System and method for trajectory analysis of science and technology topics based on map visualization

Abstract

The application relates to a science and technology theme trajectory analysis system and method based on map visualization, wherein the system comprises: a map visualization module for collecting and processing geographical position information of global scientific research institutions to generate map tiles containing point position information, and rendering and interacting the geographical spatial distribution of the scientific research institutions; a multi-source data acquisition and processing module for acquiring paper data and / or patent data from at least one target database in a semantic manner; an AI analysis module for identifying institutions in a region and calculating scientific research density in the region through frame selection based on the paper data and / or the patent data, and generating a professional analysis report containing data insights according to a user-selected analysis object and target; and a user interaction interface module for dynamically adjusting display content according to user operations to perform point clustering, zooming adaptation and intelligent label display. Thus, the problems of weak geographical spatial visualization capability in the related art, inability to support large-scale real-time rendering and interactive regional analysis, data retrieval and analysis fragmentation and lack of AI automatic report generation function, and complicated user operation are solved.

Description

Technical Field

[0001] This application relates to the fields of data visualization and scientific and technological intelligence analysis, and in particular to a system and method for analyzing the trajectory of scientific and technological topics based on map visualization. Background Technology

[0002] With increasingly fierce global technological competition, accurately grasping the trends and directions of technological development, identifying innovation hotspots, and identifying future trends are crucial for formulating national innovation strategies and selecting corporate technology routes. Traditional technology intelligence analysis models are no longer sufficient to meet current needs. How to achieve more efficient, intuitive, and comprehensive technology intelligence analysis has become a key issue supporting technological innovation decision-making.

[0003] In related technologies, science and technology intelligence analysis systems present data in the form of tables, charts, and text. There are also science and technology intelligence systems on the market such as InCites and SciVal, which can provide functions such as statistical summarization and basic analysis of scientific research data, and to a certain extent help users obtain science and technology intelligence.

[0004] However, among the related technologies, the rendering efficiency of geospatial data is low, making it difficult to intuitively display the distribution of scientific research institutions and regional innovation clusters, and it cannot support large-scale real-time rendering; data display and in-depth analysis are disconnected, lacking the ability to generate science and technology theme trajectories from a geographical perspective, and lacking AI-automated report generation functions, resulting in cumbersome user operations and seriously affecting the efficiency and depth of analysis, which urgently need to be improved. Summary of the Invention

[0005] This application provides a technology-themed trajectory analysis system and method based on map visualization to solve problems such as weak geospatial visualization capabilities of related technologies, which prevents support for large-scale real-time rendering and interactive regional analysis, fragmented data retrieval and analysis, and lack of AI-automated report generation functions, resulting in cumbersome user operations.

[0006] The first aspect of this application provides a science and technology theme trajectory analysis system based on map visualization, comprising: a map visualization module for collecting and processing geographical location information of global research institutions, and generating map tiles containing point information based on the geographical location information to render and interact with the geospatial distribution of research institutions; a multi-source data acquisition and processing module for semantically acquiring paper data and / or patent data from at least one target database; an AI analysis module for identifying institutions within a region by selecting a region and calculating research density based on the paper data and / or patent data, and generating a professional analysis report containing data insights according to the analysis object and target selected by the user; and a user interface module for dynamically adjusting the displayed content according to user operations to perform point clustering, adaptive scaling, and intelligent label display.

[0007] Through the above-mentioned technical means, the embodiments of this application can generate map tiles containing points to achieve real-time rendering of large-scale scientific research institutions. Combined with the semantic acquisition of multi-source papers and patent data, it can realize the identification of regional institutions and calculate scientific research density, so as to generate professional analysis reports and display dynamic interaction according to user selection. This enables efficient geospatial visualization, real-time retrieval of multi-source data and intelligent analysis report generation, providing more intuitive and comprehensive data support for scientific and technological innovation decision-making.

[0008] Optionally, in one embodiment of this application, the map visualization module includes: a high-performance tile service submodule, used to draw map tiles containing institutional points, execute a three-level caching strategy including memory caching, disk caching, and on-demand generation, calculate the corresponding geographic boundary based on the requested tile coordinates, query institutional point data within the boundary, determine the rendering strategy of the points according to the zoom level, draw the points and labels, and save the generated tile images to the corresponding cache level; and an adaptive point rendering submodule, used to dynamically adjust the point size and label display strategy according to the map zoom level, display only points at a preset low zoom level, and at a higher zoom level... The system includes a preset high zoom level that simultaneously displays location and institution name labels; an adjustment of the aggregation radius when the location density within the target area exceeds a preset threshold; optimization of clustering granularity and rendering of locations within the current viewport through control function parameters; and a regional scientific research density analysis submodule that is used to drag and draw rectangular selection areas on the map, obtain the map geographic boundaries of the selection areas, convert the map geographic boundaries into tile boundaries, traverse the location data in the visible tiles to filter out institutions within the selection areas, construct a JSON object describing the geometry of the selection areas, pass the selection area JSON object and the list of institutions to the AI ​​analysis module, and generate a regional scientific research density analysis report.

[0009] Through the above-mentioned technical means, the embodiments of this application can draw map tiles of institutional locations, implement a three-level caching strategy, dynamically adjust the point rendering and label display strategy in combination with the scaling level, and support map selection operations and generate regional analysis reports, effectively improving the efficiency and interactivity of rendering the geospatial distribution of scientific research institutions, making it easier for users to quickly grasp the distribution of institutions in different areas, and achieve accurate geospatial range selection and institutional identification.

[0010] Optionally, in one embodiment of this application, the multi-source data acquisition and processing module includes: an intelligent data acquisition engine, used to construct a semantic query context based on user query requirements, analyze the context based on a preset engine to determine the best query strategy and parameters, send an optimized query request, receive and process query results to extract key information, intelligently process the key information and fuse the processed data, and return the processed data to the user interface module; and a heterogeneous data standardization processing submodule, used to perform unified format conversion and standardization processing on the multi-source heterogeneous data.

[0011] Through the above-mentioned technical means, the embodiments of this application can construct semantic query context, determine the best query strategy, process query results and perform data fusion and standardization, thereby improving the accuracy and efficiency of obtaining paper and patent data, realizing the effective integration of multi-source heterogeneous data, ensuring the reliability and consistency of subsequent analysis, and providing a high-quality data foundation for subsequent analysis.

