CN117315850A - Injection storing and taking method and device based on artificial intelligence - Google Patents
Injection storing and taking method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN117315850A CN117315850A CN202311405244.3A CN202311405244A CN117315850A CN 117315850 A CN117315850 A CN 117315850A CN 202311405244 A CN202311405244 A CN 202311405244A CN 117315850 A CN117315850 A CN 117315850A
- Authority
- CN
- China
- Prior art keywords
- layer
- injection
- convolution
- identification
- identification result
- 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.)
- Granted
Links
- 238000002347 injection Methods 0.000 title claims abstract description 114
- 239000007924 injection Substances 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 29
- 239000003814 drug Substances 0.000 claims abstract description 115
- 238000003860 storage Methods 0.000 claims abstract description 48
- 229940079593 drug Drugs 0.000 claims abstract description 36
- 238000013528 artificial neural network Methods 0.000 claims abstract description 29
- 238000000605 extraction Methods 0.000 claims description 24
- 238000011176 pooling Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 19
- 230000004927 fusion Effects 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 11
- 238000012377 drug delivery Methods 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 5
- 239000000243 solution Substances 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
- G07F17/0092—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for assembling and dispensing of pharmaceutical articles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F11/00—Coin-freed apparatus for dispensing, or the like, discrete articles
- G07F11/02—Coin-freed apparatus for dispensing, or the like, discrete articles from non-movable magazines
- G07F11/04—Coin-freed apparatus for dispensing, or the like, discrete articles from non-movable magazines in which magazines the articles are stored one vertically above the other
- G07F11/16—Delivery means
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an injection access method and system based on artificial intelligence, wherein the injection access method based on artificial intelligence comprises the following steps: the method comprises the steps that a first identification unit is used for identifying an acquired injection bar code or two-dimensional code to obtain a first identification result, and the first identification result is sent to a central control unit; the central control unit distributes the storage position of the injection in the medicine cabinet according to the first identification result and the medicine cabinet storage condition, and drives the transportation unit to store the injection to the corresponding position of the medicine cabinet; when medicine is required to be taken, the prescription information is sent to a second identification unit, and a second identification result is obtained; the central control unit compares the second identification result with injection information stored in the drug cabinet database, and drives the transportation unit to take the drug according to the comparison result; the invention identifies the injection information and the prescription information based on the neural network, realizes automatic access to the injection according to the identification result and the condition in the cabinet, optimizes the access path through the RRT algorithm, and improves the injection access efficiency.
Description
Technical Field
The invention relates to the technical field of intelligent medicine cabinets, in particular to an injection storage and taking method and device based on artificial intelligence.
Background
The pharmacy and pharmacy release injection medicine all need the staff to look for according to the prescription, then manual medicine, when the number of getting it filled is more, can be very inconvenient, not only inefficiency, extravagant manpower moreover. The current intelligent medicine cabinet realizes the functions of mass storage and quick and accurate medicine distribution, so that the workload of medicine searching in a pharmacy is greatly reduced, but the intelligent medicine cabinet mainly aims at medicine box medicine filling, and the research on automatic equipment for storing and taking injection medicine is relatively less.
Disclosure of Invention
The invention aims to provide an injection storage and taking method and device based on artificial intelligence, which are used for solving the problem of low storage and taking efficiency of the existing injection medicines.
In order to overcome the defects in the prior art, the invention provides an injection access method based on artificial intelligence, which comprises the following steps: the method comprises the steps of collecting a bar code or a two-dimensional code on an injection, sending the bar code or the two-dimensional code to a first identification unit, identifying the bar code or the two-dimensional code by the first identification unit through a first neural network, obtaining a first identification result, and sending the first identification result to the central control unit; the central control unit distributes the storage position of the injection in the medicine cabinet according to the first identification result and the medicine cabinet storage condition, and sends a first signal to the transportation unit, and the transportation unit stores the injection to the corresponding position of the medicine cabinet after receiving the first signal; when medicine is required to be taken, the prescription information is sent to a second identification unit through the terminal, the second identification unit identifies the prescription information through a second neural network, a second identification result is obtained, and the second identification result is sent to the central control unit; comparing the second identification result with injection information stored in a drug cabinet database by the central control unit, if the second identification result is consistent with the injection information stored in the drug cabinet database, sending a second signal to the transportation unit, after receiving the second signal, transporting the injection matched with the prescription information to a drug taking place, and prompting a worker to take the drug through a terminal; if the information of the two information is inconsistent, the terminal informs the staff to store the medicine in time.
