College student innovation power and patent literacy consultation service platform based on big language model

By introducing large language model technology into the innovative communication model service platform for college students and providing personalized innovation and patent consultation, the problem of single content and insufficient intelligence of the existing platform has been solved, and the innovation and patent literacy of college students has been improved.

CN118967374AInactive Publication Date: 2024-11-15TIANJIN VOCATIONAL INST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410937021.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing college student innovation communication model service platform has single content, poor interactivity and low intelligence, and cannot provide targeted and effective innovation and patent consulting services based on personalized needs.

Method used

A platform for innovation and patent literacy consulting services based on large language models was designed, including user registration and login module, innovative literacy evaluation module, patent literacy evaluation module, innovative consulting module, patent consulting module, big data processing module and generation Language model module uses generative language models to provide personalized and intelligent innovation and patent consulting services.

Benefits of technology

Through big data and generative language models, personalized and intelligent innovation and patent consulting services are provided to improve college students' innovation and patent literacy, stimulate innovative thinking and patent awareness, and enhance innovation ability and patent skills.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967374A_ABST
    Figure CN118967374A_ABST
Patent Text Reader

Abstract

The invention discloses a college student innovation power and patent literacy consultation service platform based on a big language model, and relates to the technical field of education. Comprising a user registration and login module, a main control module, an innovation accomplishment evaluation module, a patent accomplishment evaluation module, an innovation consultation module, a patent consultation module, a big data processing module and a generative language model module. According to the consultation service platform, personalized, intelligent and interactive innovation and patent consultation services are provided for college students by using big data and a generative language model, so that the innovation power and patent attainment of the college students are improved, innovation and patent application of the college students are promoted, and the consultation service platform is provided for the college students according to the evaluation results of the innovation attainment and patent attainment of the users. The method can recommend appropriate innovation themes and patent themes for the user according to the innovation requirements and interests of the user, and provide corresponding innovation points and patent schemes, thereby motivating the innovation thinking and patent awareness of the user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and in particular to a consulting service platform for college students' innovation and patent literacy based on a large language model. Background Art

[0002] In today's society, innovation and patent literacy are essential abilities and qualities for college students, and are of great significance to improving the country's scientific and technological innovation level and competitiveness. However, college students currently have some problems in terms of innovation and patent literacy, such as lack of innovative thinking and methods, unfamiliarity with patent knowledge and processes, and difficulty in finding suitable innovation points and patent solutions. These problems limit college students' innovation potential and the quantity and quality of patent applications.

[0003] In order to solve these problems, there are some relevant education and service platforms, such as innovation education platform, patent education platform, patent search platform, patent analysis platform, etc. These platforms can provide college students with certain innovation and patent knowledge and skills learning and training, as well as some innovation and patent information query and analysis.

[0004] The invention with publication number CN112182440A discloses a service platform for college students' innovative communication model, including an emotional communication and interaction module, a reminder and memo module and a resource mutual assistance module. The emotional communication and interaction module, the reminder and memo module and the resource mutual assistance module are all established on a digitally quantified P2P network platform and are provided with corresponding touch selection items. The emotional communication and interaction module includes a confession module and a chat module. The resource interaction module includes a learning material sharing module, a college material sharing module and a travel material sharing module. The confession module is provided with a filling column for users to fill in the consulting questions they need to select.

[0005] As shown in the above invention, the existing innovation communication model service platform for college students generally recommends acceptance personnel to users based on the consulting questions selected by users, communicates with users, and solves users' emotional problems. However, these platforms still have some shortcomings, such as single content, poor interactivity, and low intelligence. They cannot provide targeted and effective innovation and patent consulting services based on the personalized needs and characteristics of college students. Summary of the invention

[0006] In view of the deficiencies of the prior art, the present invention provides a consulting service platform for college students' innovation and patent literacy based on a large language model, which solves the existing problems.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a college student innovation and patent literacy consulting service platform based on a large language model, including a user registration and login module, a main control module, an innovation literacy assessment module, a patent literacy assessment module, an innovation consulting module, a patent consulting module, a big data processing module and a generative language model module;

[0008] The user registration and login module is connected to the main control module and is used for users to register and log in to the platform, as well as set personal information and preferences;

[0009] The main control module is connected with the user registration and login module, the innovation literacy assessment module, the patent literacy assessment module, the innovation consulting module, the patent consulting module, the big data processing module, and the generative language model module to control the normal operation of each module;