[0012] Optionally, in one embodiment of this application, the AI ​​analysis module is further used to analyze the evolution of research topics and technical routes of institutions, analyze patent value and technology development trends and competitive intelligence, assess research frontiers and influence and cooperation networks, assess the cooperation density and innovation ecosystem among institutions, assess the scientific research and innovation vitality, distribution and evolution of target geographical regions, compare the research focus and innovation capabilities of different institutions in multiple dimensions, assess the academic influence of authors, changes in research fields, cooperation networks and results transformation, analyze inventors' technical expertise, innovation capabilities and patent portfolio value, and assess corporate patent strategies, technology layout and competitive advantages.

[0013] Through the aforementioned technical means, the embodiments of this application can further conduct multi-dimensional analysis of institutional research topics, patent value, cooperation networks, regional innovation vitality, author influence, and corporate patent strategies, thereby expanding the depth and breadth of scientific and technological intelligence analysis, providing in-depth insights into scientific and technological intelligence, and providing rich evidence for users to comprehensively assess the innovation situation and formulate strategic decisions.

[0014] Optionally, in one embodiment of this application, the AI ​​analysis module is further configured to determine the analysis object and analysis type selected by the user, construct prompt words containing key entity information, retrieve relevant data from the at least one target database, fuse the search results to construct an enhanced context, and generate at least one structured analysis report.

[0015] Through the above-mentioned technical means, the embodiments of this application can determine the user's analysis object and type, construct prompt words, retrieve and integrate data, and generate a structured report, thereby achieving the accuracy and structure of the analysis report, improving the relevance and practicality of the report generation, and meeting the diverse analysis needs of users.

[0016] Optionally, in one embodiment of this application, it further includes: an industry-academia-research collaboration analysis module, used to obtain institutional cooperation data from a preset database, construct an inter-institutional cooperation network based on the number of jointly published papers and patents, calculate key indicators of the network, identify cooperation patterns, display the cooperation network through a force-directed graph, and generate an industry-academia-research collaboration analysis report.

[0017] Through the aforementioned technical means, the embodiments of this application can present the cooperation network and model between industry, academia and research institutions through quantitative analysis and visualization, helping users to grasp the collaborative distribution of innovation resources and providing a basis for decision-making to promote cross-institutional cooperation and optimize the innovation ecosystem.

[0018] The second aspect of this application provides a method for a science and technology theme trajectory analysis system based on map visualization, comprising the following steps: collecting and processing geographical location information of global research institutions, and generating map tiles containing point information based on the geographical location information to render and interact with the geospatial distribution of research institutions; semantically acquiring paper data and / or patent data from at least one target database; identifying institutions within a region by selecting a region based on the paper data and / or patent data and calculating the research density, and generating a professional analysis report containing data insights according to the analysis object and target selected by the user; dynamically adjusting the displayed content according to user operations to perform point clustering, adaptive scaling, and intelligent label display.

[0019] Through the above-mentioned technical means, the embodiments of this application can generate map tiles containing points to achieve real-time rendering of large-scale scientific research institutions. Combined with the semantic acquisition of multi-source papers and patent data, it can realize the identification of regional institutions and calculate scientific research density, so as to generate professional analysis reports and display dynamic interaction according to user selection. This enables efficient geospatial visualization, real-time retrieval of multi-source data and intelligent analysis report generation, providing more intuitive and comprehensive data support for scientific and technological innovation decision-making.

[0020] Optionally, in one embodiment of this application, the step of collecting and processing the geographic location information of global research institutions, and generating map tiles containing location information based on the geographic location information for rendering and interacting with the geographic spatial distribution of research institutions, includes: drawing map tiles containing institution locations; executing a three-level caching strategy including memory caching, disk caching, and on-demand generation; calculating the corresponding geographic boundary based on the requested tile coordinates; querying institution location data within the boundary; determining the rendering strategy for the locations based on the zoom level; drawing the locations and labels; and saving the generated tile images to the corresponding cache level; dynamically adjusting the size of the locations based on the map zoom level. The system employs a label display strategy, displaying only points at a preset low zoom level and simultaneously displaying point and institution name labels at a preset high zoom level. It adjusts the aggregation radius when the point density within the target area exceeds a preset threshold, optimizes clustering granularity and renders points within the current viewport by controlling function parameters. The system drags and draws a rectangular selection area on the map, obtains the map's geographical boundary, converts the map's geographical boundary into a tile boundary, iterates through the point data in the visible tiles to filter out institutions within the selection area, constructs a JSON object describing the geometry of the selection area, and passes the selection area JSON object and the list of institutions to the AI ​​analysis module to generate a regional scientific research density analysis report.

[0021] Through the above-mentioned technical means, the embodiments of this application can draw map tiles of institutional locations, implement a three-level caching strategy, dynamically adjust the point rendering and label display strategy in combination with the scaling level, and support map selection operations and generate regional analysis reports, effectively improving the efficiency and interactivity of rendering the geospatial distribution of scientific research institutions, making it easier for users to quickly grasp the distribution of institutions in different areas, and achieve accurate geospatial range selection and institutional identification.

[0022] Optionally, in one embodiment of this application, the semantic acquisition of paper data and / or patent data from at least one target database includes: constructing a semantic query context based on user query requirements; analyzing the context based on a preset engine to determine the optimal query strategy and parameters; sending an optimized query request; receiving and processing query results to extract key information; intelligently processing and fusing the key information with the processed data; and returning the processed data to the user interface module; and performing unified format conversion and standardization processing on the multi-source heterogeneous data.

[0023] Through the above-mentioned technical means, the embodiments of this application can construct semantic query context, determine the best query strategy, process query results and perform data fusion and standardization, thereby improving the accuracy and efficiency of obtaining paper and patent data, realizing the effective integration of multi-source heterogeneous data, ensuring the reliability and consistency of subsequent analysis, and providing a high-quality data foundation for subsequent analysis.

[0024] Optionally, in one embodiment of this application, after identifying institutions within a region and calculating research density by selecting a region based on the paper data and / or patent data, and generating a professional analysis report containing data insights according to the user-selected analysis object and target, the analysis further includes: analyzing the evolution of research topics and technical routes of institutions, analyzing patent value and technological development trends and competitive intelligence, assessing research frontiers and influence and cooperation networks, assessing the cooperation density and innovation ecosystem among institutions, assessing the scientific research and innovation vitality, distribution and evolution of the target geographical region, comparing the research focus and innovation capabilities of different institutions from multiple dimensions, assessing the academic influence of authors, changes in research fields, cooperation networks and results transformation, analyzing the inventors' technical expertise, innovation capabilities and patent portfolio value, and assessing the enterprise's patent strategy, technology layout and competitive advantages.

[0025] Through the aforementioned technical means, the embodiments of this application can further conduct multi-dimensional analysis of institutional research topics, patent value, cooperation networks, regional innovation vitality, author influence, and corporate patent strategies, thereby expanding the depth and breadth of scientific and technological intelligence analysis, providing in-depth insights into scientific and technological intelligence, and providing rich evidence for users to comprehensively assess the innovation situation and formulate strategic decisions.

