3D printer for unmanned automatic production of artificial intelligence-based medical device implantable in human body

Abstract

A 3D printer for unmanned automatic production of an artificial intelligence-based medical device implantable in the human body is provided. According to embodiments of the present invention, 3D modeling, slicing and command code correction can be automatically performed on the basis of a deep learning model and training data so that a medical device implantable in the human body can be automatically produced in an unmanned manner, and thus the time required for production of the medical device implantable in the human body and surgery of a patient can be minimized and, simultaneously, labor costs required for the production of the medical device implantable in the human body can be minimized.

Description

3D printer for unmanned, automated production of artificial intelligence-based implantable medical devices

[0001] Embodiments of the present invention relate to a 3D printer capable of automatically and unmannedly producing a human implantable medical device based on artificial intelligence.

[0002] Recently, demand for 3D printers has been steadily increasing, as the production of various 3D-shaped objects using 3D printers has increased. Typically, 3D printers melt materials at high temperatures and then extrude them layer by layer through an extrusion nozzle at a constant pressure to create 3D objects. These 3D printed objects can be, for example, implantable Class 4 medical devices, such as artificial cheekbones, skull molding materials, or artificial knee joints.

[0003] At this time, in order to manufacture a Class 4 implantable medical device, the hospital must confirm the patient's bone loss and surgical scope, send the patient information to a 3D printing company, and the 3D printing company must manufacture the Class 4 implantable medical device based on this information and send it back to the hospital. In this case, it takes about 7 days from the manufacturing of the Class 4 implantable medical device to the patient's surgery, and the patient has no choice but to wait for the surgery while the Class 4 implantable medical device is being manufactured. As the patient's surgery is delayed, the patient's condition often worsens. In addition, there is the problem that the doctor cannot modify the Class 4 implantable medical device manufactured in this way after receiving it.

[0004] Embodiments of the present invention are directed to providing a 3D printer capable of rapidly and unmanned production of 3D outputs without the assistance of a worker through an artificial intelligence-based automated process.

[0005] According to one embodiment, a 3D printer for unmanned automatic production of an artificial intelligence-based implantable medical device is provided, comprising: an input unit for receiving patient information including a defective area of ​​a patient, a shape and dimensions of the defective area, and raw material information for manufacturing the implantable medical device; a modeling unit for extracting first learning data, which is 3D modeling data corresponding to the patient information and the raw material information, and performing 3D modeling corresponding to the implantable medical device based on a set deep learning model and the first learning data; a slicing unit for extracting second learning data, which is a production condition of the implantable medical device corresponding to the first learning data, and for setting a plurality of different production conditions based on the deep learning model and the second learning data, and converting the set production conditions into command codes in a set format; and a code modification unit for modifying the command codes according to output environmental conditions set so that the implantable medical device has a quality higher than a standard value.

[0006] The above code modification unit automatically sets the output environment conditions based on the quality inspection results of the product produced according to the second learning data, and can select and modify command codes that are out of sync with the output environment conditions among the command codes.

[0007] The above output environmental conditions may include the movement path of the extrusion nozzle.

[0008] The above 3D printer may further include a control unit that controls the amount of the raw material fed into the extruder by controlling the rotation speed of a rotating member provided in a storage where the raw material is stored so that the human implantable medical device is automatically produced according to the modified command code.

[0009] The above 3D printer may further include a feedback unit that collects quality inspection results for the implantable medical device produced according to the modified command code, and inputs the production conditions and command code set in the slicing unit into the deep learning model only when the quality inspection results for the implantable medical device are above a standard value.

[0010] The above 3D printer further includes a voice recognition unit that receives a voice command from a user during the production process of the human body implantable medical device, and based on the voice command, an operation in at least one of the modeling unit, the slicing unit, and the code modification unit is changed, and a quantitative value of the changed operation can be automatically determined based on the deep learning model.

