CN113842171B - Validity judging device for throat swab machine sampling - Google Patents

Validity judging device for throat swab machine sampling Download PDF

Info

Publication number
CN113842171B
CN113842171B CN202111147190.6A CN202111147190A CN113842171B CN 113842171 B CN113842171 B CN 113842171B CN 202111147190 A CN202111147190 A CN 202111147190A CN 113842171 B CN113842171 B CN 113842171B
Authority
CN
China
Prior art keywords
sampling
module
swab
judging
bracket
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111147190.6A
Other languages
Chinese (zh)
Other versions
CN113842171A (en
Inventor
贾硕
吴楠
安娜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Qingzhi Turing Technology Co ltd
Original Assignee
Beijing Qingzhi Turing Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Qingzhi Turing Technology Co ltd filed Critical Beijing Qingzhi Turing Technology Co ltd
Priority to CN202111147190.6A priority Critical patent/CN113842171B/en
Publication of CN113842171A publication Critical patent/CN113842171A/en
Application granted granted Critical
Publication of CN113842171B publication Critical patent/CN113842171B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B10/00Other 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
    • A61B10/0045Devices for taking samples of body liquids
    • A61B10/0051Devices for taking samples of body liquids for taking saliva or sputum samples
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/30Surgical robots
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/70Manipulators specially adapted for use in surgery
    • A61B34/76Manipulators having means for providing feel, e.g. force or tactile feedback
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Surgery (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Robotics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Pulmonology (AREA)
  • Hematology (AREA)
  • Pathology (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention discloses a validity judging device for throat swab machine sampling, which comprises: the visual identification camera is used for realizing the identification of detected personnel based on the multi-task neural network and comparing the visual identification camera with the identification card information identified by the radio frequency device, so as to ensure that a sampler is positioned in front of the machine and is the person; the head support is internally provided with a sensor for detecting whether the head is always fixed in the sampling process in real time; the clencher is designed by a parabolic hyperboloid and is used for exposing the pharyngeal rear wall of a sampler, and a tongue depressor is also arranged to avoid tongue movement in the sampling process; the sampling mechanism is provided with a force sensor and is used for detecting force data at the rear end of the swab in real time and preventing the insufficient quantity of sampled cells; and the industrial personal computer is used for taking charge of flow control and judging the effectiveness of sampling. The invention identifies the detected personnel based on the multi-task neural network and compares the detected personnel with the identification card information identified by the radio frequency device, thereby effectively preventing the risk of impersonation sampling.