As a preferable scheme of the injection access method based on artificial intelligence, the invention comprises the following steps: the first neural network comprises a feature extraction layer, a feature fusion layer and a classifier; the feature extraction layer comprises a first convolution layer, a second convolution layer, a third convolution layer, a batch normalization layer, a silu activation layer and a maximum pooling layer, wherein the convolution kernel of the first convolution layer is 1*1, the step length is 1 and is used for changing the number of channels, the convolution kernel of the second convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the third convolution layer is 3*3, the step length is 2 and is used for downsampling; the feature fusion layer comprises a spatial pyramid pooling layer, a training layer and an inference layer, wherein the spatial pyramid pooling layer is used for extracting features with different scales, the training layer comprises a fourth convolution layer and a fifth convolution layer, the convolution kernel of the fourth convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the fifth convolution layer is 1*1, the step length is 1 and is used for smoothing the features; the reasoning layer comprises a sixth convolution layer, the convolution kernel of the sixth convolution layer is 3*3, the step length is 1, and the convolution kernel is used for fusing the feature matrix output by the training layer; and carrying out feature classification and identification through a classifier.
As a preferable scheme of the injection access method based on artificial intelligence, the invention comprises the following steps: the second neural network comprises a convolution layer, a downsampling layer, a full-connection layer and a Gaussian connection layer; the convolution kernel size of the convolution layer is 5*5, and the step size is 1.
As a preferable scheme of the injection access method based on artificial intelligence, the invention comprises the following steps: further comprises: and regulating the temperature and humidity of the medicine cabinet according to the storage temperature of the injection, electronically counting the quantity of the stored or taken out injection by a sensor when the injection is stored or taken out, simultaneously identifying the stored or taken out injection by a bar code or a two-dimensional code through a first identification unit, and sending the counting result and the identification result to a medicine cabinet database.
As a preferable scheme of the injection access method based on artificial intelligence, the invention comprises the following steps: further comprises: the first signal comprises a drug storage driving signal and a shortest drug storage path; the second signal comprises a drug delivery driving signal and a shortest drug delivery path; the central control unit acquires the shortest medicine storage path and the shortest medicine taking path through an RRT algorithm.
As a preferable scheme of the injection access device based on artificial intelligence of the invention, wherein: comprising the following steps: the data acquisition module is configured to acquire a bar code or a two-dimensional code on the injection and send the bar code or the two-dimensional code to the first identification unit; the injection information identification module is configured to identify the bar code or the two-dimensional code through a first neural network by a first identification unit, obtain a first identification result and send the first identification result to the central control unit; the control module is configured to execute that the central control unit distributes the storage position of the injection in the medicine cabinet according to a first identification result and the storage condition of the medicine cabinet, sends a first signal to the transportation unit, and stores the injection to the corresponding position of the medicine cabinet after the transportation unit receives the first signal; the prescription information identification module is configured to send prescription information to the second identification unit through the terminal when medicine taking is needed, the second identification unit identifies the prescription information through the second neural network, a second identification result is obtained, and the second identification result is sent to the central control unit; the control module is further configured to execute comparison between the second identification result and injection information stored in the drug cabinet database by the central control unit, if the second identification result is consistent with the injection information stored in the drug cabinet database, a second signal is sent to the transportation unit, and after the transportation unit receives the second signal, the injection matched with the prescription information is transported to a drug taking place and a worker is prompted to take the drug by the terminal; if the information of the two information is inconsistent, the terminal informs the staff to store the medicine in time.