[0011] According to embodiments of the present invention, by automatically performing 3D modeling, slicing, and command code modification based on a deep learning model and learning data, it is possible to automatically and unmannedly produce a human implantable medical device, thereby minimizing the time required for manufacturing a human implantable medical device and performing surgery on a patient, and at the same time minimizing the labor cost required for producing a human implantable medical device.

[0012] In addition, according to embodiments of the present invention, by automatically setting optimal output environment conditions for producing quality products based on a deep learning model and learning data and then modifying the command code based on this, it is possible to produce a high-quality implantable medical device.

[0013] In addition, according to embodiments of the present invention, when the quality inspection result for a human implantable medical device produced through an automated process is above a standard, the production conditions and command code set in the slicing unit are input into the deep learning model, thereby enhancing the deep learning model.

[0014] Figure 1 is a perspective view of a 3D printer according to one embodiment of the present invention.

[0015] Figure 2 is a drawing for explaining an extruder according to one embodiment of the present invention.

[0016] Figure 3 is an example of a human implantable medical device produced through a 3D printer according to one embodiment of the present invention.

[0017] Figure 4 is a block diagram showing the detailed configuration of an unmanned automation unit according to one embodiment of the present invention.

[0018] Figure 5 is a flowchart for explaining the operation flow of an unmanned automation unit according to one embodiment of the present invention.

[0019] Figure 6 is an example of a command code according to one embodiment of the present invention.

[0020] Figure 7 is an example of a human implantable medical device produced without modifying the command code in a code modification unit according to one embodiment of the present invention.

[0021] Figure 8 is an example of a human implantable medical device produced with a command code modified in a code modification unit according to one embodiment of the present invention.

[0022] Figure 9 is a flowchart for explaining an unmanned automatic production method of a human implantable medical device according to one embodiment of the present invention.

[0023] Figure 10 is a flowchart for explaining a method for controlling the operation of a 3D printer according to a voice command input according to one embodiment of the present invention.

[0024] FIG. 11 is a block diagram illustrating a computing environment including a computing device suitable for use in exemplary embodiments.

[0025] Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to facilitate a comprehensive understanding of the methods, devices, and / or systems described herein. However, these are merely examples and the present invention is not limited thereto.

[0026] In describing embodiments of the present invention, if a detailed description of a known technology related to the present invention is judged to unnecessarily obscure the gist of the present invention, the detailed description will be omitted. In addition, the terms described below are terms defined in consideration of their functions in the present invention, and this may vary depending on the intention or custom of the user or operator. Therefore, the definitions should be made based on the contents throughout this specification. The terminology used in the detailed description is only for the purpose of describing embodiments of the present invention and should not be limited in any way. Unless clearly used otherwise, the singular form includes the plural form. In this description, expressions such as "comprises" or "having" are intended to indicate certain features, numbers, steps, operations, elements, parts or combinations thereof, and should not be construed to exclude the presence or possibility of one or more other features, numbers, steps, operations, elements, parts or combinations thereof other than those described.

[0027]

[0028] FIG. 1 is a perspective view of a 3D printer (100) according to one embodiment of the present invention, and FIG. 2 is a drawing for explaining an extruder (110) according to one embodiment of the present invention.

[0029] As illustrated in FIGS. 1 and 2, a 3D printer (100) according to one embodiment of the present invention includes an extruder (110), a plate (120), a plate transfer device (130), an unmanned automation unit (140), a storage (150), a rotating member (160), and a raw material input pipe (170).

[0030] In the present embodiments, the 3D printer (100) is a device that generates and outputs a 3D output. The 3D printer (100) can produce a 3D output using, for example, the FDM (Fused Deposition Modeling) method. Here, the 3D output can be, for example, a class 4 medical device for insertion into the human body, such as an artificial cheekbone, a skull molding material, or an artificial knee joint.

[0031] An extruder (110) is an output device that produces 3D outputs from raw materials. Here, the raw materials are thermoplastic materials used to produce 3D outputs, such as PCL (Polycaprolactone), PDO (Polydioxanone), and PLLA (Polylactic acid). These raw materials have different characteristics, such as melting point, shrinkage rate, and specific gravity, depending on their type.

