12 results about "Study analysis" patented technology

The embodiment of the invention discloses an academic research analysis method and device based on a large language model and a medium, and relates to the technical field of large language models.The method comprises the steps that under triggering of an academic research query request of a user, query text data is obtained, semantic analysis is conducted on the query text data, and a structured query task sequence is generated; querying a preset dynamic research knowledge graph based on the structured query task sequence, performing graph structure query and association expansion, and generating preliminary analysis result data with cross-thesis knowledge association; calling a field-specific scientific big language model subjected to pre-training and instruction fine tuning to process the preliminary analysis result data, and generating deep analysis result data; and quotation traceability processing and anti-illusion verification are carried out on the deep analysis result data to generate credible result data, the credible result data are returned to the user client for display, and the credible result data comprise original text fragment quotation labels and illusion evaluation indexes.

Systems and methods are provided for enabling search and query functions. A query system having a framework, executed on one or more processors, includes a plurality of Artificial Intelligence (AI) agents working to support one of text-to-Structured Query Language (SQL) or text-to-Python, wherein the plurality of AI agents include a first AI agent prompted to act as a research analyst for performing a task of interpreting a natural language query from a user, wherein the natural language query relates to natural language to the one of text-to-SQL or text-to-Python; a second AI agent prompted to act as a search data engineer for performing a task of executing a search based on the natural language query; and a third AI agent prompted to act as a code developer for performing a task of writing code based on the search, wherein the plurality of AI agents act autonomously yet collaboratively.

Systems and methods are provided for enabling search and query functions. A query system having a framework, executed on one or more processors, includes a plurality of Artificial Intelligence (AI) agents working to support one of text-to-Structured Query Language (SQL) or text-to-Python, wherein the plurality of AI agents include a first AI agent prompted to act as a research analyst for performing a task of interpreting a natural language query from a user, wherein the natural language query relates to natural language to the one of text-to-SQL or text-to-Python; a second AI agent prompted to act as a search data engineer for performing a task of executing a search based on the natural language query; and a third AI agent prompted to act as a code developer for performing a task of writing code based on the search, wherein the plurality of AI agents act autonomously yet collaboratively.

A government data analysis system that may aggregate the data of government entities in state and local education (SLED), such as K-12 schools, K-12 school districts, and higher education institutions, and process and store the data. The government data analysis system may provide, enable, or facilitate various functionality for the data, such as artificial intelligence-assisted research, analysis, procurement, compliance and other functionality. The government data analysis system may generate workspaces for users that combine data for numerous government entities in SLED that would otherwise be separate. Such data may include strategic plans, meeting materials (for example, school board agendas or meeting minutes), budgets, and contact information of the government institutions. The government data analysis system may analyze the data using artificial intelligence systems that include large language models (LLMs) in order to surface actionable insights, signals, and other information to users.

A computer-implemented federated studies system and method are disclosed. The system includes: a predefined common data model associated with a study; a set of sites of origin, each associated with a set of input devices for acquiring study data from subjects and a study data device. Each study data device includes: a database for storing study data derived from input devices; a data model translator for translating study data to a common data model format; a common model database for storing, in the data model, individual participant values derived from study data; a study compute module for determining site aggregate values from individual participant values; and an aggregate database for storing site aggregate values. A site of analysis is associated with a study analysis device that includes: an analysis compute module for processing site aggregate values received from sites of origin; and a reporting module for generating study reports.

The application provides a case retrieval method and device based on a large language model and vector retrieval, and belongs to the field of data retrieval. The method specifically comprises receiving a case retrieval query instruction; when the large language model is called to determine that the background processing branch of the case retrieval query instruction is regular case retrieval, the case facts and case causes are disassembled according to different case dimensions, case retrieval elements are generated, and retrieval weights are assigned; the preliminary recall cases corresponding to each case dimension are obtained according to the similarity values; the preliminary recall cases are screened once based on the similarity values and the retrieval weights to determine candidate cases; the candidate cases are subjected to a correlation Boolean value determination with the case facts and case causes to obtain target cases; and a case study analysis report is generated based on the case facts and case causes and the target cases by using the large language model. Through the processing scheme of the application, it is ensured that the case search will not miss any important dimension such as facts or controversial points, and the accuracy and comprehensiveness of case retrieval are greatly improved.