As a preferable scheme of the injection access device based on artificial intelligence of the invention, wherein: the injection information identification module is specifically configured to execute: the first neural network comprises a feature extraction layer, a feature fusion layer and a classifier; the feature extraction layer comprises a first convolution layer, a second convolution layer, a third convolution layer, a batch normalization layer, a silu activation layer and a maximum pooling layer, wherein the convolution kernel of the first convolution layer is 1*1, the step length is 1 and is used for changing the number of channels, the convolution kernel of the second convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the third convolution layer is 3*3, the step length is 2 and is used for downsampling; the feature fusion layer comprises a spatial pyramid pooling layer, a training layer and an inference layer, wherein the spatial pyramid pooling layer is used for extracting features with different scales, the training layer comprises a fourth convolution layer and a fifth convolution layer, the convolution kernel of the fourth convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the fifth convolution layer is 1*1, the step length is 1 and is used for smoothing the features; the reasoning layer comprises a sixth convolution layer, the convolution kernel of the sixth convolution layer is 3*3, the step length is 1, and the convolution kernel is used for fusing the feature matrix output by the training layer; and carrying out feature classification and identification through a classifier.
As a preferable scheme of the injection access device based on artificial intelligence of the invention, wherein: the injection information identification module is specifically configured to execute: the second neural network comprises a convolution layer, a downsampling layer, a full-connection layer and a Gaussian connection layer; the convolution kernel size of the convolution layer is 5*5, and the step size is 1.
As a preferable scheme of the injection access device based on artificial intelligence of the invention, wherein: further comprising a sensing module configured to perform: and regulating the temperature and humidity of the medicine cabinet according to the storage temperature of the injection, electronically counting the quantity of the stored or taken out injection by a sensor when the injection is stored or taken out, simultaneously identifying the stored or taken out injection by a bar code or a two-dimensional code through a first identification unit, and sending the counting result and the identification result to a medicine cabinet database.
As a preferable scheme of the injection access device based on artificial intelligence of the invention, wherein: further comprises: the first signal comprises a drug storage driving signal and a shortest drug storage path; the second signal comprises a drug delivery driving signal and a shortest drug delivery path; the central control unit acquires the shortest medicine storage path and the shortest medicine taking path through an RRT algorithm.
The invention has the beneficial effects that: the invention identifies the injection information and the prescription information based on the neural network, realizes automatic access to the injection according to the identification result and the condition in the cabinet, optimizes the access path through the RRT algorithm, and improves the injection access efficiency.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a flow chart of an injection accessing method based on artificial intelligence according to a first embodiment of the invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
While the embodiments of the present invention have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship 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 apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a 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.
Example 1
Referring to fig. 1, a first embodiment of the present invention provides an artificial intelligence based injection accessing method, which includes:
s1: the method comprises the steps of collecting a bar code or a two-dimensional code on an injection, sending the bar code or the two-dimensional code to a first identification unit, identifying the bar code or the two-dimensional code by the first identification unit through a first neural network, obtaining a first identification result, and sending the first identification result to a central control unit.
The method comprises the steps of collecting a bar code or a two-dimensional code on an injection through a camera, sending the collected bar code or two-dimensional code to a first identification unit, and identifying the bar code or the two-dimensional code through a first neural network by the first identification unit, wherein the first neural network comprises a feature extraction layer, a feature fusion layer and a classifier.
The feature extraction layer comprises a first convolution layer, a second convolution layer, a third convolution layer, a batch normalization layer, a silu activation layer and a maximum pooling layer, wherein the convolution kernel of the first convolution layer is 1*1, the step length is 1 and is used for changing the channel number, the convolution kernel of the second convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the third convolution layer is 3*3, the step length is 2 and is used for downsampling.
It should be noted that the silu activation layer adopts a silu activation function, and the silu activation function is a variant of the swish activation function, and the formula is as follows:
silu(x)＝x·sigmoid(x)
where x is the input.
The feature fusion layer comprises a spatial pyramid pooling layer, a training layer and an inference layer, wherein the spatial pyramid pooling layer obtains different receptive fields through maximum pooling, so that features with different scales are extracted, the training layer comprises a fourth convolution layer and a fifth convolution layer, the convolution kernel of the fourth convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the fifth convolution layer is 1*1, the step length is 1 and is used for smoothing the features; the reasoning layer comprises a sixth convolution layer, the convolution kernel of the sixth convolution layer is 3*3, the step length is 1, and the convolution kernel is used for fusing the feature matrix output by the training layer; preferably, the spatial pyramid pooling layer and the convolution layer are fused, so that the calculated amount can be reduced by half, the speed is increased, and the precision is improved.
And finally, carrying out feature classification and recognition on the features output by the feature fusion layer through a classifier, namely searching the position of the features, drawing a prediction frame, classifying and recognizing the features in the prediction frame, and obtaining a first recognition result.