[0026] Optionally, in one embodiment of this application, after identifying institutions within a region and calculating research density by selecting a region based on the paper data and / or patent data, and generating a professional analysis report containing data insights according to the analysis object and target selected by the user, the method further includes: determining the analysis object and analysis type selected by the user, constructing prompt words containing key entity information, retrieving relevant data from the at least one target database, fusing the search results to construct an enhanced context, and generating at least one structured analysis report.

[0027] Through the above-mentioned technical means, the embodiments of this application can determine the user's analysis object and type, construct prompt words, retrieve and integrate data, and generate a structured report, thereby achieving the accuracy and structure of the analysis report, improving the relevance and practicality of the report generation, and meeting the diverse analysis needs of users.

[0028] Optionally, in one embodiment of this application, the method further includes: obtaining institutional cooperation data from a preset database, constructing an inter-institutional cooperation network based on the number of jointly published papers and patents, calculating key indicators of the network, identifying cooperation patterns, displaying the cooperation network through a force-directed graph, and generating an industry-academia-research collaborative analysis report.

[0029] Through the aforementioned technical means, the embodiments of this application can clearly present the cooperation network and model between industry, academia and research institutions through quantitative analysis and visualization, helping users to grasp the collaborative distribution of innovation resources and providing a basis for decision-making to promote cross-institutional cooperation and optimize the innovation ecosystem.

[0030] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the map visualization-based technology theme trajectory analysis method as described in the above embodiments.

[0031] A fourth aspect of this application provides a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described map visualization-based science and technology topic trajectory analysis method.

[0032] A fifth aspect of this application provides a computer program product that stores a computer program that, when executed by a processor, implements the above-described method for analyzing the trajectory of science and technology topics based on map visualization.

[0033] This application's embodiments can generate map tiles containing location data to achieve real-time rendering for large-scale research institutions. Combined with semantic acquisition of multi-source papers and patent data, it enables regional institution identification and calculation of research density. Based on user selections, it generates and displays dynamic interactive professional analysis reports, thereby achieving efficient geospatial visualization, real-time multi-source data retrieval, and intelligent analysis report generation. This provides more intuitive and comprehensive data support for scientific and technological innovation decision-making. Therefore, it solves the problems of weak geospatial visualization capabilities in related technologies, which prevent support for large-scale real-time rendering and interactive regional analysis; the disconnect between data retrieval and analysis; and the lack of AI-automated report generation functions, leading to cumbersome user operations.

[0034] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0035] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0036] Figure 1 This is a schematic diagram of the structure of a map visualization-based science and technology theme trajectory analysis system provided in an embodiment of this application;

[0037] Figure 2 This is a schematic diagram of the architecture of a map-visualized science and technology intelligence analysis system provided according to an embodiment of this application;

[0038] Figure 3 This is a flowchart illustrating the high-performance tile service provided according to embodiments of this application.

[0039] Figure 4 This is a schematic diagram illustrating the implementation of regional scientific research density analysis according to an embodiment of this application;

[0040] Figure 5 This is a flowchart illustrating the model context protocol data acquisition process according to an embodiment of this application.

[0041] Figure 6 This is a flowchart illustrating the AI-driven report generation process provided in the embodiments of this application.

[0042] Figure 7 This is a flowchart of user interaction operations provided according to an embodiment of this application;

[0043] Figure 8 This is a flowchart illustrating a method for analyzing the trajectory of a science and technology theme based on map visualization, according to an embodiment of this application.

[0044] Figure 9 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application.

[0045] Figure label:

[0046] 10-Science and technology-themed trajectory analysis system based on map visualization; 100-Map visualization module, 200-Multi-source data and processing module, 300-AI analysis module, 400-User interaction interface module; 901-Memory, 902-Processor, 903-Communication interface. Detailed Implementation

[0047] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0048] The following description, with reference to the accompanying drawings, describes a map-visualized science and technology theme trajectory analysis system and method according to embodiments of this application. Addressing the issues mentioned in the background art, such as weak geospatial visualization capabilities leading to an inability to support large-scale real-time rendering and interactive regional analysis, fragmented data retrieval and analysis, and a lack of AI-automated report generation functionality, resulting in cumbersome user operations, this application provides a map-visualized science and technology theme trajectory analysis method. This method generates map tiles containing location data to achieve real-time rendering of large-scale research institutions. Combined with semantic acquisition of multi-source papers and patent data, it identifies regional institutions and calculates research density. Based on user selection, it generates and displays dynamic interactive professional analysis reports, thereby achieving efficient geospatial visualization, real-time multi-source data retrieval, and intelligent analysis report generation, providing more intuitive and comprehensive data support for science and technology innovation decision-making. This solves the problems of weak geospatial visualization capabilities in related technologies, leading to an inability to support large-scale real-time rendering and interactive regional analysis, fragmented data retrieval and analysis, and a lack of AI-automated report generation functionality, resulting in cumbersome user operations.

[0049] Specifically, Figure 1 This is a schematic diagram of the structure of a map visualization-based technology-themed trajectory analysis system provided in an embodiment of this application.

[0050] like Figure 1 As shown, the map visualization-based technology-themed trajectory analysis system 10 includes:

[0051] The map visualization module 100 is used to collect and process the geographical location information of global research institutions, and based on the geographical location information, generate map tiles containing point information to render and interact with the geospatial distribution of research institutions.

[0052] It is understood that the map tiles in this application embodiment can be square grid images that divide the Earth's surface into square grids according to certain rules. Each tile contains the geographic information and location of institutions in the corresponding area. A complete map can be formed by stitching together the tiles.

[0053] In actual implementation, the embodiments of this application can collect and process the geographical location information of global scientific research institutions, including but not limited to attributes such as latitude and longitude, name, and type. Based on the geographical data of the institutions, map tiles containing location information are generated, and caching optimization is implemented to achieve efficient rendering and interaction of the geographical spatial distribution of scientific research institutions.

[0054] This application embodiment can achieve efficient rendering and smooth interaction of the geographical distribution of scientific research institutions through map tile technology, allowing users to intuitively grasp the spatial layout of global scientific research institutions and laying the foundation for regional innovation analysis.

