Quantum chemistry generation method and device based on natural language, equipment and medium

Abstract

The invention provides a quantum chemistry generation method, device and equipment based on a natural language and a medium, and relates to the technical field of quantum chemistry calculation, and the quantum chemistry generation method based on the natural language is characterized by comprising the steps that chemical multi-dimensional information is constructed and generated, and a professional knowledge base is obtained; performing fine tuning optimization on the large language model according to the professional knowledge base and the function set to obtain an improved large language model; inputting a natural language into the improved large language model to extract key information, and converting the key information through a task translator to obtain a quantum chemistry calculation instruction; the quantum chemistry calculation instruction is converted according to quantum chemistry software, in the task processing process, the task state and the state threshold value are judged, and a result is output if the condition is met; and performing language format conversion on the output result to generate a final readable result. According to the method, the problem that non-technical background users and interdisciplinary teams face operation obstacles in quantum chemistry calculation is solved.

Description

Technical Field

[0001] The present invention relates to the field of quantum chemical computing technology, and in particular to a natural language-based quantum chemical generation method, apparatus, device, and medium. Background Art

[0002] In the current field of quantum chemistry calculations, traditional system configuration relies primarily on command-line parameter settings. This inherently requires a high level of expertise, with its operational logic and interface design primarily focused on the habits and needs of professional researchers. This can lead to operational barriers for non-technical users and interdisciplinary teams in quantum chemistry calculations.

[0003] There is an urgent need for natural language-based quantum chemical generation methods, devices, equipment and media to solve the operational obstacles faced by non-technical background users and interdisciplinary teams in quantum chemical calculations. Summary of the Invention

[0004] The present invention aims to provide a method, apparatus, device, and medium for quantum chemical generation based on natural language to improve the above-mentioned problems. To achieve the above-mentioned objectives, the present invention adopts the following technical solutions:

[0005] In a first aspect, the present application provides a natural language-based quantum chemistry generation method, comprising:

[0006] Acquiring multidimensional chemical information, including basic theory, reaction information, and experimental information;

[0007] Constructing and generating the multidimensional chemical information to obtain a professional knowledge base;

[0008] Fine-tune and optimize the large language model according to the professional knowledge base and the preset function set to obtain an improved large language model;

[0009] Inputting natural language into the improved large language model to extract key information, and converting the key information through the task translator to obtain quantum chemical calculation instructions;

[0010] The quantum chemical calculation instructions are converted and processed according to the quantum chemical software. During the task processing, the task status is judged against the preset status threshold, and the result is output if the condition is met;

[0011] Convert the output results into a readable format.

[0012] In a second aspect, the present application also provides a natural language-based quantum chemistry generation device, comprising:

[0013] An acquisition module, configured to acquire multidimensional chemical information, including basic theory, reaction information, and experimental information;

[0014] A generation module, configured to perform search enhancement and generation based on the multi-dimensional chemical information to obtain a professional knowledge base;

[0015] an optimization module, configured to fine-tune and optimize the large language model based on the professional knowledge base and the preset function set to obtain an improved large language model;

[0016] An extraction module, configured to input natural language into the improved large language model to extract key information, and convert the key information through a task translator to obtain quantum chemical calculation instructions;

[0017] a processing module for converting and processing the quantum chemical calculation instructions according to the quantum chemical software, and outputting the result if the condition is met by judging the task status and the preset state threshold during the task processing;

[0018] The conversion module is used to convert the language format of the output results to generate the final readable results.

[0019] In a third aspect, the present application also provides a quantum chemistry generation device based on natural language, including:

[0020] memory for storing computer programs;

[0021] A processor is configured to implement the steps of the natural language-based quantum chemistry generation method when executing the computer program.

[0022] In a fourth aspect, the present application further provides a medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned natural language-based quantum chemistry generation method.

[0023] The beneficial effects of the present invention are:

[0024] The present invention can efficiently and quickly generate quantum chemical calculation instructions by improving the large language model; through the task translator, the key information extracted from the improved large language model is converted into formatted instructions that can be parsed and executed by quantum chemical software, closely connecting the improved large language model with the quantum chemical calculation process, eliminating the operational obstacles encountered by non-technical users and interdisciplinary research teams when performing quantum chemical calculation tasks, and promoting the popularization and application convenience of quantum chemical calculation technology.