S2: the central control unit distributes the storage position of the injection in the medicine cabinet according to the first identification result and the medicine cabinet storage condition, sends a first signal to the transportation unit, and stores the injection to the corresponding position of the medicine cabinet after the transportation unit receives the first signal.
The first signal comprises a drug storage driving signal and a shortest drug storage path;
the central control unit can adopt a singlechip, and acquires the shortest medicine storage path through an RRT algorithm, and the principle of the RRT algorithm is as follows: the current node is further searched, the shortest distance from the current node to the adjacent nodes is searched, the combination mode of all adjacent nodes is continuously searched within a certain circle range after the optimal father node is searched, and the paths are recombined to achieve the optimal effect, so that the optimal paths are obtained, the searching speed is high, and the medicine storage time is shortened.
S3: when medicine taking is needed, the prescription information is sent to the second identification unit through the terminal, the second identification unit identifies the prescription information through the second neural network, a second identification result is obtained, and the second identification result is sent to the central control unit.
It should be noted that, the terminal may be a mobile phone, a handheld device with a wireless communication function, a computing device or other processing device connected to a wireless modem, a wearable device (such as a smart watch), which is not limited in this embodiment of the present application.
When medicine is required to be taken, the prescription information is sent to a second identification unit through a terminal, the second identification unit identifies the prescription information through a second neural network, the identification content comprises injection names, dosage and the like, and the second neural network adopts a LeNet-5 neural network which comprises a convolution layer, a downsampling layer, a full-connection layer and a Gaussian connection layer; the number of the convolution layers is 2, the number of the downsampling layers is 2, the number of the full-connection layers is 2, the convolution kernel sizes of the convolution layers are 5*5, and the step sizes are 1; the downsampling layer adopts the maximum pooling operation, the size of each window is 2 x 2, and the step length is 2; the full connection layer comprises a first full connection layer and a second full connection layer, wherein the first full connection layer pulls each characteristic graph with the size of 5*5 into a vector with the length of 400, the vector is connected through one full connection layer with 120 neurons, the second full connection layer connects the 120 neurons to 84 neurons, and finally a second identification result is output through an activation function.
The training process of the LeNet-5 uses a back propagation algorithm (BP algorithm) to optimize the weights and bias of the network by minimizing the error function (typically using a cross entropy loss function). The weights and offsets of the network are obtained by random initialization, and then the network continuously adjusts the weights and offsets by a back propagation algorithm so that the error function is minimized.
S4: comparing the second identification result with injection information stored in a medicine cabinet database by the central control unit, if the second identification result is consistent with the injection information stored in the medicine cabinet database, sending a second signal to the transportation unit, after the transportation unit receives the second signal, conveying the injection matched with the prescription information to a medicine taking place, and prompting a worker to take medicine through a terminal; if the information of the two information is inconsistent, the terminal informs the staff to store the medicine in time.
The second signal comprises a medicine taking driving signal and a shortest medicine taking path, and the central control unit acquires the shortest medicine taking path through an RRT algorithm.
In the embodiment, the staff can be informed of timely taking or storing the medicine through a display screen, a flashing lamp and other devices.
S5: and regulating the temperature and humidity of the medicine cabinet according to the storage temperature of the injection, electronically counting the quantity of the stored or taken out injection by a sensor when the injection is stored or taken out, simultaneously identifying the stored or taken out injection by a bar code or a two-dimensional code through a first identification unit, and sending the counting result and the identification result to a medicine cabinet database.
When the injection is stored or taken out, the injection information of the medicine cabinet database is synchronously updated.
The sensor may be a sensor with a counting function, which is not limited in the embodiment of the present application.
Example 2
The embodiment provides an injection access device based on artificial intelligence, which comprises,
the data acquisition module is configured to acquire a bar code or a two-dimensional code on the injection and send the bar code or the two-dimensional code to the first identification unit.
The injection information identification module is configured to identify the bar code or the two-dimensional code through the first neural network by the first identification unit, obtain a first identification result and send the first identification result to the central control unit.
The control module is configured to execute the control unit to distribute the storage position of the injection in the medicine cabinet according to the first identification result and the storage condition of the medicine cabinet, send a first signal to the transportation unit, and store the injection to the corresponding position of the medicine cabinet after the transportation unit receives the first signal; the first signal comprises a drug storage driving signal and a shortest drug storage path, and the central control unit acquires the shortest drug storage path through an RRT algorithm.
