Knowledge acquisition is the “bottleneck” of building an expert system. Based on the optimization model, an improved genetic algorithm applied to knowledge acquisition of a network fault diagnostic expert system is ...Knowledge acquisition is the “bottleneck” of building an expert system. Based on the optimization model, an improved genetic algorithm applied to knowledge acquisition of a network fault diagnostic expert system is proposed. The algorithm applies operators such as selection, crossover and mutation to evolve an initial population of diagnostic rules. Especially, a self adaptive method is put forward to regulate the crossover rate and mutation rate. In the end, a knowledge acquisition problem of a simple network fault diagnostic system is simulated, the results of simulation show that the improved approach can solve the problem of convergence better.展开更多
近年来,大语言模型(large language models,LLMs)在自然语言处理领域实现跨越式突破,在石油化工行业中被广泛应用。混合专家(mixture of experts,MoE)模型架构凭借稀疏激活多个不同的专家模块实现高效扩展并降低计算开销,成为大模型主...近年来,大语言模型(large language models,LLMs)在自然语言处理领域实现跨越式突破,在石油化工行业中被广泛应用。混合专家(mixture of experts,MoE)模型架构凭借稀疏激活多个不同的专家模块实现高效扩展并降低计算开销,成为大模型主流模型结构之一。然而MoE在落地应用时面临路由失衡、收敛不稳、算力资源受限等系统性难题。一些前沿行业研究如DeepSeek、Qwen3等通过策略组合缓解MoE架构专家负载不均衡、收敛不稳的问题,但面对石油化工领域样本数据稀疏且缺少结构化标签的现实情况,已有方案收效微乎其微,且无法减少大模型训练对算力资源的需求。为此,提出一种石化行业的多域自适应集成混合专家框架,基于多级联合训练和多尺度模型级联融合框架,解决石化行业内数据领域多样、数据结构复杂以及数据标签模糊导致模型训练效果不佳的问题,缓解超大规模参数量模型训练的算力瓶颈。该框架使用轻量级意图识别模型将用户请求智能路由至细分领域专家,各专家基于中等尺度的大模型进行微调训练,注入石油化工行业特定领域专业知识,并通过融合模型对各专业领域专家模型的输出进行融合。基于真实工业数据,提出的框架和方法已运用到石化集团的人工智能建设实践中,为石化行业大模型系统构建提供了可行路径。展开更多
Purpose: This paper proposes an expert assignment method for scientific project review that considers both accuracy and impartiality. As impartial and accurate peer review is extremely important to ensure the quality...Purpose: This paper proposes an expert assignment method for scientific project review that considers both accuracy and impartiality. As impartial and accurate peer review is extremely important to ensure the quality and feasibility of scientific projects, enhanced methods for managing the process are needed. Design/methodology/approach: To ensure both accuracy and impartiality, we design four criteria, the reviewers'fitness degree, research intensity, academic association, and potential conflict of interest, to express the characteristics of an appropriate peer review expert. We first formalize the expert assignment problem as an optimization problem based on the designed criteria, and then propose a randomized algorithm to solve the expert assignment problem of identifying reviewer adequacy. Findings: Simulation results show that the proposed method is quite accurate and impartial during expert assignment. Research limitations: Although the criteria used in this paper can properly show the characteristics of a good and appropriate peer review expert, more criteria/conditions can be included in the proposed scheme to further enhance accuracy and impartiality of the expert assignment. Practical implications: The proposed method can help project funding agencies (e.g. the National Natural Science Foundation of China) find better experts for project peer review. OriginaUty/value: To the authors' knowledge, this is the first publication that proposes an algorithm that applies an impartial approach to the project review expert assignment process. The simulation results show the effectiveness of the proposed method.展开更多
摘要Knowledge acquisition is the “bottleneck” of building an expert system. Based on the optimization model, an improved genetic algorithm applied to knowledge acquisition of a network fault diagnostic expert system is proposed. The algorithm applies operators such as selection, crossover and mutation to evolve an initial population of diagnostic rules. Especially, a self adaptive method is put forward to regulate the crossover rate and mutation rate. In the end, a knowledge acquisition problem of a simple network fault diagnostic system is simulated, the results of simulation show that the improved approach can solve the problem of convergence better.
摘要近年来,大语言模型(large language models,LLMs)在自然语言处理领域实现跨越式突破,在石油化工行业中被广泛应用。混合专家(mixture of experts,MoE)模型架构凭借稀疏激活多个不同的专家模块实现高效扩展并降低计算开销,成为大模型主流模型结构之一。然而MoE在落地应用时面临路由失衡、收敛不稳、算力资源受限等系统性难题。一些前沿行业研究如DeepSeek、Qwen3等通过策略组合缓解MoE架构专家负载不均衡、收敛不稳的问题,但面对石油化工领域样本数据稀疏且缺少结构化标签的现实情况,已有方案收效微乎其微,且无法减少大模型训练对算力资源的需求。为此,提出一种石化行业的多域自适应集成混合专家框架,基于多级联合训练和多尺度模型级联融合框架,解决石化行业内数据领域多样、数据结构复杂以及数据标签模糊导致模型训练效果不佳的问题,缓解超大规模参数量模型训练的算力瓶颈。该框架使用轻量级意图识别模型将用户请求智能路由至细分领域专家,各专家基于中等尺度的大模型进行微调训练,注入石油化工行业特定领域专业知识,并通过融合模型对各专业领域专家模型的输出进行融合。基于真实工业数据,提出的框架和方法已运用到石化集团的人工智能建设实践中,为石化行业大模型系统构建提供了可行路径。
基金supported by the National Natural Science Foundation of China under the grant (No.7160325)the Young Talent-Field Frontier Project of Wuhan Documentation and Information Center,Chinese Academy of Sciences
摘要Purpose: This paper proposes an expert assignment method for scientific project review that considers both accuracy and impartiality. As impartial and accurate peer review is extremely important to ensure the quality and feasibility of scientific projects, enhanced methods for managing the process are needed. Design/methodology/approach: To ensure both accuracy and impartiality, we design four criteria, the reviewers'fitness degree, research intensity, academic association, and potential conflict of interest, to express the characteristics of an appropriate peer review expert. We first formalize the expert assignment problem as an optimization problem based on the designed criteria, and then propose a randomized algorithm to solve the expert assignment problem of identifying reviewer adequacy. Findings: Simulation results show that the proposed method is quite accurate and impartial during expert assignment. Research limitations: Although the criteria used in this paper can properly show the characteristics of a good and appropriate peer review expert, more criteria/conditions can be included in the proposed scheme to further enhance accuracy and impartiality of the expert assignment. Practical implications: The proposed method can help project funding agencies (e.g. the National Natural Science Foundation of China) find better experts for project peer review. OriginaUty/value: To the authors' knowledge, this is the first publication that proposes an algorithm that applies an impartial approach to the project review expert assignment process. The simulation results show the effectiveness of the proposed method.