CN116383512B - Dispensing method based on face recognition and computer readable storage medium - Google Patents
Dispensing method based on face recognition and computer readable storage medium Download PDFInfo
- Publication number
- CN116383512B CN116383512B CN202310609810.6A CN202310609810A CN116383512B CN 116383512 B CN116383512 B CN 116383512B CN 202310609810 A CN202310609810 A CN 202310609810A CN 116383512 B CN116383512 B CN 116383512B
- Authority
- CN
- China
- Prior art keywords
- doctor
- model
- disease type
- prescription
- medicine group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 239000003814 drug Substances 0.000 claims abstract description 166
- 201000010099 disease Diseases 0.000 claims abstract description 109
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 109
- 229940079593 drug Drugs 0.000 claims abstract description 40
- 238000003745 diagnosis Methods 0.000 claims abstract description 35
- 230000001815 facial effect Effects 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000012552 review Methods 0.000 claims description 27
- 230000006698 induction Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000001939 inductive effect Effects 0.000 claims description 3
- 210000000697 sensory organ Anatomy 0.000 description 3
- 230000007812 deficiency Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 208000013403 hyperactivity Diseases 0.000 description 2
- 210000004185 liver Anatomy 0.000 description 2
- 208000037920 primary disease Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 229940126532 prescription medicine Drugs 0.000 description 1
- 210000000952 spleen Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/535—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a dispensing method based on face recognition and a computer readable storage medium, relating to the technical field of dispensing, and comprising the following steps: s100, diagnosing a patient by a first doctor, making a prescription after judging the disease type, establishing a medicine group with an association relation for the medicines in the prescription, and uploading the medicine group database; s200, acquiring facial information of a patient by a graph acquisition module, inputting the acquired facial information into a first model, and outputting a corresponding disease type by the first model according to the input facial information; s300, matching the disease type output by the first model with the disease type on the first diagnosis prescription; otherwise, the patient is transferred to a rechecking doctor for rechecking. The invention establishes a first model by inputting the face information corresponding to the historical cases and the patient in the case library as training data, and after a primary doctor gives a prescription to the patient, the face information of the patient is firstly acquired before the patient takes medicine and is input into the first model, and the disease type corresponding to the face information is output by the first model.
Description
Technical Field
The invention relates to the technical field of medicine dispensing, in particular to a medicine dispensing method based on face recognition and a computer readable storage medium.
Background
Traditional Chinese medicine is a perfect combination of ancient philosophy and ancient science, and a set of unique diagnosis theory is finally formed through continuous historical practice. The diagnosis of the diseases in traditional Chinese medicine is mainly carried out through looking at the inquiry, wherein looking at the diagnosis means is the most important, the face is a window outside the straight face of the user, the user can see the face not only as beautiful but also as healthy, the user can find out the corresponding five sense organs on the face, and the external forms of the color, the shape and the like of each five sense organ correspond to the condition of the five sense organs, namely, the doctor of the traditional Chinese medicine can acquire the disease type of the patient through the facial information.
In the process from prescription making by doctors to medicine taking and delivering by pharmacists, errors possibly exist in two processes of prescription diagnosis and medicine dispensing, so that the condition of illness delay occurs, and the traditional pharmacists generally cannot verify medicines in the prescriptions, so that the condition of missed medicine dispensing and mispairing often occurs in the medicine dispensing process, but in the process, if manual whole-course check is adopted, the labor cost is greatly increased, the efficiency is reduced, and in the prior art, the medicine dispensing is verified in a mode of matching acquired medicine dispensing information with prescription medicine information, so that the strength of manual participation in the medicine dispensing process is reduced.
The automatic rechecking method for the traditional Chinese medicine drink dispensing agent based on the image recognition technology comprises the steps of image preprocessing to obtain an image set, carrying out local feature extraction on the image according to an algorithm, establishing an image feature index, obtaining the traditional Chinese medicine drink image to obtain an index set, and comparing an output result with a prescription by a worker. The invention can replace the heavy work of checking the prescription in decoction piece adjustment by high-level traditional Chinese medicine, thereby improving the working efficiency and the service capability of traditional Chinese medicine.