The prescription information identification module is configured to send prescription information to the second identification unit through the terminal when medicine taking is needed, the second identification unit identifies the prescription information through the second neural network, a second identification result is obtained, and the second identification result is sent to the central control unit.
The control module is further configured to execute the comparison of the second identification result and the injection information stored in the drug cabinet database by the central control unit, if the second identification result is consistent with the injection information stored in the drug cabinet database, a second signal is sent to the transportation unit, and after the transportation unit receives the second signal, the injection matched with the prescription information is transported to a drug taking place and a worker is prompted to take the drug through the terminal; if the information of the two information is inconsistent, notifying a worker through the terminal to store the medicine in time; the second signal comprises a medicine taking driving signal and a shortest medicine storing path, and the central control unit acquires the shortest medicine taking path through an RRT algorithm.
The injection information identification module is specifically configured to execute: the first neural network comprises a feature extraction layer, a feature fusion layer and a classifier; the feature extraction layer comprises a first convolution layer, a second convolution layer, a third convolution layer, a batch normalization layer, a silu activation layer and a maximum pooling layer, wherein the convolution kernel of the first convolution layer is 1*1, the step length is 1 and is used for changing the number of channels, the convolution kernel of the second convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the third convolution layer is 3*3, the step length is 2 and is used for downsampling; the feature fusion layer comprises a spatial pyramid pooling layer, a training layer and an inference layer, wherein the spatial pyramid pooling layer is used for extracting features with different scales, the training layer comprises a fourth convolution layer and a fifth convolution layer, the convolution kernel of the fourth convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the fifth convolution layer is 1*1, and the step length is 1 and is used for smoothing the features; the reasoning layer comprises a sixth convolution layer, the convolution kernel of the sixth convolution layer is 3*3, the step length is 1, and the convolution kernel is used for fusing the feature matrix output by the training layer; and carrying out feature classification and identification through a classifier.
The injection information identification module is specifically configured to execute: the second neural network comprises a convolution layer, a downsampling layer, a full-connection layer and a Gaussian connection layer; the convolution kernel size of the convolution layer is 5*5, with a step size of 1.
A sensing module configured to perform: and regulating the temperature and humidity of the medicine cabinet according to the storage temperature of the injection, electronically counting the quantity of the stored or taken out injection by a sensor when the injection is stored or taken out, simultaneously identifying the stored or taken out injection by a bar code or a two-dimensional code through a first identification unit, and sending the counting result and the identification result to a medicine cabinet database.
It should be appreciated that embodiments of the invention may be implemented or realized by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer readable storage medium configured with a computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, in accordance with the methods and drawings described in the specific embodiments. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes (or variations and/or combinations thereof) described herein may be performed under control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications), by hardware, or combinations thereof, collectively executing on one or more processors. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable computing platform, including, but not limited to, a personal computer, mini-computer, mainframe, workstation, network or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and so forth. Aspects of the invention may be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and/or write storage medium, RAM, ROM, etc., such that it is readable by a programmable computer, which when read by a computer, is operable to configure and operate the computer to perform the processes described herein. Further, the machine readable code, or portions thereof, may be transmitted over a wired or wireless network. When such media includes instructions or programs that, in conjunction with a microprocessor or other data processor, implement the steps described above, the invention described herein includes these and other different types of non-transitory computer-readable storage media. The invention also includes the computer itself when programmed according to the methods and techniques of the present invention. The computer program can be applied to the input data to perform the functions described herein, thereby converting the input data to generate output data that is stored to the non-volatile memory. The output information may also be applied to one or more output devices such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, the components may be, but are not limited to: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components may reside within a process and/or thread of execution and a component may be localized on one computer and/or distributed between two or more computers. Furthermore, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
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, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. An injection access method based on artificial intelligence is characterized by comprising the following steps:
acquiring a bar code or a two-dimensional code on an injection, sending the bar code or the two-dimensional code to a first identification unit, identifying the bar code or the two-dimensional code by the first identification unit through a first neural network, obtaining a first identification result, and sending the first identification result to the central control unit;
the central control unit distributes the storage position of the injection in the medicine cabinet according to the first identification result and the medicine cabinet storage condition, and sends a first signal to the transportation unit, and the transportation unit stores the injection to the corresponding position of the medicine cabinet after receiving the first signal;
when medicine is required to be taken, the prescription information is sent to a second identification unit through the terminal, the second identification unit identifies the prescription information through a second neural network, a second identification result is obtained, and the second identification result is sent to the central control unit;
comparing the second identification result with injection information stored in a drug cabinet database by the central control unit, if the second identification result is consistent with the injection information stored in the drug cabinet database, sending a second signal to the transportation unit, after receiving the second signal, transporting the injection matched with the prescription information to a drug taking place, and prompting a worker to take the drug through a terminal;
if the information of the two information is inconsistent, the terminal informs the staff to store the medicine in time.
