32 results about "Research system" patented technology

The invention provides a financial research report generation method based on a large model. Comprising a data collection module, a data analysis module and a report writing module. The data collection module is used for receiving a predefined data collection task and an autonomously generated data collection task, then inputting the tasks into a deep search agent, and constructing a structured multi-modal memory for a search result for storage; the data analysis module constructs a data analysis agent, and realizes the generation of a structured multi-modal small report through cooperation of a financial calculation tool, a chart generation tool and a reference addition tool in an actor-reviewer iteration mode in which a large language model is matched with a visual language model; and the report writing module constructs a report writing agent to obtain a chapter first draft and then inputs the chapter first draft into the post-processing agent to obtain a final report. The problems that an existing deep research system and a large language model agent in the financial field are lack of financial field knowledge, limited in multi-modal ability, limited in research and report generation depth and comprehensiveness and the like are solved.

The invention discloses an AI intelligent investment and research decision optimization method based on deep learning, particularly relates to the field of artificial intelligence financial science and technology, and solves the technical problems that an existing intelligent investment and research system is insufficient in multi-source data fusion, static stiffness of feature engineering, insufficient in complex market association modeling, lagged in extreme risk protection and the like. Cross-modal alignment of structured market information and unstructured public opinions is realized through a multi-modal data fusion architecture, a self-evolution feature extraction network is constructed by adopting a deformable convolutional network and a gating circulation unit chain, and a multi-target strategy is generated based on a reinforcement learning and graph neural network coupling engine. In combination with a conditional generative adversarial network simulation extreme scene and a meta-learning framework dynamic hardening risk threshold, a cloud edge collaborative decision closed loop is finally formed, and the decision adaptability, risk control robustness and model interpretability of the system in a complex market environment are improved.

To provide a time study system, an information processing method, and a program for performing operation analysis by time study.SOLUTION: In an information processing method in an information processing system, a server device includes at least one control unit. The control unit performs: acquiring work time information indicating a time taken for work executed by at least one worker on work-by-work basis (SQ402); selecting, based on the work time information for each type of work, a tool or a service leading to reduction of the work time for each type of work (SQ405); and outputting information of the selected tool or service (SQ407).SELECTED DRAWING: Figure 4

The invention discloses a chart generation system and method based on a Highcharts chart library. The system comprises a data acquisition module, wherein the data acquisition module comprises an index library data acquisition unit and a prediction index library data acquisition unit; the chart generation module comprises a date and value drawing unit, a combined algorithm drawing unit, a chart obtaining drawing unit and a chart picture obtaining unit; the chart theme configuration module comprises a default theme configuration unit, a personalized theme configuration unit and an independent field configuration unit; and the chart output module comprises a research report calling chart unit, a PPT calling chart unit, a logic deduction calling chart unit and a chart library framework calling chart unit. The system can improve usability and individuation of chart generation, and meets complex business requirements in a financial investment research system.

The application relates to the technical field of the cross of artificial intelligence and behavior science, in particular to a market research system based on multi-source data integration and psychological analysis, which comprises a processing module, an RAG module, a retrieval module, a summary module, an analysis module and a verification module; the processing module processes feedback data of market research; the RAG module retrieves to obtain multi-modal data; the retrieval module retrieves to obtain data samples; the summary module extracts data features; the analysis module analyzes the data samples and generates analysis conclusions; and the verification module verifies the results of the analysis module. The application generates multi-modal data of feedback data in the Internet through the retrieval module, and according to the obtained data samples, the analysis module analyzes to obtain analysis conclusions by combining virtual user models of psychology and / or sociology, so that the problem that the system has weak theoretical support and single data dimension is avoided.

1. The name of this design product: Graphical user interface for scientific research system of display screen. 2. Purpose of this design product: This design display screen is used to display data from scientific research systems. 3. The key design point of this design product lies in the interface content of the graphical user interface on the screen. 4. The picture or photo that best illustrates the key points of the design: main view. 5. The display screen is of conventional design. The rear view, left view, right view, top view and bottom view are omitted and have no design points. 6. Purpose of the graphical user interface: This design is used in the interactive interface of a web page system. Through user interaction, by clicking on the graphical user interface, XX content is replaceable text. This display screen is used for computers. 7. Human-computer interaction method of the graphical user interface: The specific interaction process of this appearance design: the main view is the "Scientific Research Overview" interface. Click the "Institutional Management" button under the drop-down arrow of the "Management Center" option box on the left side of the main view to enter the interface change status diagram.