Description

Validity judging device for throat swab machine sampling
Technical Field
The invention relates to the fields of medical detection, throat swab sampling, medical robots and the like, provides technology and information support for the robots to efficiently and conveniently finish throat swab sampling tasks, and particularly relates to a validity judging device for throat swab machine sampling.
Background
Oropharyngeal swabs are a method of collecting clinical test samples of nasal secretions from the throat, and analyzing the sampled samples to determine the presence of clinical markers of organisms or other diseases. Oropharyngeal swab sampling is a relatively simple detection method compared to nasopharyngeal swab sampling. However, in the face of new or sudden epidemic situations of infectious diseases such as COVID-19 and SARS, the oropharyngeal swab sampling has a huge cross infection risk at the same time, so that a huge pressure is brought to the psychology and physiology of medical staff, and a robot mode is an important trend to replace manual sampling.
Unlike manual sampling, the effectiveness of pharyngeal swab machine sampling is difficult to determine.
Disclosure of Invention
The invention provides a validity judging device for throat swab machine sampling, which is used for identifying detected personnel based on a multi-task neural network and comparing the detected personnel with identity card information identified by a radio frequency device, so that risk of impersonation sampling is effectively prevented, and the device is described in detail below: a effectiveness decision device for pharyngeal swab machine sampling, the device comprising:
the visual identification camera is used for realizing the identification of detected personnel based on the multi-task neural network and comparing the visual identification camera with the identification card information identified by the radio frequency device, so as to ensure that a sampler is positioned in front of the machine and is the person;
the head support is internally provided with a sensor for detecting whether the head is always fixed in the sampling process in real time; the clencher is designed by a parabolic hyperboloid and is used for exposing the pharyngeal rear wall of a sampler, and a tongue depressor is also arranged to avoid tongue movement in the sampling process;
the sampling mechanism is provided with a force sensor and is used for detecting force data at the rear end of the swab in real time and preventing the insufficient quantity of sampled cells;
and the industrial personal computer is used for taking charge of flow control and judging the effectiveness of sampling.
Wherein, the industrial personal computer includes:
the sampling module is used for sampling identity information of the tested person by using the radio frequency information sampler;
the first judging module is used for judging whether the identity information is effective or not, and if so, executing the second judging module;
the second judging module is used for judging whether the identified face and the identity information are the same person, and if so, executing a third judging module;
the third judging module is used for checking whether the tested person wears the mouthpiece correctly, and if so, executing the fourth judging module;
a fourth judging module for checking whether the head of the tested person is placed on the head rest to compress the sensor, if yes, executing a fifth judging module;
a fifth judging module, configured to obtain force feedback data, judge whether the sampling mechanism moves out of the threshold distance, and if so, execute a sixth judging module;
and the sixth judging module is used for judging whether the sampling mechanism collects effective force feedback data or not by rotating and sampling when the tail end of the swab reaches the back pharyngeal wall, and if so, the sampling is effective.
In one embodiment, the visual recognition camera is based on a multi-tasking neural network comprising: a face region suggestion network, an optimization network and an output network which are sequentially cascaded;
the face region suggestion network generates a candidate window which is used for carrying out preliminary face region selection on the video image processed by the pyramid to generate candidate frames of a plurality of faces and suspected faces;
the optimization network comprises a full connection layer and is used for screening candidate frames through face frame regression and face key point positioning;
and the output network is used for outputting the final face area.
In one embodiment, the head rest comprises: the head support bracket is provided with a column groove and a rectangular groove,
the cylindrical groove is internally provided with a spring, the rectangular groove is internally provided with a micro switch, and the micro switch is connected with a power line through a first hole site on the head support bracket;
the power line is connected with the aviation plug, a chin pad is arranged on the micro switch, and the chin pad is connected with the spring through a second hole site; the top of the head support bracket is also provided with a forehead support.
In one embodiment, the parabolic hyperboloid design of the mouthpiece comprises: a tooth position positioning module, a hyperboloid oral cavity supporting module and a tongue pressing module,
the upper part and the lower part of the hyperboloid oral cavity supporting module are respectively provided with a tooth position positioning module, and the lower part of the hyperboloid oral cavity supporting module is connected with the tongue pressing module; the tooth position positioning module, the hyperboloid oral cavity supporting module and the tongue pressing module are integrally formed.
In one embodiment, the sampling mechanism with force sensor comprises: a bottom bracket, a bottom bracket and a bottom bracket,
the top of the bottom bracket is provided with a rotary steering engine, and the rotary steering engine is used for fixing the force sensor through a flange; the flange is connected with the rear part of the bearing frame, and a linear bearing is arranged at the front part of the bearing frame;
the linear bearing is connected with the bottom of the micro-switch bracket in a positioning way and is used for triggering the force sensor, and the front part of the micro-switch bracket is used for fixing the micro-switch;
the front part of the micro-switch bracket is fixedly connected with the swab bracket, and the upper part of the swab bracket is embedded with a spring piece for fixing the pharyngeal swab.
The technical scheme provided by the invention has the beneficial effects that:
1. the invention designs a throat swab machine sampling effectiveness judging device which consists of a camera, a force sensing head support, a mouth gag and a force sensing sampling mechanism, and the effectiveness condition of single sampling can be effectively judged by ensuring that sampling personnel are in effective positions and the necessary strength of the sampling action is fully exposed in a sampling area (the back wall of the pharynx);
2. the invention utilizes the visual technology, completes the identification of the detected personnel based on the multi-task neural network, and compares the identification card information identified by the radio frequency device, ensures that the sampler is positioned in front of the machine and is the person, and effectively prevents the risk of impersonation sampling;
3. the invention designs the head rest with the pressure sensor, and the built-in sensor can detect whether the head is always placed on the head rest in the sampling process in real time, and the upper part and the lower part of the head rest are dislocated at a small angle, so that the head of a sampling person is slightly inclined backwards, and the sampling person is ensured to be in a correct position;
4. the invention designs the parabolic hyperboloid mouth gag, after being correctly worn, the pharyngeal rear wall of a sampler can be fully exposed, and the tongue depressor can effectively avoid the interference of tongue movement in the sampling process and avoid the false judgment of effectiveness;