[0055] Optionally, in one embodiment of this application, the map visualization module 100 includes: a high-performance tile service submodule, used to draw map tiles containing institutional points, execute a three-level caching strategy including memory caching, disk caching, and on-demand generation, calculate the corresponding geographic boundary based on the requested tile coordinates, query institutional point data within the boundary, determine the rendering strategy of the points according to the zoom level, draw the points and labels, and save the generated tile images to the corresponding cache level; and an adaptive point rendering submodule, used to dynamically adjust the point size and label display strategy according to the map zoom level, and only display points at a preset low zoom level. The system includes features such as displaying location and institution name labels simultaneously at a preset high zoom level, adjusting the aggregation radius when the location density within the target area exceeds a preset threshold, optimizing clustering granularity and rendering locations within the current viewport through control function parameters; and a regional scientific research density analysis submodule, which is used to drag and draw rectangular selection areas on the map, obtain the map geographic boundaries of the selection areas, convert the map geographic boundaries into tile boundaries, traverse the location data in the visible tiles to filter out institutions within the selection areas, construct a JSON object describing the geometry of the selection areas, pass the selection area JSON object and the list of institutions to the AI ​​analysis module, and generate a regional scientific research density analysis report.

[0056] It is understood that in this embodiment, the zoom level can be the scale level of the map display, used to control the level of detail of the map. At a low zoom level, the map displays a large area but with few details, while at a high zoom level, the map displays a small area but with rich details. The preset zoom level can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here. The aggregation radius can be the radius parameter that merges neighboring points into an aggregation point when the point density exceeds a preset threshold. The preset threshold can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here. The viewport can be the area visible to the user in the current map interface.

[0057] In actual implementation, the high-performance tile service submodule in this embodiment can use Canvas technology to draw map tiles containing institutional locations, and implement a three-level caching strategy including memory caching, disk caching, and on-demand generation. The generated tile images are saved to the memory cache according to priority. If the memory cache is full, the earlier tile data is transferred to the disk cache. In subsequent requests, the data is retrieved from the memory cache first, then from the disk cache, and finally generated on demand. The corresponding geographic boundary is calculated based on the requested tile coordinates (x, y, z), and the institutional location data within the boundary is queried. The rendering strategy of the points is determined according to the scaling level, including but not limited to point size, whether to display labels, etc. The points and labels are drawn using the Canvas API, and the generated tile images are saved to the corresponding cache level.

[0058] The adaptive point rendering submodule can automatically adjust the point size and label display strategy according to the current map zoom level; it displays only points at the preset low zoom level and displays both points and organization name labels at the preset high zoom level; at the same time, to optimize rendering performance, the system implements a point aggregation function. When the point density in a specific area is too high, the system will automatically adjust the aggregation radius and control the aggregation granularity through relevant parameters; in addition, it also implements visibility optimization, rendering only point data within the viewport's visible area, effectively reducing the consumption of computing resources.

[0059] The regional scientific research density analysis submodule can respond to users dragging and drawing rectangular selection areas on the map to obtain the map geographic boundaries of the selection areas, call relevant conversion functions to convert the map geographic boundaries into tile boundaries, traverse the point data in the visible tiles to filter out the institutions within the selection area, construct a JSON object to describe the geometry of the selection area, and pass the selection area JSON object and the list of institutions to the AI ​​analysis module to generate a regional scientific research density analysis report.

[0060] The regional analysis indicators supported in the generated regional research density analysis report may include: an institution density heatmap, used to display the spatial distribution density of research institutions within the region; research theme distribution, used to analyze the main research fields and technological directions within the region; cooperation network strength, used to assess the closeness of cooperation among institutions within the region; innovation vitality index, used to comprehensively consider factors such as patent applications, paper publications, citation impact, and cooperation intensity; industry-academia-research collaboration, used to analyze the interaction between industry, academia, and research institutions; and regional innovation resource concentration, used to assess the spatial agglomeration of innovation resources. Through these indicators, users can intuitively understand the regional research and innovation situation and the status of industry-academia-research collaboration.

[0061] This application embodiment can draw map tiles of institutional locations, implement a three-level caching strategy, dynamically adjust the point rendering and label display strategy in combination with the zoom level, and support map selection operations and generate regional analysis reports, effectively improving the efficiency and interactivity of rendering the geospatial distribution of scientific research institutions, making it easier for users to quickly grasp the distribution of institutions in different areas, and achieving accurate geospatial range selection and institutional identification.

[0062] The multi-source data acquisition and processing module 200 is used to semantically acquire paper data and / or patent data from at least one target database.

[0063] It is understood that semantic acquisition in the embodiments of this application can be the parsing of natural language queries into structured retrieval instructions.

[0064] In practical implementation, this application embodiment can, for example, integrate patent search and paper search functions using the Floating Panel component, respectively calling the retrieval APIs in the ElasticSearch and ElasticSearch_paper modules, and employing an intelligent data acquisition engine based on MCP (Model Context Protocol) technology to achieve accurate data extraction through semantic connections. Tests show that compared to traditional query methods, the system significantly improves query relevance when processing large-scale patent data and significantly improves performance when processing paper data.

[0065] This application embodiment can accurately capture multi-source papers and patent data through semantic acquisition technology, breaking the limitations of keyword retrieval and providing more relevant data support for scientific and technological topic analysis.

[0066] Optionally, in one embodiment of this application, the multi-source data acquisition and processing module 200 includes: an intelligent data acquisition engine, used to construct a semantic query context based on user query requirements, analyze the context based on a preset engine to determine the best query strategy and parameters, send an optimized query request, receive and process query results to extract key information, intelligently process the key information and fuse the processed data, and return the processed data to the user interface module; and a heterogeneous data standardization processing submodule, used to perform unified format conversion and standardization processing on multi-source heterogeneous data.

[0067] It is understood that the preset engine in the embodiments of this application can be an intelligent data acquisition engine based on MCP. The preset engine can be set by those skilled in the art according to the actual situation, and no specific restrictions are made here. Multi-source heterogeneous data can be data from different databases with different formats and structures, such as field naming in different paper databases, format differences in patent data, etc.

[0068] For example, in this embodiment of the application, the intelligent data acquisition engine uses MCP technology to achieve efficient acquisition and processing of multi-source heterogeneous data. Based on the user's query requirements, it constructs a semantic query context; analyzes the context based on the MCP engine to determine the best query strategy and parameters; sends an optimized query request to ElasticSearch; receives and processes the query results to extract key information; intelligently processes and merges the key information into the processed data; and returns the processed data to the user interface module.

[0069] The ElasticSearch component encapsulates complex query logic, supporting multi-field composite weighted queries, multiple filtering conditions, and custom sorting. Furthermore, search strategies have been optimized for paper and patent searches respectively. For example, in paper searches, the title is weighted at 3 and the abstract at 2; in patent searches, the title is weighted at 5, the abstract at 3, and the patent classification at 2. This differentiated weighting strategy effectively improves the relevance of search results.