[0010] The innovation literacy assessment module is connected to the main control module and is used to assess the user's innovation literacy;

[0011] Patent literacy assessment module, connected to the main control module, is used to assess the user's patent literacy

[0012] Preferably, the innovation consulting module is connected to the main control module and is used to provide innovation consulting services to users based on the evaluation results of their innovation literacy and their innovation needs and interests;

[0013] The patent consulting module is connected to the main control module and is used to provide patent consulting services to users based on the user's patent literacy assessment results, as well as the user's patent needs and interests;

[0014] The big data processing module is connected to the main control module and is used to collect, store, process, analyze and mine various types of data on the platform;

[0015] The generative language model module is connected to the main control module and is used to use generative language models, such as GPT-4, to provide language generation, understanding, interaction, optimization and other functions for other modules, as well as to provide users with natural, fluent, intelligent and interesting language services;

[0016] The innovation training module is connected to the main control module and is used to train the innovation of college students.

[0017] Preferably, the user registration and login module is responsible for user registration and login, including OAuth2.0 authentication service and user information database;

[0018] Registration and login use OAuth2.0 protocol for security authentication, supporting multiple login methods, including email registration and social media login. User information is stored in an encrypted database, and passwords are encrypted using SHA-256 algorithm.

[0019] User information and preferences: Users fill in personal information and preferences and submit data through forms; data is stored in a relational database.

[0020] Preferably, the main control module controls the operation of the entire system, manages permissions and implements communication between modules through message queues;

[0021] Scheduling and management: Use the SpringBoot framework to build the main control module, implement communication and coordination between modules, and use the message queue RabbitMQ to implement asynchronous communication between modules;

[0022] Permission management: Use the role-based access control (RBAC) model to manage different permissions for users and administrators.

[0023] Preferably, the innovation literacy assessment module includes a questionnaire system LimeSurvey and a hierarchical analysis method AHP, which are used to assess the user's innovation literacy;

[0024] Questionnaire evaluation: Design a questionnaire that includes innovative thinking, problem-solving ability, and creative expression. Use the LimeSurvey tool to manage the questionnaire. The evaluation results are quantified through a scoring system and stored in a database.

[0025] Hierarchical analysis: The analytic hierarchy process (AHP) was used to comprehensively evaluate the questionnaire results and obtain the innovation literacy score.

[0026] Preferably, the patent literacy assessment module includes an online testing system and a fuzzy comprehensive evaluation method FCE, which are used to assess the patent literacy of users;

[0027] Knowledge test: Design online tests covering basic patent knowledge, patent application process, and intellectual property protection. Test results are automatically scored and stored in the database;

[0028] Evaluation algorithm: Use fuzzy comprehensive evaluation method to evaluate the test results and obtain the patent literacy score.

[0029] Preferably, the innovation consulting module uses the KNN algorithm matching system to provide personalized innovation consulting based on the user's innovation literacy assessment results; generates consulting content through the generative language model interface GPT-4

[0030] Matching algorithm: Based on the user's innovation literacy score and interest tags, the K nearest neighbor algorithm is used to match appropriate innovation consulting content;

[0031] Consulting services: Use generative language models to generate personalized innovation suggestions and guidance; support multiple consulting methods such as text, voice, and video.

[0032] Preferably, the patent consultation module uses a collaborative filtering algorithm system to provide personalized patent consultation based on the user's patent literacy assessment results; and generates consultation content through a generative language model interface;

[0033] Matching algorithm: Based on the user's patent literacy score and patent needs, a collaborative filtering algorithm is used to recommend appropriate patent consulting content;

[0034] Consulting services: Generate personalized patent application guidance and intellectual property protection suggestions using generative language models, supporting multiple consultation methods such as text, voice, and video.

[0035] Preferably, the big data processing module is responsible for collecting, storing, processing, analyzing and mining various types of data on the platform, including Apache Kafka, Hadoop HDFS, Apache Spark and cluster analysis technologies;

[0036] Data collection: Use Apache Kafka for real-time data collection;

[0037] Data storage: Use Hadoop HDFS to store big data;

[0038] Data processing and analysis: Use Apache Spark to process and analyze big data to extract useful information and patterns;

[0039] Data mining: Use data mining to discover user behavior patterns and interest trends;

[0040] Machine learning algorithms include cluster analysis and association rules.

