A method, device, storage medium and equipment for generating material structure data

Abstract

The present specification discloses a method, apparatus, storage medium and device for generating material structure data, which inputs generation task text data for characterizing the constraints of a cell structure to be generated by a user into a pre-trained large language model, so as to generate cell structure text data satisfying the constraints based on the generation task text data through the large language model, so as to combine the large language model with the cell design, thereby utilizing the high efficiency and generalization ability of the large language model to generate cell structure text data satisfying the constraints specified by the user, thereby improving the generation efficiency of the cell structure text data.

Description

Technical Field

[0001] The present invention relates to the field of material science and technology, and in particular to a method, device, storage medium and equipment for generating material structure data. Background Art

[0002] Currently, in materials science research, cell design is a method to regulate and optimize the macroscopic properties of materials by carefully planning the microscopic structural units (i.e., cells). As the basic building blocks of materials, cells are composed of points (nodes, i.e., the intersections between multiple rods) and rods (rods, beams or connectors, i.e., linear components connecting two or more nodes). The different compositions of points and rods in the cell structure make the shape, size, and arrangement of the cell structure different, which in turn makes the overall properties of the material different. Therefore, by adjusting the settings of the points and rods contained in the cell structure, highly precise control of material properties can be achieved to meet the needs of specific application scenarios.

[0003] However, since the relationship between factors such as the shape, size, arrangement and internal microstructure of the cell and the overall properties of the material is often complex, a large number of experiments and simulations are required to design different cell structures, which leads to low efficiency in cell structure design.

[0004] Therefore, how to improve the efficiency of cell structure design is an urgent problem to be solved. Summary of the invention

[0005] This specification provides a method, device, storage medium and equipment for generating material structure data to partially solve the above-mentioned problems existing in the prior art.

[0006] This manual adopts the following technical solutions:

[0007] This specification provides a method for generating material structure data, including:

[0008] Acquire generation task text data, where the generation task text data is used to characterize constraint conditions of a cell structure to be generated;

[0009] Inputting the generated task text data into a pre-trained large language model, so as to generate cell structure text data satisfying the constraint conditions according to the generated task text data through the large language model, wherein the cell structure text data is used to characterize the position and connection relationship of each node and / or rod, and each node and / or rod is used to form a cell structure;

[0010] A three-dimensional model of the cell structure is constructed according to the cell structure text data, and a task is executed according to the three-dimensional model of the cell structure.

[0011] Optionally, the generated task text data is obtained, specifically including:

[0012] Receive a task description statement input by a user;

[0013] According to the task description statement and the preset supplementary constraint statement, the generated task text data is obtained, wherein the task description statement is used to characterize the basic constraint conditions of the cell structure to be generated, and the supplementary constraint statement is used to characterize the number and format of the cell structure to be generated.

[0014] Optionally, the generation task text data is input into a pre-trained large language model, so as to generate cell structure text data satisfying the constraint condition according to the generation task text data through the large language model, specifically including:

[0015] Acquire a period configuration parameter that matches the task text data, wherein the period configuration parameter is used to characterize a time interval period for repeatedly generating cell structure text data according to the task text data;

[0016] According to the cycle configuration parameters, the generated task text data is repeatedly input into a pre-trained large language model, so that each cell structure text data satisfying the constraint condition is generated according to the generated task text data through the large language model.

[0017] Optionally, before constructing the cell structure three-dimensional model according to the cell structure text data, the method further includes:

[0018] Generate verification task text data according to the generated task text data, input the verification task text data into a pre-trained large language model, so as to generate verification cell structure text data satisfying the constraint conditions according to the verification task text data through the large language model, wherein the verification task text data is used to characterize the specified structural performance characteristics required for the cell structure to be generated to satisfy the constraint conditions;

[0019] According to the verification task text data, the cell structure text data is verified to obtain a structural performance feature verification result corresponding to the cell structure text data, wherein the structural performance feature verification result is used to characterize whether the cell structure text data has a specified structural performance feature corresponding to the verification cell structure text data;

[0020] According to the cell structure text data, a cell structure three-dimensional model is constructed, which specifically includes:

[0021] If it is determined based on the structural performance feature verification result that the cell structure text data has the specified structural performance feature corresponding to the verified cell structure text data, a cell structure three-dimensional model is constructed based on the cell structure text data.