5. the sampling mechanism with the force sensor, which is designed by the invention, can detect the force data at the rear end of the swab in real time, avoid the insufficiency of sampled upper wall cells, and judge the effectiveness only by feeding back the rational information after the screw rod moves within a certain range.
Drawings
FIG. 1 is a schematic diagram of the operation of a device for determining the effectiveness of a pharyngeal swab machine sampling;
FIG. 2 is a schematic diagram showing the determination of the validity of a sample;
FIG. 3 is another schematic diagram of a device for determining the effectiveness of a pharyngeal swab machine sampling;
FIG. 4 is a schematic diagram of a structure of face detection for a multi-tasking neural network;
FIG. 5 is a flow chart of a multitasking network;
FIG. 6 is a schematic diagram of a head rest structure incorporating a pressure sensor;
FIG. 7 is a front view of a head rest structure incorporating a pressure sensor;
FIG. 8 is a three-dimensional schematic of a mouthpiece;
FIG. 9 is a schematic dimensional view of a mouthpiece;
FIG. 10 is another dimensional schematic of the mouthpiece;
FIG. 11 is a schematic diagram of a sampling mechanism with a force sensor;
fig. 12 is a schematic view of a rotary steering engine.
In the drawings, the list of components represented by the various numbers is as follows:
1: visual recognition camera; 2: a head rest;
3: a mouthpiece; 4: a sampling mechanism;
5: and the industrial personal computer 6: a processor;
7: memory 8: a bus;
9: head support 10: a spring;
11: a micro-switch; 12: a chin pad;
13: power cord 14: aviation plug
15: a forehead support; 16: rectangular grooves;
17: a cylindrical groove; 18: a tooth position positioning module;
19: a hyperboloid oral support module; 20: a hyperboloid oral support module;
21: the width of the outline; 22: inner profile width;
23: the length of the tongue pressing module; 24: the length of the inner arc;
25: the width of the tongue pressing module; 26: a pharyngeal swab;
27: a spring piece; 28: a swab holder;
29: a micro-switch; 30: a microswitch bracket;
31: a bearing bracket; 32: a linear bearing;
33: a flange; 34: a force sensor;
35: rotating a steering engine; 36: a bottom bracket.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in further detail below.
Example 1
The embodiment of the invention provides a validity judging device for throat swab machine sampling, which adopts a camera to accurately compare the identity of a person to be sampled, adopts a force sensing head support for acquiring a correct sampling position, adopts a parabolic hyperboloid mouthpiece to fully expose the back pharyngeal wall, and adopts a force sensing sampling mechanism for ensuring the valid sampling force. The validity judging device for the throat swab machine sampling designed by the embodiment of the invention can comprehensively judge the validity of the machine throat swab sampling, and provides technical and information support for the robot to efficiently and conveniently finish the throat swab sampling task.
1. Overall design of validity judging device for throat swab machine sampling
The problem is effectively determined in the sampling of a robotic pharyngeal swab, see figure 1,
the throat swab machine sampling effectiveness judging device designed by the embodiment of the invention comprises the following five parts: the device comprises a visual recognition camera 1, a head rest 2 with a pressure sensor, a seaming device 3 with a parabolic hyperboloid design, a sampling mechanism 4 with a force sensor and an industrial personal computer 5.
The visual recognition camera 1 is used for completing recognition of detected personnel based on a multi-task neural network and comparing the recognition result with the identification card information recognized by the radio frequency device, so that a sampler is ensured to be positioned in front of the machine and is the person, and the risk of impersonation sampling is effectively prevented; the head rest 2 containing the pressure sensor is internally provided with the sensor, so that whether the head is always placed on the head rest 2 in the sampling process or not can be detected in real time, and the upper part and the lower part of the head rest 2 are dislocated at a small angle, so that the head of a person is slightly inclined backwards, and the person for sampling is positioned at a correct position; the mouth piece 3 with the parabolic hyperboloid design can fully expose the pharyngeal rear wall of a sampler after being correctly worn, and the tongue depressor can effectively avoid tongue movement interference in the placing and sampling process and reduce effectiveness misjudgment. The sampling mechanism 4 with the force sensor can detect the force data at the rear end of the swab in real time, ensure necessary force and effectively prevent the insufficient quantity of sampled cells; the industrial personal computer 5 is responsible for flow control, determination of sampling effectiveness, and the working flow of the whole device is shown in fig. 2.
The sampling effectiveness determination flow is as follows:
step 1), starting a sampling flow;
step 2) sampling identity information of a tested person by using a radio frequency information sampler, wherein effective identity information is not acquired, sampling is invalid, and the step 2) is re-executed; acquiring effective identity information, effectively sampling, and executing the step 3);
the effective information is the information such as the name, age, birth year and month, photo, etc. of the tested person. The above-mentioned rf information sampler is used for obtaining information of a user, and this component is well known to those skilled in the art, and the embodiments of the present invention will not be described in detail.
Step 3) the visual recognition camera 1 is matched with an image recognition algorithm to judge whether the recognized face is the same person as the identity information acquired in the step 2), if not, sampling is invalid, and the step 2) is executed; if the same person is available, executing step 4);
step 4) the staff checking whether the testee wears the mouthpiece 3 correctly, so that the testee fully exposes the back wall of the pharynx, the mouthpiece 3 is not worn correctly, sampling is invalid, and the step 4) is re-executed; if the mouthpiece is worn correctly, the sampling is effective, and the step 5) is executed;
step 5), the staff checks whether the head of the tested person is placed on the head rest 2 to compress the sensor, if the head of the tested person is not compressed with the sensor, sampling is invalid, and the step 5) is executed again; if the head of the tested person compresses the sensor, sampling is effective, and executing the step 6);
step 6) after the industrial personal computer 5 obtains the force feedback data, it is determined whether the sampling mechanism 4 moves out a certain reasonable distance (for example: 15cm-20 cm), if the sampling mechanism 4 does not move to the target position, sampling is invalid, and the step 6) is re-executed; if the sampling mechanism moves a reasonable distance, judging that the sampling is effective, and executing the step 7);
wherein, this step specifically is: after the sampling mechanism 4 drives the throat swab to move to the oral cavity, the obtained force feedback data are valid, and if the throat swab is touched outside the oral cavity, the feedback force data are invalid.
The distance values are set according to the needs in practical applications, and the embodiment of the invention is not limited to this.
Step 7) the tail end of the swab reaches the back pharyngeal wall, and rotary sampling is carried out, if the sampling mechanism 4 does not acquire effective force feedback data (namely, the swab does not reach the back pharyngeal wall), the sampling is invalid, and the step 7) is re-executed; if effective force feedback data (such as 0.5N of pharyngeal swab) is acquired, sampling is effective, and step 8) is executed;
step 8) is continuously judged through the steps, so that the effectiveness of throat swab sampling is ensured.
Wherein, this industrial computer 5 includes:
the sampling module is used for sampling identity information of the tested person by using the radio frequency information sampler;
the first judging module is used for judging whether the identity information is effective or not, and if so, executing the second judging module;