[0025] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or be understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0027] Figure 1 Schematic diagram of the flow of the natural language-based quantum chemistry generation method described in an embodiment of the present invention;

[0028] Figure 2 Schematic diagram of the structure of the natural language-based quantum chemistry generation device described in an embodiment of the present invention.

[0029] Markings in the figure: 800, natural language-based quantum chemistry generation device; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0031] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are used only to distinguish the description and should not be understood as indicating or implying relative importance.

[0032] Example 1:

[0033] This embodiment provides a quantum chemistry generation method based on natural language.

[0034] See also Figure 1 , the figure shows that the method includes steps S1 to S6, including:

[0035] S1: Acquire chemical multidimensional information, including basic theory, reaction information, and experimental information;

[0036] In this step, the chemical multidimensional information includes multidimensional information such as the structure, properties, reaction mechanism, and experimental data of the chemical substances;

[0037] The reaction mechanism information is reaction information, and the experimental data is experimental information.

[0038] S2: constructing and generating the chemical multidimensional information to obtain a professional knowledge base;

[0039] To clarify the specific method of obtaining the professional knowledge base, step S2 includes S21 to S23, which are:

[0040] S21: constructing the chemical multidimensional information and automated acquisition technology to obtain an initial database;

[0041] In this step, data collection is achieved by crawling chemistry-related websites, databases, academic journals, etc. through automated technology.

[0042] S22: performing structural processing on the text information in the initial database based on natural language processing technology to obtain a preprocessed database;

[0043] In this step, the text information in the initial database is processed based on the natural language processing technology, key chemical information is extracted and annotated, and the extracted and annotated information is stored according to a preset structure to obtain a preprocessed database;

[0044] The storage includes structural storage methods such as functional modules, calculation methods, and parameter types.

[0045] S23: updating and optimizing the pre-processing database based on the real-time chemical multi-dimensional information to obtain a professional knowledge base.

[0046] S3: Fine-tune and optimize the large language model according to the professional knowledge base and the preset function set to obtain an improved large language model;

[0047] In this step, the large language model includes a language interaction module and a prompt word module. The prompt word module is used to improve the efficiency and accuracy of quantum chemistry calculation tasks. The main functions of the prompt word module include semantic parsing, task construction, parameter configuration, function calling, result analysis, report generation and multi-round dialogue support.

[0048] To clarify and improve the specific method of obtaining the large language model, step S3 includes S31 to S33, specifically:

[0049] S31: performing domain adaptive pre-training on the large language model based on the background knowledge in the professional knowledge base, and obtaining an optimized large language model by integrating quantum chemistry terms and reaction rules into the large language model;

[0050] In this step, the background knowledge is fused with the existing general large language model pre-training dataset, and the large language model is domain-adaptively pre-trained using the fused pre-training dataset. The parameters of the large language model are adjusted to obtain a preliminarily optimized large language model.

[0051] Converting the quantum chemical terms and the reaction rules into high-dimensional vectors and integrating them into the knowledge graph of the large language model to further enrich the knowledge system of the large language model;

[0052] The preliminary optimized large language model and the updated knowledge graph are comprehensively optimized to obtain an optimized large language model.

[0053] S32: Performing supervised learning training on the optimized large language model according to the function set to obtain a deep large language model;

[0054] In this step, quantum chemistry-related annotated data is collected and matched with functions in the function set to form a supervised learning dataset. The supervised learning dataset is used to train and optimize the optimized large language model. During the training process, the functions in the function set are used as supervisory signals to guide the training of the model, ensuring that the optimized large language model can accurately learn the patterns and features in the quantum chemistry data.

[0055] Among them, the function set includes a generation function, a startup function and an interpretation function. The generation function is used to create an input file that meets the requirements based on the parameter configuration generated by the large language model to ensure the accurate execution of the calculation task; the startup function is responsible for submitting the generated input file to the quantum chemistry calculation software and starting the calculation task to realize the automated execution of the task; the interpretation function is used to parse and interpret the output file generated by the quantum chemistry calculation software, extract key information and format it so that the model can understand and process the calculation results.

[0056] S33: Fine-tune the in-depth large language model based on the high-dimensional feature representation capability of the embedding technology and the accurate prediction capability of the supervised learning to construct an improved large language model.

[0057] In this step, the knowledge graph in the deep large language model is analyzed based on the high-dimensional feature representation capability, and the distribution of quantum chemistry terms and reaction rules in the high-dimensional space is observed. By analyzing the distribution and combining the evaluation results of the accurate prediction capability, the deep large language model is fine-tuned to construct an improved large language model.