[0022] Optionally, for each cell structure text data, the cell structure text data is verified according to the verification task text data to obtain a structural performance feature verification result corresponding to the cell structure text data, specifically including:

[0023] Determine a consistency coefficient between the cell structure text data and the verification cell structure text data, and determine a structural performance feature verification result of the cell structure text data based on the consistency coefficient.

[0024] Optionally, performing a task according to the three-dimensional model of the cell structure specifically includes:

[0025] Performing simulation tests on the three-dimensional model of the cell structure to determine material performance parameters of the three-dimensional model of the cell structure, and judging whether the material performance parameters meet preset screening conditions, wherein the material performance parameters include at least one of volume fraction, Young's modulus, and ultimate strength;

[0026] If so, the task is executed according to the three-dimensional model of the cell structure.

[0027] Optionally, performing a task according to the three-dimensional model of the cell structure specifically includes:

[0028] In the case where there are multiple three-dimensional cell structure models, determining the order of the three-dimensional cell structure models according to the material performance parameters of the three-dimensional cell structure models, and generating a screenshot image of each three-dimensional cell structure model;

[0029] The screenshot images and the material performance parameters are recommended to the user according to the sequence, and the task is executed according to the operation instructions sent by the user for the screenshot images and the material performance parameters.

[0030] This specification provides a device for generating material structure data, including:

[0031] An acquisition module, used for acquiring generation task text data, wherein the generation task text data is used for representing the constraint conditions of the cell structure to be generated;

[0032] A generation module, used for inputting the generation task text data into a pre-trained large language model, so as to generate cell structure text data satisfying the constraint conditions according to the generation task text data through the large language model, wherein the cell structure text data is used for characterizing the position and connection relationship of each node and / or rod, and each node and / or rod is used for forming a cell structure;

[0033] An execution module is used to construct a three-dimensional model of the cell structure according to the cell structure text data, and to perform tasks according to the three-dimensional model of the cell structure.

[0034] This specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for generating material structure data is implemented.

[0035] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for generating material structure data when executing the program.

[0036] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0037] In the method for generating material structure data provided in the present specification, firstly, generation task text data for characterizing the constraint conditions of the cell structure to be generated is obtained, and the generation task text data is input into a pre-trained large language model, so as to generate cell structure text data that meets the constraint conditions according to the generation task text data through the large language model, wherein the cell structure text data is used to characterize the position and connection relationship of each node and / or rod, each node and / or rod is used to form a cell structure, and a three-dimensional model of the cell structure is constructed according to the cell structure text data, and the task is executed according to the three-dimensional model of the cell structure.

[0038] It can be seen from the above method that the large language model can be combined with cell design to utilize the high efficiency and generalization ability of the large language model to generate cell structure text data that meets the constraints specified by the user, so as to improve the generation efficiency of cell structure text data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0040] Figure 1 A schematic diagram of a method for generating material structure data provided in this specification;

[0041] Figure 2 A schematic diagram of the cell structure text data screening process provided in this specification;

[0042] Figure 3 A schematic diagram of the task execution process provided in this manual;

[0043] Figure 4 A schematic diagram of a device for generating material structure data provided in this specification;

[0044] Figure 5 A method corresponding to the Figure 1 Schematic diagram of electronic equipment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0046] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0047] Figure 1 A schematic diagram of a method for generating material structure data provided in this specification includes the following steps:

[0048] S101: Acquire generation task text data, where the generation task text data is used to characterize constraint conditions of a cell structure to be generated.

[0049] In this specification, when a user needs to obtain a cell structure, he can send a task description statement to the business platform through the device used. After receiving the task description statement input by the user, the business platform can obtain the generated task text data based on the received task description statement, and then generate the cell structure based on the generated task text data.

