CN116584978A - Test tube recovery system, equipment and medium for self-help nucleic acid sampling - Google Patents
Test tube recovery system, equipment and medium for self-help nucleic acid sampling Download PDFInfo
- Publication number
- CN116584978A CN116584978A CN202310143577.7A CN202310143577A CN116584978A CN 116584978 A CN116584978 A CN 116584978A CN 202310143577 A CN202310143577 A CN 202310143577A CN 116584978 A CN116584978 A CN 116584978A
- Authority
- CN
- China
- Prior art keywords
- test tube
- recovery
- image
- module
- label
- 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.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 220
- 238000011084 recovery Methods 0.000 title claims abstract description 95
- 150000007523 nucleic acids Chemical class 0.000 title claims abstract description 21
- 102000039446 nucleic acids Human genes 0.000 title claims abstract description 21
- 108020004707 nucleic acids Proteins 0.000 title claims abstract description 21
- 238000005070 sampling Methods 0.000 title claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000013519 translation Methods 0.000 claims abstract description 11
- 238000005057 refrigeration Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 32
- 238000001514 detection method Methods 0.000 claims description 26
- 238000004064 recycling Methods 0.000 claims description 22
- 238000003062 neural network model Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 238000013145 classification model Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 11
- 230000000007 visual effect Effects 0.000 claims description 11
- 239000007788 liquid Substances 0.000 claims description 9
- 239000003153 chemical reaction reagent Substances 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 229920000742 Cotton Polymers 0.000 claims description 7
- 239000007921 spray Substances 0.000 claims description 7
- 230000006399 behavior Effects 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 230000001954 sterilising effect Effects 0.000 claims description 3
- 238000005299 abrasion Methods 0.000 claims description 2
- 230000000249 desinfective effect Effects 0.000 claims description 2
- 238000011330 nucleic acid test Methods 0.000 abstract description 8
- 210000003128 head Anatomy 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 239000000243 solution Substances 0.000 description 6
- 230000004044 response Effects 0.000 description 4
- 238000004659 sterilization and disinfection Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 239000000645 desinfectant Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 206010011409 Cross infection Diseases 0.000 description 1
- 206010029803 Nosocomial infection Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000012085 test solution Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
- A61B10/0045—Devices for taking samples of body liquids
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
- A61B10/0045—Devices for taking samples of body liquids
- A61B10/0051—Devices for taking samples of body liquids for taking saliva or sputum samples
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B50/00—Containers, covers, furniture or holders specially adapted for surgical or diagnostic appliances or instruments, e.g. sterile covers
- A61B50/30—Containers specially adapted for packaging, protecting, dispensing, collecting or disposing of surgical or diagnostic appliances or instruments
- A61B50/36—Containers specially adapted for packaging, protecting, dispensing, collecting or disposing of surgical or diagnostic appliances or instruments for collecting or disposing of used articles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B50/00—Containers, covers, furniture or holders specially adapted for surgical or diagnostic appliances or instruments, e.g. sterile covers
- A61B50/30—Containers specially adapted for packaging, protecting, dispensing, collecting or disposing of surgical or diagnostic appliances or instruments
- A61B50/36—Containers specially adapted for packaging, protecting, dispensing, collecting or disposing of surgical or diagnostic appliances or instruments for collecting or disposing of used articles
- A61B50/39—Containers specially adapted for packaging, protecting, dispensing, collecting or disposing of surgical or diagnostic appliances or instruments for collecting or disposing of used articles the containers containing antimicrobial, antiviral or disinfectant agents
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B90/00—Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups A61B1/00 - A61B50/00, e.g. for luxation treatment or for protecting wound edges
- A61B90/08—Accessories or related features not otherwise provided for
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B90/00—Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups A61B1/00 - A61B50/00, e.g. for luxation treatment or for protecting wound edges
- A61B90/36—Image-producing devices or illumination devices not otherwise provided for
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
- A61B2010/009—Various features of diagnostic instruments
-
- 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
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W90/00—Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Surgery (AREA)
- Engineering & Computer Science (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Hematology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Pulmonology (AREA)
- Virology (AREA)
- Apparatus Associated With Microorganisms And Enzymes (AREA)
Abstract
The application relates to the technical field of unmanned supervision of nucleic acid test tube recovery, in particular to a test tube recovery system, equipment and medium for self-help nucleic acid sampling, wherein the recovery system comprises: the sample recovery module comprises a test tube, a test tube rack, a test tube recovery window, a test tube sterilizer, a test tube driving unit, a test tube translation table and a stepping motor; the voice prompt module is used for prompting whether the behavior of the target object in self-service sample recovery accords with the specification or not; the low-temperature refrigeration module is used for maintaining a low-temperature environment inside the recovery system; the intelligent processing module comprises a motion control unit and an information storage unit, wherein the motion control unit is used for controlling the sample recovery module, and the information storage unit is used for storing information of a target object and a corresponding sample. The application can realize the recovery of the nucleic acid test tube with low cost and no supervision.