[0041] Preferably, the generative language model module integrates OpenAI API, uses generative language models such as GPT-4 to provide language generation, understanding, interaction and optimization services, and uses the Transformer architecture and reinforcement learning algorithm PPO to improve the performance of the language model;

[0042] Model integration: Use OpenAI API to integrate the GPT-4 model to handle natural language generation and understanding tasks;

[0043] Language services: Provide text generation, dialogue, translation and other language services. Use the Transformer architecture to optimize the language model and improve the fluency and accuracy of language generation.

[0044] Interaction optimization: Combined with user feedback, the interaction effect of the language model is continuously optimized through reinforcement learning algorithms.

[0045] Beneficial Effects

[0046] The present invention provides a consulting service platform for college students' innovation and patent literacy based on a large language model. Compared with the prior art, it has the following beneficial effects:

[0047] 1. The university student innovation and patent literacy consulting service platform based on the big language model uses big data and generative language models to provide personalized, intelligent, and interactive innovation and patent consulting services for university students, thereby improving university students' innovation and patent literacy, and promoting their innovation and patent applications. According to the evaluation results of the user's innovation literacy and patent literacy, as well as the user's innovation needs and interests, it recommends suitable innovation topics and patent topics to the user, and provides corresponding innovation points and patent solutions, thereby stimulating the user's innovative thinking and patent awareness. It uses the generative language model to generate innovation and patent related content for the user, such as innovation solutions, patent writing, patent applications, etc., and performs language understanding, interaction, and optimization on the user's input, thereby improving the user's innovation ability and patent skills.

[0048] 2. This university student innovation and patent literacy consulting service platform based on a large language model uses big data to display relevant information about innovation and patents to users, such as innovation cases, patent searches, patent analysis, etc., and collects, stores, processes, analyzes, and mines the platform's data, thereby improving users' innovation methods and patent knowledge. It uses a generative language model to provide users with natural, fluent, intelligent, and interesting language services, thereby improving users' innovation attitudes and patent awareness. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the specific structure of the college students' innovation and patent literacy consulting service platform based on the large language model of the present invention;

[0050] Figure 2 It is a physical structure diagram of the college students' innovation and patent literacy consulting service platform based on the large language model of the present invention;

[0051] Figure 3 This is a schematic diagram of the connection of the college students' innovation and patent literacy consulting service platform system based on the large language model of the present invention;

[0052] Figure 4 It is a schematic diagram of the method flow of the college students' innovation and patent literacy consulting service platform based on the large language model of the present invention;

[0053] Figure 5 It is a flowchart of a processing method of a big data processing module of a college student innovation and patent literacy consulting service platform based on a large language model of the present invention;

[0054] Figure 6A schematic diagram of the accuracy of innovation consulting content generated by the innovation literacy evaluation results of the college students' innovation and patent literacy consulting service platform based on the large language model of the present invention;

[0055] Figure 7 A schematic diagram of the accuracy of patent consulting content generated from the patent literacy assessment results of the college students' innovation and patent literacy consulting service platform based on the large language model of the present invention.

[0056] In the figure: 1. User registration and login module; 2. Main control module; 3. Innovation literacy assessment module; 4. Patent literacy assessment module; 5. Innovation consulting module; 6. Patent consulting module; 7. Big data processing module; 8. Generative language model module; 9. Innovation training module. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0058] The present invention provides Figure 1-7 Two technical solutions are shown:

[0059] The first implementation method: A college student innovation and patent literacy consulting service platform based on a large language model, including a user registration and login module 1, a main control module 2, an innovation literacy assessment module 3, a patent literacy assessment module 4, an innovation consulting module 5, a patent consulting module 6, a big data processing module 7, a generative language model module 8 and an innovation training module 9. Each module is interconnected and coordinated through the main control module 2.

[0060] User registration and login module User registration and login module 1

[0061] Data collection: When users register, they enter their username, password, and personal information (such as name, school, major, hobbies, etc.). When logging in, their username and password are verified.

[0062] Data processing: Data is encrypted and stored in the user database. When logging in, the user's identity is verified through encryption.

[0063] Signal transmission: After the user successfully logs in, the signal is transmitted to the main control module 2, indicating that the user has logged in and requesting to load user information and preference settings.

[0064] Main control module 2

[0065] Control function: coordinate the workflow of each module. Receive the signal from the user registration and login module 1, initialize user information, and load user preferences.

[0066] Data management: The main control module 2 manages the data interaction of each module to ensure the security and efficient transmission of data.

[0067] Signal transmission: The user information is transmitted to the innovation literacy assessment module 3 and the patent literacy assessment module 4 to start the literacy assessment process.