[0070] The heterogeneous data standardization processing submodule can perform unified format conversion and standardization processing on multi-source heterogeneous data, such as converting patent data into CSV standardized fields and extracting DOI / ISSN standard numbers from paper data.

[0071] The embodiments of this application can construct semantic query context, determine the best query strategy, process query results, and perform data fusion and standardization, thereby improving the accuracy and efficiency of obtaining paper and patent data, realizing the effective integration of multi-source heterogeneous data, ensuring the reliability and consistency of subsequent analysis, and providing a high-quality data foundation for subsequent analysis.

[0072] The AI ​​analysis module 300 is used to identify institutions within a selected area based on paper data and / or patent data, calculate research density, and generate professional analysis reports containing data insights based on the user's selected analysis objects and objectives.

[0073] It is understood that in the embodiments of this application, scientific research density can be the ratio of the number of scientific research institutions in a specific area to the area of ​​the area, or the intensity of scientific research activities calculated in combination with the output of papers and patents; data insights can be hidden patterns, trends or key conclusions mined from data.

[0074] For example, this application embodiment can use the Chat component to implement AI-driven report generation functionality, triggered by the patent paper analysis function and the institution and author analysis function in the Floating Panel component. Based on the analysis object type (institution, patent, paper, etc.) and analysis target, optimized prompts are dynamically constructed to improve the professionalism and accuracy of AI-generated content; relevant data is acquired in real time, integrating geospatial information, paper data, and patent data; and automatic generation of various professional analysis reports, such as paper analysis, institution analysis, and patent analysis, is supported. Tests show that the professionalism and accuracy scores of the generated analysis reports reach a high level.

[0075] The embodiments of this application can identify and calculate the density of regional research institutions, and generate reports with in-depth insights by combining AI analysis, providing users with intuitive regional innovation assessment basis and decision support.

[0076] Optionally, in one embodiment of this application, the AI ​​analysis module 300 is further used to analyze the evolution of research topics and technical routes of institutions, analyze patent value and technology development trends and competitive intelligence, assess research frontiers and influence and cooperation networks, assess the cooperation density and innovation ecosystem among institutions, assess the scientific research and innovation vitality, distribution and evolution of target geographical regions, compare the research focus and innovation capabilities of different institutions in multiple dimensions, assess the academic influence of authors, changes in research fields, cooperation networks and results transformation, analyze inventors' technical expertise, innovation capabilities and patent portfolio value, and assess corporate patent strategies, technology layout and competitive advantages.

[0077] It is understood that, in the embodiments of this application, the evolution of research topics can be the process of changes in the core research direction of an institution over time; the innovation ecosystem can be the interdependent innovation system formed between institutions through cooperation, resource sharing, etc.; and the value of a patent portfolio can be the overall commercial value and technological barrier generated by a group of patents working together.

[0078] For example, the embodiments of the present application can analyze the research topic evolution and technical route of an institution to complete the analysis of the institution's topic trajectory; analyze patent value assessment, technology development trend and competitive intelligence to complete patent analysis; analyze research frontiers, influence assessment and cooperation network to complete paper analysis; evaluate the cooperation density and innovation ecosystem between institutions to complete the industry-university-research cooperation analysis; evaluate the scientific research innovation vitality, distribution and evolution in a specific geographical area, etc. to complete the regional analysis; conduct multi-dimensional comparison of the research focuses and innovation capabilities of different institutions to complete the institution comparison analysis, including two categories: patent institution comparison and paper institution comparison; evaluate the academic influence, research field changes, cooperation network and achievement transformation of authors to complete the paper author analysis; analyze the technical expertise, innovation ability and patent portfolio value of inventors to complete the patent inventor analysis; evaluate the patent strategy, technology layout and competitive advantage of an enterprise to complete the patent applicant analysis.

[0079] The embodiments of the present application can further conduct multi-dimensional analysis on institution research topics, patent value, cooperation network, regional innovation vitality, author influence, enterprise patent strategy, etc., expand the depth and breadth of scientific and technological intelligence analysis, provide in-depth scientific and technological intelligence insights, and provide rich basis for users to comprehensively evaluate the innovation situation and formulate strategic decisions.

[0080] Optionally, in an embodiment of the present application, the AI analysis module 300 is further configured to determine the user's selected analysis object and analysis type, construct a prompt word containing key entity information, retrieve relevant data from at least one target database, fuse the retrieval results to construct an enhanced context, and generate at least one structured analysis report.

[0081] It can be understood that in the embodiments of the present application, the key entity information can be core elements related to the analysis object, such as institution name, technical keywords, time range, etc.; the enhanced context can be a richer and more comprehensive analysis background information formed by fusing multi-source retrieval data, which improves the depth of the report.

[0082] In the actual execution process, the embodiments of the present application can determine the user's selected analysis object and analysis type, construct a prompt word containing key entity information, retrieve relevant data from databases such as ElasticSearch; fuse the retrieval results to construct an enhanced context; generate a structured analysis report including parts such as an executive summary, data analysis, trend insights, competitive situation and development suggestions.

[0083] Among them, the executive summary is used to outline the core features and main findings of the analysis object; data analysis is based on the retrieved data for quantitative analysis; trend insights are used to identify development trends and turning points; competitive situation is used to evaluate relative advantages and challenges; regional characteristics are used to analyze the innovation characteristics of geographical regions; cooperation network is used to analyze the cooperation relationship between entities; development suggestions: provide data-based strategic suggestions.

[0084] The embodiments of this application can determine the user's analysis object and type, construct prompt words, retrieve and integrate data, and generate a structured report, thereby achieving the accuracy and structure of the analysis report, improving the relevance and practicality of the generated report, and meeting the diverse analysis needs of users.

[0085] Optionally, in one embodiment of this application, it further includes: an industry-academia-research collaboration analysis module, used to obtain institutional cooperation data from a preset database, construct an inter-institutional cooperation network based on the number of jointly published papers and patents, calculate key indicators of the network, identify cooperation patterns, display the cooperation network through a force-directed graph, and generate an industry-academia-research collaboration analysis report.

[0086] It is understood that the force-directed graph in the embodiments of this application can be a visual graph that simulates physical forces to show the connection relationship of nodes in the network.

[0087] For example, embodiments of this application can obtain institutional collaboration data from the ElasticSearch database; construct a network of collaborative relationships between institutions based on the number of jointly published papers and patents; calculate key indicators of the network, including overall network density, centrality distribution, community structure, and structural holes; identify collaboration models such as industry-academia collaboration, industry-research collaboration, academic-research collaboration, and industry-academia-research tripartite collaboration; display the collaboration network through a force-directed graph, where node size represents the institution's influence and edge width represents the collaboration strength; and generate an industry-academia-research collaborative analysis report, including an overview of the collaboration, core institutions, advantageous areas, and development suggestions.