Description
Technical Field
The application relates to the technical field of unmanned supervision of nucleic acid test tube recovery, in particular to a test tube recovery system, device and medium for self-help nucleic acid sampling.
Background
The conventional nucleic acid detection system is used in a scene such as a hospital, and a large amount of nucleic acid sampling and detection work is required. In this process, the cuvette is a common sample collection and transfer tool. However, due to operator negligence or human factors, situations may sometimes occur in which test tubes are left out or misplaced, which may lead to sample loss or inaccuracy in the test results. The current nucleic acid detection system cannot timely and accurately detect the missing condition of the test tube, so that a sample is lost and the detection result is incomplete. Meanwhile, in scenes such as hospitals, the movement of people and equipment may cause dynamic changes of the scenes, thereby affecting the tracking effect of the test tube. For example, when a target object places a cuvette in the recovery window, there may be interference by other objects or people around, so that the tracking ability of the model is limited.
Disclosure of Invention
The application discloses a self-help nucleic acid sampling-oriented test tube recovery system, equipment and medium, which are used for realizing the recovery of a nucleic acid test tube with low cost and no supervision, so as to solve at least one of the prior problems.
The application provides a self-help nucleic acid sampling-oriented test tube recovery system, which comprises:
the sample recovery module comprises a test tube, a test tube rack, a test tube recovery window, a test tube sterilizer, a test tube driving unit, a test tube translation table and a stepping motor;
the voice prompt module is used for prompting whether the behavior of the target object in self-service sample recovery accords with the specification or not;
the low-temperature refrigeration module is used for maintaining a low-temperature environment inside the recovery system;
the intelligent processing module comprises a motion control unit and an information storage unit, wherein the motion control unit is used for controlling the sample recovery module, and the information storage unit is used for storing information of a target object and a corresponding sample thereof;
the visual analysis module is used for monitoring the self-help sample recovery process of the target object and comprises a camera, an image detection unit and an image tracking unit;
the low-temperature refrigerating module, the intelligent processing module, the test tube translation platform and the stepper motor are located the bottom of recovery system, the voice prompt module, the visual analysis module with the test tube recovery window is located the top of recovery system, the test tube drive unit is fixed on the test tube translation platform and is used for the drive the test tube rack removes, the test tube rack is used for fixing the test tube, the test tube recovery window has the through-hole of switching and is located the top of test tube rack, the camera is just to the position of test tube recovery window, the test tube sterilizer is used for disinfecting the test tube.
Further, the two-dimensional code is attached to the test tube, when the camera captures the two-dimensional code, the image detection unit judges that the test tube is not in the use validity period according to test tube information in the two-dimensional code, and the voice prompt module sends out a test tube disqualification prompt.
Further, the image detection unit determines the results of a first judgment, a second judgment and a third judgment based on the image classification model, the first judgment is whether the test tube cover of the test tube is in a screwing state, the second judgment is whether the test tube contains a cotton swab head and reagent liquid, the third judgment is whether the two-dimensional code on the test tube is not worn, and when the first judgment, the second judgment and the third judgment are yes, the motion control unit controls the test tube recovery window to open the through hole, and the information storage unit records information of a target object in the two-dimensional code of the test tube.