[0032] Specifically, the extruder (110) may be equipped with a heater (not shown) for melting the raw material, a temperature sensor (not shown) for detecting and controlling the temperature of the heater, an extrusion nozzle (110b) for extruding the raw material in a molten state, etc. The raw material supplied to the extruder (110) may be melted by the heater and transferred to the extrusion nozzle (110b) by rotating the extrusion screw (110a) while being introduced into the interior of the extruder (110). The extrusion screw (110a) winds the raw material and transfers it to the extrusion nozzle (110b), and accordingly, a 3D output may be produced from the extrusion nozzle (110b). In addition, a height sensor (not shown) for measuring the distance between the extrusion nozzle (110b) and the plate (120) may be provided on one side of the extruder (110). The height sensor measures the distance between the extrusion nozzle (110b) and the plate (120), and based on this, can prevent collision between the extrusion nozzle (110b) and the plate (120) while controlling the flatness of the 3D output.

[0033] The plate (120) is provided on the lower side of the extruder (110) and is the portion where the 3D output is mounted. The plate (120) may be formed in the shape of a plate of a predetermined size so that the 3D output can be mounted. The plate (120) may be transported by the plate transport device (130) and inserted into one of several storage bins of a plate storage device (not shown).

[0034] When the production of the 3D output placed on the plate (120) is completed, the plate transfer device (130) transfers the plate (120) along a predetermined transfer path. The plate transfer device (130) can move in the X-axis, Y-axis, and Z-axis directions, for example, using the X, Y, and Z absolute coordinate systems, and can be controlled by an unmanned automation unit (140) to move in a desired direction. The plate transfer device (130) can lift the plate (120) on which the 3D output is placed and then transfer it along a predetermined transfer path. Specifically, the plate transfer device (130) transfers the plate (120) located below the extruder (110) so that it can be stored in a plate storage device or replaced with another plate.

[0035] The unmanned automation unit (140) controls the operations of various components within the 3D printer (100) so that the 3D printer (100) can automatically and unmannedly produce 3D outputs. The detailed configuration and specific operations of the unmanned automation unit (140) will be described later with reference to FIGS. 4 to 8.

[0036] The storage (150) is a location where raw materials required for producing 3D prints are stored. Referring to FIG. 2, the storage (150) may have a storage space of a predetermined size. Raw materials such as PCL, PDO, and PLLA may be stored in the storage space. At this time, a rotating member (160) may be provided inside the storage (150).

[0037] A rotating member (160) is provided inside the storage (150) and rotates under the control of an unmanned automation unit (140). The rotating member (160) may include a plurality of grooves and a plurality of protrusions. The grooves and the protrusions may be formed adjacent to each other, and a hinge for rotation may be provided at the center of the rotating member (160). As described below, the rotating member (160) may rotate under the control of the unmanned automation unit (140), and accordingly, raw materials within the storage (150) may be discharged to the outside of the storage (150) and moved along the raw material input pipe (170).

[0038] A raw material input pipe (170) is provided between the storage (150) and the extruder (110) to interconnect the storage (150) and the extruder (110). The raw material inside the storage (150) can be discharged to the outside of the storage (150) according to the rotational motion of the rotating member (160), move along the raw material input pipe (170), and then be introduced into the extruder (110).

[0039]

[0040] FIG. 3 is an example of a human implantable medical device produced through a 3D printer (100) according to one embodiment of the present invention.

[0041] As illustrated in FIG. 3, implantable medical devices may be, for example, Class 4 medical devices, such as special skull molding materials, artificial cheekbones, and artificial knee joints. These implantable medical devices must be manufactured in a patient-specific manner based on the patient's defect (or gap), shape, and dimensions, and then provided to the hospital. Furthermore, the production period must be minimized to facilitate rapid surgery for the patient. Hereinafter, the process of unmanned automatic production of implantable medical devices through an unmanned automation unit (140) will be examined in more detail with reference to FIGS. 4 to 8.