[0050] The above task description statement is used to characterize the basic constraints of the cell structure to be generated.

[0051] For example: Generate a cell structure with a volume fraction of 15%.

[0052] Another example: generating a cellular structure with an ultimate strength between 0.1 MPa and 10 MPa.

[0053] The above-mentioned generation task text data is used to characterize the constraints of the cell structure that needs to be generated.

[0054] For example: Please generate a cell structure with a volume fraction between 15% and 30%.

[0055] Another example: please generate a cell structure with an ultimate strength between 0.1 MPa and 10 MPa.

[0056] In actual application scenarios, the business platform can also generate task text data based on the received task description statement and preset supplementary constraint statements after receiving the task description statement input by the user, wherein the above-mentioned supplementary constraint statements are used to characterize the number and format of cell structures that need to be generated.

[0057] For example, please generate ten cell structures with volume fractions between 15% and 30%. For each output cell structure, please use the lightweight data exchange format (JavaScript Object Notation, JSON) to represent the data.

[0058] It should be noted that after obtaining the generated task text data, the business platform can also display the obtained generated task text data to the user, and receive the user's operation instructions to edit, modify, delete or confirm the generated task text data, so as to determine the final generated task text data based on the received operation instructions.

[0059] In this specification, the execution entity used to implement the method for generating material structure data may refer to a designated device such as a server set up on a business platform, or may refer to a terminal device such as a desktop computer or a laptop computer. For the sake of ease of description, the method for generating material structure data provided in this specification is described below using the server as an example of the execution entity.

[0060] S102: Input the generated task text data into a pre-trained large language model, so as to generate cell structure text data satisfying the constraint conditions according to the generated task text data through the large language model, wherein the cell structure text data is used to characterize the position, size, and shape of each node and / or rod, and each node and / or rod is used to form a cell structure.

[0061] Furthermore, after acquiring the generated task text data, the server can input the generated task text data into a pre-trained large language model, so as to generate cell structure text data that meets the constraint conditions corresponding to the generated task text data based on the generated task text data through the large language model.

[0062] The above-mentioned cell structure text data is used to characterize the position and connection relationship of each node and / or rod, and the above-mentioned each node and / or rod is used to form a cell structure.

[0063] In actual application scenarios, the above-mentioned large language model can be deployed to the server for task execution only after training, wherein the training method of the above-mentioned large language model can be to obtain sample generation task text data, input the sample generation task text data into the pre-trained large language model, so as to generate cell structure text data that meets the constraints corresponding to the sample generation task text data according to the sample generation task text data through the large language model, as sample cell structure text data.

[0064] Furthermore, the server can determine the target loss based on the deviation between the sample cell structure text data and the standard cell structure text data corresponding to the sample generation task text data, and train the large language model with minimizing the target loss as the optimization goal to obtain the trained large language model.

[0065] Among them, the greater the deviation between the above-mentioned sample cell structure text data and the standard cell structure text data corresponding to the sample generation task text data, the greater the determined target loss.

[0066] In addition, the server can also obtain periodic configuration parameters that match the task text data, and then can repeatedly input the generated task text data into the pre-trained large language model according to the above-mentioned periodic configuration parameters, so that the large language model can regenerate the cell structure text data that meets the constraint conditions according to the generated task text data for each input, and finally obtain the cell structure text data that meets the constraint conditions output by the large language model.

[0067] The above-mentioned period configuration parameters are used to characterize the time interval period for repeatedly generating cell structure text data according to task text data.

[0068] For example, from 4:00 p.m. to 5:45 p.m. on day c of year a, cell structure text data is generated every five minutes through a large language model.

[0069] S103: constructing a three-dimensional model of the cell structure according to the cell structure text data, and executing the task according to the three-dimensional model of the cell structure.