Further, the training method of the image classification model specifically includes:
determining a pre-trained first neural network model, the first neural network model having a first output branch, a second output branch, and a third output branch;
acquiring first images in a preset number, wherein the first images are marked with a first label, a second label and a third label, the first label is a test tube cover of the test tube, the second label is a cotton swab head and reagent liquid in the test tube, the third label is a two-dimensional code on the test tube, and a dataset of the first images is input into the first neural network model;
calculating loss based on a composite weighted loss function of cross entropy, adopting a gradient descent method to optimize network parameters, and respectively outputting a data set of the first tag, a data set of the second tag and a data set of the third tag through the first output branch, the second output branch and the third output branch;
and combining output results of the first output branch, the second output branch and the third output branch to obtain an image classification model.
Further, the image detection unit enters a monitoring mode based on an image tracking model, wherein the monitoring mode is a process that the camera tracks the test tube to enter the test tube recovery window; when the image detection unit enters a monitoring mode, the camera shoots images in real time and transmits the images to the information storage unit; when the test tube cannot be captured by the camera, the voice prompt module sends out an alarm prompt; and when the monitoring mode is finished, the motion control unit controls the test tube recovery window to close the through hole, and the voice prompt module sends out a recovery success prompt.
Further, the training method of the image tracking model specifically includes:
determining a pre-trained YOLO network model, and then acquiring a data set of a second image, wherein the data set of the second image is a process that the camera tracks the test tube to enter the test tube recovery window, and the data set of the second image is input into the YOLO network model;
based on the YOLO network model, marking a fourth label for the test tube on the second image by adopting a bounding box, so as to obtain a second neural network model, wherein the marking method of the bounding box meets the requirements (x, y, w, h, confidence) and the confidence meets the requirementsWhere x and y denote coordinates of the center position of the bounding box, w and h denote width and height of the bounding box, confidence is a confidence value of the bounding box and indicates whether the bounding box contains the cuvette and the accuracy of the position of the fourth label within the bounding box, pr (Object) denotes whether the fourth label is contained within the bounding box, pr (Object) =1 if the fourth label is contained within the bounding box, otherwise Pr (Object) =0,representing an intersection between the predicted frame and the actual frame;
and processing the second neural network model according to a target tracking algorithm to obtain an image tracking model.
Further, when the target object places the test tube into the test tube recycling window, the motion control unit controls the test tube sterilizer to spray disinfectant, and then controls the test tube driving unit to move the next empty position on the test tube rack to be right below the test tube recycling window.
Further, the intelligent processing module further comprises a logic processing unit and a wireless communication unit, the wireless communication unit is connected with the mobile terminal based on a wireless network, when the logic processing unit judges that test tube racks in the recovery system are all filled with test tubes, the wireless communication unit sends a message to the mobile terminal, and the voice prompt module simultaneously sends out a prompt that the test tubes are full.
The present application also provides a computer device, comprising: memory and processor and computer program stored on the memory, which when executed on the processor, implement a training method of the image classification model or the image tracking model.
The application also provides a computer readable storage medium having stored thereon a computer program which when run by a processor implements a training method of the image classification model or the image tracking model.
Compared with the prior art, the application has at least one of the following technical effects:
1. the whole process from nucleic acid sampling to test tube recovery completely avoids personnel contact, and can effectively avoid cross infection.
2. According to the application, the image tracking model is adopted to detect the appearance of the test tube and monitor the process of putting the test tube into the recovery window by the target object, so that the whole recovery process is supervised, the standard recovery of the test tube is ensured, and the reliability is improved.
3. And the test tube recovery is not supervised by people, so that the consumption of manpower and material resources is reduced.
4. Compared with the existing mechanical arm nucleic acid sampling scheme, the system of the scheme is more beneficial to throwing in a hospital scene, and is convenient for target objects to recycle nucleic acid test tubes anytime and anywhere.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a self-help nucleic acid sampling-oriented test tube recovery system according to an embodiment of the present application;
FIG. 2 is a schematic diagram of the internal structure of a tube recovery system for self-help nucleic acid sampling according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of an intelligent processing module of a self-help nucleic acid sampling-oriented test tube recovery system according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a visual analysis module of a self-help nucleic acid sampling-oriented cuvette recycling system according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a use flow of a tube recovery system for self-help nucleic acid sampling according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in the present description and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Furthermore, the terms "first," "second," "third," and the like in the description of the present specification and in the appended claims, are used for distinguishing between descriptions and not necessarily for indicating or implying a relative importance.
