20 results about "Research task" patented technology

The invention discloses a multi-agent system for astronomical field academic research and a configuration method thereof, and belongs to the technical field of artificial intelligence. The system comprises: an astronomical academic thinking agent layer which is used as a system brain, is driven by a large language model with a thinking chain, and is responsible for planning and reflecting scientific research tasks; the astronomical academic execution agent layer serves as four limbs of the system and completes tool calling through a lightweight model; the astronomy MCP tool library is used for providing tool services such as network search and literature retrieval through a standardized MCP protocol; and the astronomical discussion platform provides an interactive interface between the multiple agents and the user and a discussion mechanism based on mention. According to the invention, by constructing a hierarchical collaborative architecture and docking with a standardized protocol, the defects of an existing intelligent agent system in the aspects of scientific research cognition depth, task collaborative efficiency and group intelligence excitation are overcome, and the crossing from passive information processing to active scientific research discovery is realized.

The application discloses an error-driven adaptive research process rectification method and system, and relates to the technical field of natural language processing. The method comprises the following steps: decomposing a research task submitted by a user into a plurality of subtasks with a dependency relationship, and generating an initial directed acyclic graph (DAG); executing each subtask according to the DAG, and performing logical verification on an intermediate result to identify an error type; when an error is identified, mapping the error type to a rectification action; adjusting the DAG according to the rectification action, including deleting an error branch, reconstructing a node sequence or inserting a new node; repeatedly executing the process based on the updated DAG until a research completion condition is met, and generating a research report. The application realizes nonlinear re-planning through dynamic adjustment of the DAG, effectively avoids error accumulation, and improves the accuracy and reliability of a complex research task.

The invention discloses a digital literacy improvement method and system for college teachers, and relates to the technical field of scientific research data management.The method comprises the steps that a scientific research data collection process is divided into a plurality of time steps delta t based on scientific research task time nodes and processes, and experimental data, literature data, code data and multimedia data are collected; and constructing a scientific research data set. And then, calculating a data integrity index and a compliance factor of the teacher at the current time step length, and triggering an early warning mechanism of a missing risk or a compliance risk. Further analyzing knowledge granularity and effective information amount of scientific research data, and calculating data weight and heterogeneous data fusion index; and the modified version information of the scientific research data set is extracted and analyzed, and a scientific research data version control index is constructed. And finally, based on the integrity index, the compliance factor, the fusion index and the version control index, forming and grading a life cycle comprehensive index, obtaining a corresponding improvement grade, and further generating a digital quality improvement strategy.

The invention relates to an interactive discussion platform construction method based on a knowledge graph, and belongs to the field of discussion. A task initiator constructs a research task framework; the research task framework and the research tasks in different fields are distributed to researchers in the corresponding fields; the researchers carry out association analysis on the received research tasks; obtaining an answer, generating a conclusion and reporting the conclusion to the task initiator; the task initiator performs primary examination and approval on each conclusion and sends a primary examination and approval result of each conclusion to summarizing personnel; after summarizing by the summarizing personnel, feeding back to the task initiator for secondary examination and approval; after secondary examination and approval, outputting a research report; according to the invention, standardization and intellectualization of the discussion process are realized, high-efficiency discussion communication is supported, and an effective conclusion is output.

The invention discloses an AI-based scientific research project full life cycle management system, and relates to the technical field of project management. Aiming at the technical defects of non-standard data acquisition, low task cooperation efficiency, insufficient progress prediction precision and rigid resource configuration of the existing scientific research management system, the system creatively integrates three breakthrough algorithms of a causal atlas inference model, a deep reinforcement learning resource scheduler and a dynamic Bayesian achievement transformation prediction model; and a four-layer architecture of a data acquisition layer, an intelligent decision-making layer, an interactive execution layer and an iterative optimization layer is constructed, so that the whole-process intelligent and precise management and control of the scientific research project from project establishment to question settlement are realized. The system can improve the scientific research task cooperation efficiency by more than 42%, the progress prediction error is controlled within 3%, the resource utilization rate is improved by 30%, the achievement conversion success rate is improved by 25%, and the system is suitable for management of various scientific research projects of colleges, scientific research institutions and enterprise research and development departments.

This invention provides a scientific intelligent agent system and its control method for interdisciplinary scientific research tasks. The system includes: an intent recognition module for parsing the descriptive information of the research task to obtain semantic parsing results; a tool retrieval module for identifying target inference tools from a tool database; a multidisciplinary domain intelligent agent cluster; a planning agent for decomposing the research task according to the task objectives, obtaining multiple sub-tasks, and assigning the target sub-tasks to target discipline domain intelligent agents according to domain type; and a code agent for providing discipline task planning code corresponding to the target sub-tasks, and planning the target sub-tasks in conjunction with the target inference tool and the discipline analysis path corresponding to the target discipline domain intelligent agent to obtain discipline task planning results. The system and control method described in this invention improve the versatility and automated task planning capabilities of scientific intelligent agent systems for complex interdisciplinary scientific research tasks.

