Transportation of particulates to target locations using 4-dimensional (4D) objects

Abstract

According to one method, a computer-implemented method includes sending one or more instructions to apply an initial influencing factor to a smart material of a 4D object. In addition, the 4D object is configured to deliver the one or more particles from the starting location to the target location along the delivery path in response to the initial influencing factor being applied to the smart material. One or more instructions are also sent to monitor movement of the 4D object along the delivery path in response to applying the initial influencing factor to the smart material. In response to determining that the 4D object has deviated from the delivery path, one or more instructions are further sent to dynamically weight the initial influencing factors applied to the smart material using one or more machine learning models.

Description

Background Technology

[0001] This disclosure relates to microparticles, and more specifically, to transporting microparticles to a target location using 4D objects.

[0002] "Microparticles" are particles with a physical size (e.g., diameter) of approximately 1 to 1000 micrometers (μm). Microparticles are traditionally obtained as raw materials, such as in ceramics, glass, polymers, and metals. They are also naturally encountered in everyday life, such as in pollen, sand, dust, flour, and powdered sugar.

[0003] While traditional microparticles have been limited to naturally occurring objects and small quantities of material, technological advancements have allowed for further miniaturization of functional components in many different technological fields. As a result, microparticles have become more advanced and can be used in numerous situations to achieve desired results. For example, advancements in medicine have allowed for the development of biodegradable microparticles. These biodegradable microparticles can be used as cell microcarriers, drug delivery containers, 3D scaffolds, and more. In other instances, microparticles can be used to assemble electronic particles, small mechanical particles, and so on.

[0004] It is evident that microparticles are particularly useful in many situations involving confined spaces, but their small size also affects the processes by which they can be handled. Therefore, the formation and storage of microparticles are detailed and precise processes. Physical systems precise enough to handle microparticles are often too large to reach their target locations. Summary of the Invention

[0005] According to a method, a computer-implemented method includes: sending one or more instructions to apply initial influencing factors to a smart material of a 4D object. Furthermore, the 4D object is configured to deliver one or more particles from a starting position along a delivery path to a target position in response to the application of the initial influencing factors to the smart material. One or more instructions are also sent to monitor the movement of the 4D object along the delivery path in response to the application of the initial influencing factors to the smart material. In response to determining that the 4D object has deviated from the delivery path, one or more instructions are further sent to dynamically weight the initial influencing factors applied to the smart material using one or more machine learning models.

[0006] According to another approach, the computer program product includes a computer-readable storage medium having program instructions embodied therein. Furthermore, the program instructions are readable by a processor, executable by the processor, or both readable and executable by the processor to cause the processor to perform the aforementioned method.

[0007] According to yet another method, a system includes: a processor, and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor. Furthermore, the logic is configured to perform the aforementioned method.

[0008] Other aspects and implementations of this disclosure will become apparent from the following detailed description, which, when taken in conjunction with the accompanying drawings, illustrates the principles of this disclosure by way of example. Attached Figure Description

[0009] Figure 1 It is a diagram of the computing environment based on a method.

[0010] Figure 2 It is a representative view of a distributed system based on a particular method.

[0011] Figure 3A It is based on a flowchart of a method.

[0012] Figure 3B It is based on a method Figure 3A A flowchart of one of the sub-procedures in the method.

[0013] Figure 3C It is based on a method Figure 3A A flowchart of one of the sub-procedures in the method.

[0014] Figure 4 It is based on a method flowchart. Detailed Implementation

[0015] The following description is for the purpose of illustrating the general principles of this disclosure and is not intended to limit the inventive concepts claimed herein. Furthermore, the specific features described herein may be used in a variety of possible combinations and permutations with other described features.

[0016] Unless otherwise expressly defined herein, all terms shall be given the broadest possible interpretation, including the meaning implied in the specification and the meaning as understood by those skilled in the art and / or as defined in dictionaries, papers, etc.

[0017] It should also be noted that, as used in the specification and appended claims, the singular forms “a,” “an,” and “the” include plural objects unless otherwise stated. It will also be understood that the terms “comprising” and / or “including”, when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0018] The following description discloses several preferred methods for evaluating particle delivery requests, generating (e.g., designing and constructing) 4D objects configured to efficiently fulfill the requests, and based on systems, methods, and computer program products that improve the performance of the 4D objects over time. Therefore, the embodiments described herein are capable of processing particles and delivering them to intended target locations, despite spatial limitations. The process of generating 4D objects, for example, as will be described in further detail below, involves using a trained machine learning model to evaluate the feature details of a received particle delivery request and determine a 4D object configured to most efficiently deliver the particles to the target location.

[0019] In a general approach, a computer-implemented method includes sending one or more instructions to apply initial influencing factors to a smart material of a 4D object. The 4D object is configured to deliver one or more particles from a starting position to a target position along a delivery path in response to the application of the initial influencing factors to the smart material. Thus, contrary to conventional drawbacks, the method of this paper is able to handle particles and deliver them to the intended target location, despite spatial limitations. This significant increase in particle applicability is achieved by the implementation of the present invention, where the development (e.g., design and printing) of the 4D object is configured to respond to the applied influencing factors without relying on any machinery for transporting the particles.

[0020] The computer-implemented method also includes sending one or more instructions to monitor the movement of a 4D object along a delivery path in response to the application of initial influencing factors to the smart material. Again, the 4D object preferably comprises both smart and static materials. The smart material is configured to physically deform in response to the application of initial influencing factors, while the static material does not physically deform significantly under nominal operating conditions (e.g., temperature). Therefore, the performance of the 4D object is examined in the presence of different influencing factors. This allows it to be determined whether the 4D object is moving toward the intended target location and / or along the intended delivery path. This reduces the number of failures experienced while fulfilling particle delivery requests.

[0021] In response to determining that a 4D object has deviated from its delivery path, some implementations send one or more instructions to dynamically weight the initial influencing factors applied to the smart material using a machine learning model. Thus, one or more influencing factors can be further dynamically adjusted in response to determining that the 4D printed object has deviated from its intended delivery path. For example, one or more trained machine learning models can be used to dynamically weight the influencing factors applied to the smart material in real time, thereby influencing (e.g., improving) the movement of the 4D printed object. These adjustments preferably guide the 4D object back to the intended delivery path toward the target location or guide the 4D object along the intended delivery path toward the target location.

[0022] In some implementations, dynamically applying weights to influencing factors includes determining the amount of force generated by the 4D object in response to an initial influencing factor being applied to the smart material. As mentioned above, influencing factors can cause the smart material to physically deform in different ways, depending on the type of smart material, the type of influencing factor applied, the strength of the applied influencing factor (e.g., weight), etc. Determining the amount of force generated by the 4D object in response to a given influencing factor applied thereto provides insight into how the 4D object reacts in a given situation. Therefore, this information can be used to interpret performance and adjust settings accordingly to improve efficiency.

[0023] Therefore, some implementations include comparing the amount of force generated by the 4D object with the movement of the 4D object along the delivery path in response to the application of initial influencing factors to the smart material. Based on this evaluation, weight values ​​can be generated. Again, one or more trained machine learning models can be used to perform this comparison and dynamically weight the influencing factors applied to the smart material in real time. This ideally redirects the movement of the 4D printed object back to the intended delivery path. These adjustments can also redirect the 4D object and particles back toward the target location. Thus, the weight values ​​can be configured to adjust the movement of the 4D object back along the delivery path in response to the application of weight values ​​to the influencing factors.

[0024] In some implementations, one or more machine learning models are trained using a repository of feature data corresponding to different influencing factors and how these factors affect the physical deformation of different smart materials. For example, in different implementations, the influencing factors may include one or more of light, heat, magnetic fields, sound, and electricity. In some implementations, the repository also includes feature data corresponding to different surrounding environments and how these factors affect the physical deformation of the corresponding smart materials in the repository. Thus, a repository can be formed and used to improve the process of developing 4D objects configured to efficiently fulfill particle delivery requests. This repository can then be used to train machine learning models to understand how each smart material responds (e.g., how it deforms) in the presence of different influencing factors. Existing smart materials that have been developed and tested can be used to populate the repository to determine the effects of different influencing factors on the smart materials. Information received from the created 4D object used for particle delivery can also be used to supplement the repository of information used to train the machine learning models described herein. It is thus concluded that a repository of feature data and how this data affects the physical deformation of different smart materials is used to train the machine learning models.