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
Referring to fig. 1 to 4, an embodiment of the present application provides a self-service nucleic acid sampling-oriented cuvette recycling system, the recycling system comprising:
a sample recovery module including a test tube 101, a test tube rack 102, a test tube recovery window 103, a test tube sterilizer 104, a test tube driving unit 105, a test tube translation stage 106, and a stepping motor 107;
the voice prompt module 2 is used for prompting whether the behavior of the target object in self-service sample recovery accords with the specification or not;
a cryorefrigeration module 3, wherein the cryorefrigeration module 3 is used for maintaining a low-temperature environment inside the recovery system;
the intelligent processing module 4, the intelligent processing module 4 comprises a motion control unit 401 and an information storage unit 402, the motion control unit 401 is used for controlling the sample recovery module, and the information storage unit 402 is used for storing information of a target object and a corresponding sample thereof;
a visual analysis module 5, wherein the visual analysis module 5 is used for monitoring the self-help sample recovery process of the target object, and comprises a camera 501, an image detection unit 502 and an image tracking unit 503;
the low-temperature refrigeration module 3, the intelligent processing module 4, the test tube translation table 106 and the stepping motor 107 are located at the bottom of the recovery system, the voice prompt module 2, the visual analysis module 5 and the test tube recovery window 103 are located at the top of the recovery system, the test tube driving unit 105 is fixed on the test tube translation table 106 and used for driving the test tube rack 102 to move, the test tube rack 102 is used for fixing the test tube 101, the test tube recovery window 103 is provided with a through hole capable of being opened and closed and is located above the test tube rack 102, the camera 501 is opposite to the position of the test tube recovery window 103, and the test tube sterilizer 104 is used for sterilizing the test tube 101.
The two-dimensional code is attached to the test tube 101, when the camera 501 captures the two-dimensional code, the image detection unit 502 judges that the test tube 101 is not in the service life according to test tube information in the two-dimensional code, and the voice prompt module 2 sends out a test tube disqualification prompt.
The image detection unit 502 determines the results of a first determination, a second determination and a third determination based on the image classification model, where the first determination is whether the tube cover of the tube 101 is in a screwed state, the second determination is whether the tube 101 contains a swab head and a reagent solution, the third determination is whether the two-dimensional code on the tube 101 is not worn, and when the first determination, the second determination and the third determination are all yes, the motion control unit 401 controls the tube recovery window 103 to open a through hole, and the information storage unit 402 records information of a target object in the two-dimensional code of the tube 101.
The image detection unit 502 enters a monitoring mode based on an image tracking model, wherein the monitoring mode is a process that the camera 501 tracks the test tube 101 entering the test tube recovery window 103; when the image detection unit 502 enters a monitoring mode, the camera 501 shoots images in real time and transmits the images to the information storage unit 402; when the camera 501 cannot capture the test tube 101, the voice prompt module 2 sends an alarm prompt; when the monitoring mode is finished, the motion control unit 401 controls the test tube recycling window 103 to close the through hole, and the voice prompt module 2 sends out a recycling success prompt.
When the target object places the test tube 101 in the test tube recovery window 103, the motion control unit 401 controls the test tube sterilizer 104 to spray the sterilizing liquid, and then controls the test tube driving unit 105 to move the next empty position on the test tube rack 102 to a position right below the test tube recovery window 103.
The intelligent processing module 4 further comprises a logic processing unit 403 and a wireless communication unit 404, the wireless communication unit 404 is connected with the mobile terminal based on a wireless network, when the logic processing unit 403 determines that the test tube racks 102 in the recovery system are all filled with test tubes, the wireless communication unit 404 sends a message to the mobile terminal, and the voice prompt module 2 simultaneously sends out a test tube full prompt.
