Science and technology project multi-dimensional information model construction system and method

Abstract

The invention provides a science and technology project multi-dimensional information model construction system and method, and belongs to the technical field of information, the science and technology project multi-dimensional information model construction system and method comprise a data collection module used for collecting various data related to science and technology projects; the data processing module is used for cleaning and sorting the collected data and classifying the data into different dimensions according to a preset standard; the model construction module is used for constructing a multi-dimensional information model of the science and technology project based on the classified data; and the analysis and display module is used for displaying a model result through a graphical interface or other forms, and the model can provide a more accurate prediction result and trend analysis by collecting and analyzing a large amount of historical data so as to help a decision maker to make a more scientific decision based on the data.

Description

Technical Field

[0001] The present invention belongs to the field of information technology, and specifically relates to a system and method for constructing a multi-dimensional information model of a scientific and technological project. Background Art

[0002] With technological advancements and intensified market competition, the success of scientific and technological projects is receiving increasing attention. To ensure smooth project implementation and achieve the desired results, comprehensive assessments of all aspects of a project are necessary. Traditional evaluation methods often rely on experience and intuition, lacking systematicity and scientificity, making it difficult to accurately predict a project's future development.

[0003] Most of the project management tools currently available on the market focus on project progress tracking and resource allocation, but are insufficient in project evaluation, especially in the integration and analysis of multi-dimensional information. These issues lead to the following major flaws:

[0004] The data silo phenomenon is serious: data from different sources often cannot be effectively integrated, resulting in information fragmentation and hindering comprehensive analysis.

[0005] Single analytical approach: Existing evaluation tools often focus on a single dimension, such as financial status or technological advancement, and fail to comprehensively consider the pros and cons of a project from multiple perspectives.

[0006] Lack of predictive capabilities: Most tools are unable to predict future development trends of projects based on historical data and cannot provide forward-looking guidance to decision makers.

[0007] Insufficient security: Due to the lack of effective data protection measures, project data is vulnerable to unauthorized access or tampering, increasing the risk of data leakage. Summary of the Invention

[0008] The present invention aims to provide a system and method for constructing a multidimensional information model for scientific and technological projects. This system aims to address the existing problem in scientific and technological project management, where data from different sources (such as internal R&D data, market research data, and financial data) often exists in isolation and lacks an effective integration mechanism. This prevents the data from forming a complete knowledge chain, making it difficult for decision makers to conduct a comprehensive assessment of the project from a holistic perspective.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A system for constructing a multi-dimensional information model of scientific and technological projects, comprising:

[0011] Data collection module, used to collect various data related to scientific and technological projects;

[0012] The data processing module is used to clean and organize the collected data and classify the data into different dimensions according to preset standards;

[0013] Model building module, used to build a multi-dimensional information model of scientific and technological projects based on classified data;

[0014] The analysis and display module is used to display model results through a graphical interface or other forms.

[0015] As a preferred solution of the present invention, the data collection module can also automatically capture relevant information from an external database.

[0016] As a preferred solution of the present invention, the data processing module further includes a data standardization processing unit for converting data from different sources into a unified format.

[0017] As a preferred solution of the present invention, the model building module further includes a weight assignment unit for assigning corresponding weight values ​​according to the importance of different dimensions.

[0018] As a preferred solution of the present invention, the analysis and display module also includes an interactive analysis tool, allowing users to dynamically adjust parameters and instantly view result changes.

[0019] As a preferred solution of the present invention, the system further includes a feedback mechanism, which allows users to make modification suggestions based on the display results and feed them back to the data processing module for updating.

[0020] As a preferred solution of the present invention, the feedback mechanism also supports users to add new evaluation dimensions and integrate them into the existing model.

[0021] As a preferred solution of the present invention, the model building module further includes a prediction analysis unit for predicting future trends and development directions based on historical data.

[0022] As a preferred solution of the present invention, the system further includes a security module for protecting data in the system from unauthorized access or tampering.

[0023] The method for constructing a multi-dimensional information model construction system for scientific and technological projects includes the following steps:

[0024] S1: Start the data collection module to collect data related to scientific and technological projects;

[0025] S2: Use the data processing module to process the collected data and classify them according to the preset standards;

[0026] S3: Application model building module to build a multi-dimensional information model based on the processed data;

[0027] S4: Display model results through the analysis and display module, and perform interactive analysis according to user needs.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. In this solution, by collecting and analyzing extensive historical data, the model can provide more accurate forecasts and trend analysis, helping decision makers make more informed decisions based on data. The system encompasses information across multiple dimensions, including technological innovation, market potential, and risk assessment, enabling decision makers to comprehensively understand the strengths and weaknesses of projects from multiple perspectives, avoiding biases stemming from a single perspective. Interactive analysis tools allow users to dynamically adjust parameters and instantly view changes in results, which is crucial for rapidly responding to market changes and adjusting strategic direction.

[0030] 2. In this solution, data encryption technology ensures data security during transmission and storage, preventing unauthorized access or tampering. An access control system ensures that only authorized users can access the corresponding data, adhering to the principle of least privilege. The system logs all operations and uses an audit mechanism to detect abnormal behavior, promptly identifying and responding to potential security threats and ensuring stable system operation. Multi-factor authentication makes it more difficult for attackers to illegally access the system, improving overall system security.