[0042]

[0043] FIG. 4 is a block diagram showing a detailed configuration of an unmanned automation unit (140) according to one embodiment of the present invention, and FIG. 5 is a flowchart for explaining the operation flow of an unmanned automation unit (140) according to one embodiment of the present invention.

[0044] Referring to FIG. 4, an unmanned automation unit (140) according to one embodiment of the present invention includes an input unit (210), a modeling unit (220), a slicing unit (230), a code modification unit (240), a control unit (250), a feedback unit (260), a voice recognition unit (270), and a deep learning model (280).

[0045] The input unit (210) receives patient information and raw material information. Here, the patient information includes, for example, the patient's defective area, the shape and dimensions of the defective area. Specifically, the defective area may be, for example, the cheekbone, skull, or knee. In addition, the raw material information may include the type, name, abbreviation, etc. of the material required for manufacturing an implantable medical device. The input unit (210) may receive patient information and raw material information from, for example, a worker or a manager. However, the method by which the input unit (210) receives patient information and raw material information is not limited thereto. The input unit (210) may also receive patient information and raw material information from, for example, a server (not shown) of a hospital requesting the manufacturing of an implantable medical device. The patient information and raw material information input in this manner may be input into the deep learning model (280).

[0046] The modeling unit (220) extracts first learning data, which is 3D modeling data corresponding to patient information and raw material information input into the input unit (210), and performs 3D modeling corresponding to a human implantable medical device based on the deep learning model (280) and the first learning data.

[0047] First, the modeling unit (220) can extract first learning data, which is 3D modeling data corresponding to the patient information and raw material information input into the input unit (210), from among the learning data learned through the deep learning model (280). Specifically, the modeling unit (220) can select patient information and raw material information having a similarity within a set error range with the patient information and raw material information input into the input unit (210) from among the learning data, and extract first learning data, which is 3D modeling data corresponding to the selected patient information and raw material information. Here, the learning data is composed of data such as patient information - raw material information - 3D modeling data - production conditions - command codes.

[0048] Next, the modeling unit (220) can perform 3D modeling corresponding to a human implantable medical device based on the deep learning model (280) and the first learning data. As an example, the modeling unit (220) can perform primary 3D modeling based on the first learning data through the deep learning model (280), and perform 3D modeling corresponding to a human implantable medical device to be produced by modifying and supplementing the primary 3D modeling according to patient information and raw material information input to the input unit (210).

[0049] As an example, if the patient information and raw material information corresponding to the first learning data (3D modeling data) are compared with the patient information and raw material information input in the input unit (210) and the patient's defective area, shape, and raw material information are the same and only the dimensions of the defective area are slightly different, the modeling unit (220) performs the first 3D modeling based on the first learning data, and modifies and supplements the first 3D modeling according to the dimensions of the defective area input in the input unit (210), thereby performing the 3D modeling corresponding to the human implantable medical device to be produced.

[0050] The slicing unit (230) extracts second learning data, which are production conditions for a human implantable medical device corresponding to the first learning data, sets a plurality of different production conditions based on the deep learning model (280) and the second learning data, and converts the set production conditions into command codes in a set format. As described above, the learning data may be composed of, for example, patient information - raw material information - 3D modeling data - production conditions - command codes.

[0051] First, the slicing unit (230) extracts second learning data (production conditions) corresponding to the first learning data (3D modeling data), and can set a plurality of different production conditions based on the deep learning model (280) and the second learning data. Here, the production conditions refer to the production conditions of 3D printing required to produce a human body implantable medical device, such as printing temperature, printing speed, output amount, internal filling pattern, internal filling line direction, internal filling overlap ratio, internal filling distance, etc. As an example, the slicing unit (230) can set a plurality of different production conditions based on the second learning data, and then modify and supplement the production conditions set based on the deep learning model (280). As in the previous example, if the patient information and raw material information corresponding to the first learning data (3D modeling data) are the same as the patient information and raw material information entered in the input unit (210) in terms of the patient's defective area, shape, and raw material information and only the dimensions of the defective area are slightly different, the slicing unit (230) sets production conditions corresponding to the second learning data, but can modify and supplement the production conditions set according to the dimensions of the defective area entered in the input unit (210) based on the deep learning model (280).