[0025] In some implementations, it can be determined that the 4D object has not deviated from the delivery path when the particles are delivered to the target location. Therefore, one or more instructions can be sent to maintain the initial influencing factors applied to the smart material. This ideally ensures that the current influencing factors are causing the 4D object to move the particles along the delivery path toward the target. However, in response to determining that the 4D object has reached the target location, one or more instructions can be sent to remove the initial influencing factors from the smart material. This ensures that the particles remain at the target location and do not continue traveling past it. As a result, the particle delivery request is fulfilled.

[0026] In another general approach, the computer program product includes a computer-readable storage medium having program instructions embodied therein. Furthermore, the program instructions are readable by a processor, executable by the processor, or both readable and executable by the processor to cause the processor to perform the aforementioned methods.

[0027] In yet another general approach, a system includes: a processor, and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor. Furthermore, the logic is configured to perform the aforementioned method.

[0028] Various aspects of this disclosure are described by narrative text, flowcharts, block diagrams of computer systems, and / or block diagrams of machine logic included in embodiments of a computer program product (CPP). Regarding any flowchart, depending on the technology involved, operations may be performed in a different order than that shown in a given flowchart. For example, again according to the technology involved, two operations shown in consecutive flowchart blocks may be performed in reverse order, as a single integrated step, simultaneously, or in a manner that at least partially overlaps in time.

[0029] Computer Program Product Embodiment (“CPP Embodiment” or “CPP”) is a term used in this disclosure to describe any collection of one or more storage media (also referred to as “media”) collectively included in a collection of one or more storage devices, the collection of one or more storage devices collectively including machine-readable code corresponding to instructions and / or data for performing computer operations specified in a given CPP claim. A “storage device” is any tangible device capable of holding and storing instructions used by a computer processor. Without limitation, a computer-readable storage medium can be an electronic storage medium, a magnetic storage medium, an optical storage medium, an electromagnetic storage medium, a semiconductor storage medium, a mechanical storage medium, or any suitable combination of the foregoing. Some known types of storage devices that include these media include: magnetic disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), memory sticks, floppy disks, mechanical encoding devices (such as punch cards or pits / platforms formed in the main surface of the disk), or any suitable combination of the foregoing. Computer-readable storage media, as used in this disclosure, should not be construed as storing transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides, optical pulses through fiber optic cables, electrical signals transmitted through wires, and / or other transmission media. As those skilled in the art will understand, data is typically moved at certain incidental points in time during the normal operation of the storage device, such as during access, defragmentation, or garbage collection; however, this does not make the storage device transient, because the data is not transient when it is stored.

[0030] Computing environment 100 includes examples of environments for executing at least some of the computer code involved in performing the methods of the present invention, such as in block 150 the code for evaluating particle delivery requests, generating (e.g., designing and constructing) 4D objects configured to efficiently fulfill the requests, and improved particle delivery code based on the performance of the 4D objects improved over time. Improvements are achieved at least in part due to the use of each SNAT port to facilitate multiple connections to the same destination IP address and DNS port. This ideally reduces processing backlogs and the number of failed request receptions.

[0031] In addition to block 150, computing environment 100 includes, for example, a computer 101, a wide area network (WAN) 102, an end-user equipment (EUD) 103, a remote server 104, a public cloud 105, and a private cloud 106. In this embodiment, computer 101 includes a processor set 110 (including processing circuitry 120 and a cache 121), communication infrastructure 111, volatile memory 112, persistent storage device 113 (including an operating system 122 and block 400, as described above), a peripheral device set 114 (including a user interface (UI) device set 123, storage device 124, and an Internet of Things (IoT) sensor set 125), and a network module 115. Remote server 104 includes a remote database 130. Public cloud 105 includes a gateway 140, a cloud coordination module 141, a host physical machine set 142, a virtual machine set 143, and a container set 144.

[0032] Computer 101 can take the form of a desktop computer, laptop computer, tablet computer, smartphone, smartwatch or other wearable computer, mainframe computer, quantum computer, or any other form of computer or mobile device now known or to be developed in the future capable of running programs, accessing networks, or querying databases such as remote database 130. As is well known in the field of computer technology, and depending on the technology, the performance of a computer-implemented method can be distributed across multiple computers and / or multiple locations. On the other hand, in this presentation of computing environment 100, the detailed discussion focuses on a single computer, specifically computer 101, to keep the presentation as simple as possible. Computer 101 can reside in the cloud, even... Figure 1 It is not shown in the cloud, and on the other hand, computer 101 does not need to be in the cloud unless it can be indicated with certainty to any extent.

[0033] Processor assembly 110 includes one or more computer processors of any type now known or to be developed in the future. Processing circuitry 120 may be distributed across multiple packages, such as multiple cooperating integrated circuit chips. Processing circuitry 120 may implement multiple processor threads and / or multiple processor cores. Cache 121 is memory located within the processor chip package and is typically used for data or code that should be readily accessible by the threads or cores running on processor assembly 110. Cache memory is typically organized into multiple levels based on its relative proximity to the processing circuitry. Alternatively, some or all of the cache in the processor assembly may be located “off-chip.” In some computing environments, processor assembly 110 may be designed to work with qubits and perform quantum computing.

[0034] Computer-readable program instructions are typically loaded onto computer 101 to cause the processor set 110 of computer 101 to perform a series of operational steps to implement a computer-implemented method, such that the instructions thus executed instantiate the method specified in the flowcharts and / or descriptive descriptions of the computer-implemented method included in this document (collectively, the “method of the invention”). These computer-readable program instructions are stored in various types of computer-readable storage media, such as cache 121 and other storage media discussed below. The program instructions and associated data are accessed by the processor set 110 to control and direct the execution of the method of the invention. In computing environment 100, at least some of the instructions for performing the method of the invention may be stored in persistent storage device 113, within block 400.

[0035] Communication structure 111 is a signal transmission path that allows the various components of computer 101 to communicate with each other. Typically, this structure consists of switches and conductive paths, such as switches and conductive paths that form buses, bridges, physical input / output ports, etc. Other types of signal communication paths can be used, such as fiber optic communication paths and / or wireless communication paths.

[0036] Volatile memory 112 is any type of volatile memory now known or to be developed in the future. Examples include dynamic random access memory (RAM) or static RAM. Typically, volatile memory 112 is characterized by random access, but this is not necessary unless explicitly stated otherwise. In computer 101, volatile memory 112 is located in a single package and is internal to computer 101; however, alternatively or additionally, volatile memory may be distributed across multiple packages and / or located externally relative to computer 101.

[0037] The persistent storage device 113 is any form of non-volatile memory known now or developed in the future for use with a computer. The non-volatility of this memory means that the stored data is retained regardless of whether power is supplied to the computer 101 and / or directly to the persistent storage device 113. The persistent storage device 113 may be a read-only memory (ROM), but typically at least a portion of the persistent memory allows data to be written, deleted, and rewritten. Some common forms of persistent storage include hard disks and solid-state storage devices. The operating system 122 may take several forms, such as various known proprietary operating systems or operating systems employing an open-source portable operating system interface type with a kernel. The code included in box 400 typically includes at least some of the computer code involved in performing the methods of the present invention.

[0038] Peripheral device set 114 includes a set of peripheral devices for computer 101. Data communication connections between peripheral devices and other components of computer 101 can be implemented in various ways, such as Bluetooth connectivity, near field communication (NFC) connectivity, connections made by cables (such as Universal Serial Bus (USB) type cables), plug-in connections (e.g., secure digital (SD) cards), connections made through local area communication networks, and even connections made through wide area networks such as the Internet. In various embodiments, UI device set 123 may include components such as displays, speakers, microphones, wearable devices (such as goggles and smartwatches), keyboards, mice, printers, touchpads, game controllers, and haptic devices. Storage device 124 is an external storage device, such as an external hard drive, or a pluggable storage device, such as an SD card. Storage device 124 can be permanent and / or volatile. In some embodiments, storage device 124 may take the form of a quantum computing storage device for storing data in the form of qubits. In embodiments where computer 101 requires substantial storage (e.g., where computer 101 locally stores and manages a large database), this storage can be provided by peripheral storage devices designed for storing very large amounts of data, such as a Storage Area Network (SAN) shared by multiple geographically distributed computers. The IoT sensor set 125 comprises sensors that can be used in IoT applications. For example, one sensor could be a thermometer, while another could be a motion detector.