[0031] 3. In this solution, the system provides a graphical interface and other display methods, enabling users to intuitively understand complex analysis results and lowering the barrier to entry. Users can freely adjust parameters and immediately see the changes in the results, enhancing the system's interactivity and flexibility, allowing users to tailor their analysis to meet their specific needs. The system allows users to propose new evaluation dimensions and integrate them into existing models, meaning the system can be expanded and customized to meet evolving needs, ensuring its long-term applicability and value. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0033] Figure 1 A flowchart of a system for constructing a multi-dimensional information model for scientific and technological projects according to the present invention;

[0034] Figure 2 A flow chart defining the data requirements for the present invention;

[0035] Figure 3 The data flow chart after loading and processing of the present invention;

[0036] Figure 4 The figure is a flow chart of obtaining analysis results of the present invention. DETAILED DESCRIPTION

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0038] In the description of the present invention, it should be noted that the terms "upper," "lower," "inner," "outer," "top / bottom," and the like, indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0039] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "installed," "provided with," "mounted / connected," and "connected" should be understood in a broad sense. For example, "connected" can mean a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0040] Example 1

[0041] See also Figure 1-4 , the present invention provides the following technical solutions:

[0042] A system for constructing a multi-dimensional information model of scientific and technological projects, comprising:

[0043] Data collection module, used to collect various data related to scientific and technological projects;

[0044] The data processing module is used to clean and organize the collected data and classify the data into different dimensions according to preset standards;

[0045] Model building module, used to build a multi-dimensional information model of scientific and technological projects based on classified data;

[0046] The analysis and display module is used to display model results through a graphical interface or other forms.

[0047] In a specific embodiment of the present invention, the data collection module:

[0048] Function: Responsible for collecting various data related to scientific and technological projects.

[0049] Implementation method:

[0050] Internal data source: Integrate the company's internal database interface to automatically obtain R&D reports, project progress reports, financial statements, etc. submitted by the R&D department.

[0051] External data sources: Develop web crawler programs to capture relevant data from public websites (such as academic journals, patent databases, industry reports, etc.); at the same time, connect to third-party API services (such as market research reports, industry news, etc.).

[0052] Output: The collected raw data is stored in a distributed file system for subsequent processing.

[0053] 2. Data processing module

[0054] Function: Clean and organize the collected data, and classify the data into different dimensions according to preset standards.

[0055] Implementation method:

[0056] Data cleaning: Develop Python scripts and use the Pandas library to perform data deduplication, missing value filling, outlier processing, etc.

[0057] Data organization: Merge the cleaned data by project ID and sort them in chronological order.

[0058] Data classification: Define multiple dimensions (such as technological innovation, market potential, risk assessment, etc.), write rule engines or use machine learning models to classify data.

[0059] Output: The classified data is stored in a relational database for easy query and modeling.

[0060] 3. Model building module

[0061] Function: Build a multi-dimensional information model of scientific and technological projects based on classified data.

[0062] Implementation method:

[0063] Model selection: Select the appropriate model type based on different dimensional requirements, such as logistic regression for predicting project success rate, cluster analysis for market segmentation, etc.

[0064] Feature engineering: Extract important features that affect model performance, such as R&D investment ratio and team experience score.

[0065] Model training: Use machine learning libraries such as Scikit-Learn to train the model and select the best parameters through cross-validation.

[0066] Model evaluation: Use multiple evaluation indicators (such as accuracy, F1 score, etc.) to evaluate model performance.

[0067] Output: The trained model is saved as a file and deployed on the server for real-time query.

[0068] 4. Analysis and display module

[0069] Function: Display model results through a graphical interface or other forms.

[0070] Implementation method:

[0071] Front-end Development: Develop user-friendly web applications using modern front-end frameworks like React or Vue.js.

[0072] Backend integration: Connect the frontend application with the backend model service through RESTful API.

[0073] Visualization component: Integrate visualization libraries such as ECharts or D3.js to display project scores, rankings, and other information in various dimensions.

[0074] Interactive design: allows users to dynamically adjust parameters and view changes in model prediction results in real time.

[0075] Output: A complete web application supporting user login, data query, and result display. This implementation utilizes four main modules (data collection, data processing, model building, and analysis and display) to comprehensively analyze and display multi-dimensional information on scientific and technological projects. The entire system not only efficiently processes large amounts of data but also provides intuitive and easy-to-understand results, helping decision makers better understand project status and development trends.

[0076] Please refer to 1-4 for details. The data collection module can also automatically capture relevant information from an external database.

[0077] In this embodiment: Data collection module

[0078] Function: Responsible for collecting various data related to scientific and technological projects, including automatically capturing relevant information from internal and external databases.

[0079] Implementation method:

[0080] 1.1 Internal data source integration:

[0081] Internal database interface: Develop API interface with the company's internal database (such as MySQL, Oracle, etc.) to automatically obtain data related to scientific and technological projects on a scheduled or on-demand basis.

[0082] Internal document management system: Integrate internal document management systems (such as SharePoint, enterprise cloud disk, etc.) to automatically read R&D reports, project progress reports, financial statements and other documents.

[0083] 1.2 External data source integration:

[0084] API interface call: For external data sources that provide open APIs (such as the patent database of the State Intellectual Property Office, CNKI and other academic paper databases), write programs to call these APIs to obtain the required data.

[0085] Example: Call the National Intellectual Property Administration API to obtain patent information, including patent number, applicant, abstract, etc.

[0086] Web crawler technology: For external data sources that do not provide APIs, develop web crawler programs to automatically capture relevant information on web pages.

[0087] Example: Use Python's Scrapy framework or BeautifulSoup library to develop a crawler program to crawl the latest research results from academic journal websites, crawl market trends from industry information websites, etc.

[0088] Data synchronization mechanism: Design a data synchronization mechanism to ensure that external data can be updated regularly and maintain data freshness.

[0089] Example: Execute a data synchronization task every morning to update the relevant information of the previous day.

[0090] 1.3 Data Storage and Management

[0091] Data storage: Data collected from internal and external data sources is stored in a centralized database or data warehouse.

[0092] Example: Use Hadoop HDFS as a distributed file system to store large amounts of raw data; use PostgreSQL as a relational database to store structured data.

[0093] Data management: Develop a data management platform that supports data import, export, backup, and recovery functions.

[0094] Example: Develop a web interface to enable administrators to easily manage data, including deleting duplicate data and repairing damaged data.

[0095] Example of implementation steps:

[0096] Specific implementation steps of the data collection module:

[0097] Internal data source integration

[0098] Step 1: Work with your IT department to gain access to your internal database.

[0099] Step 2: Develop an API interface to exchange data with the internal database.