[0058] S4: inputting natural language into the improved large language model to extract key information, and converting the key information through the task translator to obtain quantum chemical calculation instructions;

[0059] To clarify the specific method of obtaining the quantum chemical calculation instructions, step S4 includes S41 to S44, specifically:

[0060] S41: inputting the natural language into the language interaction module in the improved large language model for initial processing to obtain natural instructions;

[0061] In this step, the language interaction module is used to receive the natural language input by the user, and preliminarily parse and process it, and convert it into a natural instruction format that can be understood by the improved large language model.

[0062] S42: Based on natural instructions, key information is extracted by improving the call plug-in of the large language model, and the key information is processed by calling the startup function of the function set to generate task instructions;

[0063] In this step, the calling plug-in is used to extract key information related to the task from the natural instruction; generate accurate function call parameter configuration based on the natural instruction and the interface description of the startup function, and trigger the corresponding function execution;

[0064] The key information includes the task type and / or required resources; preferably, the calling plug-in is a FunctionCalling plug-in system.

[0065] S43: Allocate resources to the task instructions according to the task scheduling module to obtain an allocation plan;

[0066] In this step, the task scheduling module allocates resources according to the priority and resource requirements of the task instructions. When high computing demand tasks are allocated to high-performance clusters first, routine tasks are allocated to local servers to obtain an allocation plan.

[0067] The computing device initiates the computational process and supports deployment methods including, but not limited to, cloud / public cloud deployment (e.g., Kubernetes microservices), API interfaces provided by SaaS platforms, and plug-in integration into research data platforms. The execution process involves activating the task queue, invoking the corresponding tool source code from the database, generating executable code based on the rules, submitting the code to the resource manager or running it in a local execution environment to drive quantum chemistry software calculations.

[0068] The computing device partially leverages existing cluster or local computing technology, but key elements lie in the knowledge database and code optimization developed by the project's inventors. These databases store information on the capabilities, applicable scenarios, and parameter requirements of quantum chemistry calculation tools. The optimized code ensures that large-scale model task instructions can be efficiently converted into executable code and run. These advantages enable the computing device to accurately understand the task requirements, ensuring the accuracy and reliability of the calculation results.

[0069] S44: Input the task instruction into a task translator to convert it into an intermediate representation, and optimize the intermediate representation in combination with the allocation scheme to obtain a quantum chemical calculation instruction.

[0070] In this step, the task translator accurately translates the task instructions and parameters into an intermediate representation based on the software requirements and calculation methods in the task instructions, and automatically selects the most suitable quantum chemistry software;

[0071] The intermediate representation is a format recognizable by corresponding quantum chemistry software.

[0072] S5: converting and processing the quantum chemical calculation instructions according to the quantum chemical software. During the task processing, the task status is judged against the preset status threshold, and the result is output if the condition is met;

[0073] Preferably, the quantum chemistry software includes but is not limited to Gaussian, ORCA or pyscf.

[0074] To clarify the specific method of obtaining the output result, step S5 includes S51 to S53, which are:

[0075] S51: converting the quantum chemical calculation instruction into an executable input file according to the input file format of the quantum chemical software;

[0076] S52: Based on the execution engine, the quantum chemistry software is called to process the executable input file to generate a calculation task;

[0077] In this step, automated task scheduling is achieved through the execution engine, which is responsible for calling the quantum chemistry software and connecting it to the input file. It passes the input file to the quantum chemistry software and starts the calculation task.

[0078] S53: Execute the computing task, judge the task status against the preset status threshold, and output the result if the conditions are met.

[0079] In this step, during the task processing, the running status of the task is monitored in real time, including information such as calculation progress and resource usage, and is promptly fed back to the task scheduling module. Once an abnormality occurs in the task, such as calculation timeout or software error, an alarm mechanism is immediately triggered and the large language model is processed;

[0080] The running status of the real-time monitoring task represents the task status.

[0081] S6: Convert the output result into a language format to generate a final readable result.

[0082] To clarify the specific method of obtaining the readable result, step S6 includes S61 to S63, specifically:

[0083] S61: Convert the output result into a language format and store it to obtain a natural language text;

[0084] S62: Performing semantic optimization processing on the natural language text according to the deep learning model to obtain an optimized text result;

[0085] In this step, the deep learning model makes the natural language text more fluent, accurate and natural through context understanding, grammatical correction, vocabulary replacement, etc., thereby improving the semantic clarity and expression quality of the natural language text.