[0039] Network module 115 is a collection of computer software, hardware, and firmware that allows computer 101 to communicate with other computers via WAN 102. Network module 115 may include hardware such as a modem or Wi-Fi transceiver, software for packetizing and / or depacketizing data transmitted over the communication network, and / or web browser software for transmitting data over the Internet. In some embodiments, the network control and network forwarding functions of network module 115 are performed on the same physical hardware device. In other embodiments (e.g., embodiments utilizing Software-Defined Networking (SDN)), the control and forwarding functions of network module 115 are performed on physically separate devices, such that the control function manages several different network hardware devices. Computer-readable program instructions for performing the methods of the present invention can typically be downloaded to computer 101 from an external computer or external storage device via a network adapter card or network interface included in network module 115.

[0040] WAN 102 is any wide area network (e.g., the Internet) capable of transmitting computer data over non-local distances using any technology known now or developed in the future for transmitting computer data. In some embodiments, WAN 102 may be replaced by and / or supplemented by a local area network (LAN) designed to transmit data between devices located in a local area (e.g., a Wi-Fi network). WANs and / or LANs typically include computer hardware such as copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and edge servers.

[0041] End User Equipment (EUD) 103 is any computer system used and controlled by an end user (e.g., a customer of the enterprise operating computer 101) and can take any of the forms discussed above in conjunction with computer 101. EUD 103 typically receives useful and available data from the operation of computer 101. For example, assuming computer 101 is designed to provide recommendations to an end user, these recommendations are typically transmitted from network module 115 of computer 101 to EUD 103 via WAN 102. In this way, EUD 103 can display or otherwise present recommendations to the end user. In some embodiments, EUD 103 can be client equipment such as a thin client, heavy client, mainframe, desktop computer, etc.

[0042] Remote server 104 is any computer system that provides at least some data and / or functionality to computer 101. Remote server 104 can be controlled and used by the same entity operating computer 101. Remote server 104 represents a machine that collects and stores useful and available data used by other computers, such as computer 101. For example, if computer 101 is designed and programmed to provide recommendations based on historical data, that historical data can be provided to computer 101 from a remote database 130 of remote server 104.

[0043] Public cloud 105 is any computer system that can be used by multiple entities, providing on-demand availability of computer system resources and / or other computing capabilities (particularly data storage (cloud storage) and computing power) without the need for direct, active management by users. Cloud computing typically leverages resource sharing to achieve scalability consistency and economy. Direct and active management of the computing resources of public cloud 105 is performed by the computer hardware and / or software of cloud coordination module 141. The computing resources provided by public cloud 105 are typically implemented by virtual computing environments running on various computers constituting the host physical machine set 142, which is the entirety of physical computers in and / or available to the public cloud 105. Virtual computing environments (VCEs) typically take the form of virtual machines from virtual machine set 143 and / or containers from container set 144. It should be understood that these VCEs can be stored as images and can be transferred between various physical machine hosts as images or after the VCEs are instantiated. Cloud coordination module 141 manages the transfer and storage of images, deploys new instantiations of VCEs, and manages the active instantiation of VCE deployments. Gateway 140 is a collection of computer software, hardware, and firmware that allow public cloud 105 to communicate via WAN 102.

[0044] Now, we will provide some further explanation of Virtualized Computing Environments (VCEs). A VCE can be stored as an "image." A new active instance of a VCE can be instantiated from this image. Two common types of VCEs are virtual machines and containers. A container is a VCE that uses operating system-level virtualization. This refers to an operating system feature where the kernel allows multiple isolated user-space instances, called containers, to exist. From the perspective of the programs running within them, these isolated user-space instances typically appear as actual computers. Computer programs running on a regular operating system can utilize all the resources of that computer, such as connected devices, files and folders, network shares, CPU power, and quantifiable hardware capabilities. However, programs running within a container can only use the contents of the container and the devices allocated to the container; this is a characteristic known as containerization.

[0045] Private cloud 106 is similar to public cloud 105, except that computing resources are available only to a single enterprise. While private cloud 106 is depicted as communicating with WAN 102, in other embodiments, private cloud may be completely disconnected from the Internet and accessible only via a local / private network. A hybrid cloud is a combination of multiple clouds of different types (e.g., private, community, or public cloud types) typically implemented by different vendors. Each of the multiple clouds remains a separate and discrete entity, but the larger hybrid cloud architecture is bound together by standardization or proprietary technology that enables coordination, management, and / or data / application portability across the multiple component clouds. In this embodiment, public cloud 105 and private cloud 106 are both part of a larger hybrid cloud.

[0046] In some aspects, a system according to various methods may include a processor and logic integrated with and / or executable by the processor, the logic being configured to perform one or more of the processing steps described herein. The processor may be any configuration as described herein, such as a discrete processor or processing circuitry including many components such as processing hardware, memory, I / O interfaces, etc. "Integrated with" means that the processor has logic embedded therewith as hardware logic, such as application-specific integrated circuits (ASICs), FPGAs, etc. "Executable by the processor" means that the logic is hardware logic; software logic (e.g., firmware, part of an operating system, part of an application; etc.), or some combination of hardware and software logic that is accessible to the processor and configured to cause the processor to perform a certain function when executed by the processor. The software logic may be stored on local and / or remote memory of any memory type, as is known in the art. Any processor known in the art may be used, such as software processor modules and / or hardware processors, such as ASICs, FPGAs, central processing units (CPUs), integrated circuits (ICs), graphics processing units (GPUs), etc.

[0047] Of course, depending on the implementation method, this logic can be implemented as a method or computer program product on any device and / or system.

[0048] As mentioned above, "microparticles" are particles with a physical size (e.g., diameter) between approximately 1 and 1000 micrometers (μm). Microparticles are traditionally available as raw materials, including ceramics, glass, polymers, and metals. They are also naturally encountered in everyday life, such as pollen, sand, dust, flour, and powdered sugar.

[0049] While traditional microparticles have been limited to naturally occurring objects and small quantities of material, technological advancements have allowed for further miniaturization of functional components in many different technological fields. As a result, microparticles have become more advanced and can be used in numerous situations to achieve desired results. For example, advancements in medicine have allowed for the development of biodegradable microparticles. These biodegradable microparticles can be used as cell microcarriers, drug delivery containers, 3D scaffolds, and more. In other instances, microparticles can be used to assemble electronic particles, small mechanical particles, and so on.

[0050] It is evident that microparticles are particularly useful in many situations involving confined spaces, but their small size also makes them difficult to handle. This is especially true for robotic systems that lack the precision associated with forming and / or handling microparticles. Similarly, robotic systems that are precise enough to handle microparticles are often too large to reach their target location. Therefore, conventional systems can only utilize microparticles in a limited number of cases, and there is a need for methods and systems that facilitate the transport of microparticles to their appropriate target locations.

[0051] In stark contrast to the aforementioned conventional drawbacks, the embodiments described herein are capable of handling microparticles and delivering them to desired target locations, despite spatial limitations. This significant increase in microparticle applicability is achieved by the development (e.g., design and printing) of 4D objects configured to transport microparticles without relying on any machinery. Moreover, for example, as will be described in further detail below, the 4D objects of this invention are capable of transporting microparticles by implementing smart materials in different configurations.

[0052] See now Figure 2 A system 200 with a distributed architecture is illustrated according to one method. Alternatively, this system 200 can be implemented by combining features from any other methods listed herein, such as those described with reference to other figures, such as... Figure 1 However, the system 200 and other systems described herein can be used in a variety of applications and / or combinations, which may or may not be specifically described in the exemplary methods or implementations listed herein. Furthermore, the system 200 presented herein can be used in any desired environment. Therefore, Figure 2 (And other diagrams) can be considered to include any possible permutations.

[0053] As shown in the figure, system 200 includes a central server 202 connected to remote locations 204 and 206 accessible to the respective users 205 and 207. Each of these remote locations 204 and 206 and the corresponding user 205 and 207 can be separate from each other, such that they are located in different geographical locations. For example, the central server 202 and the remote locations 204 and 206 are connected to network 210.

[0054] Network 210 can be of any type, depending on the desired method. For example, in some methods, network 210 is a WAN, such as the Internet. However, an illustrative list of other network types that network 210 can implement includes, but is not limited to, LAN, PSTN, SAN, intranet, etc. As a result, any desired information, data, commands, instructions, responses, requests, etc., can be sent between users 205, 207 and / or central server 202 at remote locations 204, 206, regardless of the degree of separation between them, for example, despite being located in different geographical locations.