Referring to fig. 5, fig. 5 is a schematic diagram of a usage flow of a tube recovery system for self-help nucleic acid sampling according to an embodiment of the present application, and the specific flow is as follows.
S501: after the target object gets the test tube, scanning the two-dimensional code on the test tube, filling in the personal information of all the sampled persons, and completing the nucleic acid sampling.
S502: after the personal nucleic acid sampling is completed, the target object carries the nucleic acid test tube and goes to the test tube recovery system to carry out test tube two-dimensional code information recording, the visual analysis module of test tube recovery system scans the two-dimensional code on the test tube at first, judges whether the test tube is in the use validity period according to the test tube information in the two-dimensional code, if the test tube is not in the use validity period, the voice prompt module sends out the illegal alarm of the test tube, if the test tube is in the use validity period, the voice prompt and the next step of judgment are carried out.
S503: the visual analysis module of the test tube recycling system judges whether the recycled test tube is qualified or not through the image classification model. The image classification model uses a large number of qualified test tubes (a test tube two-dimensional code is not worn, a cotton swab head and a test solution are arranged in the test tube, a test tube cover is screwed, the appearance of the test tube is intact) and unqualified test tubes as learning samples in the early stage, and marks a plurality of labels for target detection, such as the state of the test tube cover, the state of the cotton swab head in the test tube, the state of the test tube two-dimensional code and the like, and the deep learning target detection algorithm has the functions of detecting and identifying the test tubes after training. Firstly, whether the test tube cover is in a screwing state is detected, and if the test tube cover does not meet the requirement, the voice prompt module prompts a target object to screw the test tube cover; meanwhile, whether the cotton swab head and the reagent liquid exist in the test tube or not is monitored, and if abrasion of the target or the two-dimensional code of the test tube cannot be detected, the test tube of the target object is prompted to be unqualified. And if the test tube is detected to be qualified, recording target object information in the two-dimensional code and opening a test tube receiving window.
S504: the visual analysis module monitors the target object in the whole process and places the test tube into the test tube receiving window, so that the recovery of the test tube is ensured. And if the target object does not put the test tube into the recovery window, an alarm is sent out for reminding.
S505: after the target object puts legal test tube into the test tube rack under the test tube recovery window, the test tube recovery system closes the pupil of the test tube recovery window to the target object information is recorded, and the test tube sterilizer sprays disinfection spray, accomplishes the collection and the low temperature storage of nucleic acid test tube, and moves the test tube rack through test tube translation platform and test tube drive unit, moves the empty test tube rack under the test tube recovery window, waits for next target object to use the device to retrieve the test tube. In addition, the total amount of the disinfection spray is set in advance to be matched with the storage capacity of the test tubes of the whole recovery system, and when the recovery is full, the disinfection spray is also used up.
S506: when the test tube in the test tube recovery system is full, the intelligent processing module of the recovery system can send information to related staff in mobile phone app or applet, inform the staff to go to a specific test tube recovery system to recover the test tube, and fill up the disinfectant in the recovery system, thereby ensuring the normal disinfection of the next recovery. Meanwhile, the test tube recovery system is in a state of being full of test tubes, when a target object submits the test tubes before, the system prompts that the current recovery system is full in voice, and the test tubes are put into other recovery systems. In addition, the worker may periodically collect the nucleic acid test tube in the apparatus when the test tube is not full.
In some embodiments, the training method of the image classification model specifically includes:
determining a pre-trained first neural network model, the first neural network model having a first output branch, a second output branch, and a third output branch;
acquiring first images in a preset number, wherein the first images are marked with a first label, a second label and a third label, the first label is a test tube cover of the test tube, the second label is a cotton swab head and reagent liquid in the test tube, the third label is a two-dimensional code on the test tube, and a dataset of the first images is input into the first neural network model;
calculating loss based on a composite weighted loss function of cross entropy, adopting a gradient descent method to optimize network parameters, and respectively outputting a data set of the first tag, a data set of the second tag and a data set of the third tag through the first output branch, the second output branch and the third output branch;
and combining output results of the first output branch, the second output branch and the third output branch to obtain an image classification model.