The application provides a scientific research auxiliary system and method based on port and shipping big data AI intelligent agents, which comprises collecting port and shipping multi-modal heterogeneous historical data, constructing meta-training tasks containing support sets and query sets according to scientific research tasks; extracting data feature mutual information inside each meta-training task to generate a task graph, encoding into a task feature vector and clustering into K task clusters; iteratively training the meta-tasks in each cluster to obtain the initial model parameters of the cluster and the plasticity mask generated by the gradient variance; inputting a new task, extracting the task features and calculating the affinity weight of each cluster, weighting and fusing the cluster parameters and the mask to complete multi-task knowledge transfer; modulating the basic mask into a dynamic mask that adapts to the distribution of the new task through a super network; fine-tuning the fusion parameters with the support set of the new task, and multiplying the gradient and the dynamic mask element by element to protect the general core knowledge; the fine-tuned model processes the query set to output the results, supporting intelligent optimization and deployment of port and shipping resources.

This invention discloses a multi-agent scientific research task execution method and system, relating to the fields of artificial intelligence and automation scientific research technology, to address the problems of task context loss, deviation from the original goal, and lack of scientific basis that easily occur in existing methods during scientific research task execution. The method includes: parsing the user's scientific research goal instructions to generate a sequence of task nodes; before executing any task node, performing retrieval and data matching in a three-dimensional data base, trimming the matched data to obtain a task context data package; generating system prompts, executing the task instructions of the current task node based on the systematized prompts, and obtaining the output result; performing multiple verifications on the output result and providing feedback. The multi-agent scientific research task execution method provided by this invention can avoid context loss and deviation from the original goal, and ensures the scientific validity and reliability of the scientific research task execution process through static knowledge graphs and dynamic memory graphs.

The invention discloses a multi-agent collaborative scientific hypothesis automatic generation method, and belongs to the field of creative scientific research engineering, and the method comprises the steps: inputting a to-be-researched problem and research background information of the to-be-researched problem into a creative generation agent, so as to obtain a plurality of creative hypothesis texts of the to-be-researched problem; respectively inputting the plurality of creative hypothesis texts into a hypothesis testing agent to obtain evaluation data of each creative hypothesis text under a plurality of evaluation dimensions; and according to the evaluation data of each creative hypothesis text under the plurality of evaluation dimensions, determining a target creative hypothesis text corresponding to the to-be-researched problem from all creative hypothesis texts. Through cooperative work of the creative generation agent and the hypothesis test agent, the problems of insufficient innovation, one-sided evaluation result and incomplete reasoning chain in the automatic hypothesis process are improved, and the overall working efficiency and decision quality of researchers in complex scientific research tasks are improved.

The invention relates to a research task processing method and device and electronic equipment, and the method comprises the steps: responding to a to-be-processed research task inputted by a user, and carrying out the intention recognition of the research task, and obtaining a research plan; in response to a confirmation instruction of a user for the target research plan, generating a task chain of at least one dimension according to the target research plan and the sub-agents; the task chain comprises sub-tasks with a dependency relationship; scheduling a corresponding sub-agent according to the sub-task of the task chain, and executing the sub-task through the sub-agent to obtain an execution result; and generating a research report corresponding to the research task according to the execution result. According to the embodiment of the invention, a complex research task which originally depends on manual series operation is converted into a highly parallel automatic process, so that the generation efficiency of the research report is remarkably improved, and the timeliness of a user on analysis and decision-making of the research task is improved.

The application relates to the technical field of computer systems, in particular to a lightweight material science intelligent research method and system based on double model cooperation, which comprises a user interaction interface, a double model cooperation intelligent agent core, a material science professional tool set and a bottom layer computing resource layer; the double model cooperation intelligent agent core comprises an execution coordination model and a knowledge core model; the execution coordination model and the knowledge core model are both self-recurrent language models with a parameter scale less than 100B; the execution coordination model analyzes a research task, understands a core intention and transmits a preliminary result to the knowledge core model; the knowledge core model performs deep analysis, interpretation and reasoning on the preliminary result, including physical rationality verification, and performs iterative decision-making. The application realizes decoupling and deep optimization of knowledge reasoning and complex tool chain operation in the field of material science, and aims to build an automatic and intelligent research platform with flexible architecture, strong performance and the ability to significantly accelerate the material discovery and development process.

