Assistive device modeling method and limb guide mechanism

Abstract

A method for modeling an assistive device includes the following steps: obtaining limb surface point cloud information of a corresponding limb; generating a plurality of learning data based on the limb surface point cloud information; and processing the learning data through a quasi-neural network to generate an assistive device digital model.

Description

Technical Field

[0001] The invention relates to a modeling method, in particular to an assistive device modeling method and a limb guide plate mechanism. Background Art

[0002] When a person's limbs are injured, their movements will be affected. At this time, some equipment (such as plaster, crutches, protective gear, prosthesis, etc.) is usually used for assistance. This equipment is called an assistive device. According to the functional distinction, assistive devices can include mobility aids (such as wheelchairs, corrective shoes, walkers, crutches), assistive devices that assist body functions (such as hand or leg prostheses, pen holders, special spoons), life aids (such as safety alarms, kickers), therapeutic or fixed assistive devices (such as plaster, back braces, waist protectors, knee pads, neck collars, pillows), etc. The more common protective gear that is often used by consumers is usually assistive devices related to limb activities, such as limb protective gear, walkers, prostheses, plaster, etc.

[0003] Generally speaking, assistive devices for fixing limbs are usually made by experienced doctors or medical personnel using plaster, molds or related objects, but such protective devices made of plaster will lead to a very poor user experience. For example, since plaster hardens after cooling, the user's skin will be very uncomfortable when it comes into contact with the plaster; high temperatures are generated when making protective devices with plaster as the main body; the material or structure cannot be changed to achieve customization, etc. On the other hand, assistive devices can also be produced in a fixed size, but such assistive devices cannot provide perfect support, modeling elasticity and comfort for the limbs used. In addition, the material and structure of uniformly produced assistive devices cannot be adjusted or changed according to user needs.

[0004] Therefore, how to quickly establish a digital model of a wearable assistive device, improve the design quality of the assistive device, and shorten the production cycle of customized assistive devices will become an important issue. Summary of the invention

[0005] The present invention provides an assistive device modeling method and a limb guide plate mechanism, so as to quickly establish an assistive device digital model of a wearable assistive device, improve the assistive device design quality and shorten the production cycle of a customized assistive device.

[0006] The present invention provides an assistive device modeling method, comprising the following steps: obtaining limb surface point cloud information of a corresponding limb; generating a plurality of learning data according to the limb surface point cloud information; and processing the learning data through a quasi-neural network to generate an assistive device digital model.

[0007] The present invention further provides an assistive device modeling method, comprising the following steps. A limb guide mechanism is provided, wherein the limb guide mechanism is provided with at least three positioning holes. At least three positioning marks corresponding to the at least three positioning holes are generated on the limb through the limb guide mechanism. The limb is scanned to obtain limb surface point cloud information, and the limb surface point cloud information includes at least three positioning marks. A plurality of preset assistive device digital models are obtained from a database. Based on the at least three positioning marks of the limb surface point cloud information, the limb surface point cloud information is superimposed with the preset assistive device digital model. A preset assistive device digital model that matches the limb surface point cloud information is selected. An assistive device digital model is generated based on the limb surface point cloud information and the matching preset assistive device digital model.

[0008] The present invention further provides a limb guide plate mechanism, comprising a body and at least three positioning holes, wherein the positioning holes are arranged on the body, and the positions of the positioning holes are different from each other, and the connection length between two positioning holes of the at least three positioning holes is set to be less than or equal to a preset distance.

[0009] The assistive device modeling method and limb guide mechanism disclosed in the present invention generate a plurality of learning data according to the limb surface point cloud information, and process the learning data through a quasi-neural network to generate an assistive device digital model. In addition, the embodiment of the present invention can provide a limb guide mechanism provided with at least three positioning holes, and generate at least three positioning marks corresponding to the at least three positioning holes on the limb through the limb guide mechanism. Then, the limb is scanned to obtain the limb surface point cloud information including at least three positioning marks, and the limb surface point cloud information is overlapped with a plurality of preset assistive device digital models obtained from the database according to the at least three positioning marks of the limb surface point cloud information, and the preset assistive device digital model matching the limb surface point cloud information is selected, and then the assistive device digital model is generated according to the limb surface point cloud information and the matching preset assistive device digital model. In this way, the assistive device digital model of the wearable assistive device can be effectively and quickly established, and the assistive device design quality can be improved and the production cycle of the customized assistive device can be shortened. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to better understand the above and other aspects of the present invention, the following embodiments are specifically described in detail with reference to the accompanying drawings as follows:

[0011] Figure 1 FIG. 4 is a schematic diagram of an electronic system for assistive modeling according to an embodiment of the present invention.