2. The artificial intelligence based injection access method of claim 1, wherein the first neural network comprises a feature extraction layer, a feature fusion layer and a classifier;
the feature extraction layer comprises a first convolution layer, a second convolution layer, a third convolution layer, a batch normalization layer, a silu activation layer and a maximum pooling layer, wherein the convolution kernel of the first convolution layer is 1*1, the step length is 1 and is used for changing the number of channels, the convolution kernel of the second convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the third convolution layer is 3*3, the step length is 2 and is used for downsampling;
the feature fusion layer comprises a spatial pyramid pooling layer, a training layer and an inference layer, wherein the spatial pyramid pooling layer is used for extracting features with different scales, the training layer comprises a fourth convolution layer and a fifth convolution layer, the convolution kernel of the fourth convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the fifth convolution layer is 1*1, the step length is 1 and is used for smoothing the features; the reasoning layer comprises a sixth convolution layer, the convolution kernel of the sixth convolution layer is 3*3, the step length is 1, and the convolution kernel is used for fusing the feature matrix output by the training layer;
and carrying out feature classification and identification through a classifier.
3. The artificial intelligence based injection access method of claim 1, wherein the second neural network comprises a convolution layer, a downsampling layer, a full connection layer and a gaussian connection layer; the convolution kernel size of the convolution layer is 5*5, and the step size is 1.
4. The artificial intelligence based access method of injectate as claimed in claim 2 or 3, further comprising:
and regulating the temperature and humidity of the medicine cabinet according to the storage temperature of the injection, electronically counting the quantity of the stored or taken out injection by a sensor when the injection is stored or taken out, simultaneously identifying the stored or taken out injection by a bar code or a two-dimensional code through a first identification unit, and sending the counting result and the identification result to a medicine cabinet database.
5. The method for accessing an artificial intelligence based injection according to claim 4, further comprising:
the first signal comprises a drug storage driving signal and a shortest drug storage path;
the second signal comprises a drug delivery driving signal and a shortest drug delivery path;
the central control unit acquires the shortest medicine storage path and the shortest medicine taking path through an RRT algorithm.
6. An artificial intelligence based injection access device, comprising:
the data acquisition module is configured to acquire a bar code or a two-dimensional code on the injection and send the bar code or the two-dimensional code to the first identification unit;
the injection information identification module is configured to identify the bar code or the two-dimensional code through a first neural network by a first identification unit, obtain a first identification result and send the first identification result to the central control unit;
the control module is configured to execute that the central control unit distributes the storage position of the injection in the medicine cabinet according to a first identification result and the storage condition of the medicine cabinet, sends a first signal to the transportation unit, and stores the injection to the corresponding position of the medicine cabinet after the transportation unit receives the first signal;
the prescription information identification module is configured to send prescription information to the second identification unit through the terminal when medicine taking is needed, the second identification unit identifies the prescription information through the second neural network, a second identification result is obtained, and the second identification result is sent to the central control unit;
the control module is further configured to execute comparison between the second identification result and injection information stored in the drug cabinet database by the central control unit, if the second identification result is consistent with the injection information stored in the drug cabinet database, a second signal is sent to the transportation unit, and after the transportation unit receives the second signal, the injection matched with the prescription information is transported to a drug taking place and a worker is prompted to take the drug by the terminal; if the information of the two information is inconsistent, the terminal informs the staff to store the medicine in time.