However, this patent still has the following problems: 1. the patent is only used for auxiliary examination of the prescription, but the auxiliary examination of the prescription cannot be realized, however, the face recognition technology in the prior art is relatively mature, the disease type can be judged by recognizing the face information of a patient for some specific diseases, and the disease type can be judged by combining the face recognition function with a database to be regarded as an examination mode with possibility of the prescription of the first diagnosis.
2. The matching mode of the patent to the medicine images is that each medicine image is matched with a medicine library, and after all medicines are matched, the medicines are manually compared, so that pharmacists who still need to take medicines check all prescriptions, and the auxiliary effect of the pharmacists is limited.
Disclosure of Invention
The invention aims to provide a dispensing method based on face recognition and a computer readable storage medium, which are used for solving the technical problems that the auxiliary examination of a prescription and the auxiliary effect on a pharmacist are limited in the prior art.
The invention provides a dispensing method based on face recognition, which comprises the following steps:
s100, diagnosing a patient by a first doctor, making a prescription after judging the disease type, establishing a medicine group with an association relation for the medicines in the prescription, and uploading the medicine group database;
s200, acquiring facial information of a patient by a graph acquisition module, inputting the acquired facial information into a first model, and outputting a corresponding disease type by the first model according to the input facial information;
s300, matching the disease type output by the first model with the disease type on the first diagnosis prescription, and entering step S400 if the matching result is accordant; otherwise, the examination is carried out by the rechecking doctor;
s400, taking out the medicine dispensing according to the prescription by a pharmacist, collecting the picture information of the medicine dispensing by using a machine, establishing a temporary medicine group by using the image information of all the collected medicine dispensing by the machine, and judging the difference between the temporary medicine group and the medicine group uploaded in the step S100, if the temporary medicine group is not different, taking the medicine from a patient after the medicine dispensing is finished; otherwise, prompting the pharmacist to review.
Further, in step S100, the prescriptions include the disease types obtained by diagnosing the patient by the doctor of the beginner, and the individual medicine groups are established for all the medicines involved in the single prescriptions according to the details of the medicines issued by the disease types, and all the medicines in one medicine group are issued as a whole in the dispensing link.
Further, in step S200, the step of outputting the disease type by the first model according to the input face information is:
s201, uploading historical sample data to a case library, wherein the historical sample data comprises facial information of a patient and a disease type corresponding to the patient;
s202, building and training a first model by using historical sample data;
s203, the image acquisition module inputs the acquired facial information of the patient into a first model, and the first model outputs the corresponding disease type.
Further, in step S300, the step of rechecking the doctor for rechecking includes:
s301, information forwarded to a rechecking doctor comprises a first-aid prescription and facial information of a patient;
s302, a review doctor issues a review prescription, a medicine group with association relation is built for the related medicines in the review prescription, and then a medicine group database is uploaded, and the medicine group built by the initial doctor in the step S100 is covered;
s303, uploading the facial information of the patient and the disease type of the review prescription to a case library as correction data to update the first model in an iterative manner.
Further, in step S400, the machine includes an image acquisition device, a generalization device, and a contrast device:
the image acquisition equipment is used for acquiring the dispensing information to generate image information;
the induction equipment is used for inducing all the image information to establish a temporary medicine group;
the comparison device is used for accessing the medicine group database and comparing and judging with the stored temporary medicine group.
Further, in step S400, the step of comparing the temporary drug group established by the machine with the drug group database is:
s401, placing the dispensing in a designated image acquisition area, and enabling a pharmacist to acquire dispensing information through an image acquisition device and transmit the dispensing information to induction equipment;
s402, sorting and summarizing all received image information to establish a temporary medicine group and transmitting the temporary medicine group to comparison equipment;
s403, accessing a medicine group database, comparing the stored temporary medicine group with the medicine group uploaded in the step S100, and completing medicine dispensing if the comparison result is matched; otherwise, prompting a pharmacist to review;
s404, after the comparison of the comparison equipment is finished, the temporary medicine group and the initial diagnosis medicine group are associated and then uploaded to a medicine group database to be used as exportable historical data;
s405, the information stored by the image acquisition equipment, the induction equipment and the comparison equipment is cleared after a single flow is completed.
