大语言模型因其出色的理解和生成能力被广泛应用于自动化智能助手的开发。然而,它们在处理复杂问题时,常因训练数据庞杂等局限性而难以调用正确的工具和生成准确的函数名称及参数。为了提高在对复杂问题进行任务规划时模型生成工具调用...大语言模型因其出色的理解和生成能力被广泛应用于自动化智能助手的开发。然而,它们在处理复杂问题时,常因训练数据庞杂等局限性而难以调用正确的工具和生成准确的函数名称及参数。为了提高在对复杂问题进行任务规划时模型生成工具调用的准确性,提出一种基于思维链的提示方法—思维代码(Reasoning to Annotation and Coding,ReACo),充分利用预训练的数据,通过代码和注释结合的任务规划提示方式增强语言模型对复杂任务的理解能力,并基于此提出一种新的大语言模型思维提示框架ReACoGPT。基于ReACoGPT提示的语言模型能够准确调用多个插件,依据事实提供富有逻辑的任务规划能力,从而在保持任务规划逻辑性的同时准确使用需求的真实数据。实验结果表明,相较于现有方法,ReACoGPT在RestBench数据集上的正确率、正确路径率及解决长度等多项指标得到提高,证实了ReACo提示方式能够增强大语言模型的规划和推理能力,有效利用大量训练数据对任务进行有效规划,促进了大语言模型在工具学习方面的进一步发展。展开更多
Nowadays more and more attraction is drawn by the event based implicit invocation one of useful architectural patterns, because of its loose coupling between components in the architecture and reactive integration...Nowadays more and more attraction is drawn by the event based implicit invocation one of useful architectural patterns, because of its loose coupling between components in the architecture and reactive integration in software systems. Analyzing object oriented interaction with objects, this paper, based upon the principle of software architecture, presents an approach on event based object model with Ada exception handler. Consequently it is possible for us to improve, with adding specific architectural patterns, traditional programming languages into architectural description languages.展开更多
Using gas and rock samples from major petroliferous basins in the world,the helium content,composition,isotopic compositions and the U and Th contents in rocks are analyzed to clarify the helium enrichment mechanism a...Using gas and rock samples from major petroliferous basins in the world,the helium content,composition,isotopic compositions and the U and Th contents in rocks are analyzed to clarify the helium enrichment mechanism and distribution pattern and the exploration ideas for helium-rich gas reservoirs.It is believed that the formation of helium-rich gas reservoirs depends on the amount of helium supplied to the reservoir and the degree of helium dilution by natural gas,and that the reservoir-forming process can be summarized as"multi-source helium supply,main-source helium enrichment,helium-nitrogen coupling,and homogeneous symbiosis".Helium mainly comes from the radioactive decay of U and Th in rocks.All rocks contain trace amounts of U and Th,so they are effective helium sources.Especially,large-scale ancient basement dominated by granite or metamorphic rocks is the main helium source.The helium generated by the decay of U and Th in the ancient basement in a long geologic history,together with the nitrogen generated by the cracking of the inorganic nitrogenous compounds in the basement rocks,is dissolved in the water and preserved.With the tectonic uplift,the ground water is transported upward along the fracture to the gas reservoirs,with helium and nitrogen released.Thus,the reservoirs are enriched with both helium and nitrogen,which present a clear concomitant and coupling relationship.In tensional basins in eastern China,where tectonic activities are strong,a certain proportion of mantle-derived helium is mixed in the natural gas.The helium-rich gas reservoirs are mostly located in normal or low-pressure zones above ancient basement with fracture communication,which later experience substantial tectonic uplift and present relatively weak seal,low intensity of natural gas charging,and active groundwater.Helium exploration should focus on gas reservoirs with fractures connecting ancient basement,large tectonic uplift,relatively weak sealing capacity,insufficient natural gas charging intensity,and rich ancient formation water,depending on the characteristics of helium enrichment,beyond the traditional idea of searching for natural gas sweetspots and high-yield giant gas fields simultaneously.展开更多
A large language model(LLM)is constructed to address the sophisticated demands of data retrieval and analysis,detailed well profiling,computation of key technical indicators,and the solutions to complex problems in re...A large language model(LLM)is constructed to address the sophisticated demands of data retrieval and analysis,detailed well profiling,computation of key technical indicators,and the solutions to complex problems in reservoir performance analysis(RPA).The LLM is constructed for RPA scenarios with incremental pre-training,fine-tuning,and functional subsystems coupling.Functional subsystem and efficient coupling methods are proposed based on named entity recognition(NER),tool invocation,and Text-to-SQL construction,all aimed at resolving pivotal challenges in developing the specific application of LLMs for RDA.This study conducted a detailed accuracy test on feature extraction models,tool classification models,data retrieval models and analysis recommendation models.The results indicate that these models have demonstrated good performance in various key aspects of reservoir dynamic analysis.The research takes some injection and production well groups in the PK3 Block of the Daqing Oilfield as an example for testing.Testing results show that our model has significant potential and practical value in assisting reservoir engineers with RDA.The research results provide a powerful support to the application of LLM in reservoir performance analysis.展开更多
Using remote method invocation (RMI) and a distributed object-oriented technique, this paper presents a systematic approach to developing a manufacturing execution system (MES) framework, which is open, modularized, d...Using remote method invocation (RMI) and a distributed object-oriented technique, this paper presents a systematic approach to developing a manufacturing execution system (MES) framework, which is open, modularized, distributed, configurable, interoperable and maintainable. Moreover, the design patterns for the framework .are developed and a variety of functional components are designed by inheriting appropriate patterns. And then an application is constructed by invoking corresponding methods of related components. An MES system implementing the framework and design patterns can be facilely integrated with other manufacturing applications, such as enterprise resource planning (ERP) and floor control system (FCS) .展开更多
