A throat swab collection method, device, computer device and storage medium

Abstract

The present invention discloses a throat swab collection method, device, computer device and storage medium, which relates to the field of artificial intelligence. The method includes: obtaining tactile data collected by a sensor; judging whether the cotton swab contacts the user according to the tactile data, wherein the cotton swab is fixedly clamped by a clamping device with a sensor; if so, collecting image data of the user's oral cavity; judging whether the cotton swab contacts an effective part of the user's oral cavity according to the image data; if so, judging whether an effective throat swab collection is performed according to the tactile data and the image data; if so, determining that the collection is completed. The throat swab collection is completed by fixing the cotton swab and having the user actively touch the cotton swab. At the same time, the reliability of the collection can be ensured through the tactile data and the image data. Compared with the traditional manual collection method, it only requires the user himself / herself to complete, without the need to equip medical staff, and the labor cost is extremely low. At the same time, the collection quality is also higher.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular, to a throat swab collection method, device, computer device, and storage medium. Background Art

[0002] Throat swab collection is an important means for detecting respiratory infectious diseases. Currently, throat swabs are mainly collected by medical staff. The manual collection method, on the one hand, requires a large amount of labor cost, and on the other hand, it is very easy to produce deviations by observing the collection position with the naked eye of medical staff, so the quality of throat swab collection is difficult to be guaranteed. Summary of the Invention

[0003] Embodiments of the present invention provide a throat swab collection method, device, computer device, and storage medium, aiming to solve the problems of high labor cost and difficult-to-guarantee collection quality existing in manual collection of throat swabs.

[0004] In a first aspect, an embodiment of the present invention provides a throat swab collection method, which includes:

[0005] Obtain tactile data collected by a sensor;

[0006] Judge whether the cotton swab contacts the user according to the tactile data, wherein the cotton swab is fixedly clamped by a clamping device having the sensor;

[0007] If the cotton swab contacts the user, collect image data of the interior of the user's mouth;

[0008] Judge whether the cotton swab contacts an effective part inside the user's mouth according to the image data;

[0009] If the cotton swab contacts an effective part inside the user's mouth, judge whether an effective throat swab collection is performed according to the tactile data and the image data;

[0010] If an effective throat swab collection is performed by the cotton swab, determine that the collection is completed.

[0011] In a second aspect, an embodiment of the present invention further provides a throat swab collection device, which includes units for executing the above method.

[0012] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, and a computer program is stored on the memory, and when the processor executes the computer program, the above method is implemented.

[0013] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, and the storage medium stores a computer program, and when the computer program is executed by a processor, the above method can be implemented.

[0014] The technical solution of the present invention completes the collection of throat swabs by fixing the cotton swab and allowing the user to actively touch the cotton swab. At the same time, the reliability of the collection can be ensured by tactile data and image data. Compared with the traditional manual collection method, it can be completed by the user alone without the need for medical staff, the labor cost is extremely low, and the quality of the collection is also higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0016] Figure 1 A schematic diagram of an application scenario of a throat swab collection method provided by an embodiment of the present invention;

[0017] Figure 2 A schematic diagram of a cotton swab clamping method for a throat swab collection method provided by an embodiment of the present invention;

[0018] Figure 3 A schematic diagram of a throat swab collection method provided in an embodiment of the present invention;

[0019] Figure 4 A schematic diagram of the output results of a target detection model for a throat swab collection method provided in an embodiment of the present invention;

[0020] Figure 5 A schematic block diagram of a throat swab collection device provided in an embodiment of the present invention;

[0021] Figure 6 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0024] It should also be understood that the terms used in this specification of the present invention are merely for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in this specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0025] It should be further understood that the term "and / or" used in this specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0026] As used in this specification and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" depending on the context.

[0027] Please refer to Figure 1-2 , in the embodiment of the present invention, the clamping device 4 fixedly clamps the cotton swab 5, so that the cotton swab 5 is fixed and immovable. The clamping device 4 has a sensor 2. For example, the sensor 2 can be arranged inside the clamping device 4, so that the sensor 2 can directly contact the cotton swab 5, improving the accuracy of measurement. The sensor 2 is used to collect the tactile data of the cotton swab 5. Specifically, the sensor 2 can include a force sensor and a deformation sensor. Correspondingly, the tactile data correspondingly includes contact force data and deformation data. The sensor 2 is connected to the terminal 1 and sends the collected tactile data to the terminal 1. The terminal 1 can be, for example, a computer device. At the same time, a camera 3 is also equipped, and the camera 3 is connected to the terminal 1. The camera 3 is used to collect photos of the user's oral cavity. The pharyngeal swab collection method provided by the embodiment of the present invention is applied to the terminal 1.