[0052] At this time, the slicing unit (230) can set production conditions according to the characteristics of the raw materials used in the production of the human implantable medical device. As described above, since the characteristics such as melting point, shrinkage rate, specific gravity, etc., are different depending on the type of raw material, the slicing unit (230) can set different production conditions (e.g., printing temperature, printing speed, etc.) suitable for each raw material based on learning data corresponding to the input raw material information.

[0053] Next, the slicing unit (230) can convert the production conditions set in this manner into a command code in a set format. Here, the command code is a code used to control the operation of each component within the 3D printer (100) via the control unit (250) described below, and may be, for example, G-CODE. As an example, the slicing unit (230) can convert each of the set production conditions into G-CODE.

[0054] The code correction unit (240) corrects the command code according to the output environmental conditions set so that the implantable medical device has a quality level higher than the standard. Here, the output environmental conditions are conditions that affect the quality of the implantable medical device among multiple production conditions, and may be, for example, the movement path of the extrusion nozzle (110b), the printing temperature, etc.

[0055] In general, even if 3D modeling, production condition setting, and command code conversion are performed normally through the modeling unit (220) and the slicing unit (230), unexpected quality deterioration issues may occur during the actual printing of the implantable medical device through the 3D printer (100). As an example, in the process of producing the implantable medical device while the extrusion nozzle (110b) moves, even if other production conditions are the same, the quality of the implantable medical device produced may vary depending on the path or order in which the extrusion nozzle (110b) moves. As another example, although the implantable medical device is printed according to the printing temperature set through the slicing unit (230), a case may occur in which the quality of the implantable medical device deteriorates as a result of the quality inspection, requiring the printing temperature to be increased.

[0056] To solve this problem, the code correction unit (240) automatically sets the output environment conditions based on the quality inspection results of the products produced according to the second learning data, and can select and correct the command codes that deviate from the output environment conditions among the command codes. Specifically, the code correction unit (240) can compare the production conditions for a product that shows a quality inspection result above the standard value and the production conditions for a product that shows a quality inspection result below the standard value from the quality inspection results of previously produced products, and automatically set the output environment conditions based on the comparison results. As an example, the code correction unit (240) can automatically set the following output environment conditions by comparing the quality inspection results for two products that have the same production conditions except for the movement path of the extrusion nozzle (110b).

[0057]

[0058] <Example of output environment conditions>

[0059] When patient information A / raw material information B,

[0060] Output environment conditions

[0061] - Movement path of extrusion nozzle (110b): Path A → Path B → Path C

[0062] - Printing temperature: 210℃

[0063] …

[0064]

[0065] Here, quality inspection results can be obtained through various methods, including image analysis using a vision camera (not shown) or manual inspection by a worker. These methods are not particularly limited. Furthermore, inspection items included in the quality inspection results may include the appearance, microstructure, contamination, and damage of implantable medical devices.

[0066] In this way, the code correction unit (240) can automatically set the output environment conditions based on the quality inspection results of the previously learned learning data, and then select and correct the command codes output from the slicing unit (230) that are inconsistent with the output environment conditions. As an example, the code correction unit (240) can correct the command codes related to the movement path of the extrusion nozzle (110b) among the command codes to suit the output environment conditions.

[0067] The control unit (250) controls the operations of various components within the 3D printer (100) so that a human implantable medical device can be output through the 3D printer (100). The control unit (250) controls the operations of, for example, the extruder (110), extrusion screw (110a), extrusion nozzle (110b), plate transfer device (130), and rotating member (160) described above, thereby enabling the human implantable medical device to be output normally.