[0055] However, it should be noted that two or more of the remote locations 204, 206 and / or the central server 202 may be connected differently depending on the method. According to one example, which is by no means intended to limit this disclosure, two edge computing nodes may be located relatively close to each other and connected by a wired connection, such as a cable, fiber optic link, wire, etc., or any other type of connection that will be apparent to those skilled in the art upon reading this description. The term “user” is by no means intended to be limiting. For example, while a user is described as an individual in various embodiments herein, a user can be an application, organization, provisioned process, etc. The use of “data” and “information” herein is by no means intended to be limiting and may include any desired type of detail, for example, depending on the type of prompt (e.g., request) submitted by the user.

[0056] Continue to refer to Figure 2 Remote locations 204 and 206 are shown to have configurations different from those of the central server 202. For example, in some implementations, the central server 202 includes a large (e.g., robust) processor 212 coupled to a cache 211, a machine learning module 213, and a data storage array 214 with relatively high storage capacity. The machine learning module 213 may include any desired number and / or type of machine learning models. In a preferred approach, the machine learning module 213 includes machine learning models that have been trained to analyze the details submitted in a request to transport particles from a starting location to a target location along a desired path. These machine learning models are capable of evaluating various details associated with the particles, starting location, target location, desired path, etc., to determine the most efficient options for fulfilling the request.

[0057] Therefore, a set of information (e.g., feature data) can be used to train the machine learning model in machine learning module 213, the set of information including a combination of various 4D objects capable of delivering particles; particles of various shapes, sizes, weights, etc.; a delivery path designed for delivering particles to a target location; and the surrounding environment along the intended delivery path (e.g., intestines, arteries, industrial environments, etc.). Therefore, for example, as will be described in further detail below, processor 212 and / or machine learning module 213 can perform one or more of the operations included in method 300.

[0058] Continue to refer to Figure 2 Therefore, processor 212 and / or machine learning module 213 can be used to monitor requests received from user 205. As described above, the request may involve the transfer of particles to a target location. Thus, user 205 may submit a request at remote location 204 for particles to be delivered to the target location, and this request is sent to central server 202 for processing. The results generated by processing the request can then be sent to remote location 206, enabling the construction of a 4D object capable of delivering the particles to the target location and its use for transporting the particles. Thus, the request can be evaluated in real time upon receipt and used to determine a 4D object capable of delivering the particles to the target location identified in the request.

[0059] Viewing remote location 204, processor 216, coupled to memory 218, receives and interfaces with input from user 205. For example, user 205 may use one or more of the following to input information: display screen 224, computer keyboard keys 226, computer mouse 228, microphone 230, and camera 232. Processor 216 can thus be configured to receive input (e.g., text, sound, images, motion data, etc.) from any of these components as input by user 205. This input typically corresponds to information presented on display screen 224 upon receipt of an entry. Furthermore, input received from keyboard 226 and computer mouse 228 may affect information displayed on display screen 224, data stored in memory 218, information collected from microphone 230 and / or camera 232, the state of the operating system implemented by processor 216, etc. Remote location 204 also includes a speaker 234, which can be used to play (e.g., project) audio signals for user 205 to hear.

[0060] Some components included at remote location 206 may be the same as or similar to those included at remote location 204, and some of these components have been given corresponding numbers. For example, controller 217 is coupled to memory 218, display screen 224, keys of computer keyboard 226, computer mouse 228, microphone 230, speaker 234, and camera 232.

[0061] Additionally, controller 217 is coupled to manufacturing module 238, which is configured to construct 3D and 4D objects. In some approaches, manufacturing module 238 may be able to use one or more additional manufacturing processes to print 3D and / or 4D objects. In some cases, additive manufacturing processes may be desirable because they can form objects with any desired shape, size, material composition, etc. This improves the ability of the resulting object to successfully hold and transport the desired microparticles. However, it should be noted that manufacturing module 238 may be configured to use other manufacturing processes to form 3D and / or 4D objects.

[0062] Regarding this specification, it should also be noted that "4D objects" include both static materials and smart materials. Static materials maintain a given shape, size, orientation, etc., even during use, while smart materials are configured to physically deform in response to influencing factors applied to them. In other words, applying appropriate influencing factors (e.g., external stimuli) to a 4D object printed by manufacturing module 238 causes the smart materials of the 4D object to physically deform, while the static materials remain unchanged. For example, influencing factors may include, but are not limited to, visible light, heat, physical stress and / or strain, liquids (e.g., water), magnetic fields, electricity, sound, ultraviolet (UV) light, etc.

[0063] As one example, a robotic arm capable of bending and moving in response to temperature changes could utilize smart materials, such as shape memory alloys that can remember their original shape and recover it when heated. Additional processes can be used to 3D print other static materials, including the robot's frame and joints, using materials such as plastics and metals. The smart material can then be integrated into specific areas of the robotic arm, such as the arm segment or gripper. Thus, when the robot is exposed to temperature changes, the smart material deforms, causing the arm segment to bend or the gripper to close. This movement would be programmed and controlled by the smart material and could be repeated as needed based on available influencing factors.

[0064] Furthermore, by combining static and smart materials in different combinations and configurations, the method presented in this paper can create (e.g., generate) 4D objects, each configured to achieve a desired result. In other words, by implementing smart materials that physically respond to the presence of one or more influencing factors (e.g., external stimuli), 4D objects that act in a predetermined manner while one or more influencing factors are applied can be created. Moreover, by adjusting the intensity, number, type, etc., of the influencing factors applied to the 4D objects, the implementation presented in this paper can control how the 4D objects act. For example, in some methods, increasing the weight applied to the influencing factors can result in more drastic physical deformation of the smart material of the 4D object compared to decreasing the weight applied to the influencing factors. Therefore, for example, as will be described in further detail below, the movement of the 4D object can be guided by adjusting the weight applied to the influencing factors.

[0065] In some embodiments, manufacturing module 238 can create (e.g., print) a 3D container configured to hold a corresponding 4D object. Thus, the 3D container can be designed to accommodate both the 4D object and the microparticles during transport. The size and shape of the formed 3D container can be determined by the size and / or number of the microparticles being transported. Furthermore, the material used to form the 3D container can be selected such that the resulting structure is sufficiently robust (e.g., rigid) to accommodate the microparticles and the 4D object during transport. The container can also be designed to allow for easy transport to its target location.

[0066] In addition to forming 3D and 4D objects, remote location 206 can also use 3D and / or 4D objects to attempt to deliver particles to a target location. As described above, the received particle delivery request can specify the size and / or shape of the particles, the number of particles to be delivered, the target location of the particles, the starting location, etc. The manufacturing module 238 can thus be configured to couple the particles to the 3D and / or 4D objects formed before placing them at the specified starting locations. Remote location 206 can also be configured to selectively apply one or more influencing factors to the object, thereby causing the smart material in the object to physically deform.

[0067] The smart material in each 4D object is preferably configured to physically deform and generate forces that cause the corresponding 4D object to move relative to a starting position (e.g., a reference point). As previously described, a smart material is a material designed to have one or more characteristics that can be significantly altered in a controlled manner using influencing factors. For example, shape memory alloys and shape memory polymers can be used as smart materials in 4D objects. These shape memory materials can thus induce and recover large deformations by applying temperature changes or stress changes (e.g., pseudoelasticity). The shape memory effect of smart materials is caused by martensitic phase transformation and induced elasticity at higher thermal temperatures, as should be understood by those skilled in the art upon reading this specification.

[0068] In other methods, an object formed at remote location 206 can be sent to another location for testing. For example, a 4D object printed by manufacturing module 238 can be sent to remote location 204. User 205 can then place the 4D object at the starting location, and processor 216 can perform the following... Figure 3A The processor 216 can thus cause one or more influencing factors to be applied to the 4D object, and monitor the resulting movement of the 4D object using other components at a remote location 204 (e.g., computer keyboard 226, microphone 230, camera 232, etc.). These one or more influencing factors can also be dynamically adjusted in response to determining that the 4D printed object has deviated from its intended delivery path. For example, one or more trained machine learning models can be used to dynamically weight the influencing factors applied in real time to the smart material, thereby affecting the movement of the 4D printed object. These adjustments preferably guide the 4D object back to or along the intended delivery path toward the target location, for example, as will be described in further detail below.