7. The artificial intelligence based injection access device of claim 6, wherein the injection information identifying module is specifically configured to perform:
the first neural network comprises a feature extraction layer, a feature fusion layer and a classifier;
the feature extraction layer comprises a first convolution layer, a second convolution layer, a third convolution layer, a batch normalization layer, a silu activation layer and a maximum pooling layer, wherein the convolution kernel of the first convolution layer is 1*1, the step length is 1 and is used for changing the number of channels, the convolution kernel of the second convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the third convolution layer is 3*3, the step length is 2 and is used for downsampling;
the feature fusion layer comprises a spatial pyramid pooling layer, a training layer and an inference layer, wherein the spatial pyramid pooling layer is used for extracting features with different scales, the training layer comprises a fourth convolution layer and a fifth convolution layer, the convolution kernel of the fourth convolution layer is 3*3, the step length is 1 and is used for feature extraction, the convolution kernel of the fifth convolution layer is 1*1, the step length is 1 and is used for smoothing the features; the reasoning layer comprises a sixth convolution layer, the convolution kernel of the sixth convolution layer is 3*3, the step length is 1, and the convolution kernel is used for fusing the feature matrix output by the training layer;
and carrying out feature classification and identification through a classifier.
8. The artificial intelligence based injection access device of claim 6, wherein the injection information identifying module is specifically configured to perform:
the second neural network comprises a convolution layer, a downsampling layer, a full-connection layer and a Gaussian connection layer; the convolution kernel size of the convolution layer is 5*5, and the step size is 1.
9. The artificial intelligence based injection access device of claim 7 or 8, further comprising a sensing module configured to perform:
and regulating the temperature and humidity of the medicine cabinet according to the storage temperature of the injection, electronically counting the quantity of the stored or taken out injection by a sensor when the injection is stored or taken out, simultaneously identifying the stored or taken out injection by a bar code or a two-dimensional code through a first identification unit, and sending the counting result and the identification result to a medicine cabinet database.
10. The artificial intelligence based injection access device of claim 9, further comprising:
the first signal comprises a drug storage driving signal and a shortest drug storage path;
the second signal comprises a drug delivery driving signal and a shortest drug delivery path;
the central control unit acquires the shortest medicine storage path and the shortest medicine taking path through an RRT algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311405244.3A CN117315850B (en) | 2023-10-27 | 2023-10-27 | Injection storing and taking method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311405244.3A CN117315850B (en) | 2023-10-27 | 2023-10-27 | Injection storing and taking method and device based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117315850A true CN117315850A (en) | 2023-12-29 |
| CN117315850B CN117315850B (en) | 2024-03-19 |
Family
ID=89242603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311405244.3A Active CN117315850B (en) | 2023-10-27 | 2023-10-27 | Injection storing and taking method and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117315850B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106938755A (en) * | 2016-11-29 | 2017-07-11 | 上海无线电设备研究所 | Intelligent drugstore automation medicine-feeding medicine discharge system and method |
| CN107657995A (en) * | 2017-10-11 | 2018-02-02 | 深圳诺博医疗科技有限公司 | Emergency call medication management method, Emergency call medication management system and computer-readable recording medium |
| CN108128584A (en) * | 2017-12-01 | 2018-06-08 | 上海神添实业有限公司 | A kind of intelligent and automatic dispensary |
| CN109615574A (en) * | 2018-12-13 | 2019-04-12 | 济南大学 | Chinese medicine recognition methods and system based on GPU and double scale image feature comparisons |
| CN110197710A (en) * | 2019-06-12 | 2019-09-03 | 广州巨米智能设备有限公司 | A kind of intelligent medicine cabinet system |
| CN113148513A (en) * | 2021-05-13 | 2021-07-23 | 河北工业大学 | Intelligent pharmacy and medicine dispensing method |
| CN214609858U (en) * | 2020-11-02 | 2021-11-05 | 重庆三峡医药高等专科学校 | Self-service medicine taking and automatic medicine sending robot system |