[0100] Step 3: Write a script to periodically pull data from the internal database and store it in a local or central storage system.

[0101] External data source integration

[0102] Step 1: Investigate available external data sources and make a list of required APIs.

[0103] Step 2: Register an API account and obtain an API key.

[0104] Step 3: Write API call code to periodically obtain external data.

[0105] Step 4: Develop a web crawler to crawl data from data sources without APIs.

[0106] Step 5: Store the captured data in a local or central storage system.

[0107] Data storage and management

[0108] Step 1: Select a suitable data storage solution (such as HDFS, PostgreSQL, etc.).

[0109] Step 2: Develop a data management platform to support the addition, deletion, query and modification of data.

[0110] Step 3: Back up data regularly to ensure data security.

[0111] This example describes the specific implementation of the data collection module, including the process of automatically capturing relevant information from internal and external databases. By integrating internal data sources, developing API call code, writing a web crawler, and establishing a data storage and management system, we ensure comprehensive and timely data collection, laying a solid foundation for subsequent data processing, model building, and analysis and presentation.

[0112] For details, please refer to 1-4. The data processing module further includes a data standardization processing unit for converting data from different sources into a unified format.

[0113] In this embodiment: Data processing module:

[0114] Function: Clean and organize the collected data, and classify the data into different dimensions according to preset standards.

[0115] Further functions: The data standardization processing unit is used to convert data from different sources into a unified format.

[0116] Implementation method:

[0117] 2.1 Data Cleaning

[0118] Data cleaning: Develop Python scripts and use the Pandas library to perform data deduplication, missing value filling, outlier processing, etc.

[0119] For example, for duplicate records, use the drop_duplicates() method to remove them; for missing values, use the fillna() method to fill them, which can be the mean, median, or other reasonable filling strategies.

[0120] 2.2 Data collation:

[0121] Data organization: Merge the cleaned data by project ID and sort them in chronological order.

[0122] Example: Use Pandas’ merge() function to merge multiple data tables by project ID and sort by the time field using the sort_values() method.

[0123] 2.3 Data Classification

[0124] Data classification: Define multiple dimensions (such as technological innovation, market potential, risk assessment, etc.), write rule engines or use machine learning models to classify data.

[0125] Example: Write a rule engine to score projects based on factors such as technical novelty and market demand, and assign the scoring results to different dimensions.

[0126] 2.4 Data Standardization Processing Unit

[0127] Data standardization: Convert data from different sources into a unified format to ensure data consistency and comparability.

[0128] Example: Convert date fields to the ISO 8601 standard format (YYYY--DD).

[0129] Example: Convert the currency unit to RMB (CNY). If there is a foreign currency, convert it according to the exchange rate.

[0130] Example: Standardize text fields, such as unifying uppercase and lowercase letters and removing special characters.

[0131] 2.5 Specific implementation steps of the data standardization processing unit:

[0132] Date format standardization

[0133] Step 1: Identify all tables that contain date fields.

[0134] Step 2: Write a script to convert the date field to ISO 8601 format (YYYY--DD) using Python's datetime library.

[0135] Step 3: Rewrite the converted date field into the database.

[0136] Standardization of monetary units

[0137] Step 1: Identify all tables that contain currency fields.

[0138] Step 2: Get the latest exchange rate information (available through the API interface).

[0139] Step 3: Write a script to convert currency units using Python and convert all currency amounts into RMB (CNY).

[0140] Step 4: Write the converted amount field back into the database.

[0141] Text field normalization

[0142] Step 1: Identify all data tables that contain text fields.

[0143] Step 2: Write a script that uses Python's regular expression (regex) library to remove special characters from the text field and unify the case.

[0144] Step 3: Rewrite the normalized text fields into the database.

[0145] This example describes in detail how the data standardization unit within the data processing module achieves unified format conversion for data from different sources. By standardizing date, currency, and text fields, data consistency and comparability are ensured, providing a high-quality data foundation for subsequent data classification and model building. These standardization steps help improve the accuracy and efficiency of data analysis, ensuring that the resulting multidimensional information model for scientific and technological projects reliably reflects the actual project situation.

[0146] For details, please refer to 1-4. The model building module also includes a weight allocation unit for assigning corresponding weight values ​​according to the importance of different dimensions.

[0147] In this embodiment: Model construction module

[0148] Function: Build a multi-dimensional information model of scientific and technological projects based on classified data.

[0149] Further functions: including a weight assignment unit for assigning corresponding weight values ​​according to the importance of different dimensions.

[0150] Implementation method:

[0151] 3.1 Feature Selection and Preprocessing

[0152] Feature selection: Based on the results of previous data processing, select the most meaningful features for project evaluation.

[0153] Examples: technological innovation, market potential, risk assessment, team experience, etc.

[0154] Feature preprocessing: Standardize or normalize the selected features to ensure that data of different dimensions can be compared at the same scale.

[0155] Example: Using Z-score normalization or Min-Max scaling techniques.

[0156] 3.2 Weight distribution unit

[0157] Weight allocation: Assign corresponding weight values ​​according to the importance of different dimensions to ensure that the model can reflect the true contribution of each dimension.

[0158] Example: Technological innovation accounts for 30%, market potential accounts for 40%, risk assessment accounts for 20%, and team experience accounts for 10%.

[0159] 3.3 Specific implementation steps of the weight allocation unit:

[0160] Determine the weight distribution principle

[0161] Step 1: Work with domain experts to determine the importance of each dimension based on their expertise and experience.

[0162] Step 2: Develop a set of weight allocation rules to ensure that the rules are scientific and reasonable.

[0163] Using the Analytic Hierarchy Process (AHP)

[0164] Step 1: Construct a judgment matrix and compare the importance of each dimension pairwise.

[0165] Step 2: Calculate the maximum eigenvalue of the judgment matrix and its corresponding eigenvector to obtain the weight value of each dimension.

[0166] Step 3: Perform a consistency check to ensure that the consistency ratio (CR) of the weight distribution is less than 0.1 to ensure the reliability of the weights.