The invention relates to a haemodynamics big data percentile three-dimensional visualization system based on artificial intelligence, an operation method and application, and the system comprises a data set construction unit which is configured to obtain haemodynamics sample data and construct a data set; a first fitting unit configured to: construct a data subset of the data set, and fit an LMS curve coefficient; a mapping data set construction unit configured to: construct a mapping data set of the data subsets; a second fitting unit configured to: construct a data subset of the mapping data set, and fit an LMS curve coefficient; and the percentile plane acquisition unit is configured to calculate a percentile curve value of standard two-dimensional normal distribution to obtain a percentile plane. According to the method, two dimensions are expanded to three dimensions, more change rules are displayed through a curved surface, and research and analysis of a user aiming at problems in actual work are facilitated.

The application discloses a kind of development adjusted reservoir engineering research whole-process informatization method, comprising: collecting reservoir static, production, test, monitoring, test data;Divide research and analysis object, carry out data splitting and classification;Automatic process visualization index;Man-machine interactive data iteration verification, and improve data and analysis index;Data export is converted and format conversion;Man-machine interactive scheme deployment optimization.The application can optimize the interactive relationship between reservoir engineering comprehensive researchers and programmatic platform software, form the optimization method of reservoir engineering comprehensive research quality and efficiency, and greatly improve the whole-process work efficiency of development adjusted reservoir engineering research.

The application discloses an experimental system for intrinsic flexible thickness sensor sensitive characteristic research, and belongs to the technical field of sensor performance test; the experimental system comprises a platform base, a platform displacement slider, a displacement slider supporting rod, a clamping plate connecting supporting rod, a coil fixing clamping plate and a metal sample fixing clamping plate; the system can be used to realize the thickness nondestructive detection sensitive characteristic research of the intrinsic flexible thickness sensor under the conditions of a plane and different bending states; the system can be used to conduct low-frequency transmission type nondestructive measurement experiments on metal samples with different thicknesses after the sensor is fixed on different coil fixing clamping plates, so that the intrinsic flexible sensor sensitive characteristics are obtained; the application can realize the characteristic research of the intrinsic flexible thickness sensor nondestructive detection experiment under multiple conditions, the system has simple structure and is convenient to operate, the setting of each component in the system can be flexibly adjusted according to the experimental requirements, the experimental analysis cost is low, and the system is suitable for the sensitive characteristic experiment and research analysis of the intrinsic flexible sensor.

The utility model provides a hinge buffer support test equipment, including test door, test buffer hinge, test frame, test device, test buffer hinge is hinged on test door and test frame respectively, and test device includes bearing detection component, angle detection component, buffer detection component, adopts the structure cooperation of bearing detection component, angle detection component and buffer detection component, simple structure, practical and reliable, and has the adjustment function, can adjust the initial angle of weight height and test door, sets up different test environment, is convenient for user test operation and uses, is favorable to the analysis underlink performance of different test parameters, can provide certain data source for research analysis for scientific researchers.

The utility model provides a kind of side slope water and soil conservation simulation device, it is related to side slope simulation technical field, including side slope device and root box, the side slope device includes mobile seat and shell, the shell is hinged in the top of mobile seat, and one end above mobile seat is hinged with hydraulic rod, the output end of hydraulic rod is hinged with shell, and hydraulic rod is used to push shell to tilt simulation side slope and cooperate with root box;The lower part of the inside of shell is equipped with mesh plate;The utility model carries soil by shell, can push shell rotation by hydraulic rod, simulation gradient, hydraulic adjustable, can carry out spray simulation to the soil sample in device by spray and sow component, can sample to the different interface of water gas soil by sampling component, can cooperate with monitoring supporting equipment monitoring including soil humidity, temperature monitoring, the determination of soil physicochemical property by monitoring component, thus, it is convenient to simulate research analysis to side slope water and soil conservation many factors.

Methods and systems are disclosed for using an intelligent injection device platform to perform longitudinal and other health outcome analyses. A device may include a database for storing treatment schedules, administration data, and biomarker measurements. A device may include a data collection system configured to collect biomarker data from connected monitoring devices. A device may include a compliance analysis module configured to calculate an adherence score by comparing actual administration timing and dosage to a prescribed treatment schedule. A device may include a research analytics module configured to analyze a relationship between medication regimen adherence and a patient outcome. A device may include a reporting system configured to generate an observational study report correlating a drug adherence pattern with a biomarker change and a clinical outcome.