[0088] The embodiments of this application can clearly present the cooperation network and model between industry, academia and research institutions through quantitative analysis and visualization, help users grasp the collaborative distribution of innovation resources, and provide a basis for decision-making to promote cross-institutional cooperation and optimize the innovation ecosystem.

[0089] The user interface module 400 is used to dynamically adjust the displayed content based on user operations, in order to perform point clustering, adaptive scaling, and intelligent label display.

[0090] It is understood that in the embodiments of this application, point clustering can be used to merge the locations of institutions that are close to each other on the map into a single aggregation point to avoid visual confusion caused by dense points; scaling adaptation can be used to automatically adjust the size of the points, clustering status and information display detail according to the map scaling ratio to ensure clear visual effects.

[0091] For example, embodiments of this application can listen to user map operation events, including but not limited to zooming, panning, clicking, and selecting; automatically adjust the size of points and label display strategies according to the current map zoom level; display only points at low zoom levels, and display both points and organization name labels at high zoom levels, while intelligent label display avoids overlap and prioritizes the display of important organization information.

[0092] Specifically, the embodiments of this application can respond to user mouse clicks to display institution details, support drag-and-drop selection of areas to trigger analysis; provide multi-condition input boxes, allowing users to combine and filter information, such as searching by institution name, research field, geographical region, time range, and other combined conditions; load AI analysis results in real time through a floating analysis panel, which users can drag or close, and is an independent window that can be freely moved and scaled on the map interface to display analysis results without obscuring the main map, making it convenient for users to flexibly switch between viewing the map and the report.

[0093] This application embodiment supports institution selection and region selection, provides multi-dimensional search functions, displays analysis results and reports, and provides an intuitive, flexible, and responsive visual interactive experience, enabling users to easily obtain the information they need, ensuring that the interface is clear and easy to read under different operations, improving the user interaction experience, and facilitating efficient browsing of the distribution of research institutions.

[0094] Specifically, it can be combined with Figures 2 to 7 As shown, the working principle of the map visualization-based science and technology theme trajectory analysis system in this application is explained in detail with a specific embodiment.

[0095] Figure 2 This is a schematic diagram of the architecture of a map-visualized science and technology intelligence analysis system provided according to an embodiment of this application.

[0096] like Figure 2 As shown in the example embodiment of this application, the map-visualized science and technology intelligence analysis system adopts a front-end and back-end separation architecture. The front-end implements a responsive user interface based on the Svelte framework, mainly including three core components: map, display box, and trajectory analysis. The map component is responsible for map rendering and interaction, the display box component provides buttons for search and analysis methods and displays relevant results, and the trajectory analysis component is responsible for AI-driven report generation. The back-end provides data processing, interface logic, and AI inference services.

[0097] Figure 3 This is a flowchart of a high-performance tile service provided according to an embodiment of this application.

[0098] like Figure 3 As shown, this application example may include the following steps:

[0099] Step S301: Tile coordinates.

[0100] In this embodiment of the application, Canvas technology can be used to draw map tiles containing the locations of institutions, and the tile coordinates (x, y, z) can be obtained.

[0101] Step S302: Determine the rendering strategy based on the scaling level.

[0102] In this embodiment, the size of the points and the label display strategy can be dynamically adjusted according to the map zoom level. At a low zoom level, only the points are displayed and no label information is displayed. At a high zoom level, both the points and the organization name labels are displayed.

[0103] Step S303: Caching.

[0104] In this embodiment of the application, the generated tile images can be saved to the memory cache according to priority.

[0105] Step S304: Calculate the boundary.

[0106] In this embodiment of the application, the corresponding geographic boundary can be calculated based on the requested tile coordinates (x,y,z).

[0107] Step S305: Query the point data within the boundary.

[0108] In this embodiment of the application, the location data of the institutions within the boundary can be queried.

[0109] Step S306: Draw points and labels.

[0110] In this embodiment of the application, the Canvas API can be used to draw points and labels.

[0111] Step S307: Add to cache.

[0112] In this embodiment of the application, the generated tile image can be saved to a cache.

[0113] Figure 4 This is a schematic diagram illustrating the implementation of regional scientific research density analysis according to an embodiment of this application.

[0114] like Figure 4 As shown, this application example may include the following steps:

[0115] Step S401: Select the area.

[0116] In this embodiment, the ability to identify rectangular selection areas drawn by the user on a map can be recognized.

[0117] Step S402: Obtain the latitude and longitude coordinates of the region.

[0118] In this embodiment, the map geographic boundaries of the selected area can be obtained.

[0119] Step S403: Invoke the tile service.

[0120] In this embodiment, a function can be called to convert the map geographic boundary into a tile boundary, traverse the point data in the visible tiles, and filter out the institutions within the selected area.

[0121] Step S404: Analyze the regional structure.

[0122] In this embodiment, a JSON object describing the geometry of the selected area can be constructed, and the selected area JSON object and the list of institutions can be passed to the AI ​​analysis module.

[0123] Figure 5 This is a flowchart of the model context protocol data acquisition process according to an embodiment of this application.

[0124] like Figure 5 As shown, this application example may include the following steps:

[0125] Step S501: Query context construction.

[0126] In this embodiment, a semantic query context can be constructed based on the user's query requirements.

[0127] Step S502: Determine the query strategy.

[0128] In this embodiment, the MCP engine can be used to analyze the context and determine the best query strategy and parameters.

[0129] Step S503: Send a query request.

[0130] In this embodiment of the application, an optimized query request can be sent to ElasticSearch.

[0131] Step S504: Processing result.

[0132] In this embodiment, the query results can be received and processed, key information can be extracted, and the acquired data can be intelligently processed and fused to improve the relevance and accuracy of the search results.

[0133] Step S505: Return data to the user.

[0134] In this embodiment, the processed data can be returned to the user interface or analysis module.

[0135] Figure 6 This is a flowchart of an AI-driven report generation process provided according to an embodiment of this application.

[0136] like Figure 6 As shown, this application example may include the following steps:

[0137] Step S601: Trajectory Analysis.

[0138] In this embodiment, trajectory analysis can be performed to identify the user-selected analysis object and analysis type.

[0139] Step S602: MCP retrieves database data.

[0140] In this embodiment, relevant data can be retrieved from the ElasticSearch database.

[0141] Step S603: Analyze the data based on the prompt words.

[0142] In this application embodiment, prompts containing key entity information can be constructed, search results can be integrated, and an enhanced context can be built.