[0069] Based on examples in the use of this disclosure without limiting it in any way, a 4D object includes a self-folding body configured to transform into a truncated octahedron over time while being exposed to corresponding influencing factors. The 4D object may begin as a series of shapes, most of which lie in a common plane. However, the smart material of the 4D object can physically react to exposure to influencing factors, causing the shape planes to transform into truncated octahedrons. Such a 4D object can thus be used to hold (e.g., encapsulate) one or more particles and transport the particles to a desired target location. In some methods, a 3D object configured to hold the particles can be coupled to a portion of the 4D object, which is configured to physically move along a desired path to a target location in the presence of one or more influencing factors. The 3D object can thus be used to hold the particles while the 4D object moves the particles to the target location.

[0070] See now Figure 3A The diagram illustrates a computer-implemented method 300 for transporting particles using a 4D object. In other words, method 300 can be used to develop and utilize 4D objects to deliver particles to a target location. Method 300 also includes constructing the 4D object and further adjusting its operation to improve the particle delivery process.

[0071] Method 300 can be applied according to this disclosure. Figure 1-2 This can be performed in any environment depicted herein, particularly in various methods. Of course, as those skilled in the art will understand upon reading this specification, method 300 may include more than [previous methods]. Figure 3A The specific operations described in the text may include more or fewer operations.

[0072] Each step of method 300 can be performed by any suitable component of the operating environment using known techniques and / or techniques that will become apparent to a person skilled in the art upon reading this disclosure. For example, one or more processors at a central server in a distributed system (see above). Figure 2 The processor 212 can be used to perform one or more operations in method 300. In another example, one or more processors at a remote location in the system (e.g., see above) Figure 2 (Controller 217).

[0073] Furthermore, in various methods, method 300 may be performed partially or entirely by a controller, processor, or other means having one or more processors. One or more steps of method 300 can be performed in any device using a processor (e.g., a processing circuit, chip, and / or module implemented in hardware and / or software and preferably having at least one hardware component). Illustrative processors include, but are not limited to, central processing units (CPUs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), combinations thereof, or any other suitable computing devices known in the art.

[0074] See Figure 3A Operation 302 includes receiving a particle delivery request. This request corresponds to delivering one or more particles from a starting location along a delivery path to a target location. The request may include various details describing the intended delivery of the one or more particles. For example, the request may include characteristic data (e.g., descriptive information) corresponding to the particles being delivered, the starting location, the target location, the delivery path, and one or more surrounding environments along the delivery path. According to an example, the characteristic data corresponding to the particles may include information (e.g., values) describing the size, shape, weight, surface pattern, material composition, etc., of each particle intended to be delivered to the target location.

[0075] Therefore, operation 304 includes obtaining available feature data corresponding to the received request. In other words, operation 304 includes collecting any available feature data associated with the received request (e.g., one or more particles to be transported). As described above, at least some feature data may be received along with the initial request itself. The type, quality, and quantity of feature data included in the initial request depend on the specific request received and other factors, such as the source of the request. Additional feature data may also be collected from other sources to supplement any feature data included in the request. According to the example, feature data or other information received along with the initial request may be used to identify relevant information in a lookup table.

[0076] Method 300 proceeds from operation 304 to operation 306. There, operation 306 includes using one or more machine learning models to analyze available feature data associated with the received request. The machine learning models are preferably trained to evaluate the feature data associated with the particle delivery request and to determine (e.g., design) a 4D object configured to deliver the particle to the target location specified in the delivery request.

[0077] As described above, 4D objects can include both static and smart materials. Static materials maintain a given shape, size, orientation, etc., even during use, while smart materials are configured to physically deform in response to influencing factors applied to them. The smart materials of a 4D object can thus be configured to physically react to influencing factors applied to the 4D object. In other words, applying appropriate influencing factors (e.g., external stimuli) to a 4D object causes the smart materials of the 4D object to physically deform, while the static materials remain unchanged. Influencing factors can include, but are not limited to, visible light, heat, physical stress and / or strain, liquids (e.g., water), magnetic fields, electricity, sound, ultraviolet (UV) light, etc., depending on the type of smart material used in a given 4D object.

[0078] Furthermore, by combining static and smart materials in different combinations and configurations, the method presented in this paper can create (e.g., design) 4D objects, each configured to achieve a desired result. In other words, by realizing smart materials that physically respond to the presence of one or more influencing factors (e.g., external stimuli), 4D objects that act in a predetermined manner while one or more influencing factors are applied can be created. Moreover, by adjusting the intensity, number, type, etc., of the influencing factors applied to the 4D objects, the implementation presented in this paper can control how the 4D objects act. For example, in some methods, increasing the weight applied to the influencing factors can result in more drastic physical deformation of the smart material in the 4D object compared to decreasing the weight applied to the influencing factors.

[0079] Therefore, each of the 4D objects created using a machine learning model is preferably configured such that the physical deformation experienced by the smart material generates a force capable of physically moving the corresponding 4D object. In other words, the machine learning model is trained to evaluate feature data associated with a received request, and the development (e.g., design) is configured to transfer 4D objects of particles according to the request. The physical deformation of the smart material in these 4D objects causes the 4D objects to physically move relative to a starting point. Furthermore, the motion of the 4D objects can also be controlled by adjusting the weights applied to influencing factors, for example, as will be described in further detail below.

[0080] As previously mentioned, training data received from the information repository can be used to train a machine learning model for developing 4D objects. For example, a machine learning module (see, for example, see...) Figure 2 The machine learning module 213 can receive feature datasets associated with various particle delivery requests, previously created 4D objects capable of delivering particles, the particles themselves, available smart materials, environmental conditions along the expected delivery path, delivery path, influencing factors, etc., and can use these feature datasets for training.

[0081] Therefore, information corresponding to 4D objects (e.g., deformation patterns) can be captured and stored over time. For example, the system can be equipped with sensors that capture and record data such as the deformation patterns and movement of 4D objects. The recorded data can be further stored in a database for historical analysis. In another example, the proposed system can simulate the deformation patterns and movement of 4D objects under different conditions. This simulation data can also be stored for historical analysis. In some cases, physical tests can be performed on the 4D object to determine the corresponding deformation patterns and generated movements.

[0082] Machine learning models can also be trained based on the relationships between each of different types of feature data. For example, machine learning models can be trained to identify patterns such as how certain influencing factors cause certain smart materials to react, how the characteristics of particles affect their ability to be transported, how different environmental conditions affect the physical deformation of corresponding smart materials in a storage facility, and / or the movement of 4D objects along a planned delivery path.

[0083] A repository of different types of smart materials and how various influencing factors affect each of these smart materials can be developed. This repository can then be used to train machine learning models to understand how each smart material responds (e.g., how it deforms) in the presence of different influencing factors. The repository can be populated with existing smart materials that have already been developed and tested to determine the effects of different influencing factors on the smart materials. Furthermore, this information can be represented as feature data. However, the repository can also be populated with new smart materials that have been synthesized and tested in the laboratory over time. In some approaches, these properties of the smart materials can be collected while performing various tests on the smart materials included in the repository. Information received from the created 4D object used to transfer the particles can also be used to supplement the repository of information used to train the machine learning model presented in this paper.

[0084] Therefore, a machine learning model can be trained using a repository of feature data corresponding to different influencing factors and how they affect the physical deformation of different smart materials. The machine learning model can also be trained to recognize how the affected physical deformation of the smart material redirects the motion of the entire object relative to the target position of the particles. Thus, operation 306 can evaluate the available feature data corresponding to the received delivery request and develop (e.g., design) a 4D object that can satisfy the received delivery request.

[0085] For now, please refer to the following information. Figure 3B An exemplary sub-operation is shown, based on a method, that uses a trained machine learning model to analyze a particle delivery request and determine a 4D object that can satisfy the request. Figure 3B One or more of the suboperations in can be used to perform Figure 3A Operation 306 evaluates the feature data associated with the received particle delivery request and determines (e.g., design) a 4D object configured to deliver particles to the target location specified in the delivery request. However, it should be noted that Figure 3B The suboperations are described according to a method that is by no means intended to limit this disclosure.