Further, in step S300, the disease type in the prescription prescribed by the first doctor needs to be completely matched with the disease type output by the first model for the first time, and if the disease type of the first doctor is not completely matched with the disease type output by the first model, a review stage is needed;
when the prescriptions of the first doctor are not matched with the disease types output by the first model for the first time, if the prescriptions are not completely matched with the disease types output by the first model, judging whether rechecking is needed according to the weights of the first doctor and the first model in the matching.
Further, the ratio of the rechecking times of the prescriptions of the primary doctor by the rechecking doctor to the times of the prescriptions of the non-rechecking doctor is related to the matching weight of the primary doctor, if the rechecking times of the primary doctor are larger than the non-rechecking times of the primary doctor, the primary doctor is endowed with higher judgment weight, and when the disease type of the primary doctor is different from the disease type output by the first model, the disease type of the primary doctor is still in the control; if the number of times that the primary doctor is checked is smaller than the number of times that the primary doctor is not checked, the first model is given higher judgment weight, and when the disease type of the primary doctor is different from the disease type output by the first model, the disease type output by the first model is still used as the standard, and then the check is carried out.
In order to solve the technical problems, the invention also comprises the following solutions:
a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the face recognition based dispensing method described above.
Compared with the prior art, the invention has the beneficial effects that:
(1) The invention establishes a first model by inputting the face information corresponding to the historical cases and the patient in the case library as training data, after a primary doctor gives a prescription to the patient, the face information of the patient is firstly acquired before the patient gets the medicine and is input into the first model, the disease type corresponding to the face information is output by the first model, whether the primary prescription is wrong or not can be judged by matching the disease type output by the first model with the disease type on the primary prescription, and a review doctor is submitted to review after the primary prescription is wrong.
(2) According to the invention, the medicine group with the association relation is established by the primary doctor, the medicine group is uploaded to the medicine group database, after all the medicines are scanned after the pharmacist takes the medicines, the machine automatically compares the temporary medicine group established by all the medicines with the medicine group uploaded by the primary doctor, and whether the medicines are wrong or not can be rapidly obtained without comparing all the medicines one by one.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the overall method of the embodiment;
fig. 2 is a flow diagram of the overall method of the embodiment.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown.
The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention.
All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
The following is a description of fig. 1 and fig. 2, and an embodiment of the present invention provides a dispensing method based on face recognition, including the following steps:
s100, diagnosing the patient by a first doctor, giving a prescription after judging the disease type, establishing a medicine group with association relation for the related medicines in the prescription, and uploading the medicine group database.
The prescriptions comprise disease types obtained by diagnosing patients by a first doctor and medicine details according to the disease types.
In step S100, a separate drug group is established for all drugs involved in a single prescription, and all drugs in a drug group are delivered as a whole in a dispensing link.
S200, collecting facial information of a patient by a graph collecting module, inputting the collected facial information into a first model, and outputting a corresponding disease type by the first model according to the input facial information.
The first model can be one of a convolutional neural network model, a cyclic neural network model and a long-short-term memory network model, and is provided with a model for inputting and outputting data, storing the data and establishing association relation and data matching, the input data is divided into two types of patient face information and corresponding disease types, the association relation between the face information and the corresponding disease types is required to be established one by one as the historical data for training the accuracy of the first model, and after the acquired patient face information is input into the first model, the disease type corresponding to the historical face information with the highest matching degree is output.
In step S200, the step of outputting the disease type by the first model according to the input face information is:
s201, uploading historical sample data to a case library, wherein the historical sample data comprises facial information of a patient and a disease type corresponding to the patient;
s202, building and training a first model by using historical sample data;
s203, the image acquisition module inputs the acquired facial information of the patient into a first model, and the first model outputs the corresponding disease type.
S300, matching the disease type output by the first model with the disease type on the first diagnosis prescription, and entering step S400 if the matching result is accordant; otherwise, the patient is transferred to a rechecking doctor for rechecking.