the second judging module is used for judging whether the identified face and the identity information are the same person, and if so, executing the third judging module;
the third judging module is used for checking whether the tested person wears the mouthpiece correctly, and if so, executing the fourth judging module;
a fourth judging module for checking whether the head of the tested person is placed on the head rest 2 to press the sensor, if yes, executing a fifth judging module;
a fifth judging module, configured to obtain force feedback data, judge whether the sampling mechanism 4 moves out of the threshold distance, and if so, execute a sixth judging module;
and a sixth judging module, wherein the tail end of the swab reaches the pharyngeal rear wall and is used for rotary sampling, so as to judge whether the sampling mechanism 4 collects effective force feedback data, and if so, the sampling is effective.
The above-mentioned judging module may be a component capable of executing a judging process, such as a singlechip, a microcontroller, etc., which is not described in detail in the embodiment of the present invention.
In summary, the invention designs a validity judging device for throat swab machine sampling, and aims at the validity judging problem in the throat swab sampling of a robot, and designs a head rest 2 with a pressure sensor, a seaming device 3 with a parabolic hyperboloid design and a sampling mechanism 4 with a force sensor, and the validity judging device for throat swab machine sampling is constructed by integrating a face recognition camera 1. Based on the multitasking neural network, the identification of the detected personnel is completed, and the identification card information identified by the radio frequency device is compared, so that the risk of impersonation sampling is effectively prevented; the head rest 2 with the pressure sensor can ensure that the head of a sampler is positioned at the correct position in front of the robot, so that the error of the sampling position is avoided; the mouth piece 3 with the parabolic hyperboloid design is worn correctly, so that the pharyngeal rear wall of a sampler can be fully exposed, and the interference of the tongue of the oral cavity on sampling is avoided; the sampling mechanism 4 with the force sensor can sense the stress of the sampling swab in real time, ensure necessary force and avoid insufficient pharyngeal wall cells for sampling.
Example 2
An embodiment of the present invention provides a validity determination apparatus for throat swab machine sampling, see fig. 3, the apparatus comprising: a processor 6 and a memory 7, the memory 7 storing program instructions, the processor 6 calling the program instructions stored in the memory 7 to cause the apparatus to perform the steps of:
step 1), starting a sampling flow;
step 2) sampling identity information of a tested person by using a radio frequency information sampler, and if effective identity information is acquired, performing the step 3);
step 3) the visual recognition camera 1 is matched with an image recognition algorithm to judge whether the recognized face and the identity information acquired in the step 2) are the same person, if so, the sampling is effective, and the step 4) is executed;
step 4) the staff checks whether the testee wears the mouthpiece 3 correctly, so that the testee fully exposes the back pharyngeal wall, if the testee wears the mouthpiece correctly, the sampling is effective, and the step 5) is executed;
step 5), the staff checks whether the head of the tested person is placed on the head rest 2 to compress the sensor, if the head of the tested person compresses the sensor, the sampling is effective, and the step 6) is executed;
step 6), after the industrial personal computer 5 obtains the force feedback data, if the sampling mechanism 4 moves a reasonable distance, judging that the sampling is effective, and executing the step 7);
step 7) the swab tip reaches the posterior pharyngeal wall and is rotated for sampling, if valid force feedback data is collected (e.g.: and the throat swab is 0.5N), the sampling is effective, and the effectiveness of the throat swab sampling is ensured.
The execution main bodies of the processor 6 and the memory 7 may be devices with calculation functions, such as a computer, a singlechip, a microcontroller, etc., and in particular implementation, the execution main bodies are not limited, and are selected according to the needs in practical application.
Data signals are transmitted between the memory 7 and the processor 6 via the bus 8, which is not described in detail in the embodiment of the present invention.
In summary, the embodiment of the invention ensures the effectiveness of the throat swab machine sampling through the operation, and meets various requirements in practical application.
Example 3
Based on the same inventive concept, an embodiment of the present invention further provides a computer readable storage medium, where the storage medium includes a stored program, and the apparatus in which the storage medium is controlled to execute the steps in the foregoing embodiment 3 when the program runs.
The computer readable storage medium includes, but is not limited to, flash memory, hard disk, solid state disk, and the like.
It should be noted that the readable storage medium descriptions in the above embodiments correspond to the device descriptions in the embodiments, and the embodiments of the present invention are not described herein.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the invention, in whole or in part.
The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted across a computer-readable storage medium. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc., that contain an integration of one or more available media. The usable medium may be a magnetic medium or a semiconductor medium, or the like.
Example 4
The embodiment of the invention further introduces the visual camera in the embodiment 1, and does not limit other devices, and the details are described below:
the embodiment of the invention designs a visual camera which develops a multi-task network based on a deep learning network to detect and configure a face region, so that the risk of impersonation sampling is avoided. The model keeps the robustness to the light, angle and expression change in the natural environment, the device is suitable for driving-free camera equipment of various UVC (USB Video Class) protocols, and the embodiment of the invention takes a C922pro network camera as an example. The camera is opposite to the face of the tested person, and keeps relatively static operation for 30s within a distance of 1m, so that video shooting is completed.
And developing a multi-task network based on the deep learning network, and simultaneously detecting a face region and key points of the face, so as to keep the robustness to the light, angle and expression change in the natural environment. The model mainly adopts three cascaded networks, such as the workflow of the multitasking network shown in fig. 4 and 5:
1) Performing image pyramid processing;
2) The P-Net (suggested network) network rapidly generates candidate windows;
3) The R-Net (optimized network) network selects candidate windows;
4) The O-Net (output network) network generates a face bounding box and corresponding keypoints.
The P-Net network is a face region suggestion network, and the preliminary face region selection is performed after the pictures are subjected to pyramid processing. And candidate frames of a plurality of faces and suspected faces are quickly generated, so that subsequent image processing is facilitated.
Wherein, the R-Net network is added with a full connection layer, which is more accurate for face selection. The network can delete a large number of wrong input images, and outputs the face images with certain credibility through frame regression and face key point positioning.
The O-Net network has better performance and can accurately identify the face part. And finally outputting the face frame selection area and 5 face key points.
In practical application, the embodiment of the invention selects the multi-task neural network model for face recognition in view of cost, algorithm light weight, face recognition after shielding and portability.