[0070] Furthermore, after obtaining the text data of each cell structure, the server can verify the structural performance characteristics that the cell structure text data is required to have, so as to screen the text data of each cell structure, wherein the structural performance characteristics here may be such as: validity (i.e., whether the estimated material performance parameters of the cell structure meet the preset targets), symmetry (i.e., the cell structure is symmetrical), connectivity (i.e., each rod in the cell structure is connected to at least one other rod), conformity (i.e., the intersection points and line segments of each face of the cell structure can coincide with the intersection points and line segments on other faces), etc.

[0071] It should be noted that for different structural performance characteristics, the verification method adopted by the server is also different. Specifically, the verification method for the validity of the cellular structure text data can be to determine the internal stress distribution, deformation mode and failure mechanism of the cellular structure through finite element analysis (FEA), and then obtain the structural performance characteristic verification result corresponding to the cellular structure text data.

[0072] A method for verifying the symmetry and connectivity of cell structure text data may be to analyze the position information of the points and rods of the cell structure contained in the cell structure text data to determine the verification result of the structural performance characteristics corresponding to the cell structure text data.

[0073] In addition, a method for verifying the commonality of cell structure text data can be to generate verification task text data based on generated task text data, wherein the verification task text data here is used to characterize the specified structural performance characteristics that the cell structure to be generated that meets the constraints corresponding to the generated task text data is required to possess.

[0074] For example, the verification task text data mentioned above may be “Please generate a common type of cell structure with a volume fraction of 15%”.

[0075] Furthermore, the server can input the verification task text data into a pre-trained large language model to generate verification cell structure text data that meets the constraints corresponding to the generated task text data based on the verification task text data through the large language model, so that the cell structure text data can be verified based on the verification task text data to obtain the structural performance characteristic verification results corresponding to the cell structure text data.

[0076] The above-mentioned specified structural performance characteristics may refer to the commonality of the cell structure text data, and the above-mentioned structural performance characteristics verification result is used to characterize whether the cell structure text data has the structural performance characteristics corresponding to the verified cell structure text data.

[0077] In the above content, the server verifies the cell structure text data according to the verification task text data, and the method for obtaining the structural performance characteristic verification result corresponding to the cell structure text data can be to determine the consistency coefficient between the cell structure text data and the verification cell structure text data, and determine the structural performance characteristic verification result of the cell structure text data according to the consistency coefficient.

[0078] Specifically, if the server determines that the consistency coefficient between the cell structure text data and the verification cell structure text data is higher than a preset consistency coefficient threshold, it can be determined that the cell structure text data has the specified structural performance characteristics corresponding to the verification cell structure text data.

[0079] Furthermore, the server can screen the cell structure text data generated by the large language model according to each structural performance feature verification result of each cell structure text data, as shown in the following example: Figure 2 shown.

[0080] Figure 2 A schematic diagram of the cell structure text data screening process provided in this manual.

[0081] Combination Figure 2 It can be seen that for each cell structure text data, when the server verifies the results of each structural performance feature of the cell structure text data and determines that the cell structure text data has each structural performance feature, it can construct a cell structure three-dimensional model corresponding to the cell structure text data based on the cell structure text data.

[0082] In addition, if the server verifies the results of each structural performance feature of the cell structure text data and determines that the cell structure text data does not have each structural performance feature, the cell structure text data can be saved in a preset abnormal structure data set, and the model parameters of the large language model can be fine-tuned based on the abnormal structure data set.

[0083] Specifically, for each cell structure text data in the abnormal structure data set, the standard cell structure text data of the generated task text data corresponding to the cell structure text data is obtained, and the adjustment loss is determined according to the deviation between the cell structure text data and the standard cell structure text data. With minimizing the adjustment loss as the optimization goal, the model parameters of the large language model are adjusted to obtain the adjusted large language model.

[0084] Furthermore, for each cellular structure three-dimensional model, the server can perform simulation tests on the cellular structure three-dimensional model to determine the material performance parameters of the cellular structure three-dimensional model, and then determine whether the material performance parameters of the cellular structure three-dimensional model meet the preset screening conditions. If so, the task can be executed according to the cellular structure three-dimensional model.