[0028] Figure 3 is a schematic flowchart of the pharyngeal swab collection method provided by the embodiment of the present invention. As Figure 3 shown, the method includes the following steps S1 - S6.

[0029] S1, obtain the tactile data collected by the sensor.

[0030] In specific implementation, tactile data collected by a sensor is obtained in real time. The sensor may include a force sensor and a deformation sensor. Correspondingly, the tactile data correspondingly includes contact force data and deformation data.

[0031] S2. Determine whether the cotton swab is in contact with the user according to the tactile data, wherein the cotton swab is fixedly clamped by a clamping device having the sensor.

[0032] In specific implementation, it is determined whether the cotton swab is in contact with the user according to the tactile data. In the embodiment of the present invention, the cotton swab is fixedly clamped by a clamping device having the sensor, and the cotton swab remains stationary during the acquisition process. The user opens the mouth and approaches the cotton swab so that the cotton swab contacts an effective part in the user's oral cavity. The effective part is, for example, parts such as the tonsils and the soft palate.

[0033] When the cotton swab is not in contact with the user, the tactile data will remain unchanged. When the cotton swab is in contact with the user, the tactile data will change. Therefore, it can be determined whether the cotton swab is in contact with the user by monitoring the change of the tactile data.

[0034] In one embodiment, the sensor includes a deformation sensor, the tactile data includes deformation data, and the above step S2 includes the following steps: S21 - S23.

[0035] S21. Obtain deformation data features according to the deformation data, and obtain a first difference between the deformation data features and preset reference deformation data features.

[0036] In specific implementation, when the clamping device clamps and fixes the cotton swab, reference deformation data is collected by the deformation sensor. Reference deformation data features are obtained according to the reference deformation data. If the cotton swab is not in contact with the user, the deformation data features are equal to the reference deformation data features. If the cotton swab is in contact with the user, the user will apply a force to the cotton swab. At this time, the deformation data will fluctuate, so that there is a deviation between the deformation data features and the reference deformation data features. It can be understood that both the deformation data features and the reference deformation data features can be represented by vectors, and the first difference refers to the absolute value of the difference between the deformation data features and the reference deformation data features.

[0037] For example, in one embodiment, the deformation sensor includes multiple acquisition points, and the deformation data includes the coordinates and deformation amounts of each acquisition point. Through the position coordinates of the deformed acquisition points, a straight-line equation can be fitted. At this time, the deformation data features are specifically the slope and intercept of the straight-line equation.

[0038] Or, in some other embodiments, the deformation data is input into a neural network model, and the neural network model calculates the deformation data features.

[0039] S22, determine whether the first difference is greater than a preset first threshold value.

[0040] In specific implementation, the first threshold value can be set by those skilled in the art, and the present invention does not specifically limit it.

[0041] S23, if the first difference is greater than the preset first threshold value, determine that the cotton swab has come into contact with the user.

[0042] In specific implementation, if the first difference is greater than the preset first threshold value, determine that the cotton swab has come into contact with the user.

[0043] Further, if the first difference is not greater than the preset first threshold value, determine that the cotton swab has not come into contact with the user.

[0044] In one embodiment, the sensor includes a force sensor, the tactile data includes contact force data, and the above step S2 includes the following steps: S210 - S230.

[0045] S210, obtain the contact force data feature according to the contact force data, and obtain the second difference between the contact force data feature and the preset reference contact force data feature.

[0046] In specific implementation, when the clamping device clamps and fixes the cotton swab, the reference contact force data is collected by the force sensor. The reference contact force data feature is obtained according to the reference contact force data. If the cotton swab does not contact the user, the contact force data feature is equal to the reference contact force data feature. If the cotton swab contacts the user, the user will apply a force to the cotton swab. At this time, the contact force data will fluctuate, so that there is a deviation between the contact force data feature and the reference contact force data feature. It can be understood that both the contact force data feature and the reference contact force data feature can be represented by vectors, and the second difference refers to the absolute value of the difference between the contact force data feature and the reference contact force data feature.

[0047] For example, in one embodiment, the force sensor includes multiple acquisition points, and the contact force data includes the coordinates and contact force of each acquisition point. The pressure, tension, shear force, bending moment, and torque received by the cotton swab are calculated according to the coordinates and contact force of each acquisition point. At this time, the contact force data feature is the pressure, tension, shear force, bending moment, and torque received by the cotton swab.