[0086] As shown in the figure, sub-operation 332 includes determining the amount of force generated by each available 4D object in response to influencing factors being applied to it. In other words, sub-operation 332 includes determining and evaluating the amount of force that each 4D object in the repository can generate, which can be converted into the amount of weight that each available 4D object can physically move. This evaluation can be used to identify certain 4D object configurations that can meet a received particle delivery request. Sub-operation 332 can also identify certain 4D object configurations that can travel along a specific delivery path toward a target location in a specific manner (e.g., rolling, crawling, flying, twisting, etc.).

[0087] Furthermore, sub-operation 334 includes determining a minimum amount of force associated with physically moving one or more particles to a target location. For example, sub-operation 334 may determine a minimum amount of force associated with physically moving particles along a delivery path as outlined in the received request (e.g., see [link to request]). Figure 3A Operation 302). Sub-operation 334 may thus take into account details that affect how the particles can be physically moved, such as their individual and / or combined weight, overall size, etc.

[0088] The flowchart proceeds from sub-operation 334 to sub-operation 336. Here, sub-operation 336 includes identifying a subset of sample 4D objects, each sample 4D object configured to generate a sufficient amount of force to move the 4D object and the particle. In other words, 4D objects capable of generating a force greater than the minimum amount of force determined in sub-operation 334. The 4D objects identified in the subset are preferably capable of generating at least the amount of force associated with physically moving the particle and the corresponding 4D object. The subset of identified 4D objects can also be configured to generate physical movement in a specific manner, such as rolling. In other methods, the subset of identified 4D objects may have a sufficiently small profile to reach the target location. Thus, the surrounding environment along the delivery path (e.g., intestines, arteries, industrial environments, etc.) can also influence 4D objects deemed to satisfy the received particle delivery request.

[0089] Sub-operation 338 also includes evaluating whether each 4D sample object in the identified subset is capable of physically delivering the microparticles. In some methods, this evaluation may involve determining whether the 4D object is configured to receive a container (e.g., encapsulation) containing one or more microparticles. For example, the size, shape, chemical composition, etc., of the microparticles may prevent them from being coupled to and / or placed in certain 4D objects. Similarly, these details may prevent certain microparticles from reaching the target location, for example, depending on the delivery path.

[0090] Additional factors can also be considered when evaluating samples (e.g., potential) 4D objects. For example, identifying 4D objects capable of transporting microparticles involves evaluating details associated with the microparticles, such as their weight, size, and shape. 4D objects capable of transporting microparticles of a specific size can thus be identified as potentially capable of fulfilling microparticle delivery requests.

[0091] The surrounding environment along the delivery path can also affect how the particles are anchored to the 4D object. For example, if the intended delivery path is through a humid environment, some particles may be stored in a waterproof compartment within the 4D object. In another example, if the particles will move through a viscous fluid, the system may need to consider the fluid's viscosity and the Reynolds number of the flow. The system also needs to consider any physical or chemical limitations that could restrict particle movement, such as electrostatic forces or chemical reactions. Therefore, the appropriate selection of particles and their respective motion specifications will be based on the specific details of the application and task.

[0092] In some approaches, the amount and type of mobility associated with delivering particles to a target location are also used to evaluate available 4D objects. For example, information associated with a specific task or activity involving the delivery of particles can be used to identify how the particles should be protected within a 4D object. Based on an example involving medical applications, specific mobility and flexibility associated with navigation within the human body can be considered. In another example, objects designed for manufacturing plants can consider the types of mobility associated with manipulating and transporting materials within the plant. Again, this information can be used to evaluate possible 4D objects and design configurations capable of performing the intended function while maintaining the desired level of mobility and movement.

[0093] From sub-operation 338, the flowchart is shown as returning to... Figure 3A Method 300. Thus, operation 306 can use a trained machine learning model to analyze the request received in operation 302 and determine the 4D object that can most efficiently fulfill the received request. As described above, this can be achieved by using a machine learning model trained to generate and recommend 4D objects that can fulfill the received request to evaluate the feature data associated with the particle delivery request.

[0094] Proceeding to operation 308, the 4D object determined in operation 306 is configured to most efficiently fulfill the received request. In other words, operation 308 involves sending one or more instructions to construct the 4D object output by the machine learning model as a result of executing operation 306. According to some methods, operation 308 may include sending one or more instructions to a manufacturing module configured to construct both 3D and 4D objects (e.g., see [link to relevant documentation]). Figure 2 Manufacturing module 238).

[0095] In response to receiving one or more instructions, the manufacturing module can use one or more additional manufacturing processes to print the requested 4D object. However, it should be noted that other manufacturing processes can be used to construct the 4D object. For example, the resulting 4D object may include 3D components (e.g., compartments) configured to protect the microparticles being delivered. Furthermore, the 3D components may be coupled to the surface of the 4D object. The 3D components are preferably attached to the 4D object such that the microparticles remain firmly coupled to the 4D object even as they travel along the intended delivery path.

[0096] When the transported particles are relatively small and lightweight, they can be directly attached to the surface of a 4D object using one or more adhesives, fasteners, straps, etc. For heavier and larger particles, custom-designed 3D containers can be used to hold both the particles and the 4D object. These custom containers can be designed to attach to the 4D object using clamps, hooks, mechanical fasteners, etc. In some methods, the 4D object may include a built-in container configured to hold the particles. Furthermore, mechanisms for attaching the containers can be implemented to simplify and streamline the attachment process.

[0097] Once the package is securely attached to the 4D object, it is ready to be transported to its target location. Thus, the particle container and the 4D object become a single unit when attached (e.g., coupled). In other words, once attached, the particle container and the 4D object will move together as a single unit. This attachment can be achieved using 3D printing, mechanical fastening, adhesive bonding, etc. The attachment is preferably strong enough to ensure the particles remain intact and do not separate during the movement of the 4D object along the delivery path. The implementation described in this paper can be validated using simulation and / or testing before deploying the system in a real-world scenario.

[0098] Attachment instructions can also be sent to the manufacturing module, for example, to test the constructed 4D objects. For instance, some implementations test each of the constructed 4D objects to ensure they function correctly before being used in real-world applications. Therefore, operation 310 includes sending one or more instructions to apply initial influencing factors to the smart material of the 4D object. As described above, the 4D object formed as a result of one or more instructions sent in operation 306 is configured to deliver particles from a starting position to a target position along a delivery path in response to specific influencing factors applied to its smart material. Depending on the smart material, the 4D object can be configured to respond to influencing factors of different types and intensities. Therefore, the initial influencing factors applied to the 4D object can be determined based on the type of smart material used in the 4D object.

[0099] Operation 312 includes sending instructions to monitor the movement of the 4D object along the transport path in response to the application of initial influencing factors. Operation 314 also includes determining, in the presence of initial influencing factors, whether the 4D object is moving as expected. In other words, operation 314 evaluates the direction, velocity, acceleration, etc., of the 4D object and determines whether the 4D object is currently moving towards the expected target position. Operation 314 may also consider whether the 4D object is currently moving towards the expected target position along the expected delivery path.

[0100] Method 300 is shown to proceed from operation 314 to operation 316 in response to determining that the 4D object has deviated from the delivery path. As described above, the position, direction of movement, speed, etc., of the 4D object can be monitored depending on the method. For example, as those skilled in the art will understand after reading this specification, some methods can monitor the movement of the 4D object by using machine learning models to evaluate images and / or videos captured by a camera.

[0101] For example, computer vision techniques, such as object detection and tracking, can be used to monitor the movement of 4D objects. Object detection algorithms can be used to process captured video feeds to identify 4D objects and particles. Object tracking algorithms can also be used to track the movement of 4D objects and particles over time. Thus, by analyzing the tracking data, any deviations or changes in motion patterns can be identified.

[0102] Sensor-based systems can also be used to monitor the movement of 4D objects and identify any deviations from the intended delivery path. Sensors can include accelerometers and / or gyroscopes that can be attached to the 4D object and / or particle container to measure their movement and orientation. Sensor data can also be processed to identify any deviations from the intended delivery path. In other words, in the event that a 4D object deviates from its intended delivery path, the sensor data will reflect this change in motion, which will be identified and flagged.