The application provides a special management method and system for an education research platform, which comprises the following steps: checking the personnel identity of each logged-in person respectively, issuing corresponding research tasks and research permissions, obtaining the permission exercise data generated when each logged-in person executes the research task, constructing the research archives of each logged-in person in combination with the corresponding research permissions, constructing the research access path of the corresponding logged-in person in the research platform according to the permission exercise data, obtaining the corresponding research results of this time and transmitting them to the corresponding login page for display, analyzing the research reports of all the logged-in persons under different disciplines, and transmitting them to the platform homepage for display. The learning plan for each student in the education research platform is formulated, and the learning effect is analyzed, so that the learning effect of the student in the education research platform is effectively improved.

The embodiment of the invention discloses a report generation method, system and device based on multiple agents and a storage medium. The method comprises the steps of receiving a research task; configuring at least one agent corresponding to the research task; driving the intelligent agent to execute a research task; on-line real-time calibration is carried out on at least one configuration parameter of the intelligent agent according to a cooperation log and evidence pool content generated when the intelligent agent executes the research task, and the step of driving the intelligent agent to execute the research task is executed again; wherein the configuration parameters comprise at least one of the following parameters: a prompt template, a tool permission, an evidence weight and an output structure constraint; and generating and displaying a research report generated when the intelligent agent executes the research task. By means of the mode, the configuration parameters of the agents are calibrated online in real time, real-time self-adaptive adjustment and optimization of the multi-agent role parameters are achieved, and timely adjustment and deviation correction of the configuration parameters of the agents can be achieved.

The invention provides a scientific research task autonomous planning and execution method and system. The method comprises the steps that natural language query is accepted in an interactive dialogue mode; identifying intent based on natural language query; decomposing problems based on intentions; and corresponding answers are generated and returned based on different intentions. The system is constructed by a host module and a server module based on a model context protocol; wherein the host module comprises a plant chat robot and a plant inference device; the server module comprises a knowledge agent, a data agent, a composite agent and a review agent; the host module is used for decomposing a problem into one or more sub-tasks, and is also used for defining an execution sequence and cooperation logic among the sub-tasks. According to the method and system provided by the invention, through basic training, incremental pre-training and supervised fine tuning, scientific research tasks in the fields of agriculture and the like are autonomously planned and executed, and the efficiency is improved.

The application discloses an oil-gas collaborative research implementation method and device based on minimum service units. The method comprises the following steps: generating a research task based on selected research object information and a selected service scene template; distributing the research task to researchers based on selected researchers; receiving research results of each minimum service unit reported by the researchers, and storing identification information of the minimum service units and corresponding research results; and integrating the research results of the minimum service units involved in the research task based on the identification information of the minimum service units, and generating a design scheme of a research object. Efficient collaborative research can be implemented, and a design scheme of a research object can be automatically generated.

The invention is suitable for the technical field of computers, and provides a data analysis report generation method, which comprises the following steps: obtaining an analysis demand of a user, and performing intention analysis on the analysis demand to obtain a preliminary research demand; planning a preliminary layout of an analysis report based on the preliminary research demand; based on the preliminary layout, decomposing the preliminary research demand into a plurality of research tasks; and for each research task, in combination with the content of the knowledge base, respectively carrying out deep research, generating an analysis draft, carrying out global integration and correlation analysis on each analysis draft, and compiling a complete data analysis report. A unified data conversion and data analysis process is provided, and the data integration and comprehensive analysis capability is improved.

The application provides a scientific research data processing method, a processing system and an electronic device, including: acquiring multi-modal process data corresponding to a target scientific research task; performing context alignment processing on the multi-modal process data to obtain context feature data; performing feature extraction and sensitive information processing on the context feature data to generate a data package; wherein the data package includes desensitized general feature information and corresponding result labels; in response to an external search request, determining a target data package matching the external search request based on the general feature information; recording the call flow information of the target data package to trace the origin of the target data package. This way can reconstruct the context association of the scientific research process data while protecting the privacy of the core data, so that the intermediate process data and the unsuccessfully verified data can be safely searched, reused and traced, thereby improving the flow value of the scientific research process data.

The application discloses an error-driven adaptive research process rectification method and system, and relates to the technical field of natural language processing. The method comprises the following steps: decomposing a research task submitted by a user into a plurality of subtasks with a dependency relationship, and generating an initial directed acyclic graph (DAG); executing each subtask according to the DAG, and performing logical verification on an intermediate result to identify an error type; when an error is identified, mapping the error type to a rectification action; adjusting the DAG according to the rectification action, including deleting an error branch, reconstructing a node sequence or inserting a new node; repeatedly executing the process based on the updated DAG until a research completion condition is met, and generating a research report. The application realizes nonlinear re-planning through dynamic adjustment of the DAG, effectively avoids error accumulation, and improves the accuracy and reliability of a complex research task.