In step S300, the step of rechecking the doctor for rechecking includes:
s301, information forwarded to a rechecking doctor comprises a first-aid prescription and facial information of a patient;
s302, a review doctor issues a review prescription, a medicine group with association relation is built for the related medicines in the review prescription, and then a medicine group database is uploaded, and the medicine group built by the initial doctor in the step S100 is covered;
s303, uploading the facial information of the patient and the disease type of the review prescription to a case library as correction data to update the first model in an iterative manner.
In step S300, the disease type in the prescription prescribed by the first doctor needs to be completely matched with the disease type output by the first model for the first time, and if the disease type of the first doctor is not completely matched with the disease type output by the first model, a review stage is needed;
when the prescriptions of the first doctor are not matched with the disease types output by the first model for the first time, if the prescriptions are not completely matched with the disease types output by the first model, judging whether rechecking is needed according to the weights of the first doctor and the first model in the matching.
The ratio of the rechecking times of the prescriptions of the primary doctor by the rechecking doctor to the times of the non-rechecking of the prescriptions of the primary doctor is related to the matching weight of the primary doctor, if the rechecking times of the primary doctor are larger than the non-rechecking times of the primary doctor, the primary doctor is endowed with higher judgment weight, and the primary doctor is still in control of the primary disease type when the primary disease type is different from the disease type output by the first model; if the number of times that the primary doctor is checked is smaller than the number of times that the primary doctor is not checked, the first model is given higher judgment weight, and when the disease type of the primary doctor is different from the disease type output by the first model, the disease type output by the first model is still used as the standard, and then the check is carried out.
If the machine diagnosis result and the diagnosis result in the initial diagnosis prescription are not completely consistent, a certain bifurcation point exists between the machine diagnosis result and the diagnosis result in the initial diagnosis prescription, so that the diagnosis result of the machine and the original prescription are sent to another doctor for checking, reliability of the diagnosis result is ensured, a new prescription generated after the diagnosis of the doctor is checked, and the medicine group associated with the new prescription is uploaded to a database to cover the original initial diagnosis medicine group.
When the primary doctor compares the disease type with the disease type output by the machine for the first time, when the doctor is rechecked for too many times, the service capability of the doctor is proved to be improved, so when the matching degree of the disease type machine result and the doctor diagnosis result is calculated, if the machine diagnosis result and the diagnosis result in the primary doctor prescription are in certain divergence, the machine result is given higher weight. When the doctor is checked for a small number of times, the service capability is proved to be good, so that when the matching degree of the disease type machine result and the doctor diagnosis result is calculated, if the machine diagnosis result and the diagnosis result in the initial diagnosis prescription are separated to a certain degree, the machine result is given a lower weight.
For example, the disease types commonly diagnosed by the primary doctor and the machine are in total disease 1 liver blood deficiency, disease 2 liver fire hyperactivity, disease 3 spleen deficiency, disease 4 heart fire hyperactivity, wherein the disease types diagnosed by the primary doctor on the patient result in: simultaneously, diseases 1, 2 and 3 exist; and the disease types output by the machine are: simultaneously, diseases 1, 2 and 4 exist; the two are commonly known in the disease 1 and the disease 2, and the disease 3 or the disease 4 is diverged, if the number of times of check of the primary doctor after multiple diagnosis is small, the primary doctor is given a larger weight, and the primary doctor can be regarded as the diagnosis disease type of the primary doctor, namely the disease type of the disease 1, the disease 2 and the disease 3 are the final diagnosis disease types; on the contrary, if the primary doctor is checked more times after multiple diagnosis, the disease types determined by the machine are identified as disease 1, disease 2 and disease 4.
S400, taking out the medicine dispensing according to the prescription by a pharmacist, collecting the picture information of the medicine dispensing by using a machine, establishing a temporary medicine group by using the image information of all the collected medicine dispensing by the machine, and judging the difference between the temporary medicine group and the medicine group uploaded in the step S100, if the temporary medicine group is not different, taking the medicine from a patient after the medicine dispensing is finished; otherwise, prompting the pharmacist to review.