In summary, the vision camera designed by the embodiment of the invention completes the identification of the detected personnel based on the multi-task neural network and is compared with the identification card information identified by the radio frequency device, so that the sampler is ensured to be positioned in front of the machine and is the person, and the risk of impersonation sampling is effectively prevented.
Example 5
The embodiment of the invention further describes the head rest containing the pressure sensor in the embodiment 1, and other devices are not limited, and are described in detail below:
the embodiment of the invention designs a head rest with a pressure sensor, as shown in fig. 6. Aiming at the characteristics of the head and the chin of a human body, the embodiment of the invention combines the ergonomics to design a semi-enclosed head support structure which is more fit with the forehead and the chin. The forehead part and the chin pad all adopt inclined structures, so that a user can keep an inclined angle when using the device, and the device is more convenient for the user to keep the exposed oral cavity and the pharynx, thereby facilitating the effective sampling of the sampling mechanism.
The head support device comprises a head support bracket 9, a chin pad 12, a micro switch 11, a spring 10, a forehead support 15, a power line 13 and an aviation plug 14, wherein the micro switch 11 is in 12 x 6 point contact with the micro switch.
The device can be through restriction and fixed human head, cooperates micro-gap switch 11 to ensure the head laminating, assists the throat swab machine to gather, avoids waiting to gather the people and because psychological fear deviates from correct acquisition position.
In fig. 6, the head rest support 9 can be connected with other devices through screws, the spring 10 is arranged in a cylindrical groove 17 of the head rest support 9, the micro switch 11 is arranged in a rectangular groove 16 of the head rest support 9 and is connected with the power line 13 through a hole site on the head rest support 9, the power line 13 is connected with the aviation plug 14, and a hole site on the chin pad 12 is connected with the spring 10, so that the head rest support 9 is connected into a whole.
The device is from actual beginning, to the characteristics of human head and chin, has designed a half surrounding type head rest structure of laminating forehead and chin more, and forehead support 15 and chin pad 12 all adopt inclined structure for the user can keep the angle of upwards inclining when using, and it is more convenient to keep the exposed of oral cavity and pharyngeal. The columnar structures on the two sides are convenient for a user to hold.
In the embodiment of the invention, the micro switch 11 is added at the chin pad 12, and signals are connected with other devices through the aviation plug 14 so as to confirm whether the head of a user is tightly placed at the chin pad 12 or not, thereby ensuring the head position in the full sampling process to be fixed. When the person to be collected moves backward, leftwards and rightwards due to psychological fear and physiological discomfort, the micro switch 11 is triggered. The damping structure of the spring 10 is arranged below the chin pad 12, so that the spring 10 rebounds when no one is using, the continuity and reliability of the work of the head rest device are ensured, and the comfort level of a user in using is increased. Both the forehead support 15 and the chin pad 12 of the head rest apparatus are designed to be round (i.e., without sharp points), which ensures the safety of the user during collection.
In the actual use process, as shown in fig. 6, the user needs to hold the chin on the chin pad 12 to drive the chin pad 12 to press the spring 10, so that the chin pad 12 contacts and presses the micro switch 11 to make the circuit be connected, and meanwhile, the forehead of the user clings to the forehead support 15, the user holds the columnar structures on both sides of the head support bracket 9 by the hands of the user, so that the head is fixed stably, and the head position of the user is fixed from multiple directions such as up, down, left, right, front, back and the like, thereby providing a hardware support for quick, convenient and accurate development of throat swab machine sampling.
The head rest designed by the embodiment of the invention has a round and moist structure, and can ensure the safety and comfort of a user while fixing the head of the user in the use process of the user. The forehead support 15 and the chin pad 12 of the head support device are both in an inclined structure, and the forehead support 15 is closer to the user 70mm relative to the chin pad 12, so that the user can keep the head slightly raised posture when using the head support device, the throat part of the user can be better exposed, and the subsequent examination is convenient, as shown in fig. 7.
The lower part of the chin pad 12 adopts a spring damping structure, so that the supporting mechanism can rebound in time when no one uses, the continuity and the reliability of the head rest work are ensured, and the comfort level of a user during use is improved. As shown in fig. 7, the micro switch 11 is added at the lower part of the chin pad 12, and the micro switch 11 can be connected with other devices through the aviation plug 14, so that whether the user presses the chin pad 12 or not can be judged by acquiring data of the micro switch 11, and prompt can be timely performed, so that the whole head support device has a better auxiliary effect on throat swab sampling.
In summary, according to the head rest with the pressure sensor, the built-in sensor can detect whether the head is always placed on the head rest in the sampling process in real time, and the upper part and the lower part of the head rest are dislocated at a small angle, so that the head of a sampling person is slightly tilted backwards, and the sampling person is ensured to be in a correct position.
Example 6
The embodiment of the invention further describes the seaming device of the parabolic hyperboloid design in the embodiment 1, and other devices are not limited, and the details are described below:
the embodiment of the invention designs a seaming machine with a parabolic hyperboloid design, as shown in figure 8.
The bite device consists of a tooth position positioning module 18, a hyperboloid oral cavity supporting module 20 and a tongue pressing module 19.
A tooth position positioning module 18 is respectively arranged at the upper part and the lower part of the hyperboloid oral cavity supporting module 20, and the lower part of the hyperboloid oral cavity supporting module 20 is connected with a tongue pressing module 19. The tooth position positioning module 18, the hyperboloid oral cavity supporting module 20 and the tongue pressing module 19 are integrally formed through an injection molding method.
The tooth position positioning module 18 is composed of an upper short plate and a lower short plate (boss), and is mainly used for positioning when the oral cavity supporting device is worn by a person to be collected, and determining the position of teeth biting so that the teeth are closely adhered to the inside of the upper short plate and the lower short plate.
The hyperboloid oral cavity support module 20 is hyperbolic paraboloid, and mainly plays a role of support. Meanwhile, the shape of the oral cavity is more in accordance with the structure of the oral cavity, so that the oral cavity is more in fit with the oral cavity, and the size is proper, so that the comfort is improved.
The tongue pressing module 19 is in the shape of human tongue, is more attached to the tongue when worn, can perfectly press the whole tongue including the tongue root, and ensures that the pharyngeal swab collection is successfully completed.
In fig. 8, the mouthpiece is fixed in position in the mouth of a user through the tooth position positioning module 18 during use, the mouth of the user is supported through the hyperboloid mouth support module 20, so that the collection of throat swabs is facilitated, the tongue root of the user is pressed down through the tongue pressing module 19, and the interference of the tongue on a collection mechanism during collection is avoided.