[0167] Use expert scoring

[0168] Step 1: Invite experts from multiple fields to participate in scoring.

[0169] Step 2: Each expert scores the importance of each dimension based on his or her own judgment.

[0170] Step 3: Count the scoring results of each expert and calculate the average value as the final weight value.

[0171] Weight integration and application

[0172] Step 1: Integrate the calculated weight values ​​into the model.

[0173] Step 2: During the model construction process, the impact of each dimension is weighted according to the weight value.

[0174] Step 3: Verify the effect of the weighted model to ensure that the weight distribution is reasonable and effective.

[0175] Example

[0176] Suppose we need to build a comprehensive evaluation model for a technology project, which includes four dimensions: technological innovation, market potential, risk assessment, and team experience. The specific implementation steps are as follows:

[0177] Determine the weight distribution principle

[0178] After discussions with experts, it was determined that technological innovation is the most important, followed by market potential, then risk assessment, and finally team experience.

[0179] Using the Analytic Hierarchy Process (AHP)

[0180] Construct a judgment matrix:

[0181]

[0182] The eigenvectors were calculated and the weights were: technological innovation 0.3, market potential 0.4, risk assessment 0.2, and team experience 0.1.

[0183] A consistency test was performed to confirm that CR<0.1.

[0184] Weight integration and application

[0185] Integrate the calculated weight values ​​into the model.

[0186] When building the model, the impact of each dimension is weighted according to the weight value.

[0187] This embodiment describes in detail how the weight assignment unit in the model construction module assigns corresponding weights based on the importance of different dimensions. The weights of each dimension are determined through the Analytic Hierarchy Process (AHP) or expert scoring method and applied to the model to ensure that the model can comprehensively and accurately reflect the multidimensional information of scientific and technological projects. This approach improves the scientific and practical nature of the model, enabling it to better serve the evaluation and decision-making of scientific and technological projects.

[0188] Please refer to 1-4 for details. The analysis and display module also includes an interactive analysis tool that allows users to dynamically adjust parameters and view result changes in real time.

[0189] In this embodiment: Analysis and display module:

[0190] Function: Display model results through a graphical interface or other forms.

[0191] Further features include interactive analysis tools that allow users to dynamically adjust parameters and instantly see the resulting changes.

[0192] Implementation method:

[0193] 4.1 User Interface Design

[0194] Design principles: simple, intuitive, and easy to operate.

[0195] Tool choice: Build your user interface using a modern front-end framework like React or Vue.js.

[0196] Chart library: Integrate high-performance chart libraries (such as ECharts and D3.js) for data visualization.

[0197] 4.2 Specific implementation of interactive analysis tools

[0198] Dynamic parameter adjustment:

[0199] Step 1: Set up a parameter adjustment area in the user interface and provide controls in the form of sliders, input boxes, etc.

[0200] Step 2: Allow users to adjust key parameters such as weight values ​​and thresholds in the model.

[0201] Example: Provide a slider that allows users to adjust the weight of technological innovation between 0 and 1.

[0202] Instant results show:

[0203] Step 1: Use WebSocket or polling technology to implement real-time communication to ensure that every user operation is quickly fed back to the server.

[0204] Step 2: After receiving the request, the server immediately recalculates the model results and returns the updated data.

[0205] Step 3: The front-end dynamically updates the charts and results display so that users can see the immediate effects.

[0206] Example: When the user adjusts the weight of technological innovation, the chart will refresh immediately to show the new distribution of results.

[0207] History and Version Control:

[0208] Step 1: Record every adjustment operation and its results for easy tracing.

[0209] Step 2: Provide version control functionality, allowing users to save the current state and restore to the previous state at any time.

[0210] Example: Users can select "Save current version" in the interface and select "Restore to a certain version" in the future.

[0211] User guidance and help:

[0212] Step 1: Provide a detailed user manual or help document to explain the meaning and function of each parameter.

[0213] Step 2: Embed prompt information in the interface to guide users to correct operations.

[0214] Example: Display a floating tip next to the parameter adjustment area to explain the parameter's scope and impact.

[0215] Data export and sharing

[0216] Step 1: Allow users to export current analysis results and save them in PDF or Excel format.

[0217] Step 2: Provide a sharing link function so that other users can view the current analysis status through the link.

[0218] Example: Users can click the "Export Results" button to save the current page content as a PDF file.

[0219] Suppose we are building a multi-dimensional information model display system for a scientific and technological project. The specific implementation steps are as follows:

[0220] Dynamic parameter adjustment: A slider is set on the user interface to adjust the weight of technological innovation. Users can change the weight value by dragging the slider.

[0221] Instant results display: After the user adjusts the technological innovation weight, the server immediately recalculates the model results and returns the updated data. The front-end dynamically updates the chart to display the new technological innovation score distribution.

[0222] History and version control: Records every adjustment operation and its results. Provides "save current version" and "restore to a certain version" functions.

[0223] User Guidance and Help: A floating prompt is displayed next to the parameter adjustment area, explaining the significance of the technological innovation weight. A user manual is provided, detailing the functions of each parameter.

[0224] Data export and sharing: Users can click the "Export Results" button to save the current page content as a PDF file. Users can also generate a sharing link and send it to colleagues to view the current analysis status.

[0225] This example describes in detail how the interactive analysis tools in the analysis and display module enable users to dynamically adjust parameters and instantly view changing results. By leveraging modern front-end technology and a high-performance charting library, combined with real-time communication technology, users can quickly receive feedback, improving both the user experience and the system's practicality. These features make the multidimensional information model of scientific and technological projects more flexible and practical, helping decision makers better understand and optimize projects.

[0226] For details, please refer to 1-4. The system also includes a feedback mechanism that allows users to make modification suggestions based on the display results and feed them back to the data processing module for updating.

[0227] In this embodiment: Feedback mechanism:

[0228] Function: Allow users to make modification suggestions based on the displayed results and feedback to the data processing module for updating.