[0143] Step S604: Generate a report from the large AI model.

[0144] In this embodiment, a large language model can be invoked to generate a structured analysis report, which includes an execution summary, data analysis, trend insights, competitive landscape, and development recommendations.

[0145] Step S605: Inspection report, generate complete page.

[0146] The embodiments of this application can process the generated report, including structure verification, data consistency check and format optimization.

[0147] Figure 7 This is a flowchart of user interaction operations provided according to an embodiment of this application.

[0148] like Figure 7 As shown, this application example may include the following steps:

[0149] Step S701: Mechanism trajectory analysis.

[0150] In particular, the embodiments of this application can analyze the evolution of research topics and technical routes of the institution.

[0151] Step S702: Click on the organization analysis on the map.

[0152] In particular, the embodiments of this application can provide an intuitive interactive page that identifies the organization selected by the user.

[0153] Step S703: Regional structure analysis.

[0154] The embodiments of this application can assess the scientific and technological innovation vitality, distribution, and evolution of a specific geographical region.

[0155] Step S704: Analyze the mechanism within the selected area.

[0156] In this application embodiment, an intuitive area selection tool can be provided to identify the location of institutions within the user-selected area, perform an area institution analysis method, convert the selected area information into JSON format, and pass it to the AI ​​analysis module.

[0157] Step S705: Automatically retrieve database data.

[0158] In this application embodiment, relevant data can be obtained and geospatial information, paper data and patent data can be integrated.

[0159] Step S706: Generate a report from the large AI model.

[0160] In this embodiment, a large language model can be invoked to generate a structured analysis report, which includes an execution summary, data analysis, trend insights, competitive landscape, and development recommendations.

[0161] Step S707: Inspection report, generate complete page.

[0162] The embodiments of this application can process the generated report, including structure verification, data consistency check and format optimization.

[0163] The science and technology theme trajectory analysis system based on map visualization proposed in this application can generate map tiles containing points to achieve real-time rendering of large-scale research institutions. Combined with semantic acquisition of multi-source papers and patent data, it can identify regional institutions and calculate research density. Based on user selections, it can generate and display dynamic interactive professional analysis reports, thereby achieving efficient geospatial visualization, real-time retrieval of multi-source data, and intelligent analysis report generation, providing more intuitive and comprehensive data support for science and technology innovation decision-making. This solves the problems of weak geospatial visualization capabilities in related technologies, which prevent support for large-scale real-time rendering and interactive regional analysis; the disconnect between data retrieval and analysis; and the lack of AI-automated report generation functions, leading to cumbersome user operations.

[0164] Next, referring to the accompanying drawings, a method for analyzing the trajectory of science and technology topics based on map visualization, according to an embodiment of this application, is described.

[0165] Figure 8 This is a flowchart illustrating the technology-themed trajectory analysis method based on map visualization, according to an embodiment of this application.

[0166] like Figure 8As shown, this map visualization-based method for analyzing the trajectory of science and technology themes includes the following steps:

[0167] In step S801, the geographical location information of global research institutions is collected and processed, and based on the geographical location information, map tiles containing point location information are generated to render and interact with the geographical spatial distribution of research institutions.

[0168] In step S802, semantically retrieve paper data and / or patent data from at least one target database.

[0169] In step S803, based on paper data and / or patent data, institutions within the selected area are identified and research density is calculated. A professional analysis report containing data insights is generated according to the analysis object and target selected by the user.

[0170] In step S804, the displayed content is dynamically adjusted according to user operations to perform point clustering, adaptive scaling, and intelligent label display.

[0171] Optionally, in one embodiment of this application, geographic location information of global research institutions is collected and processed, and map tiles containing location information are generated based on the geographic location information to render and interact with the geographic spatial distribution of research institutions. This includes: drawing map tiles containing institution locations; implementing a three-level caching strategy including memory caching, disk caching, and on-demand generation; calculating the corresponding geographic boundary based on the requested tile coordinates; querying institution location data within the boundary; determining the rendering strategy for the locations based on the scaling level; drawing the locations and labels; and saving the generated tile images to the corresponding caching level; dynamically adjusting the size of the locations based on the map scaling level. The system includes a label display strategy, which displays only points at a preset low zoom level and simultaneously displays point and institution name labels at a preset high zoom level. It also adjusts the aggregation radius when the point density within the target area exceeds a preset threshold, optimizes clustering granularity and renders points within the current viewport by controlling function parameters. The system allows users to drag and draw rectangular selection areas on the map, obtain the map's geographic boundaries, convert these boundaries to tile boundaries, iterate through the point data in visible tiles to filter out institutions within the selection area, construct a JSON object describing the geometry of the selection area, and pass the selection area JSON object and the list of institutions to the AI ​​analysis module to generate a regional research density analysis report.

[0172] Optionally, in one embodiment of this application, semantically acquiring paper data and / or patent data from at least one target database includes: constructing a semantic query context based on user query requirements; analyzing the context based on a preset engine to determine the optimal query strategy and parameters; sending an optimized query request; receiving and processing query results to extract key information; intelligently processing and fusing the processed data with the key information; and returning the processed data to the user interface module; and performing unified format conversion and standardization processing on multi-source heterogeneous data.

[0173] Optionally, in one embodiment of this application, after identifying institutions within a region and calculating research density by selecting a region based on paper data and / or patent data, and generating a professional analysis report containing data insights according to the user-selected analysis object and target, the analysis further includes: analyzing the evolution of research topics and technical routes of institutions, analyzing patent value and technological development trends and competitive intelligence, assessing research frontiers and influence and cooperation networks, assessing the cooperation density and innovation ecosystem among institutions, assessing the scientific research and innovation vitality, distribution and evolution of the target geographical region, comparing the research focus and innovation capabilities of different institutions from multiple dimensions, assessing the academic influence of authors, changes in research fields, cooperation networks and results transformation, analyzing the inventors' technical expertise, innovation capabilities and patent portfolio value, and assessing the enterprise's patent strategy, technology layout and competitive advantages.

[0174] Optionally, in one embodiment of this application, after identifying institutions within a region and calculating research density by selecting a region based on paper data and / or patent data, and generating a professional analysis report containing data insights according to the analysis object and target selected by the user, the method further includes: determining the analysis object and analysis type selected by the user, constructing prompt words containing key entity information, retrieving relevant data from at least one target database, fusing the search results to construct an enhanced context, and generating at least one structured analysis report.

[0175] Optionally, in one embodiment of this application, the method further includes: obtaining institutional cooperation data from a preset database, constructing an inter-institutional cooperation network based on the number of jointly published papers and patents, calculating key indicators of the network, identifying cooperation patterns, displaying the cooperation network through a force-directed graph, and generating an industry-academia-research collaborative analysis report.