[0068] Innovation Literacy Assessment Module 3

[0069] Data collection: Collect data related to users’ innovation capabilities through questionnaires, test questions, etc.

[0070] Data processing: Use the big data processing module 7 and the generative language model module 8 to analyze the user's innovation literacy and generate an evaluation report.

[0071] Signal transmission: The evaluation results are transmitted to the main control module 2, and the innovation consultation module 5 is started according to user needs and interests.

[0072] Patent Literacy Assessment Module 4

[0073] Data collection: Collect users’ patent knowledge and ability-related data through questionnaires, test questions, etc.

[0074] Data processing: Use the big data processing module 7 and the generative language model module 8 to analyze the user's patent literacy and generate an evaluation report.

[0075] Signal transmission: The evaluation results are transmitted to the main control module 2, and the patent consultation module 6 is started according to the user's needs and interests.

[0076] Innovation Consulting Module 5

[0077] Data input: Provide personalized consultation based on the user's innovation literacy assessment results and the innovation needs and interests input by the user.

[0078] Data processing: Generate innovative suggestions and solutions using the generative language model module 8.

[0079] Signaling: Feedback innovative suggestions and solutions to users and store data in user history.

[0080] Patent Consulting Module 6

[0081] Data input: Provide personalized consultation based on the user's patent literacy assessment results and the patent needs and interests input by the user.

[0082] Data processing: Generate patent application guidance and strategic recommendations using the generative language model module 8.

[0083] Signaling: Feedback patent recommendations and strategies to users and store data in user history.

[0084] Big data processing module 7

[0085] Data collection and storage: Collect various types of data on the platform, including user data, evaluation data, consulting data, etc., and store them in a structured manner.

[0086] Data processing and analysis: Clean, process and analyze the collected data, use data mining technology to extract useful information and support the work of other modules.

[0087] Signal transmission: The processing and analysis results are transmitted to the main control module 2, the generative language model module 8, etc.

[0088] Generative Language Model Module 8

[0089] Language generation and comprehension: Generative language models (such as GPT-4) are used to provide language generation and comprehension functions for each module.

[0090] Data processing and interaction: Cooperate with the big data processing module 7 to analyze user input and generate natural, fluent and intelligent language services.

[0091] Signal transmission: The generated language content is transmitted to relevant modules, such as the innovation consulting module 5 and the patent consulting module 6.

[0092] Innovation Cultivation Module 9

[0093] Data input: Develop a personalized innovation training plan based on the user's innovation literacy assessment results.

[0094] Data processing: Provide online courses, practical projects, resource recommendations, etc. to help users improve their innovation capabilities.

[0095] Signaling: Feedback the progress and results of training to users and store the data in user history.

[0096] Detailed process of signal and data processing:

[0097] 1) User registration and login

[0098] The user enters the registration information, and the system transmits the information to the user registration and login module 1 through the main control module 2.

[0099] The user registration and login module 1 performs information verification, and after the verification is passed, the data is stored in the user database.

[0100] When the user logs in, he enters his username and password, and the system authenticates the user through the main control module 2. After successful authentication, the user information and preferences are loaded.

[0101] 2) Innovation literacy and patent literacy assessment

[0102] After the user logs in, the main control module 2 starts the innovation literacy assessment module 3 and the patent literacy assessment module 4.

[0103] The evaluation module collects data through questionnaires and tests and passes it to the big data processing module 7 for analysis.

[0104] The big data processing module 7 generates an evaluation report based on the analysis results of the generative language model module 8.

[0105] The evaluation results are fed back to the user through the main control module 2, and the corresponding consulting module is started according to the results.

[0106] 3) Innovation consulting and patent consulting

[0107] When the user raises a consultation request, the main control module 2 transmits the request to the corresponding consultation module.

[0108] The innovation consulting module 5 and the patent consulting module 6 use the evaluation results and generative language models to generate personalized suggestions and solutions.

[0109] The consultation result is fed back to the user through the main control module 2 and stored in the user history record.

[0110] 4) Big Data Processing and Generative Language Models

[0111] The big data processing module 7 collects all the data on the platform and performs cleaning, storage and analysis.

[0112] The analysis results are passed to relevant modules to support functions such as innovation literacy assessment, patent literacy assessment, and consultation.

[0113] The generative language model module 8 generates natural and fluent language services based on user input to enhance the user interaction experience.

[0114] 5) Cultivation of innovation

[0115] According to the user's evaluation results, the innovation training module 9 formulates a personalized training plan.