[0085] The material performance parameters include at least one of volume fraction, Young's modulus, and ultimate strength.

[0086] In the above content, the preset filtering conditions can be determined based on the configuration information input by the user, for example: determining whether the volume fraction in the material performance parameters of the cellular structure three-dimensional model exceeds a preset threshold. If so, determining that the cellular structure three-dimensional model meets the preset filtering conditions.

[0087] For another example: determine whether the ultimate strength in the material performance parameters of the cellular structure three-dimensional model exceeds a preset threshold value. If so, determine that the cellular structure three-dimensional model meets the preset screening conditions, etc.

[0088] In the above content, the method for the server to perform the task according to each cell structure three-dimensional model that meets the preset screening condition may be, when there are multiple cell structure three-dimensional models that meet the preset screening condition, determining the order between each cell structure three-dimensional model according to the material performance parameters of each cell structure three-dimensional model, and performing the task according to the order between each cell structure three-dimensional model, specifically as follows Figure 3 shown.

[0089] Figure 3 A schematic diagram of the task execution process provided in this manual.

[0090] Combination Figure 3 It can be seen that the server can determine the order of each cell structure three-dimensional model according to the material performance parameters of each cell structure three-dimensional model, and generate a screenshot image of each cell structure three-dimensional model. Then, according to the order of each cell structure three-dimensional model, the screenshot image and material performance parameters of each cell structure three-dimensional model can be recommended to the user, and the task can be executed according to the operation instructions sent by the user for the screenshot image of each cell structure three-dimensional model and the material performance parameters.

[0091] Specifically, the server determines the order of the cellular structure three-dimensional models according to the material performance parameters of each cellular structure three-dimensional model by, according to a preset sorting rule, determining the order of the cellular structure three-dimensional models according to the material performance parameters of each cellular structure three-dimensional model.

[0092] Among them, the above-mentioned sorting rules can be set according to actual needs, for example: sorting each cellular structure three-dimensional model according to the volume fraction in the material performance parameters of each cellular structure three-dimensional model; for each cellular structure three-dimensional model with the same volume fraction, sorting these cellular structure three-dimensional models according to the ultimate strength in the material performance parameters of these cellular structure three-dimensional models; for each cellular structure three-dimensional model with the same volume fraction and ultimate strength, sorting these cellular structure three-dimensional models according to the Young's modulus in the material performance parameters of these cellular structure three-dimensional models.

[0093] The above-mentioned server recommends the screenshot image and material performance parameters of each cell structure three-dimensional model to the user, and there are multiple ways to execute the task according to the operation instructions sent by the user for the screenshot image and the material performance parameters of each cell structure three-dimensional model.

[0094] For example: the server sends the screenshot image and material performance parameters of each cellular structure three-dimensional model to the device used by the user via email, so as to display the screenshot image and material performance parameters of each cellular structure three-dimensional model to the user through the device used by the user, and obtains the reply email returned by the device used by the user according to the operation instructions sent by the user for the screenshot image of each cellular structure three-dimensional model and the material performance parameters, and then the task can be executed according to the reply email.

[0095] As another example: the server sends the screenshot image and material performance parameters of each cell structure three-dimensional model to the device used by the user through instant messaging, so as to display the screenshot image and material performance parameters of each cell structure three-dimensional model to the user through the device used by the user, and obtains the reply information returned by the device used by the user according to the operation instructions sent by the user for the screenshot image of each cell structure three-dimensional model and the material performance parameters, and then can execute the task according to the reply information.

[0096] It can be seen from the above method that the server can combine the large language model with the cell design to utilize the high efficiency and generalization ability of the large language model to generate cell structure text data that meets the constraints specified by the user, so as to improve the generation efficiency of the cell structure text data.

[0097] The above is one or more methods for generating material structure data in this specification. Based on the same idea, this specification also provides a corresponding device for generating material structure data, such as Figure 4 shown.