In practical use, referring to fig. 8, the mouthpiece is used for fixing the tooth position through the tooth position positioning module 18 and the hyperboloid oral cavity supporting module 20, expanding the oral cavity, and reducing the uncomfortable feeling of the user caused by opening the mouth for a long time in the throat swab sampling process. The tongue root is pressed down by the arc tongue-shaped tongue pressing module 19, so that the tongue is fixed, the oral cavity and the throat part are fully exposed, and the throat swab can conveniently sample a sample smoothly.
The comfort of a user is fully considered, and the length of the tongue pressing module 19 is reasonably controlled so that the head of the tongue pressing module 19 does not penetrate into the throat to push against the tonsils for the problem that the tongue pressing module 19 is easy to cause uncomfortable feeling such as nausea and vomiting caused by foreign matters in the oral cavity.
Considering the differentiation and sex of the user, the seaming apparatus according to the embodiment of the present invention obtains three types of large, medium and small sizes by adjusting the width of the tongue pressing module 19 and the length and width of the hyperboloid oral cavity supporting module 20.
Wherein, referring to fig. 9 and 10, the large, medium and small size of the external width 21 of the mouthpiece is 49mm, 47mm, 44mm respectively; the large, medium and small numbers of the inner arc width 22 are 36mm, 31mm and 25mm respectively; the length 23 of the tongue pressing module is 58mm in large size, medium size and small size; the inner arc length 24 of the hyperboloid oral cavity supporting module is 55mm, 50mm and 45mm respectively; the width 25 of the tongue pressing module is 34mm in large and medium sizes and 30mm in small size.
The user may choose the above dimensions according to the size of his own oral cavity and the comfort level of the oral support. The manufacturing material is ABS M30I medical material, so that the sanitation and safety are ensured.
The mouth gag can be used and correctly worn to avoid the mouth closure and tongue interference of a person to be collected due to psychological fear, ensure the sufficient exposure of the pharyngeal rear wall of the person to be sampled, and improve the sampling accuracy and effectiveness of a subsequent sampling mechanism.
In summary, the parabolic hyperboloid mouthpiece is designed, so that the pharyngeal wall of a sampler can be fully exposed after the device is correctly worn, and the tongue movement interference in the sampling process can be effectively avoided through the tongue depressor, so that the effectiveness misjudgment is avoided.
Example 7
The embodiment of the invention further describes the sampling mechanism with the force sensor in the embodiment 1, and other devices are not limited, and the details are described below: embodiments of the present invention contemplate a sampling mechanism that includes a force sensor, as shown in fig. 11 and 12. The sampling mechanism comprises: the throat swab 26, the swab holder 28, the spring piece 27, the micro switch 29, the micro switch bracket 30, the linear bearing 32, the bearing bracket 31, the force sensor 34, the flange 33, the rotary steering engine 35 and the bottom bracket 36. The force sensor 34 is model number SBT760B-5N with a maximum range of 5N. The model of the rotary steering engine 35 is DS3218, and the maximum load is 20kg.
The top of the bottom bracket 36 is provided with a rotary steering engine 35, and the bottom of the bottom bracket 36 is provided with a convenient interface; the rotary steering engine 35 fixes the force sensor 34 through the flange 33; the flange 33 is connected with the rear part of the bearing frame 31, and the front part of the bearing frame 31 is provided with a linear bearing 32; the linear bearing 32 is connected with the bottom of the micro-switch bracket 30 in a positioning way and is used for triggering the force sensor 34, and the front part of the micro-switch bracket 30 is used for fixing the micro-switch 29; the front part of the microswitch bracket 30 is also fixedly connected with a swab bracket 28, and the upper part of the swab bracket 28 is embedded with a spring piece 27 for fixing the pharyngeal swab 26.
The throat swab 26 may be manually or mechanically loaded, and after the limit is reached, the micro-switch 29 on the front of the sampling mechanism may be triggered to ensure successful loading. The spring plate 27 at the front of the sampling mechanism ensures that the pharyngeal swab 26 is pressed tightly, and falling off in the collecting process is avoided. The middle part of the sampling mechanism is provided with a rotary steering engine 35, and when the pharyngeal swab 26 reaches the pharyngeal rear wall, the pharyngeal swab 26 can be driven to perform rotary motion, so that the sampling area is increased. The force sensor 34 is arranged at the rear part of the sampling mechanism, so that the stress at the tail end of the sampling mechanism can be fed back in real time, the excessive or insufficient collecting force is avoided, and the safety and the effectiveness of the collecting process are ensured.
And, the bottom bracket 36 is provided with a convenient interface at the rear, and a power supply, a signal and an alarm interface which are integrated at the rear of the mechanism are convenient to install, convenient to maintain and replace, convenient to integrate with various movement mechanisms (a mechanical arm, a triaxial holder and the like), greatly improves the efficiency and the reliability of sampling of the throat swab machine, and provides hardware support for sampling of the throat swab machine.
Referring to fig. 11 and 12, the rotary steering engine 35 and the rear convenient interface are connected with other devices through screws, the force sensor 34 is installed at the front part of the rotary steering engine 35 through the flange 33, and the micro switch 29 and the force sensor 34 are used, so that whether the throat swab 26 is installed in place or not can be determined, and the acquisition of force sensing data is facilitated.
The throat swab 26 may be manually or mechanically loaded, and after the limit is reached, the front microswitch 29 of the device may be triggered to ensure successful loading. The spring plate 27 at the front of the sampling mechanism ensures that the pharyngeal swab 26 is pressed tightly, and falling off in the collecting process is avoided.
The rotary steering engine 35 is arranged in the middle of the sampling mechanism, and when the sampling mechanism reaches the back pharyngeal wall, the pharyngeal swab 26 can be driven to perform rotary motion, so that extra degrees of freedom are provided for the motion mechanism, a reliable arc line sampling curve is provided, and the sampling area is increased.
The force sensor 34 is arranged at the rear part of the sampling mechanism, so that the stress at the tail end of the sampling mechanism can be fed back in real time, and the defect that the pharyngeal wall tissue is damaged due to overlarge sampling force or the defect that the number of the cells of the sampled sample is insufficient due to overlarge sampling force is avoided, and the safety and the effectiveness of the sampling process are ensured.
In summary, through the sampling mechanism with the force sensor designed by the embodiment of the invention, the loading condition of the throat swab 26 can be automatically detected, the throat swab 26 is driven to complete the rotation motion, the stress condition of the throat swab 26 is detected, and the efficiency and the reliability of the sampling of the throat swab machine are improved from the aspects of loading, tail end motion, force sense control and the like of the throat swab 26.
The embodiment of the invention does not limit the types of other devices except the types of the devices, so long as the devices can complete the functions.
Those skilled in the art will appreciate that the drawings are schematic representations of only one preferred embodiment, and that the above-described embodiment numbers are merely for illustration purposes and do not represent advantages or disadvantages of the embodiments.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.