[0068] In particular, the control unit (250) can control the operation of various parts in the 3D printer (100) so that a human implantable medical device can be automatically produced according to the characteristics of the raw material. Specifically, the control unit (250) can control the rotation speed of the rotating member (160) provided in the storage (150) where the raw material is stored so that a human implantable medical device can be automatically produced according to the characteristics of the raw material and the above-described command code, thereby controlling the amount of raw material flowing into the extruder (110). The control unit (250) can change the rotation speed of the rotating member (160) by controlling the operation of a motor (not shown) connected to the rotating member (160), and accordingly, the amount of raw material flowing into the extruder (110) can be controlled.

[0069] The feedback unit (260) collects the quality inspection results for the implantable medical device produced according to the command code modified by the code correction unit (240), and inputs the production conditions and command codes set by the slicing unit (230) into the deep learning model (280) only when the quality inspection results for the implantable medical device are above the standard. Specifically, the feedback unit (260) may collect the quality inspection results for the implantable medical device from a vision camera or directly receive the quality inspection results from a worker. At this time, if the quality inspection results are below the standard, the feedback unit (260) may not input the production conditions and command codes set by the slicing unit (230) into the deep learning model (280), and if the quality inspection results are above the standard, the feedback unit (260) may input the production conditions and command codes set by the slicing unit (230) into the deep learning model (280). That is, the feedback unit (260) can continuously improve the deep learning model (280) by inputting the production conditions and command codes for the produced implantable medical device into the deep learning model (280) only when the quality inspection result for the produced implantable medical device is above the standard. If the quality inspection result is below the standard, the feedback unit (260) can transmit a command to the control unit (250) to discard or reproduce the produced implantable medical device.

[0070] The voice recognition unit (270) receives voice commands from the user during the manufacturing process of a medical device implantable into the human body. These voice commands may be, for example, "Increase the output value" or "Increase the printing speed." The voice recognition unit (270) recognizes voice commands using an artificial intelligence voice recognition function, converts them into text, and then transmits them to the control unit (250).

[0071] The control unit (250) can control the operation of at least one of the modeling unit (220), the slicing unit (230), and the code modification unit (240) based on a voice command. At this time, a quantitative value of the operation changed in at least one of the modeling unit (220), the slicing unit (230), and the code modification unit (240) can be automatically determined based on the deep learning model (280).

[0072] As an example, if the voice command is “increase the output value,” the control unit (250) selects learning data corresponding to the voice command and having a quality inspection result higher than a standard value among learning data corresponding to patient information and raw material information based on the deep learning model (280), and automatically determines a quantitative value or range of the changed operation (e.g., a 10% increase from the current output value) based on the selected learning data.

[0073] That is, the control unit (250) can change the operation of at least one of the modeling unit (220), the slicing unit (230), and the code correction unit (240) based on a voice command, and can automatically determine a quantitative value or range for the changed operation based on patient information, raw material information, and quality inspection results.

[0074]

[0075] Figure 6 is an example of a command code according to one embodiment of the present invention.

[0076] As described above, the command code according to one embodiment of the present invention may be, for example, G-CODE.

[0077] Referring to Figure 6, the meaning of the code values ​​in G-CODE is as follows.

[0078]

[0079] G0: Move command

[0080] G1: Output and move command

[0081] X: width / Y: height / Z: thickness (height)

[0082] E: Extrusion value

[0083] F: Movement speed

[0084]

[0085] FIG. 7 is an example of a human implantable medical device produced without modifying the command code in a code modification unit (240) according to one embodiment of the present invention, and FIG. 8 is an example of a human implantable medical device produced with the command code modified in a code modification unit (240) according to one embodiment of the present invention.

[0086] In FIGS. 7 and 8, A represents a human implantable medical device, and B represents the movement path of an extrusion nozzle (110b).

[0087] Referring to FIG. 7, it can be confirmed that the movement path (B) of the extrusion nozzle (110b) crosses at least a portion of the implantable medical device (A) before the command code is modified. In this case, the quality of the implantable medical device (A) produced may be degraded. Accordingly, the code modification unit (240) automatically sets the output environment conditions based on the quality inspection results of the product produced according to the second learning data, and selects and modifies command codes that deviate from the output environment conditions among the command codes.