[0098] Figure 4 A schematic diagram of a device for generating material structure data provided in this specification, comprising:

[0099] An acquisition module 401 is used to acquire generation task text data, where the generation task text data is used to characterize the constraint conditions of the cell structure to be generated;

[0100] A generation module 402 is used to input the generation task text data into a pre-trained large language model, so as to generate cell structure text data satisfying the constraint conditions according to the generation task text data through the large language model, wherein the cell structure text data is used to characterize the position and connection relationship of each node and / or rod, and each node and / or rod is used to form a cell structure;

[0101] The execution module 403 is used to construct a three-dimensional model of the cell structure according to the cell structure text data, and perform task execution according to the three-dimensional model of the cell structure.

[0102] Optionally, the acquisition module 401 is specifically used to receive a task description statement input by a user; and to acquire generated task text data according to the task description statement and a preset supplementary constraint statement, wherein the task description statement is used to characterize the basic constraint conditions of the cell structure to be generated, and the supplementary constraint statement is used to characterize the number and format of the cell structure to be generated.

[0103] Optionally, the generation module 402 is specifically used to obtain a period configuration parameter that matches the task text data, and the period configuration parameter is used to characterize the time interval period for repeatedly generating cell structure text data according to the task text data; according to the period configuration parameter, the generated task text data is repeatedly input into a pre-trained large language model, so as to generate each cell structure text data that meets the constraint condition according to the generated task text data through the large language model.

[0104] Optionally, the device further includes: a verification module 404;

[0105] The verification module 404 is specifically used to generate verification task text data according to the generated task text data, input the verification task text data into a pre-trained large language model, so as to generate verification cell structure text data that meets the constraint conditions according to the verification task text data through the large language model, and the verification task text data is used to characterize the specified structural performance characteristics that the cell structure that needs to be generated to meet the constraint conditions needs to have; verify the cell structure text data according to the verification task text data to obtain a structural performance characteristic verification result corresponding to the cell structure text data, and the structural performance characteristic verification result is used to characterize whether the cell structure text data has the specified structural performance characteristics corresponding to the verification cell structure text data;

[0106] The execution module 403 is specifically used to construct a cell structure three-dimensional model according to the cell structure text data if it is determined according to the structural performance feature verification result that the cell structure text data has the specified structural performance feature corresponding to the verified cell structure text data.

[0107] Optionally, the verification module 404 is specifically used to determine a consistency coefficient between the cell structure text data and the verification cell structure text data, and determine a structural performance feature verification result of the cell structure text data based on the consistency coefficient.

[0108] Optionally, the execution module 403 is specifically used to perform simulation tests on the three-dimensional model of the cellular structure to determine the material performance parameters of the three-dimensional model of the cellular structure, and to judge whether the material performance parameters meet preset screening conditions, and the material performance parameters include: volume fraction, Young's modulus, and at least one of ultimate strength; if so, the task is executed according to the three-dimensional model of the cellular structure.

[0109] Optionally, the execution module 403 is specifically used to, when there are multiple three-dimensional models of the cell structure, determine the order of the three-dimensional models of the cell structure according to the material performance parameters of the three-dimensional models of the cell structure, and generate a screenshot image of each three-dimensional model of the cell structure; according to the order, recommend the screenshot image and the material performance parameters to the user, and perform the task according to the operation instructions sent by the user for the screenshot image and the material performance parameters.

[0110] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 A method for generating material structure data is provided.

[0111] This manual also provides Figure 5 The one shown corresponds to Figure 1 A schematic diagram of the electronic device. Figure 5 As mentioned above, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 Of course, in addition to the software implementation, this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0112] For the improvement of a technology, it can be clearly distinguished whether it is a hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or a software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0113] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0114] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0115] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0116] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0118] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0120] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0121] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0122] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0123] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0124] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0126] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0127] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A method for generating material structure data, characterized in that: include: Acquire generation task text data, where the generation task text data is used to characterize constraint conditions of a cell structure to be generated; Inputting the generated task text data into a pre-trained large language model, so as to generate cell structure text data satisfying the constraint conditions according to the generated task text data through the large language model, wherein the cell structure text data is used to characterize the position and connection relationship of each node and / or rod, and each node and / or rod is used to form a cell structure; A three-dimensional model of the cell structure is constructed according to the cell structure text data, and a task is executed according to the three-dimensional model of the cell structure.