[0086] S63: Processing and analyzing the optimized text result based on the interpretation function in the function set to obtain a final readable result.

[0087] In this step, the interpretation function extracts key information, analyzes semantic structure or performs specific formatting according to preset rules or logic, and finally generates a readable result that meets user needs.

[0088] Example 2:

[0089] This embodiment provides a natural language-based quantum chemistry generation device, comprising:

[0090] An acquisition module, configured to acquire multidimensional chemical information, including basic theory, reaction information, and experimental information;

[0091] A generation module, configured to perform search enhancement and generation based on the multi-dimensional chemical information to obtain a professional knowledge base;

[0092] To clarify the specific ways to obtain the generated modules, there are:

[0093] A first construction unit is used to construct the chemical multidimensional information and automated acquisition technology to obtain an initial database;

[0094] a processing unit, configured to perform structured processing on the text information in the initial database based on natural language processing technology to obtain a preprocessed database;

[0095] The updating unit is used to update and optimize the pre-processing database based on real-time chemical multi-dimensional information to obtain a professional knowledge base.

[0096] an optimization module, configured to fine-tune and optimize the large language model based on the professional knowledge base and the preset function set to obtain an improved large language model;

[0097] To clarify the specific ways to obtain the optimization module, there are:

[0098] A first training unit is configured to perform domain-adaptive pre-training on the large language model based on background knowledge in the professional knowledge base, and to obtain an optimized large language model by integrating quantum chemistry terms and reaction rules into the large language model;

[0099] A second training unit is configured to perform supervised learning training on the optimized large language model according to the function set to obtain a deep large language model;

[0100] The second construction unit is used to fine-tune the deep large language model based on the high-dimensional feature representation capability of the embedding technology and the accurate prediction capability of the supervised learning to construct an improved large language model.

[0101] An extraction module, configured to input natural language into the improved large language model to extract key information, and convert the key information through a task translator to obtain quantum chemical calculation instructions;

[0102] a processing module for converting and processing the quantum chemical calculation instructions according to the quantum chemical software, and outputting the result if the condition is met by judging the task status and the preset state threshold during the task processing;

[0103] The conversion module is used to convert the language format of the output results to generate the final readable results.

[0104] It should be noted that, regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0105] Example 3:

[0106] Corresponding to the above method embodiment, this embodiment also provides a natural language-based quantum chemical generation device. The natural language-based quantum chemical generation device described below and the natural language-based quantum chemical generation method described above can refer to each other.

[0107] Figure 2 FIG is a block diagram of a natural language-based quantum chemistry generation device 800 according to an exemplary embodiment. Figure 2 As shown, the natural language-based quantum chemical generation device 800 may include: a processor 801 and a memory 802. The natural language-based quantum chemical generation device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0108] The processor 801 is used to control the overall operation of the natural language-based quantum chemical generation device 800 to complete all or part of the steps in the natural language-based quantum chemical generation method described above. The memory 802 is used to store various types of data to support the operation of the natural language-based quantum chemical generation device 800. This data may include, for example, instructions for any application or method operating on the natural language-based quantum chemical generation device 800, as well as application-related data such as contact information, sent and received messages, images, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the natural language-based quantum chemical generation device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more thereof, may include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0109] In an exemplary embodiment, the natural language-based quantum chemical generation device 800 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-mentioned natural language-based quantum chemical generation method.

[0110] Example 4:

[0111] Corresponding to the above method embodiment, this embodiment further provides a medium. The medium described below and the natural language-based quantum chemistry generation method described above can refer to each other.

[0112] A medium stores a computer program, which, when executed by a processor, implements the steps of the natural language-based quantum chemistry generation method of the above method embodiment.

[0113] The medium may specifically be any medium capable of storing program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0114] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

[0115] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A quantum chemical generation method based on natural language, characterized in that: include: Acquiring multidimensional chemical information, including basic theory, reaction information, and experimental information; Constructing and generating the multidimensional chemical information to obtain a professional knowledge base; Fine-tune and optimize the large language model according to the professional knowledge base and the preset function set to obtain an improved large language model; Inputting natural language into the improved large language model to extract key information, and converting the key information through the task translator to obtain quantum chemical calculation instructions; The quantum chemical calculation instructions are converted and processed according to the quantum chemical software. During the task processing, the task status is judged against the preset status threshold, and the result is output if the condition is met; Convert the output results into a readable format.