[0229] Implementation method:

[0230] 5.1 User feedback collection:

[0231] Feedback entry: Provide an obvious feedback entry in the user interface of the analysis display module, such as a "Make Suggestions" or "Feedback Issues" button.

[0232] Feedback form: Design a simple and easy-to-use feedback form where users can fill in suggestions or point out errors in the displayed results.

[0233] 5.2 Feedback processing flow:

[0234] User-submitted feedback:

[0235] Step 1: After the user clicks the "Make a Suggestion" button, a feedback form pops up.

[0236] Step 2: The user fills in the feedback content, including but not limited to the data errors found, suggested areas for improvement, etc.

[0237] Step 3: User submits feedback.

[0238] Backstage feedback

[0239] Step 1: The backend system receives feedback submitted by the user.

[0240] Step 2: Record the feedback information into the database, including user ID, feedback content, submission time, etc.

[0241] Step 3: Notify relevant personnel (such as project managers and data analysts) via email or message to review the feedback.

[0242] Feedback review and processing:

[0243] Step 1: Designate someone to review the feedback and determine its effectiveness and urgency.

[0244] Step 2: Take appropriate measures based on the feedback content, such as data correction, model adjustment, etc.

[0245] Step 3: Update the data or model in the data processing module to ensure that the feedback is properly handled.

[0246] Feedback result notification:

[0247] Step 1: After processing the feedback, notify the user of the processing results.

[0248] Step 2: Users can check the feedback processing status in the system to understand whether their suggestions have been adopted and how to improve them.

[0249] 5.3 Specific implementation steps of the feedback mechanism:

[0250] User interface design: Add a "Make a Suggestion" button to the user interface. Clicking it will pop up a feedback form. The form will include required fields (such as feedback content) and optional fields (such as contact information).

[0251] Backend processing logic: Develop an API interface to receive feedback data from the frontend. After receiving the feedback, the backend system records it in the database and notifies relevant personnel via email or system messages.

[0252] Data processing module updates: Based on feedback, the data or models in the data processing module need to be updated accordingly. The updated data is re-entered into the model building process to ensure model accuracy.

[0253] User Notification: Notify users via email or system message that their feedback has been processed. Users can check the feedback processing status in the system to understand the adoption of their suggestions.

[0254] Example:

[0255] Suppose we are building a multi-dimensional information model display system for a scientific and technological project. The specific implementation steps are as follows:

[0256] User interface design: Add a "Make Suggestions" button in the upper right corner of the analysis display module.

[0257] After the user clicks the button, a form containing a text input box pops up and the user can fill in the suggested content.

[0258] Backend processing logic: After a user submits a suggestion, the backend receives the data and stores it in the database via the API. The backend system notifies data analysts via email to review the new feedback.

[0259] Data processing module update: The data analyst reviews the feedback and discovers a data entry error. The data in the database is updated and the data processing flow is rerun.

[0260] User Notification: Users will be notified via email that their feedback has been processed and specific improvement measures will be provided. Users can log in to the system and view the feedback processing status in their personal center.

[0261] This example describes in detail how to integrate a feedback mechanism into the system, allowing users to submit modification suggestions based on the displayed results and pass this feedback to the data processing module for updating. Through this mechanism, the system can respond to user feedback promptly, ensuring data accuracy and model effectiveness, enhancing system interactivity and user satisfaction. This process not only improves system flexibility but also strengthens communication between users and the system, facilitating continuous improvement and optimization.

[0262] Please refer to 1-4 for details. The feedback mechanism also supports users to add new evaluation dimensions and integrate them into the existing model.

[0263] In this embodiment: Feedback mechanism

[0264] Function: Allow users to make modification suggestions based on the displayed results and feedback to the data processing module for updating.

[0265] Further functionality: Supports users to add new evaluation dimensions and integrate them into existing models.

[0266] Implementation method:

[0267] 5.1 User Feedback Collection

[0268] Feedback entry: Provide an obvious feedback entry in the user interface of the analysis display module, such as a "Make Suggestions" or "Feedback Issues" button.

[0269] Feedback Form: Design a simple and user-friendly feedback form where users can submit suggestions or point out errors in the displayed results. The form should include a feature for suggesting new evaluation dimensions.

[0270] 5.2 Proposal and Processing of New Assessment Dimensions

[0271] Users propose new evaluation dimensions

[0272] Step 1: After the user clicks the "Make a Suggestion" button, a feedback form pops up.

[0273] Step 2: The user fills in the suggestion form, including the proposed new assessment dimension name and its description.

[0274] Step 3: User submits feedback.

[0275] Backstage feedback

[0276] Step 1: The backend system receives feedback submitted by the user.

[0277] Step 2: Record the feedback information into the database, including user ID, feedback content, submission time, etc.

[0278] Step 3: Notify relevant personnel (such as project managers and data analysts) via email or message to review the feedback.

[0279] Feedback review and processing

[0280] Step 1: Designate someone to review the feedback and determine its effectiveness and urgency.

[0281] Step 2: Take appropriate measures based on the feedback content, such as data correction, model adjustment, etc.

[0282] Step 3: If the proposed new assessment dimension is deemed valuable, it will enter the development process.

[0283] Development of new assessment dimensions

[0284] Step 1: The development team designs corresponding data collection, processing, and analysis methods based on the proposed new assessment dimensions.

[0285] Step 2: Develop new data collection modules or adjust existing modules to collect data related to the new dimensions.

[0286] Step 3: Add processing logic to the data processing module to ensure that the data of the new dimension can be correctly processed and classified.

[0287] Step 4: Add the new evaluation dimension to the model building module and adjust the existing model to accommodate the new dimension.

[0288] Step 5: Add new charts or views in the analysis and display module to display the data analysis results of the new dimension.

[0289] Feedback result notification

[0290] Step 1: After processing the feedback, notify the user of the processing results.

[0291] Step 2: Users can check the feedback processing status in the system to understand whether their suggestions have been adopted and how to improve them.

[0292] 5.3 Specific implementation steps of the feedback mechanism:

[0293] User interface design

[0294] Add a "Make a Suggestion" button to the UI that pops up a feedback form.