In this embodiment, the multi-label image classification algorithm is adopted to label the test tube cover of the test tube, the swab head and the reagent liquid in the test tube and the two-dimensional code on the outer wall of the test tube on the same picture, and the pre-trained first neural network model can be obtained by using a neural network model in the prior art, for example, CNN (convolutional neural network) and RNN (cyclic neural network), which is not limited in any way. In calculating the loss function, the loss functions obtained by each training of the first output branch, the second output branch and the third output branch are weighted and averaged respectively to obtain a target loss function.
In some embodiments, the training method of the image tracking model specifically includes:
determining a pre-trained YOLO network model, and then acquiring a data set of a second image, wherein the data set of the second image is a process that the camera tracks the test tube to enter the test tube recovery window, and the data set of the second image is input into the YOLO network model;
based on the YOLO network model, marking a fourth label for the test tube on the second image by adopting a bounding box, so as to obtain a second neural network model, wherein the marking method of the bounding box meets the requirements (x, y, w, h, confidence) and the confidence meets the requirementsWhere x and y denote coordinates of the center position of the bounding box, w and h denote width and height of the bounding box, confidence is a confidence value of the bounding box and indicates whether the bounding box contains the cuvette and the accuracy of the position of the fourth label within the bounding box, pr (Object) denotes whether the fourth label is contained within the bounding box, pr (Object) =1 if the fourth label is contained within the bounding box, otherwise Pr (Object) =0,representing an intersection between the predicted frame and the actual frame;
and processing the second neural network model according to a target tracking algorithm to obtain an image tracking model.
In this embodiment, the image tracking model is divided into two parts, namely an image detection algorithm and a target tracking algorithm, the image detection algorithm adopts a YOLO network model, and the target tracking algorithm can be a sort target tracking algorithm, a deepsort target tracking algorithm, and the like, which is not limited in any way. In the pre-training phase of the YOLO network model, 20 convolution layers, 1 average pooling layer and 1 full connection layer of the YOLO network model are firstly trained by using image net1000 types of data, and then the YOLO network model is trained by using PASCAL VOC 20 types of labeling data to obtain the pre-trained YOLO network model, and the details of the prior art are omitted. After the pre-trained YOLO network model is determined, processing the multi-frame pictures of the process of taking the test tube into the test tube recovery window by using the camera to form a data set of a second image, inputting the data set into the YOLO network model for training to obtain the YOLO network model capable of carrying out image detection on the multi-frame pictures of the process of taking the test tube into the test tube recovery window, and finally obtaining the image tracking model by combining a target tracking algorithm.
Referring to fig. 6, the present application provides a computer device 6, comprising: a memory 602 and a processor 601 and a computer program 603 stored on the memory, which computer program 603, when executed on the processor 601, implements a training method of the image classification model or the image tracking model.
The computer device 6 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The computer device may include, but is not limited to, a processor 601, a memory 602. It will be appreciated by those skilled in the art that fig. 6 is merely an example of computer device 6 and is not intended to be limiting of computer device 6, and may include more or fewer components than shown, or may combine certain components, or different components, such as may also include input-output devices, network access devices, etc.
The processor 601 may be a central processing unit (Central Processing Unit, CPU), the processor 601 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 602 may in some embodiments be an internal storage unit of the computer device 6, such as a hard disk or a memory of the computer device 6. The memory 602 may also be an external storage device of the computer device 6 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 6. Further, the memory 602 may also include both internal storage units and external storage devices of the computer device 6. The memory 602 is used to store an operating system, application programs, boot loader (BootLoader), data, and other programs, such as program code for the computer program. The memory 602 may also be used to temporarily store data that has been output or is to be output.
The present application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a training method of the image classification model or the image tracking model.