[0012] Figure 2 FIG. 4 is a flow chart of a method for modeling an auxiliary tool according to an embodiment of the present invention.

[0013] Figure 3 It is a schematic diagram of generating a plurality of learning data according to limb surface point cloud information according to an embodiment of the present invention.

[0014] Figure 4 FIG. 4 is a schematic diagram of an electronic system for assistive modeling according to an embodiment of the present invention.

[0015] Figure 5 The figure is a schematic diagram of the corresponding relationship between the positioning holes of the limb guide mechanism and the positioning marks on the limb according to an embodiment of the present invention.

[0016] Figure 6 FIG. 4 is a flow chart of an auxiliary tool modeling method according to another embodiment of the present invention.

[0017] Figure 7 FIG. 4 is a flow chart of an auxiliary tool modeling method according to another embodiment of the present invention.

[0018] Figure 8 It is a schematic diagram of the corresponding relationship among the limb surface point cloud information, the preset assistive device digital model and the superimposed model according to the present invention.

[0019] Fig. 9 for Figure 7 Detailed flowchart of step S714.

[0020] Fig.10 It is a schematic diagram of dividing the appearance shape of a matching preset auxiliary tool digital model into multi-layer cross sections according to the present invention.

[0021] Fig.11 FIG. 4 is a flow chart of an auxiliary tool modeling method according to another embodiment of the present invention.

[0022] Reference numerals list

[0023] 100, 400: Electronic systems for auxiliary modeling

[0024] 110: 3D scanning device

[0025] 120: Processing device

[0026] 130: 3D printing device

[0027] 310, 810: Limb surface point cloud information

[0028] 320: Rotation direction

[0029] 410: Limb guide mechanism

[0030] 411: Ontology

[0031] 412, 413, 414: Positioning holes

[0032] 420: Hands

[0033] 511, 512, 513: Positioning marks

[0034] 820: Preset digital model of auxiliary equipment

[0035] 830: Superposition Model

[0036] S202~S208, S602~S612, S702~S716, S902~S906, S1102~S1104: Steps DETAILED DESCRIPTION

[0037] The technical terms in this specification refer to the customary terms in the technical field. If some terms are explained or defined in this specification, the interpretation of these terms shall be based on the explanation or definition in this specification. Each embodiment of the present disclosure has one or more technical features. Under the premise of possible implementation, a person with ordinary knowledge in the technical field can selectively implement some or all of the technical features in any embodiment, or selectively combine some or all of the technical features in these embodiments.

[0038] In the various embodiments listed below, the same reference numerals will be used to represent the same or similar components or elements.

[0039] Figure 1 Schematic diagram of an electronic system for modeling an auxiliary tool according to an embodiment of the present invention. Figure 1 The electronic system 100 for assisting modeling includes a three-dimensional scanning device 110 , a processing device 120 and a three-dimensional printing device 130 .

[0040] The three-dimensional scanning device 110 is used to scan the user's limbs to generate limb surface point cloud information of the corresponding limb. For example, the user can place the hand or foot in the scanning area of ​​the three-dimensional scanning device 110 for scanning to generate limb surface point cloud information of the corresponding limb (i.e., the user's hand or foot).

[0041] The processing device 120 is coupled to the three-dimensional scanning device 110 to receive the limb surface point cloud information generated by the three-dimensional scanning device 110 and generate a suitable assistive device digital model according to the limb surface point cloud information.

[0042] In this embodiment, the processing device 120 may include a processor and a database. The processor may be, for example, a central processing unit (CPU), a microprocessor (Microprocessor), a microcontroller, a digital signal processor (DSP), an application specific integrated circuit (ASIC) or other similar devices. The database may be, for example, a memory, a hard disk, a solid state drive, etc., for storing relevant information.