[0048] Or, in some other embodiments, by inputting the contact force data into a neural network model, the contact force data feature is calculated by the neural network model.

[0049] S220, determine whether the second difference is greater than a preset second threshold value.

[0050] In specific implementation, the second threshold can be set by those skilled in the art, and the present invention does not specifically limit it.

[0051] S230, if the second difference is greater than a preset second threshold, it is determined that the cotton swab is in contact with the user.

[0052] In specific implementation, if the second difference is greater than a preset second threshold, it is determined that the cotton swab is in contact with the user.

[0053] Further, if the second difference is not greater than a preset second threshold, it is determined that the cotton swab is not in contact with the user.

[0054] In one embodiment, in order to improve the accuracy, the sensor includes a force sensor and a deformation sensor, and the tactile data includes deformation data and contact force data. The above step S2 includes the following steps: S201 - S204.

[0055] S201, obtain the deformation data feature according to the deformation data, and obtain the first difference between the deformation data feature and a preset reference deformation data feature.

[0056] In specific implementation, the implementation manner of step S201 is similar to that of step S21, and will not be elaborated here.

[0057] S202, obtain the contact force data feature according to the contact force data, and obtain the second difference between the contact force data feature and a preset reference contact force data feature.

[0058] In specific implementation, the implementation manner of step S202 is similar to that of step S210, and will not be elaborated here.

[0059] S203, determine whether it simultaneously satisfies that the first difference is greater than a preset first threshold and the second difference is greater than a preset second threshold.

[0060] In specific implementation, both the first threshold and the second threshold can be set by those skilled in the art, and the present invention does not specifically limit them.

[0061] S204, if the first difference is greater than a preset first threshold and the second difference is greater than a preset second threshold, it is determined that the cotton swab is in contact with the user.

[0062] In the embodiment of the present invention, if the first difference is greater than a preset first threshold and the second difference is greater than a preset second threshold, it is determined that the cotton swab is in contact with the user, thereby being able to avoid misjudgment caused by measurement errors brought by a single sensor.

[0063] Further, if it does not simultaneously satisfy that the first difference is greater than a preset first threshold and the second difference is greater than a preset second threshold, it is determined that the cotton swab is not in contact with the user.

[0064] S3. If the cotton swab comes into contact with the user, collect the image data of the user's oral cavity interior.

[0065] In specific implementation, if the cotton swab comes into contact with the user, collect the image data of the user's oral cavity interior. For example, collect the image data of the user's oral cavity interior through a camera. To improve the imaging quality, the user's oral cavity interior can be irradiated by a fill light.

[0066] Further, if the cotton swab does not come into contact with the user, return to step S1. Meanwhile, the user can be prompted to continue the collection.

[0067] S4. Determine whether the cotton swab touches an effective part of the user's oral cavity interior according to the image data.

[0068] In specific implementation, determine whether the cotton swab touches an effective part of the user's oral cavity interior according to the image data. The effective parts are, for example, the tonsils and the soft palate and other parts.

[0069] In one embodiment, step S4 above specifically includes the following steps: S41 - S43.

[0070] S41. Identify the image data according to a pre-trained object detection model to obtain a first regression box of the cotton swab and a second regression box of the effective part.

[0071] In specific implementation, the object detection model is pre-trained in advance so that the object detection model has the ability to identify the cotton swab and the effective part. In this embodiment, the YOLOX model is specifically selected for the object detection model. Those skilled in the art can also adopt other types of object detection models, and the present invention does not make specific limitations thereto.

[0072] By inputting the image data into the pre-trained object detection model, the object detection model identifies the image data to obtain the first position information and the first recognition probability of the cotton swab and the second position information and the second recognition probability of the effective part. The first position information includes the geometric position and size of the first regression box, and the first regression box is used to frame the position of the cotton swab. The second position information includes the geometric position and size of the second regression box, and the second regression box is used to frame the position of the effective part.

[0073] For example, referring to Figure 4 , after inputting the image into the pre-trained object detection model, the object detection model marks the first regression box 100 and the second regression box 200 in the image.

[0074] S42. Determine whether the first regression box is located within the second regression box.

[0075] S43. If the first regression box is located within the second regression box, it is determined that the cotton swab has contacted an effective part inside the user's oral cavity.

[0076] In specific implementation, if the first regression box is located within the second regression box, it is determined that the cotton swab has contacted an effective part inside the user's oral cavity.

