性,再回報人工智慧單元(Y),使人工智慧單元(Y)根據回報學習確認;其中,發藥室(20)係指具備暫時存放藥袋(W),並將藥袋(W)確認交付給予取藥人員(30)之場所;而,該人員(21)係為配置於發藥室(20),再確認藥袋(W)之各處方藥(V)正確性,並協助將藥袋(W)分配者;該人工智慧單元(Y)係指由人製造出來的機器所表現出來的智慧型。通常人工智慧是指透過普通電腦程式來呈現人類智慧型的技術,目前人工智慧已經有初步成果,甚至在一些影像辨識、語言分析、棋類遊戲等等單方面的能力達到了超越人類的水平。 This step C (C) is shown in Figure 4C. The goal is to manually reconfirm the correctness of each prescription (V) in the medicine bag (W) by the personnel (21), and then report the artificial intelligence unit (Y) so that the artificial intelligence unit ( Y) Confirmation according to the return study; among them, the medicine distribution room (20) refers to the place where the medicine bag (W) is temporarily stored and the medicine bag (W) is confirmed to be delivered to the person who takes medicine (30); and the person ( 21) It is the person who is placed in the medicine distribution room (20), and then confirms the correctness of each prescription (V) of the medicine bag (W), and assists in the distribution of the medicine bag (W); the artificial intelligence unit (Y) refers to the reason The intelligence shown by the machines made by humans. Usually artificial intelligence refers to the technology that presents human intelligence through ordinary computer programs. At present, artificial intelligence has made preliminary results, and even some unilateral capabilities such as image recognition, language analysis, and board games have reached a level that surpasses humans.
其中,第1圖之步驟D(D)係為將該藥袋(W)交付給一取藥人員(30),重複該些步驟A到D。 Wherein, step D (D) in Figure 1 is to deliver the medicine bag (W) to a medicine picker (30), and repeat the steps A to D.
該步驟D(D)如第4C圖呈現,目的是將步驟C(C)確認完的藥袋(W)交付取藥人員(30),並重複以上步驟強化該人工智慧單元(Y)辨識能力;其中,取藥人員(30)係指病患或協助病患者,其為拿取藥袋(W)之人員。 This step D (D) is shown in Figure 4C, and the purpose is to deliver the medicine bag (W) confirmed in step C (C) to the medicine picker (30), and repeat the above steps to strengthen the recognition ability of the artificial intelligence unit (Y) ; Among them, the person who takes medicine (30) refers to the patient or assisting patient, who is the person who takes the medicine bag (W).
以上,該人工智慧單元(Y)依據該步驟B之該處方藥(V)之狀態及步驟C之再次檢驗該處方藥(V)正確性來訓練判別能力。 Above, the artificial intelligence unit (Y) trains the discrimination ability according to the state of the prescription drug (V) in the step B and the correctness of the prescription drug (V) in the step C.
其中,如第4a、4b及4c圖呈現,本實施例該藥袋(W)由一輸送帶設備(40)帶動從該配藥室(10)移至該發藥室(20)。 Wherein, as shown in Figures 4a, 4b and 4c, the medicine bag (W) of this embodiment is moved from the medicine dispensing room (10) to the medicine dispensing room (20) by a conveyor belt device (40).
請參考第2圖所示,為本發明一種藥物辨識方法之第二實施型態,在第一實施型態與第1、4a、4b及4c圖中已說明的特徵與第2圖相同者,於第2圖的符號標示或省略不再贅述。第二實施型態與第一實施型態的主要方法差異在於分別增設顯示設備(12,22)於配藥室(10)及發藥室(20)。 Please refer to Figure 2, which is the second embodiment of a drug identification method of the present invention. The features described in the first embodiment and Figures 1, 4a, 4b, and 4c are the same as those in Figure 2. The symbols or omissions in Figure 2 will not be repeated. The main method difference between the second embodiment and the first embodiment is to add display devices (12, 22) in the dispensing room (10) and the dispensing room (20) respectively.
請參考第2圖表述之第二實施型態,本發明為一種藥物辨識方法,其包含步驟A(A)、步驟A1(A1)、步驟B(B)、步驟C(C)、步驟C1(C1)及步驟D(D)。 Please refer to the second embodiment described in Figure 2. The present invention is a drug identification method, which includes step A(A), step A1(A1), step B(B), step C(C), step C1( C1) and step D(D).