In this embodiment, the integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing device/terminal apparatus, recording medium, computer Memory, read-Only Memory (ROM), random access Memory (RAM, random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the disclosed embodiments of the application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the apparatus/terminal device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application 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 technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. A self-service nucleic acid sampling oriented cuvette recycling system, the recycling system comprising:
the sample recovery module comprises a test tube, a test tube rack, a test tube recovery window, a test tube sterilizer, a test tube driving unit, a test tube translation table and a stepping motor;
the voice prompt module is used for prompting whether the behavior of the target object in self-service sample recovery accords with the specification or not;
the low-temperature refrigeration module is used for maintaining a low-temperature environment inside the recovery system;
the intelligent processing module comprises a motion control unit and an information storage unit, wherein the motion control unit is used for controlling the sample recovery module, and the information storage unit is used for storing information of a target object and a corresponding sample thereof;
the visual analysis module is used for monitoring the self-help sample recovery process of the target object and comprises a camera, an image detection unit and an image tracking unit;
the low-temperature refrigerating module, the intelligent processing module, the test tube translation platform and the stepper motor are located the bottom of recovery system, the voice prompt module, the visual analysis module with the test tube recovery window is located the top of recovery system, the test tube drive unit is fixed on the test tube translation platform and is used for the drive the test tube rack removes, the test tube rack is used for fixing the test tube, the test tube recovery window has the through-hole of switching and is located the top of test tube rack, the camera is just to the position of test tube recovery window, the test tube sterilizer is used for disinfecting the test tube.
2. The recycling system according to claim 1, wherein the test tube is attached with a two-dimensional code, when the camera captures the two-dimensional code, the image detection unit judges that the test tube is not in a use validity period according to test tube information in the two-dimensional code, and the voice prompt module sends out a test tube failure prompt.
3. The recycling system according to claim 1, wherein the image detecting unit determines the results of a first judgment, a second judgment and a third judgment based on an image classification model, the first judgment being whether a test tube cover of the test tube is in a screwed state, the second judgment being whether a swab head and a reagent liquid are contained in the test tube, the third judgment being whether there is no abrasion of a two-dimensional code on the test tube, the movement control unit controlling the test tube recycling window to open a through hole when the first judgment, the second judgment and the third judgment are both yes, the information storing unit recording information of a target object in the two-dimensional code of the test tube.
4. A recycling system according to claim 3, wherein the training method of the image classification model specifically comprises:
determining a pre-trained first neural network model, the first neural network model having a first output branch, a second output branch, and a third output branch;
acquiring first images in a preset number, wherein the first images are marked with a first label, a second label and a third label, the first label is a test tube cover of the test tube, the second label is a cotton swab head and reagent liquid in the test tube, the third label is a two-dimensional code on the test tube, and a dataset of the first images is input into the first neural network model;
calculating loss based on a composite weighted loss function of cross entropy, adopting a gradient descent method to optimize network parameters, and respectively outputting a data set of the first tag, a data set of the second tag and a data set of the third tag through the first output branch, the second output branch and the third output branch;
and combining output results of the first output branch, the second output branch and the third output branch to obtain an image classification model.
5. The recycling system according to claim 1, wherein the image detection unit enters a monitoring mode based on an image tracking model, the monitoring mode being a process in which the camera tracks the test tube entering the test tube recycling window; when the image detection unit enters a monitoring mode, the camera shoots images in real time and transmits the images to the information storage unit; when the test tube cannot be captured by the camera, the voice prompt module sends out an alarm prompt; and when the monitoring mode is finished, the motion control unit controls the test tube recovery window to close the through hole, and the voice prompt module sends out a recovery success prompt.
6. The recycling system according to claim 5, wherein the training method of the image tracking model specifically comprises:
determining a pre-trained YOLO network model, and then acquiring a data set of a second image, wherein the data set of the second image is a process that the camera tracks the test tube to enter the test tube recovery window, and the data set of the second image is input into the YOLO network model;
based on the YOLO network model, marking a fourth label for the test tube on the second image by adopting a bounding box, so as to obtain a second neural network model, wherein the marking method of the bounding box meets the requirements (x, y, w, h, confidence) and the confidence meets the requirementsWherein x and y represent bounding boxesCoordinates of the center position, w and h represent width and height of the bounding box, confidence is a confidence value of the bounding box and represents whether the bounding box contains the cuvette and accuracy of the position of the fourth label within the bounding box, pr (Object) represents whether the fourth label is contained within the bounding box, pr (Object) =1 if the fourth label is contained within the bounding box, otherwise Pr (Object) =0,>representing an intersection between the predicted frame and the actual frame;
and processing the second neural network model according to a target tracking algorithm to obtain an image tracking model.