[0295] The form includes required items (such as feedback content), optional items (such as contact information), etc., and adds a section specifically for proposing new evaluation dimensions.

[0296] Backend processing logic

[0297] Develop API interface to receive feedback data from the front end.

[0298] After receiving the feedback, the backend system records it in the database and notifies relevant personnel via email or system messages.

[0299] Data processing module update

[0300] Based on the feedback content, the data or model in the data processing module needs to be updated accordingly.

[0301] The updated data re-enters the model building process to ensure the accuracy of the model.

[0302] Model Building Module Updates

[0303] In the model building module, the model structure and algorithm are adjusted according to the new evaluation dimension to ensure that the new dimension can be effectively evaluated.

[0304] Train and validate existing models to ensure their reliability and effectiveness.

[0305] Analysis and display module update

[0306] Add new charts or views in the analysis and display module to display the data analysis results of the new evaluation dimension.

[0307] Users can view the analysis results of the new dimensions in the updated interface and perform interactive analysis.

[0308] Example

[0309] Suppose we are building a multi-dimensional information model display system for a scientific and technological project. The specific implementation steps are as follows:

[0310] User interface design

[0311] Added a "Make a Suggestion" button in the upper right corner of the analysis display module.

[0312] After the user clicks the button, a form pops up containing a text input box where the user can fill in the suggestion content, including a section for proposing new evaluation dimensions.

[0313] Backend processing logic

[0314] After the user submits a suggestion, the backend receives the data and stores it in the database through the API.

[0315] The backend system notifies the data analyst via email to review the new feedback.

[0316] Data processing module update

[0317] Data analysts reviewed the feedback and found that users proposed a new evaluation dimension - "environmental impact".

[0318] The development team designs data collection plans and adjusts existing data processing modules to support data processing of new dimensions.

[0319] Model Building Module Updates

[0320] Data analysts added the "environmental impact" dimension to the model building module and adjusted the model algorithm to ensure that the new dimension could be correctly evaluated.

[0321] Train and validate the model to ensure its reliability.

[0322] Analysis and display module update

[0323] Add a new chart in the analysis and display module to display the data analysis results of the "environmental impact" dimension.

[0324] Users can view the analysis results of the new dimensions in the updated interface and perform interactive analysis.

[0325] This example describes in detail how to support users in adding new evaluation dimensions within the feedback mechanism and integrating them into the existing model. Through this mechanism, users can not only suggest modifications to existing dimensions but also propose new ones, enabling the system to more comprehensively reflect the actual conditions of scientific and technological projects. This process not only improves the system's flexibility and adaptability but also strengthens interaction between users and the system, facilitating continuous improvement and optimization.

[0326] Please refer to 1-4 for details. The model building module further includes a prediction analysis unit for predicting future trends and development directions based on historical data.

[0327] In this embodiment: Model construction module

[0328] Function: Build a multi-dimensional information model of scientific and technological projects based on classified data.

[0329] Further features: Includes a predictive analysis unit for predicting future trends and development directions based on historical data.

[0330] Implementation method:

[0331] 3.1 Feature Selection and Preprocessing

[0332] Feature selection: Based on the results of previous data processing, select the most meaningful features for project evaluation.

[0333] Examples: technological innovation, market potential, risk assessment, team experience, etc.

[0334] Feature preprocessing: Standardize or normalize the selected features to ensure that data of different dimensions can be compared at the same scale.

[0335] Example: Using Z-score normalization or Min-Max scaling techniques.

[0336] 3.2 Weight distribution unit

[0337] Weight allocation: Assign corresponding weight values ​​according to the importance of different dimensions to ensure that the model can reflect the true contribution of each dimension.

[0338] Example: Technological innovation accounts for 30%, market potential accounts for 40%, risk assessment accounts for 20%, and team experience accounts for 10%.

[0339] 3.3 Specific implementation of the prediction analysis unit

[0340] Selecting a forecasting model

[0341] Step 1: Select an appropriate forecasting model based on the forecasting target, such as time series analysis (ARIMA, SARIMA), machine learning algorithm (random forest, support vector machine), deep learning model (LSTM, GRU), etc.

[0342] Example: If the goal is to predict market potential, an ARIMA model based on time series can be chosen.

[0343] Historical data analysis

[0344] Step 1: Use historical data to train the model and find patterns and regularities in the data.

[0345] Step 2: Evaluate the predictive performance of the model through methods such as cross-validation.

[0346] Example: Train an ARIMA model using market potential data from the past five years and evaluate the model's accuracy and stability using a rolling window validation method.

[0347] Model training and optimization

[0348] Step 1: Use the selected model to train historical data.

[0349] Step 2: Adjust model parameters through grid search, Bayesian optimization and other techniques to obtain the best prediction results.

[0350] Example: Use GridSearchCV to find the best parameter combination for an ARIMA model.

[0351] Future trend predictions

[0352] Step 1: Predict the trend for a period of time in the future based on the trained model.

[0353] Step 2: Generate prediction results and display them visually, such as trend charts and prediction intervals.

[0354] Example: Predict the growth trend of market potential in the next year and generate a trend chart.

[0355] Prediction result interpretation

[0356] Step 1: Interpret the forecast results and analyze the factors that may cause future changes.

[0357] Step 2: Propose corresponding strategy recommendations based on the prediction results.

[0358] Example: If the forecast shows that the market potential will increase significantly, it is recommended to increase marketing efforts.

[0359] Example

[0360] Suppose we need to build a comprehensive evaluation model for a technology project, including four dimensions: technological innovation, market potential, risk assessment, and team experience, and we need to predict the development trend of market potential. The specific implementation steps are as follows:

[0361] Select Forecast Model: Select ARIMA model for forecasting market potential.

[0362] Historical data analysis: Use the market potential data of the past five years to train the ARIMA model and evaluate the model performance through cross-validation.

[0363] Model training and optimization: Use GridSearchCV to find the best parameter combination of the ARIMA model to obtain the best prediction effect.