首先,第2圖之步驟A(A)與第4a圖係為在一配藥室(10)之一人員(11)依據一處方箋(U)將至少一處方藥(V)置於一藥袋(W)中。 First, the steps A (A) and 4a of Figure 2 show that a person (11) in a dispensing room (10) places at least one prescription drug (V) in a medicine bag ( W)中.
在該步驟A(A)同時,增設步驟A1(A1),步驟A1(A1)係由一顯示設備(12)(如第4a圖表示)呈現該處方藥(V)外觀;依此,由該處方藥(V)外觀提醒人員(11)取藥確認。 At the same time as step A(A), step A1(A1) is added. Step A1(A1) is displayed by a display device (12) (as shown in Figure 4a) to present the appearance of the prescription drug (V); accordingly, the prescription drug (V) (V) Appearance reminds personnel (11) Confirmation of taking medicine.
跟著,第2圖之步驟B(B)與第4b圖係為由一藥袋辨識系統(X)對該藥袋(W)實行藥物辨識,比對該處方箋(U)得到針對該處方藥(V)之確定正確、確定錯誤或無法確認狀態。 Then, the steps B (B) and 4b of Figure 2 show that a drug bag identification system (X) performs drug identification on the drug bag (W), and compares the prescription (U) to obtain the prescription drug ( V) The confirmation is correct, the confirmation is wrong or the status cannot be confirmed.
接著,第2圖之步驟C(C)與第4c圖係為依據該處方藥(V)之確定錯誤或無法確認狀態,由一發藥室(20)之一人員(21)再次檢驗該藥袋(W)之各處方藥(V)正確性,並回報一人工智慧單元(Y)。 Next, steps C (C) and 4c of Figure 2 are based on the prescription drug (V) determination error or unrecognizable status, and a staff member (21) of a drug delivery room (20) re-inspects the drug bag (W) Each prescription (V) is correct, and an artificial intelligence unit (Y) is reported.
在該步驟C(C)同時,增設步驟C1(C1),步驟C1(C1) 係由一顯示設備(22)(如第4c圖表示)呈現該處方藥(V)外觀;依此,由該處方藥(V)外觀提醒人員(21)檢查處方藥(V)得以確認。 At the same time as step C (C), add step C1 (C1), step C1 (C1) A display device (22) (as shown in Figure 4c) presents the appearance of the prescription drug (V); accordingly, the prescription drug (V) appearance reminder (21) to check the prescription drug (V) for confirmation.
最後,第2圖之步驟D(D)與第4c圖係為將該藥袋(W)交付給一取藥人員(30),重複該些步驟A到D。 Finally, steps D (D) and 4c in Fig. 2 show that the medicine bag (W) is delivered to a medicine picker (30), and these steps A to D are repeated.
請參考第3圖所示,為本發明一種藥物辨識方法之第三實施型態,在第一實施型態與第1、4a、4b及4c圖中已說明的特徵與第3圖相同者,於第1、4a、4b及4c圖的符號標示或省略不再贅述。第三實施型態與第一實施型態的主要方法差異在於步驟A(A)後增加驟A2(A2)、步驟C(C)後增加驟C2(C2)。 Please refer to Figure 3, which is the third embodiment of a drug identification method of the present invention. The features described in the first embodiment and Figures 1, 4a, 4b, and 4c are the same as those in Figure 3. The symbols in Figures 1, 4a, 4b and 4c are marked or omitted and will not be repeated here. The main method difference between the third embodiment and the first embodiment is that step A2 (A2) is added after step A (A), and step C2 (C2) is added after step C (C).
請參考第3圖表述之第三實施型態,本發明為一種藥物辨識方法,其包含步驟A(A)、步驟A2(A2)、步驟B(B)、步驟C(C)、步驟C2(C2)及步驟D(D)。 Please refer to the third embodiment described in Figure 3. The present invention is a drug identification method, which includes step A (A), step A2 (A2), step B (B), step C (C), step C2 ( C2) and step D(D).
首先,第3圖之步驟A(A)與第4a圖係為在一配藥室(10)之一人員(11)依據一處方箋(U)將至少一處方藥(V)置於一藥袋(W)中。 First, the steps A (A) and 4a of Fig. 3 show that a person (11) in a dispensing room (10) places at least one prescription medicine (V) in a medicine bag according to a prescription (U). W)中.