[0077] Further, if the first regression box is not located within the second regression box, it is determined that the cotton swab has not contacted an effective part inside the user's oral cavity.

[0078] S5. If the cotton swab has contacted an effective part inside the user's oral cavity, determine whether an effective throat swab collection has been performed based on the tactile data and the image data.

[0079] In specific implementation, to improve the quality of throat swab collection, in the embodiments of the present invention, after the cotton swab has contacted an effective part inside the user's oral cavity, further determine whether an effective throat swab collection has been performed based on the tactile data and the image data, so as to ensure the quality of throat swab collection.

[0080] Further, if the cotton swab has not contacted an effective part inside the user's oral cavity, return to step S1. Meanwhile, the user can be prompted to continue the collection.

[0081] In one embodiment, step S5 above specifically includes the following steps: S51 - S53.

[0082] S51. Identify the image data according to a pre-trained object detection model to obtain the first recognition probability and first position information of the cotton swab and the second recognition probability and second position information of the effective part.

[0083] In specific implementation, similar to step S41 above, by inputting the image data into a pre-trained object detection model, the object detection model identifies the image data to obtain the first position information and first recognition probability of the cotton swab and the second position information and second recognition probability of the effective part. The first position information includes the geometric position and size of the first regression box, and the first regression box is used to frame the position of the cotton swab. The second position information includes the geometric position and size of the second regression box, and the second regression box is used to frame the position of the effective part.

[0084] It can be understood that step S41 and step S51 can be the same step.

[0085] S52. Determine whether the first recognition probability, the first position information, the second recognition probability, the second position information, and the tactile data satisfy a pre-trained feature pattern.

[0086] In specific implementation, a large number of sample data of throat swabs are effectively collected in advance (the sample data includes the first recognition probability, the first position information, the second recognition probability, the second position information, and tactile data), and a feature pattern is obtained after training and learning.

[0087] Judge whether the first recognition probability, the first position information, the second recognition probability, the second position information, and the tactile data meet the pre-trained feature pattern. If they meet, it indicates that this collection is an effective throat swab collection.

[0088] The feature pattern can be represented, for example, by the following function G(u, f, r1, r2, g1, g2; t) = 0, where u is deformation data, f is contact force data, r1 is the first recognition probability, r2 is the second recognition probability, g1 is the first position information, g2 is the second position information, and t is time. Both u and f belong to tactile data. The function G(u, f, r1, r2, g1, g2; t) = 0 can be obtained through training and learning with sample data.

[0089] S53, if the first recognition probability, the first position information, the second recognition probability, the second position information, and the tactile data meet the pre-trained feature pattern, determine that the cotton swab has performed an effective throat swab collection.

[0090] In specific implementation, if the first recognition probability, the first position information, the second recognition probability, the second position information, and the tactile data meet the pre-trained feature pattern, determine that the cotton swab has performed an effective throat swab collection.

[0091] Furthermore, if the first recognition probability, the first position information, the second recognition probability, the second position information, and the tactile data do not meet the pre-trained feature pattern, determine that the cotton swab has not performed an effective throat swab collection.

[0092] S6, if the cotton swab has performed an effective throat swab collection, determine that the collection is completed.

[0093] In specific implementation, if the cotton swab has performed an effective throat swab collection, determine that the collection is completed. After the collection is completed, a prompt can be sent to the user to inform the user that the collection is completed.

[0094] Furthermore, if the cotton swab has not performed an effective throat swab collection, return to step S1. At the same time, the user can be prompted to continue the collection.

[0095] The technical solution of the present invention completes the pharyngeal swab collection by fixing the cotton swab in place and having the user actively touch the cotton swab. At the same time, the reliability of the collection can be ensured through tactile data and image data. Compared with the traditional manual collection method, it only requires the user himself / herself to complete, without the need to deploy medical staff, with extremely low labor costs, and at the same time, the collection quality is also higher.