[0364] Future trend forecast: Based on the trained ARIMA model, predict the growth trend of market potential in the next year and generate a trend chart.

[0365] Interpretation of forecast results: Explain the forecast results, analyze the factors that may lead to market potential growth, and make strategic recommendations.

[0366] This example describes in detail how the predictive analysis unit within the model building module predicts future trends and development directions based on historical data. By selecting an appropriate predictive model, analyzing historical data, training and optimizing the model, predicting future trends, and interpreting the prediction results, the accuracy and practicality of the predictions are ensured. These steps help improve the scientific nature and reliability of the model, enabling it to better serve the evaluation and decision-making of scientific and technological projects.

[0367] Please refer to 1-4 for details. The system also includes a security module for protecting data in the system from unauthorized access or tampering.

[0368] In this embodiment: security module

[0369] Function: Protect data in the system from unauthorized access or tampering.

[0370] Implementation method:

[0371] 6.1 User Authentication

[0372] Authentication: Ensures that only authenticated users can access the system.

[0373] Example: Basic authentication using username and password.

[0374] Advanced authentication: Use multi-factor authentication (MFA), such as SMS verification codes, hardware tokens, or biometrics.

[0375] 6.2 Access Control

[0376] Permission management: Assign different access rights based on user roles and responsibilities.

[0377] Example: Administrators can access all data, while ordinary users can only view information related to their own projects.

[0378] Principle of least privilege: Ensure that users have access to only the minimum data necessary to perform their duties.

[0379] 6.3 Data Encryption

[0380] Transmission encryption: Ensures that data is not eavesdropped or tampered with during transmission.

[0381] Example: Use SSL / TLS protocol to encrypt all HTTP communications.

[0382] Static encryption: Encrypt sensitive data stored in the database so that it cannot be directly read even if the data is illegally obtained.

[0383] 6.4 Audit and Monitoring

[0384] Logging: Records all system activity, including login attempts, data access, and modification.

[0385] Example: Logs the user's login time and IP address, as well as any changes to the data.

[0386] Anomaly detection: Uses machine learning algorithms to detect unusual login behavior or data access patterns.

[0387] 6.5 Specific implementation steps of the security module:

[0388] User authentication

[0389] Step 1: The user is asked to provide a username and password on the login page.

[0390] Step 2: Use a hash algorithm to store passwords and compare them when logging in.

[0391] Step 3: Implement multi-factor authentication (such as SMS verification code) for important operations.

[0392] Access Control

[0393] Step 1: Define user roles and their permissions, such as administrator, common user, etc.

[0394] Step 2: Set up an access control list (ACL) in the database to limit the scope of user access to data.

[0395] Step 3: Regularly review user permissions to ensure the principle of least privilege is followed.

[0396] Data encryption

[0397] Step 1: Use SSL / TLS protocol to encrypt all communications between the server and the client.

[0398] Step 2: Encrypt and store sensitive data (such as passwords and financial information) in the database.

[0399] Step 3: Manage encryption keys using an encryption key management system (KMS).

[0400] Audit and Monitoring

[0401] Step 1: Record user login information, operation logs, etc., and store them on a secure log server.

[0402] Step 2: Analyze logs regularly to look for unusual behavior.

[0403] Step 3: Use an intrusion detection system (IDS) to monitor network traffic and detect potential security threats.

[0404] Example

[0405] Suppose we are building a multi-dimensional information model system for a scientific and technological project. The specific implementation steps are as follows:

[0406] User authentication: Users are required to enter their username and password when logging in. Passwords are hashed when stored, and the hash value is compared when logging in. For key operations, such as modifying weight values, a text message verification code is required.

[0407] Access Control: Define user roles: Administrator, Data Analyst, and General User. General users can only view information related to their own projects. Administrators can access all data and configure the system.

[0408] Data encryption: Communications between the system and users are encrypted using the HTTPS protocol. Sensitive data stored in the database, such as user passwords, is encrypted using AES-256. Encryption keys are stored in a separate KMS service, and access rights are strictly managed.

[0409] Audit and monitoring: Record all user login times and IP addresses. Monitor user operations, especially data modification records. Use IDS to detect abnormal traffic or attack behavior in the system.

[0410] This embodiment describes in detail how the security module in the system protects data from unauthorized access and tampering. System security is ensured through user authentication, access control, data encryption, and auditing and monitoring. These security measures help protect system integrity and safeguard user data, thereby enhancing system reliability and user trust.

[0411] The usage process of the present invention is as follows: first, when a user uses the system for the first time, he needs to register an account, enter personal information (such as name, email address, mobile phone number, etc.), set a login password, verify the email address or mobile phone number, and ensure the authenticity of the information. The user uses the registered account information to log in to the system, enter the user name and password, perform identity authentication, and enable multi-factor authentication (such as SMS verification code, fingerprint recognition, etc.). After logging in, the user can see a list of all projects he is responsible for or involved in. He can filter according to conditions such as project name, status, person in charge, etc., select a project, view the basic information of the project (such as project name, introduction, participants, etc.), view the historical data and current status of the project, and the user can upload various data related to the project, such as R&D reports, market analysis, financial statements, etc. The data can be submitted by file upload or online input, and the user can edit the relevant information of the project as needed, such as update Edited information such as project progress and added notes will be saved and can be used for subsequent data processing. Users can access the analysis and display module of the system to view the analysis results of the project in various dimensions, and can view the model results through a graphical interface or other forms. In the analysis and display module, users can dynamically adjust parameters such as weight distribution and thresholds through interactive tools, and instantly view the changes in the results after parameter adjustment. If the user finds that there are places that need to be modified in the display results, they can submit modification suggestions through the feedback mechanism in the system and fill in the specific suggestions in the feedback form, including proposals for new evaluation dimensions. Users can view the processing status of their submitted feedback in the system, receive notifications of feedback processing results, and understand whether the suggestions have been adopted. After use, the user should log out of the system safely to prevent others from using their account to operate. After confirming logout, clear the browser cache to prevent sensitive information leakage.