在該步驟A(A)後,增設步驟A2(A2),步驟A2(A2)係由該藥袋辨識系統(X)透過該藥袋(W)表面之一處方標籤(U1)確認為該處方箋(U);依此可防止步驟B(B)因排單混亂導致順序錯誤造成辨識上的困擾;該處方標籤(U1)可為二維條碼,二維條碼有容錯機制在即使沒有辨識到全部的條碼、或是說條碼有汙損時,也可以正確地還原條碼上的資訊。 After step A(A), step A2(A2) is added. Step A2(A2) is confirmed by the medicine bag identification system (X) through a prescription label (U1) on the surface of the medicine bag (W) as the prescription Note (U); in this way, it can prevent the identification trouble caused by the wrong order due to the disorder of the order in step B (B); the prescription label (U1) can be a two-dimensional bar code, and the two-dimensional bar code has a fault-tolerant mechanism even if it is not recognized All the barcodes, or when the barcodes are dirty, the information on the barcodes can be restored correctly.
跟著,第3圖之步驟B(B)與第4b圖係為由一藥袋辨識系統 (X)對該藥袋(W)實行藥物辨識,比對該處方箋(U)得到針對該處方藥(V)之確定正確、確定錯誤或無法確認狀態。 Then, step B(B) in Figure 3 and Figure 4b are based on a medicine bag identification system (X) Perform drug identification on the medicine bag (W), and compare the prescription note (U) to obtain the correct, incorrect, or unconfirmed status for the prescription drug (V).
接著,第3圖之步驟C(C)與第4c圖係為依據該處方藥(V)之確定錯誤或無法確認狀態,由一發藥室(20)之一人員(21)再次檢驗該藥袋(W)之各處方藥(V)正確性,並回報一人工智慧單元(Y)。 Next, steps C (C) and 4c in Figure 3 are based on the prescription drug (V) determination error or unrecognizable status, and a staff (21) of a drug delivery room (20) re-inspects the drug bag (W) Each prescription (V) is correct, and an artificial intelligence unit (Y) is reported.
在該步驟C(C)後,增設步驟C2(C2),步驟C2(C2)如第4d圖所示係再由一藥袋校正辨識系統(Z)對該藥袋(W)實行藥物辨識,並回報該人工智慧單元(Y);其中,該人工智慧單元(Y)依據該藥袋校正辨識系統(Z)之圖像來訓練判別能力。 After step C (C), step C2 (C2) is added. Step C2 (C2) is shown in Figure 4d by a drug bag correction and identification system (Z) to perform drug identification on the drug bag (W). And report the artificial intelligence unit (Y); wherein, the artificial intelligence unit (Y) trains the discrimination ability according to the image of the medicine bag correction and identification system (Z).
最後,第3圖之步驟D(D)與第4c圖係為將該藥袋(W)交付給一取藥人員(30),重複該些步驟A到D。 Finally, steps D (D) and 4c in Fig. 3 show that the medicine bag (W) is delivered to a medicine picker (30), and the steps A to D are repeated.
以上各實施型態,由人員回覆可靠狀態來校正人工智慧的不確定性,進而改善下次的確認能力。因此本發明之功效有別於一般藥物辨識方法,此於藥物辨識當中實屬首創,符合發明專利要件,爰依法俱文提出申請。 In each of the above implementation types, the personnel respond to the reliability status to correct the uncertainty of artificial intelligence, thereby improving the ability to confirm next time. Therefore, the effect of the present invention is different from the general drug identification method. It is the first in drug identification and meets the requirements of a patent for invention, so an application is filed in accordance with the law.
惟,需再次重申,以上所述者僅為本發明之較佳實施型態,舉凡應用本發明說明書、申請專利範圍或圖式所為之等效變化,仍屬本發明所保護之技術範疇,因此本發明之保護範圍當視後附之申請專利範圍所界定者為準。 However, it needs to be reiterated that the above are only the preferred implementation modes of the present invention. Any equivalent changes made by applying the specification, patent application scope, or drawings of the present invention still belong to the technical scope protected by the present invention. Therefore, The scope of protection of the present invention shall be subject to those defined by the attached patent scope.