The invention relates to the technical field of robots, automatic driving and industrial internet of things, in particular to a multi-source data fusion visualization system which comprises a unified data access layer, a time-space synchronization engine, a customizable fusion visualization panel and a visualization information interaction module by expanding a Foxglove platform. The unified data access layer accesses and standardizes multi-source heterogeneous data, the time-space synchronization engine realizes data time alignment and space registration, the customizable panel flexibly displays multi-dimensional data, and the interaction module realizes man-machine operation and hardware feedback. The system solves the problems of multi-tool fragmentation, difficulty in data synchronization, visualization fixation and lack of self-research system adaptation in the prior art, adapts to a lightweight self-research system of an ARM embedded platform, and improves the research, development and debugging efficiency of robots and automatic driving equipment.

The invention discloses a domestic and overseas research and analysis system based on a large language model, and relates to the technical field of scientific research and analysis. Comprising an AI index system and a big language research and analysis model; the AI index system comprises a research development process index module and a related research achievement index module, and the large language research analysis model comprises a development process generation model and a research achievement architecture model; arranging development process contents through a development process generation model to generate a basic development process framework diagram; a related research result construction module is arranged on the development process framework diagram, and the indexed related research results and data are constructed on the development process framework diagram. Through the AI index system and the big language research and analysis model, the problems that existing analysis and research depend on summarization of professionals, and there is no more efficient and accurate analysis and research system are solved, efficient and accurate association combination and combination analysis of multiple fields can be achieved, and the problems that cross-field combination analysis is difficult and not high in precision are solved.

The invention discloses an information interaction method, device and equipment applied to an investment and research system, and a storage medium, and relates to the technical field of information interaction, and the method comprises the steps: obtaining interaction information of a user in a preset instruction window; determining a matching degree between the interaction information and each preset business processing module in the investment and research system, and determining a target business processing module according to each matching degree, each preset business processing module corresponding to each business function page in the investment and research system; obtaining a preset processing rule of a target business function page corresponding to the target business processing module; and processing the interaction information through the target business processing module according to a preset processing rule to obtain a processing result. The target business processing module can be automatically determined according to the matching degree of the interaction information, so that manual switching and searching among a plurality of business function pages by a user are avoided, and the convenience and efficiency of user operation are improved.

The invention belongs to the field of information technology and nuclear power engineering management cross technology, and particularly relates to a multi-reactor nuclear power station knowledge management intelligent platform and method based on a block chain technology. Comprising a cloud computing and big data driven knowledge storage integration module which is a function block shared by all block chain nodes on a chain; the block chain enabled decentralized collaborative network comprises a multi-node trust mechanism module and an intelligent contract rule base; the intelligent knowledge management module driven by artificial intelligence comprises an intelligent knowledge pushing module, an intelligent editing and research system and an active pushing and synchronous updating module; an Internet of Things and edge computing integration module; and a one-key copy block chain node regeneration module. The method is used for realizing knowledge integration, resource sharing, risk management and control and efficient cooperation in the global strategy of the nuclear power project.

In order to evaluate the stability of a high-proportion power electronic system, the discrete state space model establishing method and device suitable for the direct-current three-port element are provided on the basis of an original discrete state space modeling method, and the specific scene range of the discrete state space model is further expanded. The method comprises the following steps: firstly, deducing a direct current three-port element discrete state space model, establishing a direct current three-port element discrete equivalent circuit model, further establishing an alternating current and direct current hybrid system whole-network discrete state matrix containing the direct current three-port element, and verifying the correctness and practicability of the matrix. The small-signal model established by the method has relatively high expansibility, is convenient for subsequently establishing a full-system state space model connected with a large area containing a direct-current three-port element, and establishes a basis for researching the stability of the system.

The invention relates to cross application of an artificial intelligence technology in the field of market investigation, in particular to a technology for generating simulated human equipment by using an AI (artificial intelligence) big language model and performing dynamic interactive investigation, which comprises the following steps of: acquiring and processing original data containing user characteristic information to form a standardized, high-quality and low-noise data set; defining a human device parameter system, and based on the data set and by utilizing an AI large language model, generating a plurality of simulated human devices which have corresponding attribute characteristics and can carry out context association dialogue according to each group of human device parameters, so as to form a simulated human device library; generating an investigation questionnaire based on to-be-investigated target content, selecting a target simulation person from the simulation person library, sending the investigation questionnaire to the simulation person to simulate a real interview, and performing multiple rounds of investigation to obtain interaction data; and generating an investigation report based on the interaction data, so that a target market user group can be dynamically simulated in a large-scale and low-cost manner, and new products, new concepts and new schemes can be quickly fed back.