[0088] Referring to FIG. 8, it can be confirmed that the movement path (B) of the extrusion nozzle (110b) after modification of the command code does not cross at least a portion of the implantable medical device (A). In this case, the quality can be improved compared to the implantable medical device (A) produced in FIG. 7.

[0089]

[0090] Figure 9 is a flowchart illustrating an unmanned, automated production method for implantable medical devices according to one embodiment of the present invention. While the illustrated flowchart depicts the method as divided into multiple steps, at least some of the steps may be performed in reverse order, combined with other steps and performed together, omitted, divided into substeps, or performed with one or more additional steps not illustrated.

[0091] In step S102, the input unit (210) receives patient information including the patient's defective area, the shape and dimensions of the defective area, and raw material information for manufacturing a human body implantable medical device.

[0092] In step S104, the modeling unit (220) extracts first learning data, which is 3D modeling data corresponding to patient information and raw material information, and performs 3D modeling corresponding to a human implantable medical device based on the set deep learning model and first learning data.

[0093] In step S106, the slicing unit (230) extracts second learning data, which is a production condition of a human implantable medical device corresponding to the first learning data, sets a plurality of different production conditions based on the deep learning model and the second learning data, and converts the set production conditions into a command code in a set format.

[0094] At step S108, the code correction unit (240) corrects the command code according to the output environment conditions set so that the human implantable medical device has a quality higher than the standard.

[0095] At step S110, the control unit (250) controls the operation of various parts in the 3D printer (100) according to the modified code.

[0096] At step S112, the feedback unit (260) collects quality inspection results for the implantable medical device produced according to the modified command code.

[0097] In step S114, if the quality inspection result for the human implantable medical device is above the standard, the feedback unit (260) inputs the production conditions and command code set in the slicing unit (230) into the deep learning model (280).

[0098]

[0099] FIG. 10 is a flowchart for explaining a method for controlling the operation of a 3D printer according to a voice command input according to one embodiment of the present invention.

[0100] In step S202, the voice recognition unit (270) receives a voice command from the user during the production process of a human implantable medical device.

[0101] In step S204, the voice recognition unit (270) can recognize a voice command through an artificial intelligence voice recognition function, convert it into text, and then transmit it to the control unit (250).

[0102] In step S206, the control unit (250) controls the operation of at least one of the modeling unit (220), the slicing unit (230), and the code modification unit (240) based on the voice command.

[0103]

[0104] Figure 11 is a block diagram illustrating a computing environment including a computing device suitable for use in exemplary embodiments. In the illustrated embodiment, each component may have different functions and capabilities other than those described below, and may include additional components other than those described below.

[0105] The illustrated computing environment (10) includes a computing device (12). In one embodiment, the computing device (12) may be a 3D printer (100) or one or more components included in an unmanned automation unit (140) of the 3D printer (100).

[0106] A computing device (12) includes at least one processor (14), a computer-readable storage medium (16), and a communication bus (18). The processor (14) may cause the computing device (12) to operate according to the exemplary embodiments mentioned above. For example, the processor (14) may execute one or more programs stored in the computer-readable storage medium (16). The one or more programs may include one or more computer-executable instructions, which, when executed by the processor (14), may be configured to cause the computing device (12) to perform operations according to the exemplary embodiments.

[0107] A computer-readable storage medium (16) is configured to store computer-executable instructions or program code, program data, and / or other suitable forms of information. A program (20) stored in the computer-readable storage medium (16) includes a set of instructions executable by the processor (14). In one embodiment, the computer-readable storage medium (16) may be a memory (volatile memory such as random access memory, non-volatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, any other form of storage medium that can be accessed by the computing device (12) and store desired information, or a suitable combination thereof.

[0108] A communication bus (18) interconnects various other components of the computing device (12), including the processor (14) and computer-readable storage media (16).