文摘大语言模型因其出色的理解和生成能力被广泛应用于自动化智能助手的开发。然而,它们在处理复杂问题时,常因训练数据庞杂等局限性而难以调用正确的工具和生成准确的函数名称及参数。为了提高在对复杂问题进行任务规划时模型生成工具调用的准确性,提出一种基于思维链的提示方法—思维代码(Reasoning to Annotation and Coding,ReACo),充分利用预训练的数据,通过代码和注释结合的任务规划提示方式增强语言模型对复杂任务的理解能力,并基于此提出一种新的大语言模型思维提示框架ReACoGPT。基于ReACoGPT提示的语言模型能够准确调用多个插件,依据事实提供富有逻辑的任务规划能力,从而在保持任务规划逻辑性的同时准确使用需求的真实数据。实验结果表明,相较于现有方法,ReACoGPT在RestBench数据集上的正确率、正确路径率及解决长度等多项指标得到提高,证实了ReACo提示方式能够增强大语言模型的规划和推理能力,有效利用大量训练数据对任务进行有效规划,促进了大语言模型在工具学习方面的进一步发展。
基金Supported by National Natural Science Foundation of China(6 97730 41)
文摘Nowadays more and more attraction is drawn by the event based implicit invocation one of useful architectural patterns, because of its loose coupling between components in the architecture and reactive integration in software systems. Analyzing object oriented interaction with objects, this paper, based upon the principle of software architecture, presents an approach on event based object model with Ada exception handler. Consequently it is possible for us to improve, with adding specific architectural patterns, traditional programming languages into architectural description languages.
基金Supported by the National Natural Science Foundation of China(42141022,42272189)Project of Ministry of Natural Resources of China(QGYQZYPJ2022-1)CNPC Core Project(2021ZG12)。
文摘Using gas and rock samples from major petroliferous basins in the world,the helium content,composition,isotopic compositions and the U and Th contents in rocks are analyzed to clarify the helium enrichment mechanism and distribution pattern and the exploration ideas for helium-rich gas reservoirs.It is believed that the formation of helium-rich gas reservoirs depends on the amount of helium supplied to the reservoir and the degree of helium dilution by natural gas,and that the reservoir-forming process can be summarized as"multi-source helium supply,main-source helium enrichment,helium-nitrogen coupling,and homogeneous symbiosis".Helium mainly comes from the radioactive decay of U and Th in rocks.All rocks contain trace amounts of U and Th,so they are effective helium sources.Especially,large-scale ancient basement dominated by granite or metamorphic rocks is the main helium source.The helium generated by the decay of U and Th in the ancient basement in a long geologic history,together with the nitrogen generated by the cracking of the inorganic nitrogenous compounds in the basement rocks,is dissolved in the water and preserved.With the tectonic uplift,the ground water is transported upward along the fracture to the gas reservoirs,with helium and nitrogen released.Thus,the reservoirs are enriched with both helium and nitrogen,which present a clear concomitant and coupling relationship.In tensional basins in eastern China,where tectonic activities are strong,a certain proportion of mantle-derived helium is mixed in the natural gas.The helium-rich gas reservoirs are mostly located in normal or low-pressure zones above ancient basement with fracture communication,which later experience substantial tectonic uplift and present relatively weak seal,low intensity of natural gas charging,and active groundwater.Helium exploration should focus on gas reservoirs with fractures connecting ancient basement,large tectonic uplift,relatively weak sealing capacity,insufficient natural gas charging intensity,and rich ancient formation water,depending on the characteristics of helium enrichment,beyond the traditional idea of searching for natural gas sweetspots and high-yield giant gas fields simultaneously.
基金Supported by the National Talent Fund of the Ministry of Science and Technology of China(20230240011)China University of Geosciences(Wuhan)Research Fund(162301192687)。
文摘A large language model(LLM)is constructed to address the sophisticated demands of data retrieval and analysis,detailed well profiling,computation of key technical indicators,and the solutions to complex problems in reservoir performance analysis(RPA).The LLM is constructed for RPA scenarios with incremental pre-training,fine-tuning,and functional subsystems coupling.Functional subsystem and efficient coupling methods are proposed based on named entity recognition(NER),tool invocation,and Text-to-SQL construction,all aimed at resolving pivotal challenges in developing the specific application of LLMs for RDA.This study conducted a detailed accuracy test on feature extraction models,tool classification models,data retrieval models and analysis recommendation models.The results indicate that these models have demonstrated good performance in various key aspects of reservoir dynamic analysis.The research takes some injection and production well groups in the PK3 Block of the Daqing Oilfield as an example for testing.Testing results show that our model has significant potential and practical value in assisting reservoir engineers with RDA.The research results provide a powerful support to the application of LLM in reservoir performance analysis.
基金The National Natural Science Foundation of China (59990470).
文摘Using remote method invocation (RMI) and a distributed object-oriented technique, this paper presents a systematic approach to developing a manufacturing execution system (MES) framework, which is open, modularized, distributed, configurable, interoperable and maintainable. Moreover, the design patterns for the framework .are developed and a variety of functional components are designed by inheriting appropriate patterns. And then an application is constructed by invoking corresponding methods of related components. An MES system implementing the framework and design patterns can be facilely integrated with other manufacturing applications, such as enterprise resource planning (ERP) and floor control system (FCS) .