The invention relates to the technical field of computer systems, in particular to a material research system and method based on a multi-agent game, and the system comprises a man-machine interaction module, a scheme generation module, a review module, an arbitration module, a scheme execution module and a knowledge base module: the man-machine interaction module generates a task instruction according to a user demand; the scheme generation module is used for generating a plurality of candidate schemes; the review module performs multi-view cross review and risk interception on the candidate schemes; the arbitration module is used for processing opinion conflicts among multiple agents; the scheme execution module is used for executing an experiment and collecting data; and the knowledge base module is used for providing static knowledge support and closed-loop backflow of dynamic experimental data for the system. According to the method, multi-target conflicts, knowledge uncertainty and theoretical and practical differences in material research and development are converted into a structured and computable dynamic game process, so that the comprehensiveness of scheme generation, the preciseness of review and the success rate of experimental conversion are systematically improved.

The invention relates to the technical field of deep learning, and particularly discloses a museum exhibit deep research system fused with a multi-modal large model. The system comprises a multi-modal data aggregation module, a cross-modal semantic alignment module, a research path generation module, a dynamic argumentation construction module and a research conclusion generation module, through multi-modal data fusion, semantic alignment and intelligent path planning, an argumentation structure is automatically constructed, and a standard research conclusion is generated. The whole-process intelligent support of exhibit research is realized, and the research efficiency and systematicness are improved.

The invention provides a key area identification and power grid oscillation risk early warning method and device based on node modal voltage distribution in order to evaluate the stability of a multi-ring network wind and light distributed access system and further analyze an instability scene of the multi-ring network wind and light distributed access system, and the key area identification and power grid oscillation risk early warning method and device based on node modal voltage distribution are combined according to linear transformation of a research system node voltage equation and a discrete state space state variable. And the modal quantity response condition of each node of the system is calculated, and a node modal voltage distribution coefficient is defined as an index, so that a key area and a line are positioned, and system operation personnel are helped to strengthen monitoring on a local power grid and take related countermeasures at a proper position. According to the method, verification is carried out in combination with an actual multi-ring network wind and light distributed access system, and the effectiveness of the method is verified through time domain simulation and eigenvalue analysis.

The invention discloses a legal management research system for AIGC generation error risk division. The system comprises a dynamic error data acquisition and test module, a risk level evaluation and traceability module, a legal responsibility system and adaptation module, a user cognitive intervention and feedback module and a collaborative optimization and strategy iteration module. Collecting and preprocessing AIGC model generation content; constructing an evaluation matrix of error risks, dividing risk levels, and tracing error causes; on the basis of the risk level, legal terms are associated through a semantic matching algorithm, responsibility rules for developers, platforms and users are constructed, and a responsibility traceability chain of block chain evidence storage is generated; generating an authenticity tag, embedding the authenticity tag into an AIGC model to generate a content sample, pushing the content sample to a user, and collecting feedback data; iterating each module parameter based on a reinforcement learning algorithm; according to the method, AIGC model generation content is linked with legal responsibility rules, technical traceability is combined with execution support, and accurate intervention is designed for AIGC model generation error features.

The invention discloses an archive editing and research automation system based on machine learning and natural language processing, and relates to the technical field of archive management and information processing, and the system comprises an archive editing and research system which automatically collects, arranges, analyzes, studies and compiles archive information to form various archive editing and research results, and a data collection and processing module which is used for collecting and processing the archive information. The method is used for collecting archive information from various channels. According to the archive editing and research automation system based on machine learning and natural language processing, through the data collecting and processing module and the natural language processing module, information can be automatically extracted, the time cost and the error rate of traditional manual retrieval are greatly reduced, the efficiency and the accuracy of processing a large amount of diversified and unstructured archive data are improved, and the archive editing and research automation system is suitable for popularization and application. Through the machine learning module, the efficiency and systematicness of data management are improved by utilizing the classification and arrangement functions of machine learning, and deep knowledge is conveniently extracted from archive data through the application of the NLP technology of the archive editing and research generation module.