[0109] The computing device (12) may also include one or more input / output interfaces (22) that provide interfaces for one or more input / output devices (24) and one or more network communication interfaces (26). The input / output interfaces (22) and the network communication interfaces (26) are connected to the communication bus (18). The input / output devices (24) may be connected to other components of the computing device (12) via the input / output interfaces (22). Exemplary input / output devices (24) may include input devices such as pointing devices (such as a mouse or a trackpad), a keyboard, a touch input device (such as a touchpad or a touchscreen), a voice or sound input device, various types of sensor devices and / or photographing devices, and / or output devices such as display devices, printers, speakers and / or network cards. The exemplary input / output devices (24) may be included within the computing device (12) as a component constituting the computing device (12), or may be connected to the computing device (12) as a separate device distinct from the computing device (12).

[0110]

[0111] While the present invention has been described in detail above through representative examples, those skilled in the art will understand that various modifications to the above-described embodiments are possible without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined not only by the claims set forth below but also by equivalents thereof.

[0112]

[0113] [Explanation of symbols]

[0114] 100: 3D printer

[0115] 110: Extruder

[0116] 110a: Extrusion screw

[0117] 110b: Extrusion nozzle

[0118] 120: Plate

[0119] 130: Plate transfer device

[0120] 140: Unmanned Automation Department

[0121] 150: Storage

[0122] 160: Rotating member

[0123] 170: Raw material input pipe

[0124] 210: Input section

[0125] 220: Modeling Department

[0126] 230: Slicing section

[0127] 240: Code correction unit

[0128] 250: Control unit

[0129] 260: Feedback Department

[0130] 270: Voice recognition unit

[0131] 280: Deep Learning Model

Claims

1. A 3D printer for unmanned automatic production of artificial intelligence-based implantable medical devices. An input unit for receiving patient information including a patient's defective area, the shape and dimensions of the defective area, and raw material information for manufacturing the human body implantable medical device; A modeling unit that extracts first learning data, which is 3D modeling data corresponding to the patient information and raw material information, and performs 3D modeling corresponding to the human body implantable medical device based on the set deep learning model and the first learning data; A slicing unit that extracts second learning data, which is a production condition of the human implantable medical device corresponding to the first learning data, sets a plurality of different production conditions based on the deep learning model and the second learning data, and converts the set production conditions into a command code in a set format; and A 3D printer for unmanned automatic production of an artificial intelligence-based implantable medical device, comprising a code modification unit that modifies the command code according to output environmental conditions set so that the implantable medical device has a quality higher than a standard.

2. In claim 1, The above code modification unit automatically sets the output environment conditions based on the quality inspection results of the product produced according to the second learning data, and selects and modifies command codes that are out of compliance with the output environment conditions among the command codes, a 3D printer for unmanned automatic production of an artificial intelligence-based human implantable medical device.

3. In claim 2, The above output environment conditions are for a 3D printer for unmanned automatic production of an artificial intelligence-based human implantable medical device, including the movement path of an extrusion nozzle.

4. In claim 1, A 3D printer for unmanned automatic production of an implantable medical device based on artificial intelligence, further comprising a control unit that controls the rotational speed of a rotating member provided in a storage where the raw material is stored so that the implantable medical device is automatically produced according to the modified command code, thereby controlling the amount of the raw material fed into the extruder.

5. In claim 1, A 3D printer for unmanned automatic production of an artificial intelligence-based implantable medical device, further comprising a feedback unit that collects quality inspection results for the implantable medical device produced according to the modified command code, and inputs the production conditions and command code set in the slicing unit into the deep learning model only when the quality inspection results for the implantable medical device are above a standard value.

6. In claim 1, In the production process of the above human implantable medical device, a voice recognition unit for receiving a voice command from a user is further included. A 3D printer for unmanned automatic production of an artificial intelligence-based implantable medical device, wherein an operation of at least one of the modeling unit, the slicing unit, and the code modification unit is changed based on the voice command, and a quantitative value of the changed operation is automatically determined based on the deep learning model.

Images