7. The recycling system according to claim 1, wherein the motion control unit controls the tube sterilizer to spray the sterilizing liquid after the target subject puts the tube into the tube recycling window, and then controls the tube driving unit to move the next empty position on the tube rack to be directly under the tube recycling window.
8. The recycling system according to claim 1, wherein the intelligent processing module further comprises a logic processing unit and a wireless communication unit, the wireless communication unit is connected with the mobile terminal based on a wireless network, when the logic processing unit judges that test tube racks in the recycling system are all filled with test tubes, the wireless communication unit sends a message to the mobile terminal, and the voice prompt module simultaneously sends out a test tube full prompt.
9. A computer device, the device comprising: memory and processor and computer program stored on the memory, which, when executed on the processor, implements the training method of claim 4 or 6.
10. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the training method of claim 4 or 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310143577.7A CN116584978A (en) | 2023-02-21 | 2023-02-21 | Test tube recovery system, equipment and medium for self-help nucleic acid sampling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310143577.7A CN116584978A (en) | 2023-02-21 | 2023-02-21 | Test tube recovery system, equipment and medium for self-help nucleic acid sampling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116584978A true CN116584978A (en) | 2023-08-15 |
Family
ID=87592559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310143577.7A Pending CN116584978A (en) | 2023-02-21 | 2023-02-21 | Test tube recovery system, equipment and medium for self-help nucleic acid sampling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116584978A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117110593A (en) * | 2023-08-16 | 2023-11-24 | 杭州博欣科技有限公司 | Urine and faeces collecting system |
-
2023
- 2023-02-21 CN CN202310143577.7A patent/CN116584978A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117110593A (en) * | 2023-08-16 | 2023-11-24 | 杭州博欣科技有限公司 | Urine and faeces collecting system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111680551B (en) | Method, device, computer equipment and storage medium for monitoring livestock quantity | |
| Cucchiara et al. | A multi‐camera vision system for fall detection and alarm generation | |
| CN107005679B (en) | Intelligent target identification device, system and method based on cloud service | |
| US20200012894A1 (en) | Visually Aided Active Learning for Training Object Detector | |
| CN106355367A (en) | Warehouse monitoring management device | |
| CN110049121B (en) | Data center inspection system based on augmented reality technology | |
| WO2021043074A1 (en) | Urban pet motion trajectory monitoring method based on image recognition, and related devices | |
| CN111310596A (en) | Animal diseased state monitoring system and method | |
| US11763566B2 (en) | Target association using occlusion analysis, clustering, or both | |
| CN116584978A (en) | Test tube recovery system, equipment and medium for self-help nucleic acid sampling | |
| CN113052295B (en) | Training method of neural network, object detection method, device and equipment | |
| CN113936340B (en) | AI model training method and device based on training data acquisition | |
| CN110370273A (en) | A kind of Obstacle Avoidance, device and system | |
| CN108874910B (en) | Vision-based small target recognition system | |
| CN113990500A (en) | Vital sign parameter monitoring method and device and storage medium | |
| CN113869177A (en) | Method and device for tracking multiple targets | |
| US20220202329A1 (en) | Method and apparatus for inversion detection | |
| US20220335725A1 (en) | Monitoring presence or absence of an object using local region matching | |
| US20220147749A1 (en) | Adversarial masks for scene-customized false detection removal | |
| CN115793632A (en) | Unmanned vehicle control method and server | |
| CN113916899A (en) | Method, system and device for detecting large soft infusion bag product based on visual identification | |
| CN106650280A (en) | System for automatically analyzing historical human body health data by artificial intelligence technology | |
| CN113807150A (en) | Data processing method, attitude prediction method, data processing device, attitude prediction device, and storage medium | |
| CN112598745B (en) | Method and device for determining person-goods association event | |
| US20240020963A1 (en) | Object embedding 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 |