[0103] Still referencing Figure 3A Method 300 can then proceed to operation 316 in response to the identification that the 4D object is no longer on the expected delivery path. There, operation 316 involves using one or more trained machine learning models to dynamically weight the influencing factors currently applied to the 4D object. As described above, adjusting the intensity, quantity, type, etc., of the influencing factors applied to the 4D object controls how the smart material behaves. For example, in some methods, increasing the weight applied to the influencing factors can cause more drastic physical deformation of the smart material in the 4D object compared to decreasing the weight applied to the influencing factors. Thus, the movement of the 4D object can be guided by adjusting the weights applied to the influencing factors in real time.

[0104] The shape (e.g., size) of a 4D object can also influence the weights applied to influencing factors. In some methods, various sensors and / or tracking systems, such as cameras, pressure sensors, motion sensors, etc., can be used to determine the shape of the 4D object. These sensors can be placed at key locations on the 4D object to determine its shape and the movement of different parts during deformation. The captured data can be processed and analyzed by machine learning models to track deformation patterns over time. This information can be used to monitor the performance of the 4D object and make any adjustments and / or repairs to improve its functionality.

[0105] For reference only Figure 3C An exemplary sub-operation is shown, based on a method, to dynamically weight the influencing factors currently applied to a 4D object using a machine learning model. Thus, Figure 3C The sub-operations are preferably performed in real time as the information is received (e.g., received and processed from a sensor). For example, a machine learning model can evaluate the deformation of a 4D object as it moves relative to an applied influencing factor.

[0106] In some approaches, this assessment can involve analyzing changes in the shape and size of a 4D object as it moves, and how these changes relate to the forces acting upon it. This can help identify any areas of the 4D object that are subjected to higher stresses or strains than expected, and further refine the design to increase operational efficiency and durability. Figure 3C One or more suboperations in this context can thus be used to perform... Figure 3A Operation 316. However, it should be noted that, Figure 3C The sub-procedures are illustrated according to a method that is by no means intended to limit this disclosure.

[0107] In some approaches, machine learning models may include convolutional neural networks (CNNs) and / or other types of deep learning algorithms capable of performing image analysis and recognition tasks. For example, CNNs include multiple layers of convolution and pooling operations, which can be used to identify features in complex datasets, such as images. The output of the convolutional layers can then be passed through fully connected layers, which are used to make predictions based on the identified features.

[0108] Based on the example, a CNN can be used to analyze deformation patterns of 4D objects, where the input data to be analyzed includes images and / or videos of 4D objects undergoing deformation. The CNN is then trained to recognize patterns in the deformation that correspond to specific types and intensities of influencing factors. For example, the CNN can learn to recognize specific deformation patterns that correspond to a specific type of force being applied to a particular 4D object. Once trained, the CNN can be used to analyze new images or videos of 4D objects undergoing deformation and movement. Furthermore, these CNNs may be able to dynamically generate adjustments to the type and intensity of influencing factors applied to the 4D object to ensure they remain on the intended delivery path.

[0109] Still referencing Figure 3C Sub-operation 352 includes determining the amount of force generated by the 4D object in response to a current influencing factor applied to the smart material. Furthermore, sub-operation 354 includes comparing the amount of force determined in sub-operation 352 with the movement of the 4D object experienced in response to the application of the current influencing factor. Additionally, sub-operation 356 includes generating a weight value configured to adjust the 4D object's backward movement along the delivery path in response to applying that weight value to an initial influencing factor.

[0110] By comparing the amount of force generated with the actual amount of movement experienced by the 4D object, machine learning models can be used to determine how influencing factors should be adjusted to ensure that the 4D object is on the expected delivery path.

[0111] To achieve this, it is preferable to measure the displacement of the 4D printing robot and the relative deformation of the smart material. Various sensors, such as strain gauges and displacement sensors, can be used to measure the displacement. Therefore, the system can calculate the force that generates the displacement based on factors such as the type of smart material used, its characteristics, and the magnitude of the deformation caused by external factors. It should also be noted that a library of feature data and how different types of feature data interact with each other can be used to train a machine learning model. Thus, any machine learning model described herein can be implemented to perform… Figure 3C Suboperations 352, 354, and 356.

[0112] return Figure 3A Method 300 is shown to proceed from operation 316 to operation 318. Similarly, in response to determining that the 4D object is behaving as expected given the presence of current influencing factors, method 300 proceeds from operation 314 to operation 318. In other words, method 300 proceeds from operation 314 to operation 318 in response to determining that the 4D object has returned to the expected delivery path.

[0113] There, operation 318 includes determining whether the 4D object has reached the target position. In response to determining that the 4D object has not yet reached the target position, method 300 returns to operation 312, allowing the movement of the 4D object to continue being monitored. However, in response to determining that the 4D object has reached the target position, method 300 proceeds from operation 318 to operation 320. There, operation 320 includes sending one or more instructions to remove any influencing factors from the smart material applied to the 4D object. By removing the influencing factors, the 4D object preferably stops moving.

[0114] Method 300 may terminate in response to sending one or more instructions in operation 320. However, it should be noted that although method 300 may terminate upon reaching operation 320, any or more processes included in method 300 may be repeated to satisfy additional particle delivery requests. In other words, any or more processes included in method 300 may be repeated for subsequently received particle delivery requests.

[0115] Furthermore, the operations and sub-operations of method 300 are capable of evaluating particle delivery requests, generating (e.g., designing and constructing) 4D objects configured to efficiently fulfill the requests, and improving the performance of the 4D objects based on usage over time. Method 300 is thus able to process particles and deliver them to their intended target locations, despite spatial constraints. This significant increase in particle applicability is achieved in the implementation of this paper because the development (e.g., design and construction) of 4D objects is configured to transport particles to target locations. The process of developing 4D objects involves using a trained machine learning model to evaluate the feature details of the received particle delivery requests and determine the 4D objects configured to most efficiently deliver particles to the target locations.

[0116] As described above, 4D objects can generate motion without relying on any mechanical structure. Instead, by implementing smart materials in different configurations, the 4D objects presented in this paper are capable of transporting particles, allowing the 4D objects to move in the presence of one or more influencing factors. The characteristics of the 4D objects can also be adjusted based on the target location of the particles and / or any details along their path. This allows the method presented in this paper to monitor the motion of the 4D objects during use and dynamically redirect the objects to their appropriate targets in real time. As a result, the implementation presented in this paper is able to create 4D objects configured to efficiently deliver particles to target locations, and to monitor and refine the performance of the 4D objects. This allows for further performance improvement over time as the machine learning model is further trained.

[0117] Now for reference Figure 4 A flowchart of method 409 according to a method is shown. Method 409 can be implemented according to this disclosure. Figure 1-3BIt can be performed in any environment depicted herein using various methods, etc. Of course, as those skilled in the art will understand upon reading this specification, method 409 may include methods such as... Figure 4 The specific operations described in the text may include more or fewer operations.

[0118] Each step of method 409 can be performed by any suitable component of the operating environment. For example, in various methods, method 409 can be performed partially or entirely by processing circuitry, such as an IaC access manager, or some other device having one or more processors. A processor (e.g., processing circuitry, a chip, and / or module implemented in hardware and / or software, and preferably having at least one hardware component) can be used in any device to perform one or more steps of method 409. Illustrative processors include, but are not limited to, central processing units (CPUs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), combinations thereof, or any other suitable computing devices known in the art.

[0119] While it is understood that processing software associated with evaluating particle delivery requests, generating (e.g., designing and constructing) 4D objects configured to effectively fulfill the requests, and improving the performance of 4D objects over time can be deployed manually by loading it directly onto client, server, and proxy computers via storage media such as CDs, DVDs, etc., the processing software can also be deployed automatically or semi-automatically to computer systems by sending it to a central server or a set of central servers. The processing software is then downloaded to the client computer that will execute it. Alternatively, the processing software can be sent directly to the client system via email. The processing software is then separated into or loaded into a directory by executing a set of program instructions to separate it into a directory. Another alternative is to send the processing software directly to a directory on the client computer's hard drive. When a proxy server is present, the process selects proxy server code, determines which computers the proxy server code will be placed on, transmits the proxy server code, and then installs the proxy server code on the proxy computers. The processing software is sent to the proxy server, and then it is stored on the proxy server.

[0120] Continuing with method 409, step 400 begins the deployment of the process software. The initial step is to determine whether any program will reside on one or more servers when the process software is executed (401). If so, the server that will contain the executable program is identified (509). The process software for one or more servers is transferred directly to the server's storage via FTP or some other protocol, or by copying using a shared file system (510). The process software is then installed on the server (511).