[0412] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A multi-dimensional information model construction system for scientific and technological projects, characterized by: include: Data center, used to store various information logs of scientific and technological projects; An analysis module, connected to the data center, for determining multiple key factors in the project and performance indicators of each factor based on the information log; The correlation module is connected to the data center and is used to determine the mutual influence relationship between key factors in the project; Dynamic monitoring module, used to monitor project progress data in real time; The anomaly identification module is connected to the dynamic monitoring module to identify data points that deviate from the expected target and form an abnormal data set; The risk assessment module is connected with the analysis module, association module and anomaly identification module to calculate the risk assessment index of each key factor and output the main risk points.

2. The system for constructing a multi-dimensional information model of a scientific and technological project according to claim 1, characterized in that: The analysis module further comprises: A data extraction unit, used for extracting key factor logs from information logs; a data classification unit for classifying information logs by category; Correlation analysis unit is used to determine the performance indicators of each key factor and the strength of their correlation.

3. The system for constructing a multi-dimensional information model of a scientific and technological project according to claim 2, characterized in that: The algorithm adopted by the correlation analysis unit includes: Determine all performance indicators corresponding to the key factor categories and summarize them into a performance indicator set; The strength of the association between the key factor and the performance indicator is calculated, which is determined by the frequency of occurrence of the key factor log in all logs.

4. The system for constructing a multi-dimensional information model of a scientific and technological project according to any one of claims 1 to 3, characterized in that: The anomaly identification module further includes: a parameter identification unit, used to identify data points that deviate from the expected target; The anomaly summary unit is used to group all data points that deviate from the expected target into an abnormal data set.

5. The system for constructing a multi-dimensional information model of a scientific and technological project according to claim 1, characterized in that: The risk assessment module further comprises: Anomaly fitting unit, used to calculate the natural fitting value of the current abnormal state and each key factor; AI computing unit, used to calculate risk assessment indicators based on natural fitting values ​​and the mutual influence relationship between key factors; Risk output unit, used to output major risk points.

6. The system for constructing a multi-dimensional information model of a scientific and technological project according to claim 5, characterized in that: The natural fitting value Fnatural(K) is obtained by the formula The calculation shows that N1 and N2 are the total number of elements in the intersection and union of the abnormal data and the key factor performance indicator set, respectively. is the key factor K and performance indicator a j The strength of the correlation between j is the weight of the abnormal parameter fitting, and m is the total number of performance indicators in the intersection.

7. The system for constructing a multi-dimensional information model of a scientific and technological project according to claim 6, characterized in that: The AI ​​association algorithm used by the AI ​​computing unit includes: Construct the key factor set B={b1,b2,…,b k }; Calculate the U-th iteration correlation index F for each key factor K U (K); By formula Where P is the total number of other key factors caused by key factor K, C t is the tth key factor caused, Key factors K and C t The weight of the association between .

8. The system for constructing a multi-dimensional information model of scientific and technological projects according to claim 7, characterized in that: The iteration termination condition is when the difference between two consecutive iterations is less than or equal to the iteration error threshold ∈, that is, \F U ()-F U-1 (K)\≤∈, where the value range of ∈ is 0.01-0.

1.

9. The system for constructing a multi-dimensional information model of a scientific and technological project according to claim 8, characterized in that: The risk output unit further includes: Screen key factors whose risk assessment indicators are higher than the preset risk threshold and identify them as high-risk factors; Sort high-risk factors according to the size of risk assessment indicators and output them in the form of priority.

10. A method for constructing a system for constructing a multi-dimensional information model of a scientific and technological project, using the system for constructing a multi-dimensional information model of a scientific and technological project according to any one of claims 1 to 9, characterized in that: The steps include: S1: Demand Analysis and Planning Clarify the goal: Determine the purpose of building a multidimensional information model, such as improving project management efficiency, reducing project risks, etc. Requirements gathering: Communicate with project-related personnel to understand project characteristics, existing processes, potential problems and improvement needs. Resource Assessment: Assess the available human, material, and financial resources, as well as the support capacity of the technical infrastructure. S2: System Design Architecture design: Based on the results of demand analysis, design the overall architecture of the system, including data center, analysis module, correlation module, dynamic monitoring module, anomaly identification module and risk assessment module. Data structure design: Define the data storage format, including the structure of the information log, the representation of key factors and performance indicators, etc. Functional module design: Detailed design of the functions of each module, including data processing flow, algorithm implementation, user interaction interface, etc. S3: Development and Integration Module development: Develop each functional module separately according to the design documents to ensure that each module can run independently. Interface definition: Define the communication protocol and data exchange format between modules to ensure seamless connection between modules. System integration: Integrate each module into a unified system and conduct overall testing to ensure the system is stable and reliable. S4: Data preparation and initialization Data collection: Collect historical and real-time data from existing project management systems, documentation, and other sources. Data cleaning: Clean the collected data to remove invalid, duplicate or erroneous data to ensure data quality. Data import: Import cleaned data into the data center to provide a basis for subsequent analysis and monitoring. S5: System Configuration and Debugging Parameter setting: Configure the parameters of each module according to the project characteristics and requirements, such as the threshold for anomaly recognition and the risk threshold for risk assessment. Functional testing: Perform functional testing on each module to ensure that all functions operate normally. Performance tuning: Tune the system to ensure efficient operation under high load conditions. S6: User training and launch User training: Provide system operation training to project managers and users to ensure that they can use the system proficiently. Trial run: Conduct a trial run in an actual project to collect feedback and further optimize system functions. Official launch: After confirming that the system is stable and reliable, it is officially launched and put into operation, and the multi-dimensional information model is applied in project management. S7: Operation and maintenance and continuous optimization Daily operation and maintenance: Regularly check the system's operating status to identify and resolve problems in a timely manner. Data update: Regularly update the data in the data center to ensure the timeliness and accuracy of the information. Function expansion: According to the needs of project development, continuously expand and optimize system functions to improve the applicability and flexibility of the system.

Images