[0043] The three-dimensional printing device 130 is coupled to the processing device 120, and generates an assistive device suitable for the user based on the assistive device digital model generated by the processing device 120. In this way, the assistive device modeling electronic system 100 can quickly establish an assistive device digital model of a wearable assistive device, thereby improving the assistive device design quality and shortening the production cycle of a customized assistive device.

[0044] Figure 2 This is a flow chart of a method for modeling an auxiliary tool according to an embodiment of the present invention. Figure 1 and Figure 2 In step S202, the processing device 120 obtains the limb surface point cloud information of the corresponding limb, such as Figure 3 The limb surface point cloud information is generated by scanning the limb of the user through the three-dimensional scanning device 110. In this embodiment, the user's hand is used as an example of the limb of the embodiment of the present invention.

[0045] In step S204, the processing device 120 generates a plurality of learning data according to the limb surface point cloud information. Specifically, the processing device 120 rotates the limb surface point cloud information to a plurality of different angles and performs proportional scaling to sequentially generate a plurality of learning data. For example, the processing device 120 may generate a plurality of learning data by: Figure 3 The limb surface point cloud information is rotated to a plurality of different angles in the rotation direction 310 shown in the figure to generate a plurality of learning data corresponding to the original proportions. Then, the processing device 120 can scale the limb surface point cloud information in the same proportion and perform the following steps: Figure 3 The rotation direction 310 shown rotates the above-mentioned proportionally scaled limb surface point cloud information to multiple different angles to generate multiple learning data corresponding to different scales and different angles.

[0046] In step S206, the processing device 120 processes the learning data through a neural network to generate a digital model of the assistive device. That is, the processing device 120 processes the learning data through a convolutional neural network, for example, to generate a corresponding limb model, and draws a digital model of the assistive device corresponding to the limb model based on the limb model to generate a digital model of the assistive device.

[0047] In step S208, the assistive device is generated according to the assistive device digital model by the three-dimensional printing device 130. In this way, the assistive device digital model of the wearable assistive device can be quickly established, thereby improving the assistive device design quality and shortening the production cycle of the customized assistive device.

[0048] Figure 4 Schematic diagram of an electronic system for modeling an auxiliary tool according to an embodiment of the present invention. Figure 4The electronic system 400 for assistive device modeling includes a three-dimensional scanning device 110, a processing device 120, a three-dimensional printing device 130, and a limb guide plate mechanism 410. In this embodiment, the three-dimensional scanning device 110, the processing device 120, the three-dimensional printing device 130, and the limb guide plate mechanism 410. Figure 1 The three-dimensional scanning device 110, the processing device 120, and the three-dimensional printing device 130 are the same or similar, and can be referred to Figure 1 The embodiments of the present invention are described in detail, so they will not be repeated here.

[0049] In this embodiment, the limb guide mechanism 410 includes a body 411 and three positioning holes 412, 413, 414. The positioning holes 412, 413, 414 are disposed on the body 411. The limb guide mechanism 410 of this embodiment is used to float on the user's hand 420, and can fix the posture of the user's hand 420, and generate positioning marks 511, 512, 513 corresponding to the positioning holes 412, 413, 414 on the user's hand 420, such as Figure 5 Next, the limb surface point cloud information obtained by the three-dimensional scanning device 110 will also include positioning marks 511, 512, 513, so that the processing device 120 can perform subsequent operations based on the information of the positioning marks 511, 512, 513. In this way, it can be avoided that the three-dimensional scanning device 110 obtains wrong information due to the shaking of the user's hand.

[0050] In this embodiment, the positions of the positioning holes 412, 413, and 414 are different from each other, and the connection length of two positioning holes (for example, positioning holes 412 and 413 or positioning holes 413 and 414) of the positioning holes 412, 413, and 414 is less than or equal to the preset distance. In other words, the connection length of the positioning holes 412 and 413 and the connection length of the positioning holes 413 and 414 are respectively less than or equal to the preset distance. In addition, the above-mentioned preset distance is, for example, 7 centimeters (cm), but the embodiment of the present invention is not limited thereto. The user can adjust the length of the preset distance according to his needs.