[0121] Next, it is determined whether to deploy the processing software by having a user access the processing software on one or more servers (402). If the user wants to access the processing software on the server, the server address where the processing software will be stored is identified (403).

[0122] Determine whether to establish a proxy server (500) to store the processing software. A proxy server is a server located between a client application, such as a web browser, and the real server. It intercepts all requests to the real server to see if it can fulfill the request itself. If not, it forwards the request to the real server. Two main benefits of a proxy server are improved performance and filtering of requests. If a proxy server is needed, it is installed (501). The processing software is sent to the server(s) via a protocol such as FTP, or copied directly from the source file to the server file via file sharing (502). Another method involves sending a transaction to the server(s) containing the processing software and having the server process the transaction, then receiving the processing software and copying it to the server's file system. Once the processing software is stored on the server, the user accesses the processing software on the server through their client computer and copies it to their client computer's file system (503). Another method is to have the server automatically copy the processing software to each client and then run an installer for the processing software on each client computer. The user executes a program (512) to install the processing software on their client computer, and then exits the process (408).

[0123] In step 404, it is determined whether to deploy the processing software by sending it to users via email. The set of users to be deployed with the processing software and the addresses of their client computers are identified (405). The processing software is sent to each user's client computer via email (504). The user then receives the email (505) and detaches the processing software from the email to a directory on their client computer (506). The user executes a program to install the processing software on their client computer (512) and then exits the process (408).

[0124] Finally, it is determined whether the processing software should be sent directly to the user's directory on their client computer (406). If so, the user directory is identified (407). The processing software is then transferred directly to the user's client computer directory (507). This can be done in several ways, such as, but not limited to, sharing a file system directory and then copying it from the sender's file system to the recipient's file system, or alternatively, using a transfer protocol such as File Transfer Protocol (FTP). The user accesses the directory on their client file system to prepare for the installation of the processing software (508). The user executes the program to install the processing software on their client computer (512) and then exits the process (408).

[0125] It will also be understood that the methods disclosed herein may be provided in the form of services deployed on behalf of clients to provide services on demand.

[0126] Various methods of this disclosure have been described for illustrative purposes, but are not intended to be exhaustive or limited to the disclosed methods. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described methods. The terminology used herein has been chosen to best explain the principles of the methods, their practical application, or technical improvements found in the market, or to enable others skilled in the art to understand the methods disclosed herein.

Claims

1. A computer-implemented method, comprising: Send one or more instructions to apply initial influencing factors to a smart material of a 4D object, wherein the 4D object is configured to deliver one or more particles from a starting position to a target position along a delivery path in response to the application of the initial influencing factors to the smart material; Send one or more instructions to monitor the movement of the 4D object along the delivery path in response to the application of the initial influencing factors to the smart material; and In response to determining that the 4D object has deviated from the delivery path, one or more instructions are sent to dynamically weight the initial influencing factors applied to the smart material using one or more machine learning models.

2. The computer-implemented method according to claim 1, wherein, Sending one or more instructions to dynamically weight the initial influencing factors using the one or more machine learning models includes: Determine the amount of force generated by the 4D object in response to the application of the initial influencing factors to the smart material; The amount of force generated by the 4D object is compared with the movement of the 4D object along the delivery path in response to the application of the initial influencing factors to the smart material; and A weight value is generated, which is configured to adjust the movement of the 4D object back along the delivery path in response to applying the weight value to the initial influencing factor.

3. The computer-implemented method according to claim 1, wherein, The 4D object includes the smart material and the static material, wherein the smart material is configured to physically deform in response to the initial influencing factor being applied to it.

4. The computer-implemented method according to claim 3, wherein, The smart material is configured to generate forces that can physically move the 4D object due to physical deformation.

5. The computer-implemented method according to claim 3, wherein, The one or more machine learning models are trained using a repository of feature data corresponding to different influencing factors and how they affect the physical deformation of different smart materials.

6. The computer-implemented method according to claim 5, wherein, The storage includes feature data corresponding to different surrounding environments and how these data affect the physical deformation of the corresponding smart materials in the storage.

7. The computer-implemented method according to claim 1, wherein, The influencing factors are selected from the group consisting of: light, heat, magnetic field, sound, and electricity.

8. The computer-implemented method according to claim 1, further comprising: In response to determining that the 4D object has not deviated from the delivery path, one or more instructions are sent to maintain the initial influencing factors applied to the smart material; as well as In response to determining that the 4D object has reached the target location, one or more instructions are sent to remove the initial influencing factor from the smart material.

9. A computer program product comprising a computer-readable storage medium having program instructions embodied therein, the program instructions being readable by a processor, executable by the processor, or readable and executable by the processor to cause the processor to: Send one or more instructions to apply initial influencing factors to the smart material of the 4D object, wherein, The 4D object is configured to deliver one or more particles from a starting position to a target position along a delivery path in response to the initial influencing factor being applied to the smart material; Send one or more instructions to monitor the movement of the 4D object along the delivery path in response to the application of the initial influencing factors to the smart material; as well as In response to determining that the 4D object has deviated from the delivery path, one or more instructions are sent to dynamically weight the initial influencing factors applied to the smart material using one or more machine learning models.

10. The computer program product according to claim 9, wherein, Sending one or more instructions to dynamically weight the initial influencing factors using the one or more machine learning models includes: Determine the amount of force generated by the 4D object in response to the application of the initial influencing factors to the smart material; The amount of force generated by the 4D object is compared with the movement of the 4D object along the delivery path in response to the application of the initial influencing factors to the smart material; and A weight value is generated, which is configured to adjust the movement of the 4D object back along the delivery path in response to applying the weight value to the initial influencing factor.

11. The computer program product according to claim 9, wherein, The 4D object includes the smart material and the static material, wherein the smart material is configured to physically deform in response to the initial influencing factor being applied to it.

12. The computer program product according to claim 11, wherein, The smart material is configured to generate forces that can physically move the 4D object due to physical deformation.

13. The computer program product according to claim 11, wherein, The one or more machine learning models are trained using a repository of feature data corresponding to different influencing factors and how they affect the physical deformation of different smart materials.

14. The computer program product according to claim 13, wherein, The storage includes feature data corresponding to different surrounding environments and how these data affect the physical deformation of the corresponding smart materials in the storage.

15. The computer program product according to claim 9, wherein, The influencing factors are selected from the group consisting of: light, heat, magnetic field, sound, and electricity.

16. The computer program product according to claim 9, wherein, The program instructions are readable and / or executable by the processor, so as to cause the processor to: In response to determining that the 4D object has not deviated from the delivery path, one or more instructions are sent to maintain the initial influencing factors applied to the smart material; as well as In response to determining that the 4D object has reached the target location, one or more instructions are sent to remove the initial influencing factor from the smart material.

17. A system comprising: processor; as well as Logic integrated with the processor and executable by the processor, or logic integrated with the processor and executable by the processor, wherein the logic is configured to: Send one or more instructions to apply initial influencing factors to a smart material of a 4D object, wherein the 4D object is configured to deliver one or more particles from a starting position to a target position along a delivery path in response to the application of the initial influencing factors to the smart material; Send one or more instructions to monitor the movement of the 4D object along the delivery path in response to the application of the initial influencing factors to the smart material; and In response to determining that the 4D object has deviated from the delivery path, one or more instructions are sent to dynamically weight the initial influencing factors applied to the smart material using one or more machine learning models.

18. The system according to claim 17, wherein, Sending one or more instructions to dynamically weight the initial influencing factors using the one or more machine learning models includes: Determine the amount of force generated by the 4D object in response to the application of the initial influencing factors to the smart material; The amount of force generated by the 4D object is compared with the movement of the 4D object along the delivery path in response to the application of the initial influencing factors to the smart material; and A weight value is generated, which is configured to adjust the movement of the 4D object back along the delivery path in response to applying the weight value to the initial influencing factor.

19. The system according to claim 17, wherein, The 4D object includes the smart material and the static material, wherein the smart material is configured to physically deform in response to the initial influencing factor being applied to it.

20. The system according to claim 17, wherein, The logic is configured as follows: In response to determining that the 4D object has not deviated from the delivery path, one or more instructions are sent to maintain the initial influencing factors applied to the smart material; as well as In response to determining that the 4D object has reached the target location, one or more instructions are sent to remove the initial influencing factor from the smart material.

Images