[0096] See Figure 5 , Figure 5 Figure Figure 5 is a schematic block diagram of a pharyngeal swab collection device provided by an embodiment of the present invention. Corresponding to the above pharyngeal swab collection method, the present invention also provides a pharyngeal swab collection device. The pharyngeal swab collection device includes units for performing the above pharyngeal swab collection method, and the pharyngeal swab collection device can be configured in terminals such as desktop computers, tablet computers, laptops, etc. Specifically, the pharyngeal swab collection device includes:

[0097] An acquisition unit 21, configured to acquire tactile data collected by a sensor;

[0098] A first judgment unit 22, configured to judge whether the cotton swab is in contact with the user according to the tactile data, wherein the cotton swab is fixedly clamped by a clamping device having the sensor;

[0099] A collection unit 23, configured to collect image data of the interior of the user's oral cavity if the cotton swab is in contact with the user;

[0100] A second judgment unit 24, configured to judge whether the cotton swab contacts an effective part inside the user's oral cavity according to the image data;

[0101] A third judgment unit 25, configured to judge whether an effective pharyngeal swab collection is performed by the cotton swab according to the tactile data and the image data if the cotton swab contacts an effective part inside the user's oral cavity;

[0102] A determination unit 26, configured to determine that the collection is completed if an effective pharyngeal swab collection is performed by the cotton swab.

[0103] In one embodiment, the tactile data includes deformation data, and judging whether the cotton swab is in contact with the user according to the tactile data includes:

[0104] Obtaining a deformation data feature according to the deformation data, and obtaining a first difference between the deformation data feature and a preset reference deformation data feature;

[0105] Judging whether the first difference is greater than a preset first threshold;

[0106] If the first difference is greater than the preset first threshold, it is determined that the cotton swab is in contact with the user.

[0107] In one embodiment, the tactile data includes contact force data, and determining whether the cotton swab is in contact with the user based on the tactile data includes:

[0108] Obtaining contact force data features based on the contact force data, and obtaining a second difference between the contact force data features and preset reference contact force data features;

[0109] Determining whether the second difference is greater than a preset second threshold;

[0110] If the second difference is greater than the preset second threshold, it is determined that the cotton swab is in contact with the user.

[0111] In one embodiment, the tactile data includes deformation data and contact force data, and determining whether the cotton swab is in contact with the user based on the tactile data includes:

[0112] Obtaining deformation data features based on the deformation data, and obtaining a first difference between the deformation data features and preset reference deformation data features;

[0113] Obtaining contact force data features based on the contact force data, and obtaining a second difference between the contact force data features and preset reference contact force data features;

[0114] Determining whether it simultaneously satisfies that the first difference is greater than a preset first threshold and the second difference is greater than a preset second threshold;

[0115] If the first difference is greater than the preset first threshold and the second difference is greater than the preset second threshold, it is determined that the cotton swab is in contact with the user.

[0116] In one embodiment, determining whether the cotton swab has contacted an effective part inside the user's oral cavity based on the image data includes:

[0117] Identifying the image data according to a pre-trained object detection model to obtain a first regression box of the cotton swab and a second regression box of the effective part;

[0118] Determining whether the first regression box is located inside the second regression box;

[0119] If the first regression box is located inside the second regression box, it is determined that the cotton swab has contacted an effective part inside the user's oral cavity.

[0120] In one embodiment, determining whether an effective throat swab collection has been performed with the cotton swab based on the tactile data and the image data includes:

[0121] Identify the image data according to a pre-trained object detection model to obtain the first recognition probability and the first position information of the cotton swab, as well as the second recognition probability and the second position information of the effective part;

[0122] Determine whether the first recognition probability, the first position information, the second recognition probability, the second position information, and the tactile data satisfy a pre-trained feature pattern;

[0123] If the first recognition probability, the first position information, the second recognition probability, the second position information, and the tactile data satisfy the pre-trained feature pattern, determine that an effective throat swab collection has been performed with the cotton swab.

[0124] It should be noted that those skilled in the art can clearly understand that the specific implementation processes of the above throat swab collection device and each unit can refer to the corresponding descriptions in the foregoing method embodiments. For the sake of convenience and brevity of description, they will not be elaborated herein.

[0125] The above throat swab collection device can be implemented in the form of a computer program, and this computer program can run on a computer device as shown in Figure 6 shown.

[0126] As shown in Figure 6 shown, an embodiment of the present application provides a computer device, including a processor 111, a communication interface 112, a memory 113, and a communication bus 114. Among them, the processor 111, the communication interface 112, and the memory 113 complete mutual communication through the communication bus 114.

[0127] The memory 113 is used to store a computer program;

[0128] In an embodiment of the present application, when the processor 111 is used to execute the program stored on the memory 113, it executes a throat swab collection method proposed in any of the foregoing method embodiments.

[0129] Those of ordinary skill in the art can understand that all or part of the processes of the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. This computer program can be stored in a storage medium, and this storage medium is a computer-readable storage medium. This computer program is executed by at least one processor in the computer system to implement the flow steps of the method embodiments of the above.