[0051] In some embodiments, at least one of the positioning holes 412, 413, and 414 may correspond to a joint point of a limb. Assume that the user's hand is used as an example of a limb in an embodiment of the present invention. For example, the positioning hole 412 corresponds to the joint point of the user's thumb adjacent to the base of the palm, the positioning hole 413 corresponds to the joint point of the user's wrist, and the positioning hole 414 corresponds to the joint point of the user's hand axis. In addition, the connection between the positioning holes 412 and 413 and the connection between the positioning holes 413 and 414 may form an angle. The angle of the above-mentioned angle may be adjusted as needed, for example, based on a doctor's advice.

[0052] In addition, the user can further confirm whether the connection length of two positioning holes (e.g., positioning holes 412 and 413 or positioning holes 413 and 414) of the positioning holes 412, 413, and 414 is less than or equal to the preset distance to confirm whether to adjust the position of the positioning holes. For example, when the connection length of the positioning holes 412 and 413 is less than or equal to the preset distance, the positions of the positioning holes 412 and 413 remain corresponding to the joints of the limbs respectively, that is, the positioning hole 412 still corresponds to the joint of the user's thumb near the base of the palm, and the positioning hole 413 still corresponds to the joint of the user's wrist. When the connection length of the positioning holes 413 and 414 is not less than or equal to the preset distance, that is, the connection length of the positioning holes 413 and 414 is greater than the preset distance, then the position of one of the positioning holes 413 and 414 is adjusted according to the preset distance. For example, adjusting the position of the positioning hole 414 means adjusting the position of the positioning hole 414 to the position between the user's wrist and the hand axis, and the adjusted position of the positioning hole 414 can be as follows Figure 5 The position of the locating hole 414 of the limb guide mechanism 410 is shown.

[0053] In addition, the number of positioning holes of the limb guide plate mechanism 410 is three as an example, but it is not used to limit the embodiment of the present invention. The number of positioning holes of the limb guide plate mechanism 410 can be four or more, and the positions of the four or more positioning holes are also different from each other, and the same technical effect can still be achieved. The setting method of the four or more positioning holes can also be set and adjusted as in the above embodiment, so it will not be repeated here.

[0054] In addition, assuming that the present embodiment uses the user's hand as an example of a limb of the embodiment of the present invention, the electronic system 400 for modeling the assistive device further includes a finger ring (not shown). This finger ring is used, for example, to be placed on the thumb of the user's hand, so that the limb surface point cloud information obtained by the three-dimensional scanning device 110 will also include the information corresponding to the finger ring. Then, the processing device 120 can use the known information corresponding to the finger ring as a basis for modifying and adjusting the selected preset assistive device digital model. In this way, the accuracy and quality of the generated wearable assistive device can be further increased.

[0055] Figure 6 This is a flow chart of a method for modeling an auxiliary tool according to another embodiment of the present invention. Figures 3 to 6 In this embodiment, the user's hand is used as an example of a limb of the present invention. In step S602, at least three positioning marks 511, 512, 513 corresponding to at least three positioning holes 412, 413, 414 on the limb guide mechanism 410 are generated on the limb. In step S604, the processing device 120 obtains the limb surface point cloud information corresponding to the limb, such as Figure 3The limb surface point cloud information is generated by scanning the user's limbs with the three-dimensional scanning device 110 , and the limb surface point cloud information includes three positioning marks 511 , 512 , and 513 .

[0056] In step S606, the processing device 120 turns the limb surface point cloud information to a preset position according to at least three positioning marks 511, 512, 513, for example, corresponding to Figure 3 That is, when the position of the limb surface point cloud information generated by the three-dimensional scanning device 110 is Figure 3 When the position of the limb is different, the processing device 120 can quickly turn the limb surface point cloud information to the coordinate system defined by the positioning marks 511, 512, and 513. Figure 3 The position of the reference numeral 310 is, for example, the position where the palm of the user's hand is exposed. In this way, the positioning of the limb surface point cloud information can be accelerated. The above-mentioned preset position is an implementation example of the present invention and is not used to limit the embodiments of the present invention. The user can also adjust the form of the preset position according to his needs, such as the position where the back of the palm of the user's hand is exposed, etc., and the same effect can be achieved.

[0057] In step S608, the processing device 120 generates a plurality of learning data according to the limb surface point cloud information. Specifically, the processing device 120 rotates the limb surface point cloud information to a plurality of different angles and performs proportional scaling to sequentially generate a plurality of learning data. Figure 2 The same as step S204, please refer to Figure 2 The description of step S204 is omitted here and will not be repeated here.

[0058] In step S610, the processing device 120 processes the learning data through a convolutional neural network to generate an assistive device digital model. That is, the processing device 120 processes the learning data through a convolutional neural network to generate a corresponding digital model of a limb, and draws an assistive device digital model corresponding to the digital model of the limb based on the digital model of the limb to generate an assistive device digital model.

[0059] In step S612, the three-dimensional printing device 130 is used to generate an assistive device according to the assistive device digital model. In this way, the wearable assistive device can be quickly established, the assistive device design quality can be improved, and the production cycle of the customized assistive device can be shortened.

[0060] Figure 7 This is a flow chart of a method for modeling an auxiliary tool according to another embodiment of the present invention. Figures 3 to 5In step S702, a limb guide mechanism 410 is provided, wherein the limb guide mechanism 410 is provided with at least three positioning holes 412, 413, 414, such as Figure 4 , 5 In step S704, at least three positioning marks 511, 512, 513 corresponding to at least three positioning holes 412, 413, 414 are generated on the limb by the limb guide mechanism 410, as shown in FIG. Figure 5 shown.

[0061] In step S706, the limb is scanned to obtain limb surface point cloud information, and the limb surface point cloud information includes at least three positioning marks 511, 512, 513. The limb surface point cloud information is generated by scanning the user's limb by the three-dimensional scanning device 110, and the limb surface point cloud information includes three positioning marks 511, 512, 513.

[0062] In step S708, the processing device 120 obtains a plurality of preset assistive device digital models from the database. In other words, the processing device 120 can obtain all preset assistive device digital models from the database so as to compare the preset assistive device digital models with the limb surface point cloud information, and then confirm whether there is a preset assistive device digital model corresponding to the limb surface point cloud information.

[0063] In step S710, the processing device 120 overlays the limb surface point cloud information with the preset assistive device digital model according to at least three positioning marks 511, 512, 513 of the limb surface point cloud information. For example, the processing device 120 can position and align the limb surface point cloud information with the preset assistive device digital model according to the coordinate system defined by the positioning marks 511, 512, 513 and the preset coordinate system defined by the preset assistive device digital model, such as Figure 8 shown.

[0064] exist Figure 8 In the figure, the limb surface point cloud information 810 and the preset assistive device digital model 820 have been adjusted to correspond to the same coordinate system. Next, the processing device 120 combines the limb surface point cloud information 810 and the preset assistive device digital model 820 to form a Figure 8 The superimposed model 830 is shown. In this way, the superimposition speed of the limb surface point cloud information and the preset assistive device digital model can be accelerated.

[0065] In step S712, a preset assistive device digital model that matches the limb surface point cloud information is selected. That is, after the processing device 120 superimposes the limb surface point cloud information with the preset assistive device digital model, the processing device 120 can obtain a plurality of superimposed models as described above, and select a preset assistive device digital model that matches the limb surface point cloud information from the superimposed models.

[0066] In step S714, the processing device 120 generates an assistive device digital model based on the limb surface point cloud information and the matched preset assistive device digital model. That is, the processing device 120 can adjust the appearance shape of the matched preset assistive device digital model based on the limb surface point cloud information, so that the appearance shape of the preset assistive device digital model can conform to the size of the limb surface point cloud information, and use the adjusted preset assistive device digital model as the assistive device digital model.

[0067] In step S716, the assistive device is generated according to the assistive device digital model by the three-dimensional printing device 130. In this way, the assistive device digital model of the wearable assistive device can be quickly established, thereby improving the assistive device design quality and shortening the production cycle of the customized assistive device.

[0068] Fig. 9 for Figure 7 Please also refer to the detailed flow chart of step S714. Figures 3 to 5 and 7 to 9. In step S902, the processing device 120 confirms the correspondence between the first shape corresponding to the limb surface point cloud information and the second shape corresponding to the matching preset assistive device digital model. In other words, the processing device 120 confirms the correspondence between the limb surface point cloud information and the appearance shape of the matching preset assistive device digital model as a basis for adjusting the preset assistive device digital model.

[0069] In step S904, when it is confirmed that the corresponding relationship is that the second shape is larger than the first shape, the processing device 120 adjusts the second shape of the preset assistive device digital model to match the first shape through the first algorithm to generate the assistive device digital model. In this embodiment, the first algorithm is, for example, a Boolean operation subtraction method. That is, when the size of the appearance shape of the matched preset assistive device digital model is larger than the size of the appearance shape of the limb surface point cloud information, the processing device 120 calculates the difference between the sizes of the appearance shapes, for example, through the Boolean operation subtraction method, and adjusts the second shape of the preset assistive device digital model to match the first shape based on the calculated difference, so as to generate the assistive device digital model.

[0070] In step S906, when it is confirmed that a portion of the second shape is larger than the first shape and another portion of the second shape is smaller than the first shape, or the second shape is smaller than the first shape, the processing device 120 adjusts the second shape of the preset assistive device digital model to match the first shape through a second algorithm to generate an assistive device digital model. In this embodiment, the second algorithm is, for example, a multi-layer contour method.

[0071] That is, when the size of the appearance shape of the matched preset assistive device digital model is partially or completely smaller than the size of the appearance shape of the limb surface point cloud information, the processing device 120 divides the appearance shape of the matched preset assistive device digital model into multi-layer cross sections by, for example, a multi-layer contour line method to obtain contour lines corresponding to the multi-layer cross sections, such as Fig.10 Then, the processing device 120 adjusts the contour lines of the above multi-layer cross-sections according to the limb surface point cloud information, so that the second shape of the preset assistive device digital model is adjusted to match the first shape, so as to generate the assistive device digital model. In this way, the assistive device digital model of the wearable assistive device can be quickly established, and the assistive device design quality can be improved and the production cycle of the customized assistive device can be shortened.

[0072] Fig.11 This is a flow chart of a method for modeling an auxiliary tool according to another embodiment of the present invention. Figures 3 to 5 In this embodiment, steps S702-716 and Figure 7 The steps S702 to S716 are the same or similar to those in Figure 7 The embodiments of the present invention are described in detail, so they will not be repeated here.

[0073] Following step S710, in step S1102, the processing device 120 determines whether the limb surface point cloud information matches at least one of the preset assistive device digital models. In other words, the processing device 120 determines whether there is a suitable preset assistive device digital model in the database.

[0074] When it is confirmed that the limb surface point cloud information matches at least one of the preset assistive device digital models, it means that the difference between the limb surface point cloud information and the preset assistive device digital model is small, and there is a suitable preset assistive device digital model in the database that can be used. Then, step S712 is entered to select the preset assistive device digital model that matches the limb surface point cloud information, and steps S714 to S716 are executed to generate a suitable assistive device.

[0075] When it is confirmed that the limb surface point cloud information does not match the preset assistive device digital model, it means that the limb surface point cloud information is significantly different from the preset assistive device digital model, and there is no suitable preset assistive device digital model in the database. Then, the process proceeds to step S1104, where the processing device 120 can process the limb surface point cloud information through a neural network to generate an assistive device digital model. In other words, the processing device 120 can process the limb surface point cloud information through a neural network to generate an assistive device digital model. Figure 6 Steps S604 to S610 are used to generate a suitable digital model of the auxiliary tool, that is, step S1104 of this embodiment may include Figure 6 Steps S604 to S610.

[0076] In the aforementioned embodiment, when the above step S1102 confirms that the limb surface point cloud information matches at least one of the preset assistive device digital models, the shape of the preset assistive device digital model can be adjusted by Boolean operation subtraction method or multi-layer contour line method to generate an assistive device digital model. This embodiment is only an implementation example of the embodiment of the present invention, but the embodiment of the present invention is not limited to this. In future assistive device modeling applications, the processing device 120 can use the above-mentioned neural network-like learning method to replace the Boolean operation subtraction method or the multi-layer contour line method to generate an assistive device digital model, which can also achieve a similar assistive device modeling effect.

[0077] In summary, the assistive device modeling method and limb guide mechanism disclosed in the embodiment of the present invention generate a plurality of learning data according to the limb surface point cloud information, and process the learning data through a quasi-neural network to generate an assistive device digital model. In addition, the embodiment of the present invention can also provide a limb guide mechanism provided with at least three positioning holes, and generate at least three positioning marks corresponding to the at least three positioning holes on the limb through the limb guide mechanism. Then, the limb is scanned to obtain the limb surface point cloud information including at least three positioning marks, and according to the at least three positioning marks of the limb surface point cloud information, the limb surface point cloud information is superimposed with a plurality of preset assistive device digital models obtained from the database, and the preset assistive device digital model matching the limb surface point cloud information is selected, and then the assistive device digital model is generated according to the limb surface point cloud information and the matching preset assistive device digital model. In this way, the assistive device digital model of the wearable assistive device can be effectively and quickly established, and the assistive device design quality can be improved and the production cycle of the customized assistive device can be shortened.

[0078] Although the present invention is disclosed as above by embodiments, it is not intended to limit the scope of the present invention. Any technician can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be based on the scope defined by the claims.

Claims

1. A method for modeling an assistive device, which is suitable for making an assistive device corresponding to a limb, and the method for modeling an assistive device is executed by a processing device and comprises the following steps: Obtaining limb surface point cloud information and a preset assistive device digital model, wherein the limb surface point cloud information includes at least three positioning marks; According to the coordinate system defined by the positioning marks of the limb surface point cloud information, the limb surface point cloud information is rotated to a plurality of different angles to generate a plurality of learning data corresponding to the original proportions, and the limb surface point cloud information is scaled proportionally, and then the scaled limb surface point cloud information is rotated to a plurality of different angles according to the rotation direction to generate a plurality of learning data for superimposing the preset assistive device digital model; as well as The limb surface point cloud information is compared with the preset assistive device digital model to confirm whether there is a preset assistive device digital model that matches the limb surface point cloud information. If yes, the preset assistive device digital model that matches the limb surface point cloud information is selected to generate an assistive device digital model. If not, the learning data is processed through a quasi-neural network to generate an assistive device digital model. The step of selecting the preset assistive device digital model that matches the limb surface point cloud information and generating the assistive device digital model comprises: Confirming a correspondence between a first shape corresponding to the limb surface point cloud information and a second shape corresponding to the matched preset assistive device digital model; When it is confirmed that the corresponding relationship is that the second shape is larger than the first shape, the second shape of the preset assistive device digital model is adjusted to match the first shape through a first algorithm to generate the assistive device digital model; When it is confirmed that the corresponding relationship is that a portion of the second shape is larger than the first shape and another portion of the second shape is smaller than the first shape, or the corresponding relationship is that the second shape is smaller than the first shape, the second shape of the preset assistive device digital model is adjusted to match the first shape through a second algorithm to generate the assistive device digital model.

2. The auxiliary tool modeling method according to claim 1, further comprising: At least three positioning marks corresponding to at least three positioning holes on the limb guide mechanism are generated by the limb guide mechanism.

3. The auxiliary tool modeling method according to claim 1, further comprising: The auxiliary tool is produced by a three-dimensional printing device according to the auxiliary tool digital model.

4. The assistive device modeling method as claimed in claim 1, wherein the step of obtaining the point cloud information corresponding to the limb surface comprises: The limb is scanned by a three-dimensional scanning device to obtain surface point cloud information of the limb corresponding to the limb.

5. A method for modeling an auxiliary tool, which is suitable for making an auxiliary tool corresponding to a limb, and the method for modeling an auxiliary tool comprises: Providing a limb guide mechanism, wherein the limb guide mechanism is provided with at least three positioning holes; At least three positioning marks corresponding to the at least three positioning holes are generated on the limb by the limb guide mechanism; A processing device is provided to perform the following steps: Scanning the limb to obtain point cloud information of the limb surface, wherein the point cloud information of the limb surface includes the at least three positioning marks; Obtain multiple preset digital models of assistive devices from the database; According to the coordinate system defined by the at least three positioning marks of the limb surface point cloud information and the preset coordinate system defined by the preset assistive device digital models, the limb surface point cloud information is rotated and proportionally scaled to be superimposed with the preset assistive device digital models; Comparing the limb surface point cloud information with the preset assistive device digital models and selecting a preset assistive device digital model that matches the limb surface point cloud information from the preset assistive device digital models; as well as According to the limb surface point cloud information and the matched preset assistive device digital model, an assistive device digital model is generated, the steps of which include: Confirming a correspondence between a first shape corresponding to the limb surface point cloud information and a second shape corresponding to the matched preset assistive device digital model; When it is confirmed that the corresponding relationship is that the second shape is larger than the first shape, the second shape of the preset assistive device digital model is adjusted to match the first shape through a first algorithm to generate the assistive device digital model; When it is confirmed that the corresponding relationship is that a portion of the second shape is larger than the first shape and another portion of the second shape is smaller than the first shape, or the corresponding relationship is that the second shape is smaller than the first shape, the second shape of the preset assistive device digital model is adjusted to match the first shape through a second algorithm to generate the assistive device digital model.

6. The auxiliary tool modeling method according to claim 5, further comprising: Confirming whether the limb surface point cloud information matches at least one of the preset assistive device digital models; When it is confirmed that the limb surface point cloud information matches at least one of the preset assistive device digital models, selecting the preset assistive device digital model that matches the limb surface point cloud information; and When it is confirmed that the limb surface point cloud information does not match the preset assistive device digital models, the limb surface point cloud information is processed through a quasi-neural network to generate the assistive device digital model.

7. The assistive device modeling method as claimed in claim 6, wherein the step of processing the limb surface point cloud information through the neural network to generate the assistive device digital model comprises: According to the point cloud information of the limb surface, a plurality of learning data are generated; as well as The learning data are processed by this type of neural network to generate the digital model of the auxiliary tool.

8. The assistive device modeling method as claimed in claim 7, wherein the step of generating the learning data according to the limb surface point cloud information comprises: According to the at least three positioning marks, the limb surface point cloud information is turned to a preset position; as well as The limb surface point cloud information is rotated to a plurality of different angles and scaled proportionally to generate the learning data. 9 . The auxiliary tool modeling method as claimed in claim 5 , wherein the first algorithm is a Boolean operation subtraction method, and the second algorithm is a multi-layer contour method.

10. The auxiliary tool modeling method according to claim 5, further comprising: The auxiliary tool is produced according to the auxiliary tool digital model by a three-dimensional printing device.

11. The assistive device modeling method as claimed in claim 5, wherein the step of scanning the limb to obtain the point cloud information of the limb surface comprises: The limb is scanned by a three-dimensional scanning device to obtain point cloud information of the limb surface.

12. A limb guide mechanism, comprising: ontology; as well as At least three positioning holes are arranged on the body, and the positions of the at least three positioning holes are different from each other, and the connection length between two positioning holes of the at least three positioning holes is set to be less than or equal to a preset distance, wherein, At least three positioning marks corresponding to the at least three positioning holes are generated on the limb by the limb guide mechanism, so that the limb surface point cloud information includes the at least three positioning marks, and the limb surface point cloud information is superimposed with a preset assistive device digital model based on the at least three positioning marks of the limb surface point cloud information, and a preset assistive device digital model matching the limb surface point cloud information is selected to generate an assistive device digital model, the steps of which include: Confirming a correspondence between a first shape corresponding to the limb surface point cloud information and a second shape corresponding to the matched preset assistive device digital model; When it is confirmed that the corresponding relationship is that the second shape is larger than the first shape, the second shape of the preset assistive device digital model is adjusted to match the first shape through a first algorithm to generate the assistive device digital model; When it is confirmed that the corresponding relationship is that a portion of the second shape is larger than the first shape and another portion of the second shape is smaller than the first shape, or the corresponding relationship is that the second shape is smaller than the first shape, the second shape of the preset assistive device digital model is adjusted to match the first shape through a second algorithm to generate the assistive device digital model.

13. The limb guide mechanism of claim 12, wherein at least one of the at least three positioning holes corresponds to a joint point of the limb.

14. A limb guide mechanism as described in claim 13, wherein when the connection length between two of the at least three positioning holes is less than or equal to the preset distance, the two positioning holes maintain the joint points corresponding to the limb respectively, and when the connection length between two of the at least three positioning holes is greater than the preset distance, the position of one of the two positioning holes is adjusted so that the adjusted connection length between the two positioning holes is less than or equal to the preset distance.

Images