| CN115565180A (en) * | 2022-10-14 | 2023-01-03 | 深圳市瑞意博医疗设备有限公司 | Quick automatic identification equipment of injection medicine |
| CN115761834A (en) * | 2022-10-14 | 2023-03-07 | 奥比中光科技集团股份有限公司 | Multi-task mixed model for face recognition and face recognition method |
| CN116758609A (en) * | 2023-05-24 | 2023-09-15 | 淮阴工学院 | Lightweight face recognition method based on feature model improvement |
-
2023
- 2023-10-27 CN CN202311405244.3A patent/CN117315850B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106938755A (en) * | 2016-11-29 | 2017-07-11 | 上海无线电设备研究所 | Intelligent drugstore automation medicine-feeding medicine discharge system and method |
| CN107657995A (en) * | 2017-10-11 | 2018-02-02 | 深圳诺博医疗科技有限公司 | Emergency call medication management method, Emergency call medication management system and computer-readable recording medium |
| CN108128584A (en) * | 2017-12-01 | 2018-06-08 | 上海神添实业有限公司 | A kind of intelligent and automatic dispensary |
| CN109615574A (en) * | 2018-12-13 | 2019-04-12 | 济南大学 | Chinese medicine recognition methods and system based on GPU and double scale image feature comparisons |
| CN110197710A (en) * | 2019-06-12 | 2019-09-03 | 广州巨米智能设备有限公司 | A kind of intelligent medicine cabinet system |
| CN214609858U (en) * | 2020-11-02 | 2021-11-05 | 重庆三峡医药高等专科学校 | Self-service medicine taking and automatic medicine sending robot system |
| CN113148513A (en) * | 2021-05-13 | 2021-07-23 | 河北工业大学 | Intelligent pharmacy and medicine dispensing method |
| CN115565180A (en) * | 2022-10-14 | 2023-01-03 | 深圳市瑞意博医疗设备有限公司 | Quick automatic identification equipment of injection medicine |
| CN115761834A (en) * | 2022-10-14 | 2023-03-07 | 奥比中光科技集团股份有限公司 | Multi-task mixed model for face recognition and face recognition method |
| CN116758609A (en) * | 2023-05-24 | 2023-09-15 | 淮阴工学院 | Lightweight face recognition method based on feature model improvement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117315850B (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11055349B2 (en) | Efficient storage and processing of high-dimensional feature vectors | |
| Zantalis et al. | A review of machine learning and IoT in smart transportation | |
| Liu et al. | CPS-based smart warehouse for industry 4.0: A survey of the underlying technologies | |
| US10607484B2 (en) | Privacy-preserving distributed visual data processing | |
| Wang et al. | Mango fruit load estimation using a video based MangoYOLO—Kalman filter—hungarian algorithm method | |
| Ashraf et al. | Application of deep convolutional neural networks and smartphone sensors for indoor localization | |
| US20210117948A1 (en) | Mobile device platform for automated visual retail product recognition | |
| EP3499414A1 (en) | Lightweight 3d vision camera with intelligent segmentation engine for machine vision and auto identification | |
| Shelke et al. | Static and dynamic activity detection with ambient sensors in smart spaces | |
| Vítek et al. | A distributed wireless camera system for the management of parking spaces | |
| CN109670546B (en) | Commodity matching and quantity regression recognition algorithm based on preset template | |
| Carrillo et al. | Magicfinger: 3d magnetic fingerprints for indoor location | |
| Sánchez et al. | Video sensor architecture for surveillance applications | |
| Iftikhar et al. | Target detection and recognition for traffic congestion in smart cities using deep learning-enabled UAVs: A review and analysis | |
| CN109741108A (en) | Streaming application recommended method, device and electronic equipment based on context aware | |
| Qian et al. | An orthogonal weighted occupancy likelihood map with IMU-aided laser scan matching for 2D indoor mapping | |
| Mentasti et al. | Controlling the flight of a drone and its camera for 3D reconstruction of large objects | |
| Kozák et al. | Data-driven object pose estimation in a practical bin-picking application | |
| Suto | A novel plug-in board for remote insect monitoring | |
| Shin et al. | A vision-based collision monitoring system for proximity of construction workers to trucks enhanced by posture-dependent perception and truck bodies’ occupied space | |
| CN117315850B (en) | Injection storing and taking method and device based on artificial intelligence | |
| Kainz et al. | Traffic monitoring from the perspective of an unmanned aerial vehicle | |
| Patel et al. | Effective motion sensors and deep learning techniques for unmanned ground vehicle (UGV)-based automated pavement layer change detection in road construction | |
| CN109035558B (en) | Commodity recognition algorithm online learning system for unmanned sales counter | |
| Moon et al. | Smart count system based on object detection using deep learning |
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 |