A‧‧‧步驟A A‧‧‧Step A
B‧‧‧步驟B B‧‧‧Step B
C‧‧‧步驟C C‧‧‧Step C
D‧‧‧步驟D D‧‧‧Step D
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW108142499A TWI730508B (en) | 2019-11-22 | 2019-11-22 | Drug identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW108142499A TWI730508B (en) | 2019-11-22 | 2019-11-22 | Drug identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| TW202121323A TW202121323A (en) | 2021-06-01 |
| TWI730508B true TWI730508B (en) | 2021-06-11 |
Family
ID=77516722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW108142499A TWI730508B (en) | 2019-11-22 | 2019-11-22 | Drug identification method |
Country Status (1)
| Country | Link |
|---|---|
| TW (1) | TWI730508B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200811678A (en) * | 2006-08-24 | 2008-03-01 | Ko Da Pharmaceutical Co Ltd | Drug prescription inspection system and method thereof |
| TW201222308A (en) * | 2010-11-19 | 2012-06-01 | Sun Ten Pharmaceutical Co Ltd | Integrated intelligent pharmacy management system |
| TWM441869U (en) * | 2012-06-21 | 2012-11-21 | Mackay Memorial Hospital | Drug re-check device |
| TW201437942A (en) * | 2013-03-20 | 2014-10-01 | Univ Nan Kai Technology | Automatic image identification and auxiliary dispensing system |
| US20160251160A1 (en) * | 2008-12-05 | 2016-09-01 | Remedi Technology Holdings, Llc | Pharmaceutical dispensing system and associated method |
-
2019
- 2019-11-22 TW TW108142499A patent/TWI730508B/en active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200811678A (en) * | 2006-08-24 | 2008-03-01 | Ko Da Pharmaceutical Co Ltd | Drug prescription inspection system and method thereof |
| US20160251160A1 (en) * | 2008-12-05 | 2016-09-01 | Remedi Technology Holdings, Llc | Pharmaceutical dispensing system and associated method |
| TW201222308A (en) * | 2010-11-19 | 2012-06-01 | Sun Ten Pharmaceutical Co Ltd | Integrated intelligent pharmacy management system |
| TWM441869U (en) * | 2012-06-21 | 2012-11-21 | Mackay Memorial Hospital | Drug re-check device |
| TW201437942A (en) * | 2013-03-20 | 2014-10-01 | Univ Nan Kai Technology | Automatic image identification and auxiliary dispensing system |
Also Published As
| Publication number | Publication date |
|---|---|
| TW202121323A (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210050106A1 (en) | Apparatus and method for recognition of patient activities when obtaining protocol adherence data | |
| US10357428B2 (en) | Medication organizer tray apparatus | |
| US11314964B2 (en) | Apparatus and method for determination of medication location | |
| US10565545B2 (en) | Drug inspection support apparatus and method | |
| US9345636B2 (en) | System and processes for automating and verifying medication order fulfillment compliance and medication administration compliance | |
| US20060079994A1 (en) | Unit-dose medication dispensing cart and method of operating the same | |
| US20140324216A1 (en) | Method, system and apparatus for managing medication delivery | |
| CN105808965A (en) | Method and system for medicine blending g detection | |
| CN101673362A (en) | Method and system for reducing error rate of drug administration | |
| JP2019093236A (en) | Drug delivery support system | |
| CN108968520A (en) | A kind of dispensing equipment for preventing from mismatching drug | |
| CN108133547A (en) | Hospital's automatic medicine-dispensing and get it filled control method and its system | |
| CN208156785U (en) | Hospital self-service medicine fetching control system | |
| TWI730508B (en) | Drug identification method | |
| TWM572232U (en) | Drug access device | |
| CN110232506A (en) | A kind of pharmacist deploys the real time evaluating method and system of state | |
| TWM616937U (en) | Drug identification system prior to administration of drug | |
| TW201437942A (en) | Automatic image identification and auxiliary dispensing system | |
| TW201633246A (en) | Method for accessing medicines from medicine cabinet | |
| TWM524524U (en) | Hospital inpatient department pharmaceutical affair management system | |
| TWI864868B (en) | Dispensing device and method for managing cancer medicine through technology identification | |
| TWI857669B (en) | Detection method for detection system used in medication collection | |
| TWI890233B (en) | Medication system for traditional chinese medicine | |
| IL268796B1 (en) | Machine and system for drug distribution | |
| TWM647277U (en) | Technical identification and management of cancer drug dispensing device |