The present invention discloses an online teaching and research system and device based on a collaborative whiteboard, wherein the online teaching and research system includes a lecturer client, a plurality of student clients, a plurality of reviewer clients, an audio and video server, a class whiteboard server, and a reviewer whiteboard server, and further includes a lecturer client. The lecturer client is connected to the audio and video server and the class whiteboard server respectively, each student client is connected to the audio and video server and the class whiteboard server respectively, and each reviewer client is connected to the audio and video server and the reviewer whiteboard server respectively; the lecturer client is logged in and used by the lecturer, the student client is logged in and used by the student, and the reviewer client is logged in and used by the reviewer. The present invention utilizes audio and video synchronization technology and whiteboard collaborative technology to connect the relatively separated scenes of teaching, reviewing, listening to classes, and reviewing in traditional offline teaching and research activities.

The invention discloses a student companion teaching research system based on computer simulation, and relates to modeling, simulation experiments and data analysis of student companion teaching behaviors. The system is composed of a student companion teaching behavior strategy simulation module, a social simulation module and a data collection and analysis module, can simulate various student interactive behaviors, and performs experimental analysis on the influence of emotion, experience, neighbors and other factors on the behaviors. A core experiment framework of the system is formed by five behavior selection strategies (based on emotions, win-win people and input people exchange, the highest accumulated reward, most of historical behaviors of opponents and most of neighbors) and three network structures (full connection, grids and small world networks), the complex dynamic state of student companion teaching can be efficiently simulated, and factors influencing the interactive behaviors of the students are revealed. The system adopts an agent modeling technology, and each student is regarded as an independent agent and can autonomously select behaviors and update emotional states in interaction. Experimental results show that a behavior selection strategy and a network structure have significant influence on student interaction behaviors, for example, an emotion-based strategy can better encourage companion teaching in a full-connection network, and existence of a fixed behavior agent also affects a behavior mode of a whole group. The invention provides an efficient and flexible research platform for exploring the relationship between the student companion teaching behaviors and various factors, and provides a reference basis for the school to optimize the companion teaching environment.

To provide a time study system, an information processing method, and a program which can effectively use information.SOLUTION: In a time study system, a control unit of a server apparatus acquires work time information including a time spent on each type of work executed by at least one worker, selects a tool or service that contributes to shortening the work for each type of work on the basis of the work time information for each type of work, and outputs information on the selected tool or service. The control unit receives start time information indicating when each type of work executed by at least one worker is started and end time information indicating when the work is completed, and calculates the work time information for each type of work on the basis of the start time information and the end time information.SELECTED DRAWING: Figure 4

Some embodiments provide a method for generating a graphical user interface (GUI) for a research system. The method receives a request from a user of the research system for information about a particular category. The method generates a chart that displays a set of events associated with the particular category over a particular period of time. The method incorporates the chart into a GUI for the particular category for transmission to the user. Some embodiments generate a list of events associated with the particular category and generate a GUI that displays the list of the events. Each event is represented in the list by a title of a document identified by the research system as representative of the event.

Some embodiments provide a method for generating a graphical user interface (GUI) for a research system that identifies documents relevant to several categories. The method receives a user objective and at least one initial category for a recurring search that identifies documents relevant to several categories for presentation to a user. The method provides for display in the GUI several selectable additional categories related to the received initial category for the user objective. The method receives a selection of a set of categories through the GUI. The method provides for display in the GUI an optimized modifiable set of filters for removing specific types of documents that are relevant to the set of categories from the recurring search. The method generates the recurring search for the user based on the received categories and a modified set of filters.

1. Name of the Design Product: Graphical User Interface for Displaying Fund Data of Electronic Devices. 2. Use of the Design Product: For an electronic device. 3. Design Key Points of the Design Product: Lies in the interface content of the graphical user interface. 4. Picture or Photo Most Indicating the Design Key Points: The front view of Design 1. 5. Design 1 is designated as the basic design. 6. Use of the Graphical User Interface: This graphical user interface of the design is used to display fund data. The front view of Design 1 is the display page of the fund evaluation and research system. Basic functions are shown in the interface. When the user clicks the "View Now" button in the first functional area, the change state diagram of Design 1 can be presented, which is used to view the fund income data situation. The front view of Design 2 is the display page of the fund evaluation and research system. Basic functions are shown in the interface. When the user clicks the "View Now" button in the second functional area, the change state diagram of Design 2 can be presented, which is used to view the fund data situation. 7. Other Situations Requiring Explanation: Other Explanation: "××" in the interface represents variable text.