In step S400, the machine comprises an image acquisition device, a generalization device and a contrast device:
the image acquisition equipment is used for acquiring the dispensing information to generate image information;
the induction equipment is used for inducing all the image information to establish a temporary medicine group;
the comparison device is used for accessing the medicine group database and comparing and judging with the stored temporary medicine group.
In step S400, the step of comparing the temporary drug group established by the machine with the drug group database is:
s401, placing the dispensing in a designated image acquisition area, and enabling a pharmacist to acquire dispensing information through an image acquisition device and transmit the dispensing information to induction equipment;
s402, sorting and summarizing all received image information to establish a temporary medicine group and transmitting the temporary medicine group to comparison equipment;
s403, the comparison equipment accesses a medicine group database, compares the stored temporary medicine group with the medicine group uploaded in the step S100, and completes the medicine dispensing if the comparison result is matched; otherwise, prompting a pharmacist to review;
s404, after the comparison of the comparison equipment is finished, the temporary medicine group and the initial diagnosis medicine group are associated and then uploaded to a medicine group database to be used as exportable historical data;
s405, the information stored by the image acquisition equipment, the induction equipment and the comparison equipment is cleared after a single flow is completed.
The temporary medicine group in the comparison device is matched with the medicine group uploaded by the primary doctor to judge whether the temporary medicine group belongs to the same medicine group, for example, A, B, C medicines in the prescription form one medicine group. After a pharmacist dispenses, the image acquisition equipment recognizes that the dispensing results after all medicines are recognized are two types of medicines A and B, and the contrast equipment prompts the pharmacist to review the dispensing results because one medicine group only contains the medicines A and B.
The invention establishes a first model by inputting the face information corresponding to the historical cases and the patient in the case library as training data, after a primary doctor gives a prescription to the patient, the face information of the patient is firstly acquired before the patient gets the medicine and is input into the first model, the disease type corresponding to the face information is output by the first model, whether the primary prescription is wrong or not can be judged by matching the disease type output by the first model with the disease type on the primary prescription, and a review doctor is submitted to review after the primary prescription is wrong.
According to the invention, the medicine group with the association relation is established by the primary doctor, the medicine group is uploaded to the medicine group database, after all the medicines are scanned after the pharmacist takes the medicines, the machine automatically compares the temporary medicine group established by all the medicines with the medicine group uploaded by the primary doctor, and whether the medicines are wrong or not can be rapidly obtained without comparing all the medicines one by one.
In order to solve the technical problems, the invention also comprises the following solutions:
a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the face recognition based dispensing method described above.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (9)
1. The dispensing method based on face recognition is characterized by comprising the following steps of:
s100, diagnosing a patient by a first doctor, making a prescription after judging the disease type, establishing a medicine group with an association relation for the medicines in the prescription, and uploading the medicine group database;
s200, acquiring facial information of a patient by a graph acquisition module, inputting the acquired facial information into a first model, and outputting a corresponding disease type by the first model according to the input facial information;
s300, matching the disease type output by the first model with the disease type on the first diagnosis prescription, and entering step S400 if the matching result is accordant; otherwise, the examination is carried out by the rechecking doctor;
s400, taking out the medicine dispensing according to the prescription by a pharmacist, collecting the picture information of the medicine dispensing by using a machine, establishing a temporary medicine group by using the image information of all the collected medicine dispensing by the machine, and judging the difference between the temporary medicine group and the medicine group uploaded in the step S100, if the temporary medicine group is not different, taking the medicine from a patient after the medicine dispensing is finished; otherwise, prompting the pharmacist to review.
2. A face recognition-based dispensing method according to claim 1, wherein in step S100, the prescription includes a disease type obtained by diagnosing the patient by a doctor in the first doctor, and a separate medicine group is established for all medicines involved in a single prescription according to a medicine prescription of the disease type, and all medicines in one medicine group are dispensed as a whole in a dispensing link.