Claims (5)

1. A effectiveness determining apparatus for machine sampling of pharyngeal swabs, the apparatus comprising:
the visual identification camera is used for realizing the identification of detected personnel based on the multi-task neural network and comparing the visual identification camera with the identification card information identified by the radio frequency device, so as to ensure that a sampler is positioned in front of the machine and is the person;
the head support is internally provided with a sensor for detecting whether the head is always fixed in the sampling process in real time;
the clencher is designed by a parabolic hyperboloid and is used for exposing the pharyngeal rear wall of a sampler, and a tongue depressor is also arranged to avoid tongue movement in the sampling process;
the sampling mechanism is provided with a force sensor and is used for detecting force data at the rear end of the swab in real time and preventing the insufficient quantity of sampled cells;
the industrial personal computer is used for taking charge of flow control and judging the effectiveness of sampling;
the industrial personal computer comprises:
the sampling module is used for sampling identity information of the tested person by using the radio frequency information sampler;
the first judging module is used for judging whether the identity information is effective or not, and if so, executing the second judging module;
the second judging module is used for judging whether the identified face and the identity information are the same person, and if so, executing a third judging module;
the third judging module is used for checking whether the tested person wears the mouthpiece correctly, and if so, executing the fourth judging module;
a fourth judging module for checking whether the head of the tested person is placed on the head rest to compress the sensor, if yes, executing a fifth judging module;
a fifth judging module, configured to obtain force feedback data, judge whether the sampling mechanism moves out of the threshold distance, and if so, execute a sixth judging module;
a sixth judging module, wherein the tail end of the swab reaches the pharyngeal wall and carries out rotary sampling, and the sixth judging module is used for judging whether the sampling mechanism collects effective force feedback data or not, and if so, the sampling is effective;
the visual recognition camera is based on a multi-task neural network comprising: a face region suggestion network, an optimization network and an output network which are sequentially cascaded;
the face region suggestion network generates a candidate window which is used for carrying out preliminary face region selection on the video image processed by the pyramid to generate candidate frames of a plurality of faces and suspected faces;
the optimization network comprises a full connection layer and is used for screening candidate frames through face frame regression and face key point positioning;
the output network is used for outputting a final face area;
the head rest includes: the head support bracket is provided with a column groove and a rectangular groove,
the cylindrical groove is internally provided with a spring, the rectangular groove is internally provided with a micro switch, and the micro switch is connected with a power line through a first hole site on the head support bracket;
the power line is connected with the aviation plug, a chin pad is arranged on the micro switch, and the chin pad is connected with the spring through a second hole site; the top of the head support bracket is also provided with a forehead support;
the forehead support and the chin pad are both round and moist structures;
the seaming apparatus of the parabolic hyperboloid design comprises: a tooth position positioning module, a hyperboloid oral cavity supporting module and a tongue pressing module,
the upper part and the lower part of the hyperboloid oral cavity supporting module are respectively provided with a tooth position positioning module, and the lower part of the hyperboloid oral cavity supporting module is connected with the tongue pressing module; the tooth position positioning module, the hyperboloid oral cavity supporting module and the tongue pressing module are integrally formed.
2. The effectiveness judgment device for throat swab machine sampling of claim 1, wherein said tooth position positioning module is composed of an upper and a lower short plates, said short plates being boss-shaped.
3. The effectiveness judgment device for throat swab machine sampling of claim 1, wherein the hyperbolic oral support module is a hyperbolic paraboloid structure and the tongue depressor module is a human tongue shape.
4. A effectiveness determination apparatus for throat swab machine sampling of claim 1, wherein said sampling mechanism with force sensor comprises: a bottom bracket, a bottom bracket and a bottom bracket,
the top of the bottom bracket is provided with a rotary steering engine, and the rotary steering engine is used for fixing the force sensor through a flange; the flange is connected with the rear part of the bearing frame, and a linear bearing is arranged at the front part of the bearing frame;
the linear bearing is connected with the bottom of the micro-switch bracket in a positioning way and is used for triggering the force sensor, and the front part of the micro-switch bracket is used for fixing the micro-switch;
the front part of the micro-switch bracket is fixedly connected with the swab bracket, and the upper part of the swab bracket is embedded with a spring piece for fixing the pharyngeal swab.
5. The device of claim 4, wherein the bottom of the bottom bracket is provided with a convenient interface.
CN202111147190.6A 2021-09-29 2021-09-29 Validity judging device for throat swab machine sampling Active CN113842171B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111147190.6A CN113842171B (en) 2021-09-29 2021-09-29 Validity judging device for throat swab machine sampling