2. The natural language-based quantum chemistry generation method according to claim 1, characterized in that: The multi-dimensional chemical information is constructed and generated to obtain a professional knowledge base, including: constructing the chemical multidimensional information and automated acquisition technology to obtain an initial database; Performing structural processing on the text information in the initial database based on natural language processing technology to obtain a preprocessed database; The pre-processing database is updated and optimized based on real-time chemical multi-dimensional information to obtain a professional knowledge base.

3. The natural language-based quantum chemistry generation method according to claim 1, characterized in that: Fine-tuning and optimizing the large language model according to the professional knowledge base and the preset function set to obtain an improved large language model includes: Performing domain-adaptive pre-training on the large language model based on the background knowledge in the professional knowledge base, and obtaining an optimized large language model by integrating quantum chemistry terms and reaction rules into the large language model; Performing supervised learning training on the optimized large language model according to the function set to obtain a deep large language model; The in-depth large language model is fine-tuned based on the high-dimensional feature representation capability of the embedding technology and the accurate prediction capability of the supervised learning to construct an improved large language model.

4. The natural language-based quantum chemistry generation method according to claim 1, characterized in that: Inputting natural language into the improved large language model to extract key information, converting the key information through the task translator to obtain quantum chemical calculation instructions, including: Inputting natural language into the language interaction module in the improved large language model for initial processing to obtain natural instructions; Based on natural instructions, we extract key information by improving the call plug-in of the large language model, process the key information by calling the startup function of the function set, and generate task instructions; Allocate resources to the task instructions according to the task scheduling module to obtain an allocation plan; The task instruction is input into a task translator to be converted into an intermediate representation, and the intermediate representation is optimized in combination with the allocation scheme to obtain a quantum chemical calculation instruction.

5. The natural language-based quantum chemistry generation method according to claim 1, characterized in that: Convert the output results into a readable format, including: Converting the output result into a natural language format and storing the converted result; Performing semantic optimization processing on the natural language text according to the deep learning model to obtain an optimized text result; The optimized text result is processed and analyzed based on the interpretation function in the function set to obtain a final readable result.

6. A quantum chemical generation device based on natural language, characterized in that: include: An acquisition module, configured to acquire multidimensional chemical information, including basic theory, reaction information, and experimental information; A generation module, configured to construct and generate the chemical multidimensional information to obtain a professional knowledge base; an optimization module, configured to fine-tune and optimize the large language model based on the professional knowledge base and the preset function set to obtain an improved large language model; An extraction module, configured to input natural language into the improved large language model to extract key information, and convert the key information through a task translator to obtain quantum chemical calculation instructions; a processing module for converting and processing the quantum chemical calculation instructions according to the quantum chemical software, and outputting the result if the condition is met by judging the task status and the preset state threshold during the task processing; The conversion module is used to convert the language format of the output results to generate the final readable results.

7. The natural language-based quantum chemistry generation device according to claim 6, characterized in that: The generation module includes: A first construction unit is used to construct the chemical multidimensional information and automated acquisition technology to obtain an initial database; a processing unit, configured to perform structured processing on the text information in the initial database based on natural language processing technology to obtain a preprocessed database; The updating unit is used to update and optimize the pre-processing database based on real-time chemical multi-dimensional information to obtain a professional knowledge base.

8. The natural language-based quantum chemistry generation device according to claim 6, characterized in that: The optimization module includes: A first training unit is configured to perform domain-adaptive pre-training on the large language model based on background knowledge in the professional knowledge base, and to obtain an optimized large language model by integrating quantum chemistry terms and reaction rules into the large language model; A second training unit is configured to perform supervised learning training on the optimized large language model according to the function set to obtain a deep large language model; The second construction unit is used to fine-tune the deep large language model based on the high-dimensional feature representation capability of the embedding technology and the accurate prediction capability of the supervised learning to construct an improved large language model.

9. A quantum chemical generation device based on natural language, characterized in that include: memory for storing computer programs; A processor, configured to implement the steps of the natural language-based quantum chemistry generation method according to any one of claims 1 to 5 when executing the computer program.

10. A medium, characterized in that: The medium stores a computer program, which, when executed by a processor, implements the steps of the natural language-based quantum chemistry generation method according to any one of claims 1 to 5.

Images