3. A dispensing method based on face recognition according to claim 1, wherein in step S200, the step of outputting the disease type by the first model according to the inputted face information is:
s201, uploading historical sample data to a case library, wherein the historical sample data comprises facial information of a patient and a disease type corresponding to the patient;
s202, building and training a first model by using historical sample data;
s203, the image acquisition module inputs the acquired facial information of the patient into a first model, and the first model outputs the corresponding disease type.
4. A dispensing method based on face recognition according to claim 1, wherein in step S300, the step of rechecking the doctor for rechecking includes:
s301, information forwarded to a rechecking doctor comprises a first-aid prescription and facial information of a patient;
s302, a review doctor issues a review prescription, a medicine group with association relation is built for the related medicines in the review prescription, and then a medicine group database is uploaded, and the medicine group built by the initial doctor in the step S100 is covered;
s303, uploading the facial information of the patient and the disease type of the review prescription to a case library as correction data to update the first model in an iterative manner.
5. A face recognition-based dispensing method according to claim 1, wherein in step S400, the machine comprises an image acquisition device, a generalization device and a contrast device:
the image acquisition equipment is used for acquiring the dispensing information to generate image information;
the induction equipment is used for inducing all the image information to establish a temporary medicine group;
the comparison device is used for accessing the medicine group database and comparing and judging with the stored temporary medicine group.
6. A face recognition based dispensing method according to claim 5, wherein in step S400, the step of comparing the temporary drug group established by the machine with the drug group database is:
s401, placing the dispensing in a designated image acquisition area, and enabling a pharmacist to acquire dispensing information through an image acquisition device and transmit the dispensing information to induction equipment;
s402, sorting and summarizing all received image information to establish a temporary medicine group and transmitting the temporary medicine group to comparison equipment;
s403, accessing a medicine group database, comparing the stored temporary medicine group with the medicine group uploaded in the step S100, and completing medicine dispensing if the comparison result is matched; otherwise, prompting a pharmacist to review;
s404, after the comparison of the comparison equipment is finished, the temporary medicine group and the initial diagnosis medicine group are associated and then uploaded to a medicine group database to be used as exportable historical data;
s405, the information stored by the image acquisition equipment, the induction equipment and the comparison equipment is cleared after a single flow is completed.
7. The dispensing method based on face recognition according to claim 1, wherein in step S300, the disease type in the prescription prescribed by the first doctor needs to be completely matched when the first doctor is matched with the disease type output by the first model, and if the first doctor is not completely matched with the disease type output by the first model, a review stage is needed;
when the prescriptions of the first doctor are not matched with the disease types output by the first model for the first time, if the prescriptions are not completely matched with the disease types output by the first model, judging whether rechecking is needed according to the weights of the first doctor and the first model in the matching.
8. The dispensing method based on face recognition according to claim 7, wherein the ratio of the number of times the review doctor issues the prescription to the primary doctor to the number of times the prescription of the primary doctor is not reviewed is related to the matching weight of the primary doctor, if the number of times the primary doctor is reviewed is greater than the number of times the primary doctor is not reviewed, the primary doctor is given a higher judgment weight, and when the disease type of the primary diagnosis is different from the disease type output by the first model, the disease type of the primary diagnosis is still in reference; if the number of times that the primary doctor is checked is smaller than the number of times that the primary doctor is not checked, the first model is given higher judgment weight, and when the disease type of the primary doctor is different from the disease type output by the first model, the disease type output by the first model is still used as the standard, and then the check is carried out.
9. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, which when executed by a processor, implements a face recognition based dispensing method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310609810.6A CN116383512B (en) | 2023-05-29 | 2023-05-29 | Dispensing method based on face recognition and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310609810.6A CN116383512B (en) | 2023-05-29 | 2023-05-29 | Dispensing method based on face recognition and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116383512A CN116383512A (en) | 2023-07-04 |
| CN116383512B true CN116383512B (en) | 2023-08-22 |
Family
ID=86965970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310609810.6A Active CN116383512B (en) | 2023-05-29 | 2023-05-29 | Dispensing method based on face recognition and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116383512B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109994202A (en) * | 2019-03-22 | 2019-07-09 | 华南理工大学 | A method of the face based on deep learning generates prescriptions of traditional Chinese medicine |
| CN110739038A (en) * | 2019-10-12 | 2020-01-31 | 深圳市宝安区人民医院 | Medicine distribution system based on medical advice |
| CN113948181A (en) * | 2021-08-13 | 2022-01-18 | 北京内景健康科技发展有限公司 | Cloud clinic platform for traditional Chinese medicine |
| CN114842942A (en) * | 2022-04-01 | 2022-08-02 | 武汉理工大学 | Intelligent terminal management system for pharmacy |
| CN115691752A (en) * | 2022-09-07 | 2023-02-03 | 宁波市中医院 | Traditional Chinese medicine tracking system, tracking method and medicine storage box |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1552461A2 (en) * | 2002-10-18 | 2005-07-13 | Mckesson Automation Systems, Inc. | Automated drug substitution, verification, and reporting system |
-
2023
- 2023-05-29 CN CN202310609810.6A patent/CN116383512B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109994202A (en) * | 2019-03-22 | 2019-07-09 | 华南理工大学 | A method of the face based on deep learning generates prescriptions of traditional Chinese medicine |
| CN110739038A (en) * | 2019-10-12 | 2020-01-31 | 深圳市宝安区人民医院 | Medicine distribution system based on medical advice |
| CN113948181A (en) * | 2021-08-13 | 2022-01-18 | 北京内景健康科技发展有限公司 | Cloud clinic platform for traditional Chinese medicine |
| CN114842942A (en) * | 2022-04-01 | 2022-08-02 | 武汉理工大学 | Intelligent terminal management system for pharmacy |
| CN115691752A (en) * | 2022-09-07 | 2023-02-03 | 宁波市中医院 | Traditional Chinese medicine tracking system, tracking method and medicine storage box |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116383512A (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11883153B2 (en) | Digital platform to identify health conditions and therapeutic interventions using an automatic and distributed artificial intelligence system | |
| Lai et al. | Item banking to improve, shorten and computerize self-reported fatigue: an illustration of steps to create a core item bank from the FACIT-Fatigue Scale | |
| KR102237449B1 (en) | Method, server and program of learning a patient diagnosis | |
| US9251310B2 (en) | Therapy management system and method for peritoneal dialysis | |
| CN109285605A (en) | A kind of medical diagnosis system and diagnostic method based on artificial intelligence | |
| US20090210256A1 (en) | System For Real-Time Online Health Care Insurance Underwriting | |
| WO2017117150A1 (en) | Machine learning system for creating and utilizing an assessment metric based on outcomes | |
| CN109035187A (en) | A kind of mask method and device of medical image | |
| CN107526933A (en) | A kind of Telemedicine System | |
| CN105956412A (en) | System and method for realizing coronary heart disease clinical data collection based on intelligent image-text identification | |
| CN112116990A (en) | Internet artificial intelligence based doctor-patient management system and method | |
| CN105160182A (en) | Automatic evaluation system of diagnosis and treatment correctness on the basis of virtual case | |
| CN113948181A (en) | Cloud clinic platform for traditional Chinese medicine | |
| CN116383512B (en) | Dispensing method based on face recognition and computer readable storage medium | |
| CN117038106A (en) | Intelligent medical guiding cloud platform | |
| CN110706788A (en) | Remote traditional Chinese medicine diagnosis and treatment method and system | |
| CN102646153A (en) | Novel TCM (traditional Chinese medicine) diagnosis process and device | |
| Meredith et al. | Patient-centered communication scoring method report on nine coded interviews | |
| US20050065816A1 (en) | Healthcare management information system | |
| CN115713994A (en) | Medical management system and electronic medical record management system for tumor whole-course integration | |
| CN105160183A (en) | Automatic evaluation method of diagnosis and treatment correctness on the basis of virtual case | |
| CN113870984A (en) | AI diagnosis and treatment follow-up system-based standardized diagnosis and treatment center authentication and assessment system | |
| CN110957031B (en) | Disease prevention information service platform | |
| Braspenning et al. | Indicators for quality and safety of care | |
| CN113948179A (en) | Remote asynchronous MDT multidisciplinary consultation platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |