Assist device printing method and device, electronic equipment, storage medium and computer program product

Abstract

The invention provides an assist device printing method and device, electronic equipment, a storage medium and a computer program product, and the method comprises the steps: obtaining a first physiological data set of a first user; calling a first artificial intelligence model to process the first physiological data set to obtain a first constraint parameter set; the first artificial intelligence model is used for recommending a constraint parameter group based on an input physiological data group; the constraint parameter set represents constraints related to the mechanical performance requirements corresponding to the input physiological data set; taking the first constraint parameter group as a constraint, and calling a generative design algorithm to process the first physiological data group to obtain a first design parameter group; the generative design algorithm is used for generating a design parameter set meeting the corresponding comfort requirement based on the input physiological data set, and the design parameter set comprises a plurality of design parameters of the assist device; and generating a first file based on the first design parameter group and the slice parameter group, and outputting the first file to the three-dimensional printing device.

Description

Cross Reference to Related Applications

[0001] This application is based on the Chinese patent application No. 202510888877.7, filed on June 30, 2025, and claims priority to the Chinese patent application No. 202510888877.7, and the whole content of the Chinese patent application No. 202510888877.7 is incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to the technical field of computer, and in particular, to an auxiliary device printing method and device, electronic device, storage medium and computer program product. BACKGROUND

[0003] In the related art, a three-dimensional digital model of an auxiliary device, i.e., an auxiliary device model, is generated based on a manually designed manner, and then a three-dimensional printing device is used to print the generated auxiliary device model to convert the auxiliary device model into a physical entity to obtain a printed auxiliary device. In actual applications, in the process of generating the auxiliary device model, a plaster bandage is used by a designer to wrap and form on the surface of a part to be worn with the auxiliary device, and plaster is poured to obtain a mold of the part, and then a computer aided design (CAD) or other digital design software is used to model an auxiliary device that is adapted to the mold of the part based on the structure measurement data of the mold of the part, to obtain an auxiliary device model, and then the auxiliary device model is adjusted multiple times according to the adaptation simulation of the auxiliary device model and the mold of the part to obtain a finally generated auxiliary device model. However, for customized auxiliary devices, the efficiency of manual design is low, which affects the printing efficiency of the auxiliary device. SUMMARY

[0004] To solve the problems in the related art, the embodiments of the present application provide an auxiliary device printing method, device, electronic device, storage medium and computer program product.

[0005] The technical solutions of the embodiments of the present application are implemented as follows: The embodiments of the present application provide an auxiliary device printing method, which comprises: obtaining a first physiological data set of a first user; the first physiological data set is used to determine the mechanical performance requirement and the comfort requirement of a first auxiliary device required by the first user; calling a first artificial intelligence model to process the first physiological data set to obtain a first constraint parameter set; the first artificial intelligence model is used to recommend a constraint parameter set based on an input physiological data set; the constraint parameter set represents the constraint related to the mechanical performance requirement corresponding to the input physiological data set; call a generative design algorithm to process the first physiological data set by taking the first constraint parameter set as a constraint, to obtain a first design parameter set; the generative design algorithm is used to generate a design parameter set meeting the corresponding comfort requirement based on an input physiological data set, and the design parameter set contains multiple design parameters of the assistive device; generate a first file based on the first design parameter set and a slicing parameter set, and output the first file to a three-dimensional printing device; the slicing parameter set is used to configure the printing parameters of the three-dimensional printing device; and the first file is used to control the three-dimensional printing device to print out the first assistive device.

[0006] The embodiment of the present application also provides an assistive device printing device, which comprises: An acquisition unit is configured to acquire a first physiological data set of a first user; the first physiological data set is used to determine the mechanical performance requirement and the comfort requirement of a first assistive device required by the first user; A first calling unit is configured to call a first artificial intelligence model to process the first physiological data set, to obtain a first constraint parameter set; the first artificial intelligence model is used to recommend a constraint parameter set based on an input physiological data set; and the constraint parameter set represents the constraint related to the mechanical performance requirement corresponding to the input physiological data set; A second calling unit is configured to call a generative design algorithm to process the first physiological data set by taking the first constraint parameter set as a constraint, to obtain a first design parameter set; the generative design algorithm is used to generate a design parameter set meeting the corresponding comfort requirement based on an input physiological data set, and the design parameter set contains multiple design parameters of the assistive device; A generating unit is configured to generate a first file based on the first design parameter set and a slicing parameter set, and output the first file to a three-dimensional printing device; the slicing parameter set is used to configure the printing parameters of the three-dimensional printing device; and the first file is used to control the three-dimensional printing device to print out the first assistive device.

[0007] The embodiment of the present application also provides an electronic device, which comprises a processor and a memory for storing a computer program capable of running on the processor, When the processor runs the computer program, the processor is configured to execute the steps of the foregoing method.

[0008] The present application also provides a storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the steps of the foregoing method.

[0009] The present application also provides a computer program product comprising a computer program, and the computer program is executed by a processor to implement the steps of the foregoing method.

[0010] In the embodiment of the present application, a first physiological data set of the first user is obtained, which is used to determine the mechanical performance requirement and the comfort requirement of the first assistive device required by the first user; then, a first artificial intelligence model is called to process the first physiological data set, to obtain a first constraint parameter set, the first artificial intelligence model being used to recommend a constraint parameter set based on an input physiological data set, the constraint parameter set representing a constraint related to the mechanical performance requirement corresponding to the input physiological data set; then, the first constraint parameter set is taken as a constraint, and a generative design algorithm is called to process the first physiological data set, to obtain a first design parameter set, wherein the generative design algorithm is used to generate a design parameter set meeting the corresponding comfort requirement based on an input physiological data set, and the design parameter set contains multiple design parameters of the assistive device; then, based on the first design parameter set and a slicing parameter set, a first file is generated and output to a three-dimensional printing device, the slicing parameter set being used to configure the printing parameters of the three-dimensional printing device, and the first file being used to control the three-dimensional printing device to print the first assistive device. In the above scheme, the first artificial intelligence model is called to process the physiological data set of the first user to obtain the constraint parameter set, and then the constraint parameter set is taken as a constraint of the generative design algorithm to drive the generative design algorithm to output the design parameter set corresponding to the assistive device to be printed, and on this basis, the first file is generated, so that the three-dimensional printing device prints the first assistive device. In this way, the printed first assistive device can meet the mechanical performance requirement of the assistive device required by the first user, and can also meet the comfort requirement of the assistive device required by the first user; that is, by driving the generative design algorithm by the artificial intelligence model, the design parameters of the assistive device required by the user are automatically determined based on the physiological data set of the user, compared with the related art, the design parameters of the customized assistive device can be determined without manual design, thereby improving the printing efficiency of the assistive device. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 An implementation flowchart of a printing method provided by the embodiment of the present application is shown; Figure 2 A flowchart of a printing method provided by the application embodiment is shown; Figure 3 A structural schematic diagram of a printing device provided by the embodiment of the present application is shown; Figure 4 A hardware composition structural schematic diagram of an electronic device provided by the embodiment of the present application is shown. DETAILED DESCRIPTION

[0012] In the related art, a three-dimensional digital model of an assistive device, i.e., an assistive device model, is generated based on a manual design method; then, the generated assistive device model is printed by using a three-dimensional printing device, to convert the assistive device model into an entity, to obtain a printed assistive device.

[0013] In actual application, the auxiliary device can be used to provide rehabilitation assistance for the affected part of the wearer. For example, the affected part can include a residual limb, and the auxiliary device can be used to replace the corresponding defective part of the residual limb or correct the deformed part of the residual limb.

[0014] In actual application, in the process of generating the auxiliary device model, the designer uses a plaster bandage to wrap and form on the surface of the affected part of the auxiliary device to be worn, and pours plaster to obtain a mold of the affected part. Then, based on the structure measurement data of the mold of the affected part, a computer-aided design (CAD) or other digital design software is used to model an auxiliary device adapted to the mold of the affected part to obtain an auxiliary device model. Then, the auxiliary device model is adjusted multiple times according to the adaptation simulation of the auxiliary device model and the mold of the affected part to obtain the finally generated auxiliary device model. However, for customized auxiliary devices, the efficiency of manual design is low, which affects the printing efficiency of the auxiliary device.

[0015] Therefore, in the embodiments of the present application, the first physiological data set of the first user is obtained, which is used to determine the mechanical performance requirement and the comfort requirement of the first auxiliary device required by the first user. Then, the first artificial intelligence model is called to process the first physiological data set to obtain the first constraint parameter set. The first artificial intelligence model is used to recommend a constraint parameter set based on the input physiological data set. The constraint parameter set represents the constraint related to the mechanical performance requirement corresponding to the input physiological data set. Then, the generative design algorithm is called to process the first physiological data set with the first constraint parameter set as a constraint to obtain the first design parameter set. The generative design algorithm is used to generate a design parameter set that meets the corresponding comfort requirement based on the input physiological data set. The design parameter set includes multiple design parameters of the auxiliary device. Then, based on the first design parameter set and the slicing parameter set, the first file is generated and output to the three-dimensional printing device. The slicing parameter set is used to configure the printing parameters of the three-dimensional printing device. The first file is used to control the three-dimensional printing device to print the first auxiliary device. In the above scheme, the first artificial intelligence model is called to process the physiological data set of the first user to obtain the constraint parameter set. Then, the constraint parameter set is used as a constraint for the generative design algorithm to drive the generative design algorithm to output the design parameter set corresponding to the auxiliary device to be printed. Based on this, the first file is generated, so that the three-dimensional printing device prints the first auxiliary device. In this way, the printed first auxiliary device can meet the mechanical performance requirement of the auxiliary device required by the first user and the comfort requirement of the auxiliary device required by the first user. That is, by driving the generative design algorithm with the artificial intelligence model, the design parameters of the auxiliary device required by the user are automatically determined based on the physiological data set of the user. Compared with related technologies, the design parameters of the customized auxiliary device can be determined without manual design, thereby improving the printing efficiency of the auxiliary device.

[0016] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.

[0017] This application provides an auxiliary printing method, see [link to relevant documentation]. Figure 1 The method includes: Step 101: Obtain the first physiological data set of the first user.

[0018] The first set of physiological data is used to determine the mechanical performance and comfort requirements of the first assistive device required by the first user.

[0019] Here, the first user can be understood as a user who needs to use an assistive device, the first physiological data set can be understood as the physiological data set of the first user, and the first assistive device can be understood as the customized assistive device required by the first user.

[0020] In practical applications, assistive devices can be characterized as one or more of the following: prostheses, orthotics.

[0021] In one embodiment, the first assistive device is characterized as one or more of the following: a prosthesis, an orthosis.

[0022] In practical applications, orthotics can be used to improve limb shape by supporting, protecting, correcting or compensating for limb structure.

[0023] Prostheses can be used to replace missing limb parts, thereby providing support, protection, correction, or compensation for the remaining limb parts, and can also be considered as tools to improve limb morphology. Therefore, in practical applications, prostheses can also be regarded as orthotics. For example, prostheses can include orthotic prostheses.

[0024] In practical applications, the first assistive device can be characterized as both a prosthesis and an orthosis.

[0025] In practical applications, physiological data sets can be used to describe a user's physiological condition. Physiological data sets can include various types of physiological data. For example, a physiological data set can include, but is not limited to, one or more of the following types of physiological data corresponding to the user: age, height, weight, body fat percentage, scan data of the affected area, scan data of the healthy limb, and exercise ability assessment data; the affected area can include the stump.

[0026] For multiple users with different physiological conditions, the mechanical performance and comfort requirements of the customized assistive device required by each user may be different. Each user's physiological data set can be used to determine the mechanical performance and comfort requirements of the customized assistive device required by that user.

[0027] For example, for a user weighing 100 kg with a leg disability, the mechanical performance requirements of the assistive device required by this user may include: supporting a load of 120 kg, and the comfort requirements of the assistive device required by this user may include: the assistive device weighing less than 10 kg; wherein, supporting the load or the weight of the assistive device can be understood as a requirement item, and 120 kg or 10 kg can be understood as the requirement content corresponding to the requirement item. For a user weighing 50 kg with a leg disability, the mechanical performance requirements of the assistive device required by this user may include: supporting a load of 70 kg, and the comfort requirements of the assistive device required by this user may include: the assistive device weighing less than 5 kg.

[0028] In practical applications, the requirements for mechanical performance or comfort can be determined based on common standards within the assistive device manufacturing industry, and the specific requirements can be determined based on the user's physiological data set. Both the mechanical performance and comfort requirements, and the specific requirements, can be determined based on the user's physiological data set.

[0029] In practical applications, multiple design parameters for the assistive device required by the user can be determined based on the user's physiological data set. These design parameters can then be used to determine the corresponding assistive device model, thereby realizing the design of the assistive device required by the user. For example, the multiple design parameters can at least describe one or more of the following related to the assistive device: style, type, part selection, material thickness, component shape, and component structure.

[0030] It should be noted that the assistant model in this application embodiment refers to the three-dimensional digital model of the assistant, rather than a physical entity. By printing the assistant model, the three-dimensional digital model represented by the assistant model can be converted into a physical entity, resulting in the printed assistant.

[0031] In practical applications, the specific process of determining multiple design parameters of the first assistive device required by the first user based on the first set of physiological data can be found in steps 102 and 103, which will be explained in detail below.

[0032] Step 102: Call the first artificial intelligence model to process the first physiological data set to obtain the first constraint parameter set.

[0033] The first artificial intelligence model is used to recommend a set of constraint parameters based on the input set of physiological data; the set of constraint parameters represents the constraints related to the mechanical performance requirements corresponding to the input set of physiological data.

[0034] In practical applications, during the process of determining multiple design parameters of the auxiliary device, the constraint parameter set recommended by the first artificial intelligence model can provide constraints for the process, so that the auxiliary device corresponding to the determined design parameters can meet the mechanical performance requirements corresponding to the constraint parameter set.

[0035] In practical applications, the model architecture of the first artificial intelligence model can be flexibly configured according to the actual business scenario of the assistant printer, so as to balance the processing accuracy, scalability and computing efficiency of the first artificial intelligence model.

[0036] For example, in scenarios with high precision requirements or sufficient computing resources, the first artificial intelligence model can adopt a model architecture that integrates a large model architecture and a composite inference mechanism. This model architecture can be built on the basis of the large model architecture by combining multiple modular architectures.

[0037] In practical applications, multiple modular architectures can work together based on multiple sub-mechanisms, with each modular architecture corresponding to one sub-mechanism.

[0038] These sub-mechanisms may include: Mixture of Experts (MoE), Chain of Thought (CoT), Supervised Fine-Tuning (SFT), and Multi-Choice Prompting (MCP).

[0039] The multi-expert scheduling mechanism can integrate expert sub-models into the same model framework. Then, the gating network automatically activates the most suitable sub-model based on the input data to enhance the system's generalization ability under diverse user conditions.

[0040] Chain-based reasoning mechanisms can introduce step-by-step decision-making logic into the processing, outputting constraint parameter sets through a multi-stage thinking approach, thereby improving the interpretability and flexibility of the reasoning path. This mechanism is suitable for decision-making tasks involving complex multi-factor interactions, such as material selection and mechanical support structure design.

[0041] Supervised fine-tuning training mechanisms can be trained based on mechanical performance test data to ensure that the model has higher prediction accuracy and real-world adaptability.

[0042] The multi-selection suggestion mechanism can provide several candidate solutions for key parameter outputs, such as material schemes and printing path strategies. The model can recommend the optimal solution, or it can support manual selection to realize human-machine collaborative optimization process.

[0043] In scenarios with limited computing resources, the first AI model can adopt a lightweight and mature model architecture. For example, this model architecture can include regression models or deep neural network models.

[0044] It should be noted that the architecture in this example is only for illustrating the possible architecture settings. In actual applications, the first artificial intelligence model may not be limited to the architecture in this example.

[0045] Step 103: Using the first set of constraint parameters as constraints, call the generative design algorithm to process the first set of physiological data to obtain the first set of design parameters.

[0046] Among them, the generative design algorithm is used to generate a set of design parameters that meet the corresponding comfort requirements based on the input set of physiological data, and the set of design parameters contains multiple design parameters of the assistive device.

[0047] In practical applications, generative design algorithms can be built based on the design experience of assistant designers.

[0048] In practical applications, if only one aspect—mechanical performance or comfort—is considered when designing an assistive device, it may negatively impact the other. For example, designing an assistive device with a thicker material may improve mechanical performance, but it will increase the overall weight of the assistive device, thereby reducing its comfort.

[0049] Here, the first set of constraint parameters is used as a constraint, and the generative design algorithm is called to process the first set of physiological data. Based on this, the first set of constraint parameters can provide constraints for the processing of the generative design algorithm, so that the first set of design parameters recommended by the generative design algorithm can balance comfort and mechanical performance. In this way, the assistive device corresponding to the first set of design parameters can meet both the corresponding mechanical performance requirements and the corresponding comfort requirements, thus adapting to the corresponding user.

[0050] Here, the first set of constraint parameters is recommended by the first artificial intelligence model. Therefore, using the first set of constraint parameters as constraints to call the generative design algorithm to process the first physiological data set can also be regarded as using the first artificial intelligence model to drive the generative design algorithm to process the first physiological data set.

[0051] In practical applications, when using the first set of constraint parameters as constraints to call the generative design algorithm to process the first set of physiological data, the generative design algorithm can be called to process both the first set of physiological data and the first set of constraint parameters. That is, both the first set of constraint parameters and the first set of physiological data are input into the generative design algorithm.

[0052] It should be noted that the constraint parameter set output by the first artificial intelligence model in this embodiment does not affect the underlying logic of the generative design algorithm, but rather influences the design parameters output by the generative design algorithm through constraints.

[0053] Step 104: Based on the first design parameter group and the slicing parameter group, generate the first file and output the first file to the 3D printing device.

[0054] Among them, the slice parameter group is used to configure the printing parameters of the 3D printing device; the first file is used to control the 3D printing device to print the first auxiliary device.

[0055] In practical applications, the first set of design parameters can be used to determine the auxiliary device model of the first auxiliary device. Based on the first set of design parameters, the generated first file can describe the auxiliary device model of the first auxiliary device. Thus, outputting the first file to a 3D printing device allows the 3D printing device to print the auxiliary device model described in the first file, thereby printing the first auxiliary device.

[0056] The auxiliary model described in the first document can be divided into multiple slices. During the printing process based on the first document, the 3D printing device can print these slices layer by layer. By configuring the printing parameters of the 3D printing device, the printing method of the 3D printing device for the multiple slices corresponding to the 3D digital model can be controlled.

[0057] Here, the slice parameter group is used to configure the printing parameters of the 3D printing device. For example, the slice parameter group can be used to configure at least one or more of the following printing parameters of the 3D printing device: print layer height, print speed, print temperature, infill density, shell thickness, and wiring path.

[0058] In practical applications, the first file generated based on the slice parameter group can describe the slice parameter group. Thus, by outputting the first file to the 3D printing device, the printing parameters of the 3D printing device can be configured, thereby controlling the printing method of the 3D printing device for multiple slices corresponding to the auxiliary model.

[0059] In practical applications, the file type corresponding to the first file can include: GCode (Geometric Code) or X3G (MakerBot Print), etc.

[0060] Here, outputting the first file to the 3D printing device can be understood as inputting the generated first file into the 3D printing device, so that the 3D printing device can print based on the first file.

[0061] In practical applications, the first file can be input into the 3D printing device manually via physical transmission, or it can be input into the 3D printing device wirelessly, thereby reducing manual intervention and improving the efficiency of the auxiliary printing process.

[0062] In practical applications, after the first set of design parameters and slicing parameters are determined, the process of generating the first file and outputting the first file to the 3D printing device can be carried out automatically. This reduces manual intervention, improves the automation level from auxiliary device design to auxiliary device printing, and thus improves the printing efficiency of the auxiliary device. In this embodiment, a first artificial intelligence model is invoked to process the physiological data set of a first user to obtain a constraint parameter set. This constraint parameter set is then used as a constraint on a generative design algorithm, driving the algorithm to output a design parameter set corresponding to the assistive device to be printed. Based on this, a first file is generated, enabling the 3D printing device to print the first assistive device. Thus, the printed first assistive device meets both the mechanical performance and comfort requirements of the first user. In other words, by using an artificial intelligence model to drive the generative design algorithm, the design parameters of the assistive device required by the user are automatically determined based on the user's physiological data set. Compared to related technologies, this eliminates the need for manual design to determine the design parameters of customized assistive devices, thereby improving printing efficiency. Therefore, in practical applications, even when large-scale production of customized assistive devices is required, these devices can be printed efficiently, ensuring the compatibility between the customized assistive devices and the user.

[0063] In practical applications, the slice parameter set can be automatically determined based on the first user's first physiological data set, thereby further improving the printing efficiency of the assistant and making the first assistant have better mechanical performance and comfort.

[0064] The method for determining the slice parameter group is explained further below.

[0065] In one embodiment, the first artificial intelligence model is also used to recommend a set of slice parameters based on the input set of physiological data; Correspondingly, based on the first design parameter set and the slice parameter set, a first file is generated, including: Based on the first design parameter set and the first slice parameter set, a first file is generated; the first slice parameter set represents the slice parameter set obtained by calling the first artificial intelligence model to process the first physiological data set.

[0066] In practical applications, when the first artificial intelligence model is called to process the first physiological data set, the first artificial intelligence model can output the first constraint parameter set and the first slice parameter set at the same time.

[0067] In practical applications, the settings of the slicing parameter group can affect the mechanical performance and comfort of the first assistive device. For example, if the 3D printing device is configured with a lower layer height, the printed first assistive device will have a thinner wall thickness, which may not be sufficient to support the first user's mobility and may easily be damaged during daily use, thus failing to meet the mechanical performance requirements of the first user. If the 3D printing device is configured with a higher infill density, the printed first assistive device will be heavier, which may result in a greater burden on the first user, thus failing to meet the comfort requirements of the first user.

[0068] In this embodiment, based on the processing of the first physiological data set by the first artificial intelligence model, a slice parameter set is determined, thereby improving the matching degree between the slice parameter set and the physiological condition of the first user. This allows the first assistive device printed based on the slice parameter set to more evenly meet the mechanical performance and comfort requirements of the first user, improving the adaptability between the first assistive device and the first user. Furthermore, the processing of the first artificial intelligence model automates the process of determining the slice parameter set, avoiding manual intervention when configuring the printing parameters of the 3D printing device, thus further improving the printing efficiency of the assistive device.

[0069] In one embodiment, after processing the first physiological data set using a generative design algorithm with the first set of constraint parameters as constraints to obtain the first set of design parameters, the assistive device printing method provided in this application further includes: The second artificial intelligence model is invoked to process the first physiological data set and the first design parameter set to obtain a first processing result, which characterizes the force distribution of the first assistive device; the second artificial intelligence model is used to predict the force distribution of the assistive device corresponding to the input design parameter set based on the input physiological data set. Based on the first processing result, determine the second slice parameter group; Correspondingly, based on the first design parameter set and the slice parameter set, a first file is generated, including: The first file is generated based on the first design parameter group and the second slice parameter group.

[0070] In practical applications, a second artificial intelligence model can be used to simulate the user usage of the auxiliary device corresponding to the input design parameter set, thereby predicting the force distribution of the auxiliary device.

[0071] The force distribution predicted by the second artificial intelligence model may include one or more of the following information for the corresponding auxiliary device: the location of the force, the mode of force application, the changes in force during movement, and the vulnerable areas.

[0072] During the simulation process, the second artificial intelligence model can simulate the usage of the corresponding user based on the input physiological data set, so that the determined force distribution is close to the actual usage of the user; on this basis, the determined slice parameter set can further improve the mechanical performance of the assistive device while ensuring comfort.

[0073] In practical applications, the second artificial intelligence model can adopt the same architecture as the first artificial intelligence model, or it can adopt other architectures; there are no restrictions here.

[0074] In practical applications, the second slice parameter set can be generated directly based on the determined force distribution; alternatively, the determined slice parameter set can be optimized based on the force distribution to obtain the optimized slice parameter set, which is the second slice parameter set.

[0075] In one embodiment, determining the second slice parameter set based on the first processing result includes: Based on the first processing result, the first slice parameter group is optimized to obtain the second slice parameter group; the first slice parameter group represents the slice parameter group obtained by calling the first artificial intelligence model to process the first physiological data group.

[0076] In practical applications, a first artificial intelligence model can be used to process the first set of physiological data to obtain a first set of slice parameters. Then, based on the processing results, the first set of slice parameters can be optimized to obtain a second set of slice parameters. The second set of slice parameters is determined through joint generation and optimization, thereby improving the mechanical performance of the first assistive device while ensuring comfort.

[0077] In practical applications, the processing power of the first artificial intelligence model can be affected by the training method. The training method of the first artificial intelligence model will be further explained below.

[0078] In one embodiment, before invoking the first artificial intelligence model to process the first physiological data set, the assistive device printing method provided in this application embodiment further includes: Generative design algorithms are called to process multiple preset second physiological data sets to obtain multiple second design parameter sets, and multiple second assistive devices are printed based on the multiple second design parameter sets; the multiple preset second physiological data sets are determined based on the different physiological conditions of the target population for the assistive devices; Acquire first test data; the first test data represents the test data obtained by performing mechanical performance tests on multiple second auxiliary devices respectively; The first artificial intelligence model is trained based on multiple pre-set second physiological data sets and first test data.

[0079] In practical applications, each of the multiple printed second aids can correspond to a second set of design parameters, that is, a set of physiological data.

[0080] After printing out multiple second aids, mechanical performance tests can be performed on each of these second aids to obtain first test data, which can also be understood as mechanical performance test data. Then, a training dataset is constructed based on multiple preset second physiological data sets and the first test data. The first artificial intelligence model is then trained based on this training dataset, so that the first artificial intelligence model learns the relationship between different physiological conditions of users and the design parameters of the aids that meet the corresponding mechanical performance requirements, thereby providing appropriate constraints for generative design algorithms.

[0081] In practical applications, the user group of the assistive device can be determined based on the user group that provides business support services for the assistive device in the actual application. The various physiological conditions corresponding to the user group of the assistive device can be regarded as constituting the physiological data processing range corresponding to the generative design algorithm. This physiological data processing range can also be described as the algorithm generation range.

[0082] For example, assuming that the heaviest user among assistive device users weighs 200kg and the lightest user weighs 30kg, then, among the various physiological conditions corresponding to assistive device users, the maximum and minimum weight values ​​are 200kg and 30kg respectively. The weight-related algorithm generation range corresponding to the generative design algorithm can be from 30kg to 200kg.

[0083] Here, multiple pre-defined second physiological data sets are determined based on different physiological conditions of the target population for the assistive device. In this way, the training data in the constructed training dataset can be as relevant as possible to the physiological data processing range corresponding to the generative design algorithm, thereby increasing the comprehensiveness of the training data and making the training data fit the actual processing scenario, improving the training effect of the first artificial intelligence model and enhancing the processing capability of the trained first artificial intelligence model.

[0084] For example, when the weight-related algorithm generation range corresponding to the generative design algorithm is 30kg to 200kg, each of the preset multiple second physiological data groups can contain one weight data, and the maximum value of the multiple weight data corresponding to the preset multiple second physiological data groups is 200kg and the minimum value is 30kg.

[0085] In one embodiment, multiple second auxiliary devices are printed based on multiple sets of second design parameters, including: Multiple first auxiliary models are selected from multiple auxiliary models corresponding to multiple second design parameter groups. The failure probability of the auxiliary models corresponding to the multiple first auxiliary models is higher than that of the auxiliary models corresponding to the second auxiliary models. The second auxiliary models represent the other auxiliary models besides the first auxiliary models among the multiple auxiliary models corresponding to multiple second design parameter groups. The 3D printing device is controlled to print multiple first auxiliary models to produce multiple second auxiliary models.

[0086] In practical applications, after determining multiple sets of second design parameters, the auxiliary device designs that are prone to damage can be selected from the auxiliary device models corresponding to these sets of second design parameters, that is, multiple first auxiliary device models can be selected. Then, the multiple first auxiliary device models are printed to obtain multiple second auxiliary devices. Then, the mechanical performance of these second auxiliary devices is tested to obtain first test data. Then, the first artificial intelligence model is trained based on the mechanical performance test data of the easily damaged auxiliary devices and the corresponding physiological data sets.

[0087] The probability of failure of the auxiliary device corresponding to the second set of design parameters can be determined based on the experience of the auxiliary device designer or through simulation.

[0088] In practical applications, the mechanical performance test data of easily damaged assistive devices can typically reflect the relationship between physiological data and the mechanical performance of assistive devices. If the first artificial intelligence model is trained based solely on these mechanical performance test data and the corresponding physiological data, it can also achieve training results. At the same time, compared with all assistive device models corresponding to multiple second design parameter groups, the selected first assistive device model reduces the number of assistive devices that need to be printed during the construction of the training set, shortens the printing time, and thus reduces training costs and improves training efficiency while ensuring training results.

[0089] In one embodiment, multiple second auxiliary devices are printed based on multiple sets of second design parameters, including: Based on multiple sets of second design parameters and each of the multiple sets of third slice parameters preset, the 3D printing device is controlled to print multiple auxiliary models corresponding to the multiple sets of second design parameters, so as to print multiple second auxiliary models. Among them, the preset multiple third slice parameter groups are determined based on different configurations of printing parameters supported by the 3D printing device.

[0090] In practical applications, after determining the multiple auxiliary device models to be printed corresponding to the second set of design parameters, for each auxiliary device model, the 3D printing device can be controlled to print the auxiliary device model based on each of the multiple third slice parameter sets, thereby obtaining multiple second auxiliary devices corresponding to that auxiliary device model. Thus, the printed multiple second auxiliary devices also correspond to different slice parameter sets. Based on this, the training dataset constructed using corresponding mechanical performance test data and physiological parameter sets allows the first artificial intelligence model to learn the relationship between the slice parameter sets and physiological parameter sets, enhancing the first artificial intelligence model's ability to recommend slice parameter sets.

[0091] In practical applications, during the training of the first artificial intelligence model, the generative design algorithm can be optimized based on the training results to improve its processing capabilities.

[0092] In practical applications, the training method of the second artificial intelligence model can also be understood by referring to the training method of the first artificial intelligence model.

[0093] In this embodiment of the application, the first artificial intelligence model used to process the first physiological data set of the first user can be regarded as the first artificial intelligence model that has been trained. In practical applications, after the first aid device is printed out, the mechanical performance of the first aid device can be tested to obtain test data. The training dataset is then updated based on the test data and the first physiological data set. The first artificial intelligence model is then retrained based on the updated training dataset to further enhance the processing capability of the first artificial intelligence model and improve the compatibility between the subsequently printed aid device and the user.

[0094] The present application will be further described in detail below with reference to application examples.

[0095] This application provides an auxiliary printing method, see the following embodiments. Figure 2 The processing flow corresponding to this auxiliary printing method mainly includes the following steps: Step 1: Construct a generative design algorithm.

[0096] In practical applications, generative design algorithms can be built based on the design experience of assistant designers.

[0097] Step 2: Generate multiple auxiliary device models based on multiple preset physiological data sets.

[0098] Here, the preset multiple physiological data sets are equivalent to the multiple second physiological data sets in the embodiments of this application, and the generated multiple auxiliary device models are equivalent to the multiple auxiliary device models corresponding to the multiple second design parameter sets in the embodiments of this application. These auxiliary device models can be multiple auxiliary device models that are selected as easily damaged.

[0099] In practical applications, multiple pre-set physiological data sets can be determined based on the different physiological conditions of the target population for the assistive device.

[0100] Step 3: Print the generated multiple helper models according to each of the preset multiple slice parameter groups to obtain multiple printed helpers.

[0101] Here, the preset multiple slice parameter groups are equivalent to the multiple third slice parameter groups in the embodiments of this application, and the multiple printed assistants are equivalent to the multiple second assistants in the embodiments of this application.

[0102] Step 4: Perform mechanical performance tests on the printed auxiliary devices to obtain mechanical performance test data.

[0103] In practical applications, a training dataset can be constructed based on the obtained mechanical performance test data and the corresponding physiological data set.

[0104] Step 5: Train the first artificial intelligence model based on the constructed training dataset.

[0105] In practical applications, the first artificial intelligence model can be used to recommend a set of constraint parameters based on the input physiological data set. This set of constraint parameters can then be used to constrain generative design algorithms, thus obtaining a generative design algorithm driven by the first artificial intelligence model.

[0106] Step 6: Call the first artificial intelligence model to process the first physiological data set of the first user to obtain the first constraint parameter set.

[0107] Here, the first set of constraint parameters can be understood as the set of constraint parameters recommended by the first artificial intelligence model based on the first set of physiological data.

[0108] The first set of physiological data can be used to determine the mechanical performance and comfort requirements of the first assistive device required by the first user.

[0109] Step 7: Using the first set of constraint parameters as constraints, call the generative design algorithm to process the first set of physiological data to obtain the first set of design parameters.

[0110] Here, the first set of design parameters can be understood as multiple design parameters recommended by the generative design algorithm. In practical applications, the assistive device corresponding to the first set of design parameters can meet both the comfort requirements corresponding to the first set of physiological data and the corresponding mechanical performance requirements.

[0111] Step 8: Determine the slice parameter group corresponding to the first physiological data group.

[0112] In practical applications, the first set of physiological data can be processed using a first artificial intelligence model to determine the first set of constraint parameters and the corresponding slice parameter set. Alternatively, a second artificial intelligence model can be used to process the first set of physiological data and the first set of design parameters to obtain the force distribution of the first assistive device required by the first user, and then the second slice parameter set can be determined based on this force distribution.

[0113] The second artificial intelligence model can be used to predict the force distribution of the assist device corresponding to the input design parameter set based on the input physiological data.

[0114] Step 9: Based on the first design parameter set and the slicing parameter set, control the 3D printing device to print the first auxiliary device.

[0115] In practical applications, a GCode file can be generated based on the first design parameter group and the slicing parameter group, and the GCode file can be output to the 3D printing device so that the 3D printing device can print out the first auxiliary device. The first auxiliary device can meet the mechanical performance requirements and comfort requirements of the first user, that is, it is adapted to the first user.

[0116] In this application embodiment, a first artificial intelligence model is invoked to process the physiological data set of a first user to obtain a constraint parameter set. This constraint parameter set is then used as a constraint on a generative design algorithm, driving the algorithm to output a design parameter set corresponding to the assistive device to be printed. Based on this, a first file is generated, enabling the 3D printing device to print the first assistive device. Thus, the printed first assistive device meets both the mechanical performance requirements and the comfort requirements of the first user. In other words, by using an artificial intelligence model to drive the generative design algorithm, the design parameters of the assistive device required by the user are automatically determined based on the user's physiological data set. Compared to related technologies, this eliminates the need for manual design to determine the design parameters of customized assistive devices, thereby improving printing efficiency. Therefore, in practical applications, even when large-scale production of customized assistive devices is required, these devices can be printed efficiently, ensuring the compatibility between the customized assistive devices and the user.

[0117] Based on the embodiments described above, this application also provides an auxiliary printing device, see [link to relevant documentation]. Figure 3 The auxiliary printing device includes: Acquisition unit 31 is used to acquire a first set of physiological data of the first user; the first set of physiological data is used to determine the mechanical performance requirements and comfort requirements of the first assistive device required by the first user; The first invocation unit 32 is used to invoke the first artificial intelligence model to process the first physiological data set to obtain the first constraint parameter set; the first artificial intelligence model is used to recommend the constraint parameter set based on the input physiological data set; the constraint parameter set represents the constraints related to the mechanical performance requirements corresponding to the input physiological data set. The second calling unit 33 is used to call a generative design algorithm to process the first physiological data set using the first constraint parameter set as a constraint, so as to obtain a first design parameter set; the generative design algorithm is used to generate a design parameter set that meets the corresponding comfort requirements based on the input physiological data set, and the design parameter set includes multiple design parameters of the assistive device; The generation unit 34 is used to generate a first file based on the first design parameter group and the slicing parameter group, and output the first file to the 3D printing device; the slicing parameter group is used to configure the printing parameters of the 3D printing device; the first file is used to control the 3D printing device to print the first auxiliary device.

[0118] In one embodiment, the first artificial intelligence model is further used to recommend a set of slice parameters based on the input set of physiological data; Correspondingly, the generation unit 34 generates a first file based on the first design parameter group and the slice parameter group, including: Based on the first design parameter set and the first slice parameter set, a first file is generated; the first slice parameter set represents the slice parameter set obtained by calling the first artificial intelligence model to process the first physiological data set.

[0119] In one embodiment, the auxiliary printing device further includes a third calling unit, the third calling unit being used for: After processing the first physiological data set using the first constraint parameter set as a constraint and invoking a generative design algorithm to obtain the first design parameter set, the second artificial intelligence model is invoked to process the first physiological data set and the first design parameter set to obtain a first processing result. The first processing result characterizes the force distribution of the first assistive device. The second artificial intelligence model is used to predict the force distribution of the assistive device corresponding to the input design parameter set based on the input physiological data set. Based on the first processing result, determine the second slice parameter group; Correspondingly, the generation unit 34 generates a first file based on the first design parameter group and the slice parameter group, including: A first file is generated based on the first design parameter group and the second slice parameter group.

[0120] In one embodiment, the third calling unit determines the second slice parameter group based on the first processing result, including: Based on the first processing result, the first slice parameter group is optimized to obtain the second slice parameter group; the first slice parameter group represents the slice parameter group obtained by calling the first artificial intelligence model to process the first physiological data group.

[0121] In one embodiment, the auxiliary printing device further includes a training unit, the training unit being used for: The generative design algorithm is invoked to process multiple preset second physiological data sets to obtain multiple second design parameter sets, and multiple second assistive devices are printed based on the multiple second design parameter sets; the multiple preset second physiological data sets are determined based on different physiological conditions corresponding to the target population of the assistive devices; Acquire first test data; the first test data represents the test data obtained by performing mechanical performance tests on the plurality of second auxiliary devices respectively; The first artificial intelligence model is trained based on the preset multiple second physiological data sets and the first test data.

[0122] In one embodiment, the training unit prints out a plurality of second assistants based on the plurality of second design parameter sets, including: Multiple first auxiliary models are selected from multiple auxiliary models corresponding to multiple second design parameter groups, wherein the failure probability of the auxiliary model corresponding to the multiple first auxiliary model is higher than the failure probability of the auxiliary model corresponding to the second auxiliary model, and the second auxiliary model represents other auxiliary models other than the first auxiliary model among the multiple auxiliary models corresponding to multiple second design parameter groups. The 3D printing device is controlled to print the multiple first auxiliary models respectively, so as to print multiple second auxiliary models.

[0123] In one embodiment, the training unit prints out a plurality of second assistants based on the plurality of second design parameter sets, including: Based on the plurality of second design parameter groups and each of the preset plurality of third slice parameter groups, the 3D printing device is controlled to print the plurality of auxiliary models corresponding to the plurality of second design parameter groups respectively, so as to print the plurality of second auxiliary devices. The preset multiple third slice parameter groups are determined based on different configurations of printing parameters supported by the 3D printing device.

[0124] In one embodiment, the first assistive device is characterized as one or more of the following: a prosthesis, an orthosis.

[0125] In practical applications, the acquisition unit 31, the first calling unit 32, the second calling unit 33, the generation unit 34, the third calling unit, and the training unit can be implemented by the processor in the auxiliary printing device.

[0126] It should be noted that the auxiliary printer device provided in the above embodiments is only illustrated by the division of the above-described program modules when printing auxiliary printers. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the auxiliary printer device and the auxiliary printer method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0127] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of this application, this application also provides an electronic device, see [link to relevant documentation]. Figure 4 The electronic device includes: Communication interface 1 enables information exchange with other devices; Processor 2 is connected to communication interface 1 to enable information interaction with other devices and, when running a computer program, executes the methods provided by one or more technical solutions in the above embodiments. The computer program is stored in memory 3.

[0128] Specifically, the processor 2 is used to acquire a first set of physiological data of the first user; the first set of physiological data is used to determine the mechanical performance requirements and comfort requirements of the first assistive device required by the first user. The first artificial intelligence model is invoked to process the first physiological data set to obtain a first constraint parameter set; the first artificial intelligence model is used to recommend constraint parameter sets based on the input physiological data set; the constraint parameter set represents the constraints related to the mechanical performance requirements corresponding to the input physiological data set. Using the first set of constraint parameters as constraints, a generative design algorithm is invoked to process the first set of physiological data to obtain a first set of design parameters; the generative design algorithm is used to generate a set of design parameters that meet the corresponding comfort requirements based on the input set of physiological data, and the set of design parameters includes multiple design parameters of the assistive device; and, Based on the first design parameter group and the slicing parameter group, a first file is generated and output to the 3D printing device; the slicing parameter group is used to configure the printing parameters of the 3D printing device; the first file is used to control the 3D printing device to print the first auxiliary device.

[0129] In one embodiment, the first artificial intelligence model is further used to recommend a set of slice parameters based on the input set of physiological data; Correspondingly, the processor 2 generates a first file based on the first design parameter group and the slice parameter group, including: Based on the first design parameter set and the first slice parameter set, a first file is generated; the first slice parameter set represents the slice parameter set obtained by calling the first artificial intelligence model to process the first physiological data set.

[0130] In one embodiment, after the processor 2 processes the first physiological data set using the first set of constraint parameters as constraints and calls a generative design algorithm to obtain the first set of design parameters, it is further configured to: The second artificial intelligence model is invoked to process the first physiological data set and the first design parameter set to obtain a first processing result, which characterizes the force distribution of the first assistive device; the second artificial intelligence model is used to predict the force distribution of the assistive device corresponding to the input design parameter set based on the input physiological data set. Based on the first processing result, determine the second slice parameter group; Correspondingly, the processor 2 generates a first file based on the first design parameter group and the slice parameter group, including: A first file is generated based on the first design parameter group and the second slice parameter group.

[0131] In one embodiment, the processor 2 determines a second slice parameter set based on the first processing result, including: Based on the first processing result, the first slice parameter group is optimized to obtain the second slice parameter group; the first slice parameter group represents the slice parameter group obtained by calling the first artificial intelligence model to process the first physiological data group.

[0132] In one embodiment, before invoking the first artificial intelligence model to process the first physiological data set, the processor 2 is further configured to: The generative design algorithm is invoked to process multiple preset second physiological data sets to obtain multiple second design parameter sets, and multiple second assistive devices are printed based on the multiple second design parameter sets; the multiple preset second physiological data sets are determined based on different physiological conditions corresponding to the target population of the assistive devices; Acquire first test data; the first test data represents the test data obtained by performing mechanical performance tests on the plurality of second auxiliary devices respectively; The first artificial intelligence model is trained based on the preset multiple second physiological data sets and the first test data.

[0133] In one embodiment, the processor 2 prints out a plurality of second auxiliary devices based on the plurality of second design parameter sets, including: Multiple first auxiliary models are selected from multiple auxiliary models corresponding to multiple second design parameter groups, wherein the failure probability of the auxiliary model corresponding to the multiple first auxiliary model is higher than the failure probability of the auxiliary model corresponding to the second auxiliary model, and the second auxiliary model represents other auxiliary models other than the first auxiliary model among the multiple auxiliary models corresponding to multiple second design parameter groups. The 3D printing device is controlled to print the multiple first auxiliary models respectively, so as to print multiple second auxiliary models.

[0134] In one embodiment, the processor 2 prints out a plurality of second auxiliary devices based on the plurality of second design parameter sets, including: Based on the plurality of second design parameter groups and each of the preset plurality of third slice parameter groups, the 3D printing device is controlled to print the plurality of auxiliary models corresponding to the plurality of second design parameter groups respectively, so as to print the plurality of second auxiliary devices. The preset multiple third slice parameter groups are determined based on different configurations of printing parameters supported by the 3D printing device.

[0135] In one embodiment, the first assistive device is characterized as one or more of the following: a prosthesis, an orthosis.

[0136] It should be noted that the specific processing procedure of communication interface 1 can be understood by referring to the above method.

[0137] Of course, in practical applications, the various components in an electronic device are coupled together through bus system 4. It can be understood that bus system 4 is used to achieve communication and connection between these components. In addition to the data bus, bus system 4 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 4 The general will label all buses as Bus System 4.

[0138] The memory 3 in this embodiment is used to store various types of data to support operation in the electronic device. Examples of such data include any computer program used to operate on the electronic device.

[0139] The methods disclosed in the embodiments of this application can be applied to the processor 2, or implemented by the processor 2. The processor 2 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 2 or by instructions in the form of software. The processor 2 mentioned above may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 2 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in the memory 3. The processor 2 reads the information in the memory 3 and combines its hardware to complete the steps of the aforementioned method.

[0140] In an exemplary embodiment, the electronic device may be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general-purpose processors, controllers, MCUs, microprocessors, or other electronic components to perform the aforementioned method.

[0141] It is understood that the memory 3 in the embodiments of this application can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable types of memories.

[0142] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a memory 3 that stores a computer program, which can be executed by a processor 2 to complete the steps described in the aforementioned method.

[0143] In an exemplary embodiment, this application also provides a computer program product, including a computer program that can be executed by a processor 2 to perform the steps described in the foregoing method.

[0144] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0145] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, the term "one or more" in this document refers to any combination of at least two of any one or more elements from a set of A, B, and C. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set of A, B, and C. Additionally, the term "one or more" in this document is an exemplary expression and can be replaced with any possible expressions, such as one or more, at least one, or at least one of, etc.

[0146] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0147] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.

Claims

1. An auxiliary printing method, characterized in that, The method includes: Acquire the first set of physiological data of the first user; the first set of physiological data is used to determine the mechanical performance requirements and comfort requirements of the first assistive device required by the first user; The first artificial intelligence model is invoked to process the first physiological data set to obtain a first constraint parameter set; the first artificial intelligence model is used to recommend constraint parameter sets based on the input physiological data set; the constraint parameter set represents the constraints related to the mechanical performance requirements corresponding to the input physiological data set. Using the first set of constraint parameters as constraints, a generative design algorithm is invoked to process the first set of physiological data to obtain a first set of design parameters. The generative design algorithm is used to generate a set of design parameters that meet the corresponding comfort requirements based on the input set of physiological data, and the set of design parameters contains multiple design parameters of the assistive device. Based on the first design parameter group and the slicing parameter group, a first file is generated and output to the 3D printing device; the slicing parameter group is used to configure the printing parameters of the 3D printing device; the first file is used to control the 3D printing device to print the first auxiliary device.

2. The method according to claim 1, characterized in that, The first artificial intelligence model is also used to recommend slice parameter sets based on the input physiological data set; Correspondingly, based on the first design parameter group and the slice parameter group, a first file is generated, including: Based on the first design parameter set and the first slice parameter set, a first file is generated; the first slice parameter set represents the slice parameter set obtained by calling the first artificial intelligence model to process the first physiological data set.

3. The method according to claim 1, characterized in that, After using the first set of constraint parameters as constraints to process the first set of physiological data using a generative design algorithm to obtain the first set of design parameters, the method further includes: The second artificial intelligence model is invoked to process the first physiological data set and the first design parameter set to obtain a first processing result, which characterizes the force distribution of the first assistive device; the second artificial intelligence model is used to predict the force distribution of the assistive device corresponding to the input design parameter set based on the input physiological data set. Based on the first processing result, determine the second slice parameter group; Correspondingly, based on the first design parameter group and the slice parameter group, a first file is generated, including: A first file is generated based on the first design parameter group and the second slice parameter group.

4. The method according to claim 3, characterized in that, The step of determining the second slice parameter group based on the first processing result includes: Based on the first processing result, the first slice parameter group is optimized to obtain the second slice parameter group; the first slice parameter group represents the slice parameter group obtained by calling the first artificial intelligence model to process the first physiological data group.

5. The method according to claim 1, characterized in that, Before invoking the first artificial intelligence model to process the first set of physiological data, the method further includes: The generative design algorithm is invoked to process multiple preset second physiological data sets to obtain multiple second design parameter sets, and multiple second assistive devices are printed based on the multiple second design parameter sets; the multiple preset second physiological data sets are determined based on different physiological conditions corresponding to the target population of the assistive devices; Acquire first test data; the first test data represents the test data obtained by performing mechanical performance tests on the plurality of second auxiliary devices respectively; The first artificial intelligence model is trained based on the preset multiple second physiological data sets and the first test data.

6. The method according to claim 5, characterized in that, The process of printing multiple second auxiliary devices based on the multiple sets of second design parameters includes: Multiple first auxiliary models are selected from multiple auxiliary models corresponding to multiple second design parameter groups, wherein the failure probability of the auxiliary model corresponding to the multiple first auxiliary model is higher than the failure probability of the auxiliary model corresponding to the second auxiliary model, and the second auxiliary model represents other auxiliary models other than the first auxiliary model among the multiple auxiliary models corresponding to multiple second design parameter groups. The 3D printing device is controlled to print the multiple first auxiliary models respectively, so as to print multiple second auxiliary models.

7. The method according to claim 5, characterized in that, The process of printing multiple second auxiliary devices based on the multiple sets of second design parameters includes: Based on the plurality of second design parameter groups and each of the preset plurality of third slice parameter groups, the 3D printing device is controlled to print the plurality of auxiliary models corresponding to the plurality of second design parameter groups respectively, so as to print the plurality of second auxiliary devices. The preset multiple third slice parameter groups are determined based on different configurations of printing parameters supported by the 3D printing device.

8. The method according to claim 1, characterized in that, The first assistive device is characterized as one or more of the following: prosthesis, orthosis.

9. An auxiliary printing device, characterized in that, include: The acquisition unit is used to acquire the first physiological data set of the first user. The first set of physiological data is used to determine the mechanical performance and comfort requirements of the first assistive device required by the first user; The first invocation unit is used to invoke the first artificial intelligence model to process the first physiological data set to obtain the first constraint parameter set; the first artificial intelligence model is used to recommend the constraint parameter set based on the input physiological data set. The constraint parameter set represents the constraints related to the mechanical performance requirements corresponding to the input physiological data set; The second calling unit is used to call the generative design algorithm to process the first physiological data group using the first constraint parameter group as a constraint, so as to obtain the first design parameter group. The generative design algorithm is used to generate a set of design parameters that meet the corresponding comfort requirements based on the input set of physiological data, and the set of design parameters includes multiple design parameters of the assistive device. The generation unit is used to generate a first file based on the first design parameter group and the slicing parameter group, and output the first file to the 3D printing device. The slice parameter group is used to configure the printing parameters of the 3D printing device; The first document is used to control the 3D printing device to print the first auxiliary device.

10. An electronic device, characterized in that, include: The processor and the memory used to store computer programs that can run on the processor. When the processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 8.

11. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.

Images