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111147190.6A CN113842171B (en) 2021-09-29 2021-09-29 Validity judging device for throat swab machine sampling

Publications (2)

Publication Number Publication Date
CN113842171A CN113842171A (en) 2021-12-28
CN113842171B true CN113842171B (en) 2024-03-01

Family

ID=78976829

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111147190.6A Active CN113842171B (en) 2021-09-29 2021-09-29 Validity judging device for throat swab machine sampling

Country Status (1)

Country Link
CN (1) CN113842171B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114916964B (en) * 2022-07-14 2022-11-04 河南科技学院 Pharynx swab sampling effectiveness detection method and self-service pharynx swab sampling method
CN115337044B (en) * 2022-07-18 2023-06-09 深圳市安保数字感控科技有限公司 Nucleic acid sampling monitoring method, device, system and computer readable storage medium
CN116188748B (en) * 2023-04-27 2023-08-15 深圳市辉诚实业有限公司 Image recognition system based on intelligent throat swab sampling equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108377398A (en) * 2018-04-23 2018-08-07 太平洋未来科技(深圳)有限公司 Based on infrared AR imaging methods, system and electronic equipment
CN111631754A (en) * 2020-05-26 2020-09-08 清华大学 Automatic sampling system of pharynx swab
CN111820952A (en) * 2020-07-17 2020-10-27 清华大学 Portable pharynx swab sampling robot
CN112381075A (en) * 2021-01-18 2021-02-19 北京蒙帕信创科技有限公司 Method and system for carrying out face recognition under specific scene of machine room
CN113133787A (en) * 2021-03-17 2021-07-20 北京航空航天大学 Robot-machine cooperative interaction control method and system for nasopharynx swab sampling robot

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108377398A (en) * 2018-04-23 2018-08-07 太平洋未来科技(深圳)有限公司 Based on infrared AR imaging methods, system and electronic equipment
CN111631754A (en) * 2020-05-26 2020-09-08 清华大学 Automatic sampling system of pharynx swab
CN111820952A (en) * 2020-07-17 2020-10-27 清华大学 Portable pharynx swab sampling robot
CN112381075A (en) * 2021-01-18 2021-02-19 北京蒙帕信创科技有限公司 Method and system for carrying out face recognition under specific scene of machine room
CN113133787A (en) * 2021-03-17 2021-07-20 北京航空航天大学 Robot-machine cooperative interaction control method and system for nasopharynx swab sampling robot

Also Published As

Publication number Publication date
CN113842171A (en) 2021-12-28

Similar Documents

Publication Publication Date Title
CN113842171B (en) Validity judging device for throat swab machine sampling
US10813568B2 (en) System and method for classifier-based atrial fibrillation detection with the aid of a digital computer
TWI322680B (en) An ear-type blood-pressure meter and a method of processing in the ear-type blood-pressure meter
CN108882850B (en) Medical diagnostic apparatus, system and method of use
JP7024000B2 (en) Approach to measure capillary refill time
WO2013089072A1 (en) Information management device, information management method, information management system, stethoscope, information management program, measurement system, control program and recording medium
CN112804941A (en) Apparatus and method for detecting physiological events
US11948690B2 (en) Pulmonary function estimation
WO2017165761A1 (en) Methods and systems for collecting spirometry data
CN104146684B (en) The dizzy detector of a kind of eyeshield formula
US20220005601A1 (en) Diagnostic device for remote consultations and telemedicine
EP3488771B1 (en) System and method for machine-learning-based atrial fibrillation detection
TW202221621A (en) Virtual environment training system for nursing education
Oresko Portable heart attack warning system by monitoring the ST segment via smartphone electrocardiogram processing
WO2020237571A1 (en) Medical procedure recording method, medical device, and storage medium
CN201308477Y (en) Facial expression pressing pain analyzer
CN107349073B (en) Clinical nursing method, device, equipment and storage medium
CN108201443B (en) Laser blood sampling instrument
CN212546889U (en) Medical oral cavity detection device
TWI463428B (en) Automatic moving health-care device
US20120283602A1 (en) Wireless electronic pegboard setup for quantification of dexterity
JP2008167866A (en) Diagnostic robot, and control method and control program of diagnostic robot
US20130131532A1 (en) Medical Diagonstic System
TW201132334A (en) A mimic Chinese medicine pulse diagnosis system combining capacitive pressure sensing unit
Yanti et al. Application for COVID-19 severity diagnosis and asynchronous telehealth: development and prototype of G-COV

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