2. The method according to claim 1, characterized in that Get the generated task text data, including: Receive a task description statement input by a user; According to the task description statement and the preset supplementary constraint statement, the generated task text data is obtained, wherein the task description statement is used to characterize the basic constraint conditions of the cell structure to be generated, and the supplementary constraint statement is used to characterize the number and format of the cell structure to be generated.

3. The method according to claim 1, characterized in that Inputting the generated task text data into a pre-trained large language model, so as to generate cell structure text data satisfying the constraint conditions according to the generated task text data through the large language model, specifically including: Acquire a period configuration parameter that matches the task text data, wherein the period configuration parameter is used to characterize a time interval period for repeatedly generating cell structure text data according to the task text data; According to the cycle configuration parameters, the generated task text data is repeatedly input into a pre-trained large language model, so that each cell structure text data satisfying the constraint condition is generated according to the generated task text data through the large language model.

4. The method according to claim 1, characterized in that Before constructing the cell structure three-dimensional model according to the cell structure text data, the method further includes: Generate verification task text data according to the generated task text data, input the verification task text data into a pre-trained large language model, so as to generate verification cell structure text data satisfying the constraint conditions according to the verification task text data through the large language model, wherein the verification task text data is used to characterize the specified structural performance characteristics required for the cell structure to be generated to satisfy the constraint conditions; According to the verification task text data, the cell structure text data is verified to obtain a structural performance feature verification result corresponding to the cell structure text data, wherein the structural performance feature verification result is used to characterize whether the cell structure text data has a specified structural performance feature corresponding to the verification cell structure text data; According to the cell structure text data, a cell structure three-dimensional model is constructed, which specifically includes: If it is determined based on the structural performance feature verification result that the cell structure text data has the specified structural performance feature corresponding to the verified cell structure text data, a cell structure three-dimensional model is constructed based on the cell structure text data.

5. The method according to claim 4, characterized in that For each cell structure text data, the cell structure text data is verified according to the verification task text data to obtain a structural performance feature verification result corresponding to the cell structure text data, specifically including: Determine a consistency coefficient between the cell structure text data and the verification cell structure text data, and determine a structural performance feature verification result of the cell structure text data based on the consistency coefficient.

6. The method according to claim 1 or 3, characterized in that: According to the three-dimensional model of the cell structure, the task is executed, specifically including: Performing simulation tests on the three-dimensional model of the cell structure to determine material performance parameters of the three-dimensional model of the cell structure, and judging whether the material performance parameters meet preset screening conditions, wherein the material performance parameters include at least one of volume fraction, Young's modulus, and ultimate strength; If so, the task is executed according to the three-dimensional model of the cell structure.

7. The method according to claim 6, characterized in that According to the three-dimensional model of the cell structure, the task is executed, specifically including: In the case where there are multiple three-dimensional cell structure models, determining the order of the three-dimensional cell structure models according to the material performance parameters of the three-dimensional cell structure models, and generating a screenshot image of each three-dimensional cell structure model; The screenshot images and the material performance parameters are recommended to the user according to the sequence, and the task is executed according to the operation instructions sent by the user for the screenshot images and the material performance parameters.

8. A device for generating material structure data, characterized in that: include: An acquisition module, used for acquiring generation task text data, wherein the generation task text data is used for representing the constraint conditions of the cell structure to be generated; A generation module, used for inputting the generation task text data into a pre-trained large language model, so as to generate cell structure text data satisfying the constraint conditions according to the generation task text data through the large language model, wherein the cell structure text data is used for characterizing the position and connection relationship of each node and / or rod, and each node and / or rod is used for forming a cell structure; An execution module is used to construct a three-dimensional model of the cell structure according to the cell structure text data, and to perform tasks according to the three-dimensional model of the cell structure.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 7 is implemented.

Images