[0130] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. This storage medium stores a computer program. When this computer program is executed by a processor, the processor is caused to execute a throat swab collection method proposed in any of the foregoing method embodiments.

[0131] The storage medium is a physical, non-transitory storage medium, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a magnetic disk, or an optical disc, etc., which are various physical storage media that can store program codes. The computer-readable storage medium can be non-volatile or volatile.

[0132] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0133] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0134] The steps in the method embodiments of the present invention can be adjusted, combined, and deleted according to actual needs. The units in the device embodiments of the present invention can be combined, divided, and deleted according to actual needs. In addition, the functional units in each embodiment of the present invention can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0135] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention.

[0136] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, provided that these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

[0138] As described above, the above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A throat swab collection method, characterized in that, Including: Obtain the tactile data collected by the sensor; Judge whether the cotton swab is in contact with the user according to the tactile data, wherein the cotton swab is fixedly clamped by a clamping device with the sensor; If the cotton swab is in contact with the user, collect the image data of the inside of the user's mouth; Judge whether the cotton swab touches the effective part inside the user's mouth according to the image data, including: identifying the image data according to a pre-trained object detection model to obtain the first regression box of the cotton swab and the second regression box of the effective part; judging whether the first regression box is located within the second regression box; if the first regression box is located within the second regression box, determine that the cotton swab touches the effective part inside the user's mouth; If the cotton swab touches the effective part inside the user's mouth, judge whether the cotton swab has performed an effective throat swab collection according to the tactile data and the image data; If the cotton swab has performed an effective throat swab collection, determine that the collection is completed.

2. The throat swab collection method according to claim 1, wherein, The tactile data includes deformation data, and judging whether the cotton swab is in contact with the user according to the tactile data includes: Obtain the deformation data feature according to the deformation data, and obtain the first difference between the deformation data feature and the preset reference deformation data feature; Judge whether the first difference is greater than a preset first threshold; If the first difference is greater than the preset first threshold, determine that the cotton swab is in contact with the user.

3. The throat swab collection method according to claim 1, wherein, The tactile data includes contact force data, and judging whether the cotton swab is in contact with the user according to the tactile data includes: Obtain the contact force data feature according to the contact force data, and obtain the second difference between the contact force data feature and the preset reference contact force data feature; Judge whether the second difference is greater than a preset second threshold; If the second difference is greater than the preset second threshold, determine that the cotton swab is in contact with the user.

4. The throat swab collection method according to claim 1, characterized in that The tactile data includes deformation data and contact force data, and judging whether the cotton swab is in contact with the user according to the tactile data includes: Obtain the deformation data feature according to the deformation data, and obtain the first difference between the deformation data feature and the preset reference deformation data feature; Obtain the contact force data feature according to the contact force data, and obtain the second difference between the contact force data feature and the preset reference contact force data feature; Judge whether it simultaneously satisfies that the first difference is greater than the preset first threshold and the second difference is greater than the preset second threshold; If the first difference is greater than the preset first threshold and the second difference is greater than the preset second threshold, determine that the cotton swab is in contact with the user.

5. The throat swab collection method according to claim 1, wherein Judging whether the cotton swab has performed an effective throat swab collection according to the tactile data and the image data includes: Identifying the image data according to a pre-trained object detection model to obtain the first recognition probability and the first position information of the cotton swab and the second recognition probability and the second position information of the effective part; Judge whether the first recognition probability, the first position information, the second recognition probability, the second position information, and the tactile data satisfy the pre-trained feature pattern; If the first recognition probability, the first position information, the second recognition probability, the second position information, and the tactile data satisfy a pre-trained feature pattern, it is determined that an effective throat swab sample collection has been performed with the cotton swab.

6. The throat swab collection method according to claim 1, wherein, The method further includes: If there is no contact between the cotton swab and the user, return to the step of obtaining the tactile data collected by the sensor; If the cotton swab does not contact an effective part inside the user's oral cavity, return to the step of obtaining the tactile data collected by the sensor; If the cotton swab does not perform an effective throat swab sample collection, return to the step of obtaining the tactile data collected by the sensor.

7. A throat swab collection device, characterized in that, It includes a unit for executing the method according to any one of claims 1-6.

8. A computer device, characterized in that, The computer device includes a memory and a processor. A computer program is stored on the memory. When the processor executes the computer program, the method according to any one of claims 1-6 is implemented.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program. When the computer program is executed by a processor, the method according to any one of claims 1-6 can be implemented.

Images