[0176] It should be noted that the foregoing explanation of the embodiment of the map visualization-based science and technology theme trajectory analysis system also applies to the map visualization-based science and technology theme trajectory analysis method of this embodiment, and will not be repeated here.

[0177] The technology-themed trajectory analysis method based on map visualization proposed in this application can generate map tiles containing points to achieve real-time rendering of large-scale research institutions. Combined with semantic acquisition of multi-source papers and patent data, it enables regional institution identification and calculation of research density. Based on user selection, it generates and displays dynamic interactive professional analysis reports, thereby achieving efficient geospatial visualization, real-time retrieval of multi-source data, and intelligent analysis report generation, providing more intuitive and comprehensive data support for technological innovation decision-making. This solves the problems of weak geospatial visualization capabilities in related technologies, which prevent support for large-scale real-time rendering and interactive regional analysis; the disconnect between data retrieval and analysis; and the lack of AI-automated report generation functions, leading to cumbersome user operations.

[0178] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0179] The memory 901, the processor 902, and the computer program stored on the memory 901 and capable of running on the processor 902.

[0180] When the processor 902 executes the program, it implements the map visualization-based science and technology theme trajectory analysis method provided in the above embodiments.

[0181] Furthermore, electronic devices also include:

[0182] Communication interface 903 is used for communication between memory 901 and processor 902.

[0183] The memory 901 is used to store computer programs that can run on the processor 902.

[0184] The memory 901 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0185] If the memory 901, processor 902, and communication interface 903 are implemented independently, then the communication interface 903, memory 901, and processor 902 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 9The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0186] Optionally, in a specific implementation, if the memory 901, processor 902, and communication interface 903 are integrated on a single chip, then the memory 901, processor 902, and communication interface 903 can communicate with each other through an internal interface.

[0187] The processor 902 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0188] This embodiment also provides a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for analyzing the trajectory of science and technology topics based on map visualization.

[0189] This application also provides a computer program product storing a computer program that, when executed by a processor, implements the above-described map visualization-based science and technology theme trajectory analysis method.

[0190] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0191] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0192] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0193] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0194] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0195] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0196] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0197] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A technology-themed trajectory analysis system based on map visualization, characterized in that, include: The map visualization module is used to collect and process the geographical location information of global research institutions, and based on the geographical location information, generate map tiles containing point location information to render and interact with the geographical spatial distribution of research institutions. A multi-source data acquisition and processing module is used to semantically acquire paper data and / or patent data from at least one target database. The AI ​​analysis module is used to identify institutions within a selected area and calculate research density based on the paper data and / or patent data, and generate a professional analysis report containing data insights according to the analysis object and target selected by the user. The user interface module is used to dynamically adjust the displayed content based on user operations, in order to perform point clustering, adaptive scaling, and intelligent label display.

2. The system according to claim 1, characterized in that, The map visualization module includes: The high-performance tile service submodule is used to draw map tiles containing institutional points, execute a three-level caching strategy including memory caching, disk caching and on-demand generation, calculate the corresponding geographic boundary based on the requested tile coordinates, query institutional point data within the boundary, determine the rendering strategy of the points according to the scaling level, draw the points and labels, and save the generated tile images to the corresponding cache level. The adaptive point rendering submodule is used to dynamically adjust the point size and label display strategy according to the map zoom level, display only points at the preset low zoom level, display both points and organization name labels at the preset high zoom level, adjust the aggregation radius when the point density in the target area is greater than a preset threshold, and optimize the clustering granularity and render points in the current viewport by controlling function parameters. The regional scientific research density analysis submodule is used to drag and draw a rectangular selection area on the map, obtain the map geographical boundary of the selection area, convert the map geographical boundary into a tile boundary, traverse the point data in the visible tiles to filter out the institutions within the selection area, construct a JSON object to describe the geometry of the selection area, pass the selection area JSON object and the list of institutions to the AI ​​analysis module, and generate a regional scientific research density analysis report.

3. The system according to claim 1, characterized in that, The multi-source data acquisition and processing module includes: The intelligent data acquisition engine is used to construct a semantic query context based on user query requirements, analyze the context based on a preset engine to determine the best query strategy and parameters, send an optimized query request, receive and process query results to extract key information, intelligently process and fuse the key information into processed data, and return the processed data to the user interface module. The heterogeneous data standardization processing submodule is used to perform unified format conversion and standardization processing on the multi-source heterogeneous data.

4. The system according to claim 1, characterized in that, The AI ​​analysis module is further used to analyze the evolution of research topics and technical routes of institutions, analyze patent value, technology development trends and competitive intelligence, assess research frontiers and influence, and cooperation networks, evaluate the cooperation density and innovation ecosystem among institutions, assess the scientific research and innovation vitality, distribution and evolution of target geographical regions, compare the research focus and innovation capabilities of different institutions from multiple dimensions, evaluate the academic influence of authors, changes in research fields, cooperation networks and results transformation, analyze inventors' technical expertise, innovation capabilities and patent portfolio value, and evaluate corporate patent strategies, technology layout and competitive advantages.

5. The system according to claim 4, characterized in that, The AI ​​analysis module is also used to determine the analysis object and analysis type selected by the user, construct prompt words containing key entity information, retrieve relevant data from the at least one target database, fuse the search results to construct an enhanced context, and generate at least one structured analysis report.

6. The system according to claim 1, characterized in that, Also includes: The industry-academia-research collaboration analysis module is used to obtain institutional cooperation data from a preset database, construct a network of cooperation relationships between institutions based on the number of jointly published papers and patents, calculate key indicators of the network, identify cooperation patterns, display the cooperation network through a force-directed graph, and generate an industry-academia-research collaboration analysis report.

7. A method for analyzing the trajectory of science and technology themes based on map visualization, characterized in that, include: Collect and process the geographic location information of global research institutions, and generate map tiles containing point location information based on the geographic location information to render and interact with the geographic spatial distribution of research institutions. Semantically extract paper data and / or patent data from at least one target database; Based on the paper data and / or patent data, the system identifies institutions within a selected area and calculates research density, and generates a professional analysis report containing data insights based on the user's selected analysis object and objective. The displayed content is dynamically adjusted based on user actions to perform point clustering, adaptive scaling, and intelligent label display.

8. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, the processor executing the program to implement the map visualization-based science and technology theme trajectory analysis method as described in claim 7.

9. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the map visualization-based technology-themed trajectory analysis method as described in claim 7.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the map visualization-based technology theme trajectory analysis method as described in claim 7.

Images