The invention discloses an intelligent risk analysis and research system and method based on a browser plug-in, and relates to the technical field of financial science and technology. The system comprises a visual process arrangement interface, a process engine and an AI model. The system receives a modular risk control node process arranged by a user through a visual interface, and is driven and executed by a process engine. The core of the method is that in the process of process execution, a system can respond to an interrupt waiting node or a user natural language instruction to suspend the process and wait for interaction; the instruction intention can be analyzed to realize flow skipping or backtracking; after the nodes are executed again, the AI model carries out comparative analysis on execution results and generates a report; and finally integrating node outputs to generate a structured risk control conclusion. According to the method, the problems of low efficiency, lack of deep insight and flexibility of a traditional risk control process are solved, intelligent risk analysis of man-machine cooperation is realized, and the method is particularly suitable for financial risk management scenes such as commercial factoring and the like.

The invention relates to the technical field of artificial intelligence and behavioral science crossing, in particular to a market research system based on multi-source data integration and psychological analysis, which comprises a processing module, an RAG module, a retrieval module, a summarization module, an analysis module and a verification module. The processing module is used for processing feedback data of market research; the RAG module carries out retrieval to obtain multi-modal data; the retrieval module performs retrieval to obtain a data sample; the summarization module performs data feature extraction; the analysis module analyzes the data sample and generates an analysis conclusion; and the verification module verifies the result of the analysis module. The multi-modal data of the feedback data is generated in the Internet through the retrieval module, and according to the obtained data sample, the analysis module performs analysis by combining a psychological and / or sociology virtual user model to obtain an analysis conclusion, so that the problems of weak theoretical support and single data dimension of the system are avoided.

This application relates to the technical field of ship performance testing, and specifically to a land-based ship ladder virtual-real symbiotic rocking system and device. The system comprises: a digital simulation module that constructs a virtual digital model of the ship hull based on wave parameters and ship type data, simulates the motion of the hull in different sea conditions, obtains control signals from the three servo motors of the ship ladder in roll, pitch, and heave, and optimizes the control signals; and a physical simulation module in which the three servo motors control the three degrees of freedom of roll, pitch, and heave, respectively, using the control signals optimized by the digital simulation module. This application aims to improve the accuracy of the ship ladder land-based rocking test bench in simulating real sea conditions, and to establish a scientific research system and platform that can conduct ship ladder technology research at any time on land.

The embodiment of the invention provides a space-time research and judgment method, a research and judgment system, electronic equipment and a storage medium. The method comprises the following steps: acquiring network access data corresponding to an entity to be researched and judged, and processing according to a preset feature extraction rule to obtain basic feature information and associated feature information; constructing a spatial-temporal feature sequence according to the basic feature information and the associated feature information, and inputting the spatial-temporal feature sequence into a trained feature recognition model to obtain behavior feature information; comparing the behavior characteristic information with behavior characteristic conditions in a behavior rule base to obtain a characteristic comparison result; according to a feature comparison result, when it is determined that the entity to be researched and judged meets a preset research and judgment condition, determining an expanded network entity according to the associated feature information; and according to the research and judgment result of the entity to be researched and judged and the expanded network entity, generating and outputting a space-time research and judgment result. According to the invention, the time-space research and judgment of the target entity and the associated network space thereof are realized, and the comprehensiveness and accuracy of identification are improved.

The invention relates to the technical field of ship performance testing, in particular to a ship ladder virtual-real symbiotic land-based swing system and device.The system comprises a digital simulation module, a ship ladder virtual-real symbiotic land-based swing system and device.The digital simulation module constructs a virtual digital model of a ship body according to sea wave parameters and ship type data and simulates the motion states of the ship body in different sea conditions; control signals of the ship ladder on the rolling servo motor, the pitching servo motor and the heaving servo motor are obtained, and optimization processing is conducted on the control signals; three servo motors of the physical simulation module respectively control three-degree-of-freedom motions of rolling, pitching and heaving through control signals optimized and processed by the digital simulation module. The invention aims to improve the accuracy of the ship ladder land-based swing test bed for simulating the physical sea condition, and establishes a scientific research system and platform which can carry out ship ladder technical research at any time on the land.