[0116] Provide online courses, practical projects and other resources to help users improve their innovation.

[0117] The training results are fed back to the user through the main control module 2 and stored in the user history record.

[0118] Through the above-mentioned data and signal processing process, the modules work together efficiently, achieving a comprehensive improvement in college students' innovation and patent literacy.

[0119] like Figure 1 , 2 As shown in FIG. 3 , the user registration and login module 1 is connected to the main control module 2 and is used for user registration and login to the platform, as well as setting personal information and preferences;

[0120] User registration and login module 1 is responsible for user registration and login, including OAuth2.0 authentication service and user information database;

[0121] Registration and login use OAuth2.0 protocol for security authentication, supporting multiple login methods, including email registration and social media login. User information is stored in an encrypted database, and passwords are encrypted using SHA-256 algorithm.

[0122] User information and preferences: Users fill in personal information and preferences and submit data through forms; data is stored in a relational database;

[0123] User registration login module 1 registration method is as follows:

[0124] Users register and log in through the platform's web page or mobile terminal, and set personal information and preferences, such as name, gender, age, school, major, innovation interests, patent interests, etc.; the platform will generate a personalized user portrait for the user based on the user's information and preferences, as well as an initial innovation literacy and patent literacy assessment result as the basis for the user to use the platform.

[0125] The main control module 2 is connected with the user registration and login module 1, the innovation literacy assessment module 3, the patent literacy assessment module 4, the innovation consulting module 5, the patent consulting module 6, the big data processing module 7, and the generative language model module 8, and is used to control the normal operation of each module;

[0126] The main control module 2 controls the operation of the entire system, manages permissions and implements communication between modules through message queues;

[0127] Scheduling and management: Use the SpringBoot framework to build the main control module 2, realize the communication and coordination between modules, and use the message queue RabbitMQ to realize asynchronous communication between modules;

[0128] Permission management: Use the role-based access control (RBAC) model to manage different permissions for users and administrators.

[0129] The innovation literacy assessment module 3 is connected to the main control module 2 and is used to assess the user's innovation literacy;

[0130] Innovation literacy assessment module 3 includes the questionnaire system LimeSurvey and the analytic hierarchy process AHP, which are used to assess the user's innovation literacy;

[0131] Questionnaire evaluation: Design a questionnaire that includes innovative thinking, problem-solving ability, and creative expression. Use the LimeSurvey tool to manage the questionnaire. The evaluation results are quantified through a scoring system and stored in a database.

[0132] Hierarchical analysis: Use the analytic hierarchy process (AHP) to comprehensively evaluate the questionnaire results and obtain the innovation literacy score;

[0133] Innovation Literacy Assessment Module 3 Assessment Method:

[0134] Through this module, users can evaluate their own innovative qualities, including innovative thinking, innovative methods, innovative ability, innovative attitude, etc., and give corresponding scores and suggestions.

[0135] Patent literacy assessment module 4, connected to main control module 2, for assessing the patent literacy of the user;

[0136] Patent literacy assessment module 4 includes an online testing system and fuzzy comprehensive evaluation method FCE, which are used to assess the patent literacy of users;

[0137] Knowledge test: Design online tests covering basic patent knowledge, patent application process, and intellectual property protection. Test results are automatically scored and stored in the database;

[0138] Evaluation algorithm: Use fuzzy comprehensive evaluation method to evaluate the test results and obtain patent literacy scores;

[0139] Patent Literacy Assessment Module 4 Assessment Method:

[0140] Through this module, users can evaluate their patent literacy, including patent knowledge, patent process, patent skills, patent awareness, etc., and give corresponding scores and suggestions; this module will test the user's patent literacy level through a series of patent-related questions, and give corresponding feedback and guidance; for example, this module will ask users the following questions:

[0141] What is the definition of a patent?

[0142] What are the types of patents?

[0143] What are the application conditions for a patent?

[0144] What is the patent application process?

[0145] What are the requirements for patent writing?

[0146] What are the methods for searching patents?

[0147] What are the analysis methods for patents?

[0148] What is the scope of protection of a patent?

[0149] How is patent infringement determined?

[0150] How is patent assignment and licensing performed?

[0151] Users can select or enter answers based on their knowledge and understanding. The module will give corresponding scores and suggestions based on the correctness and completeness of the answers, and provide learning and training resources on relevant patent knowledge and skills, such as patent teaching materials, patent cases, patent videos, etc., to help users improve their patent literacy.

[0152] The innovation consulting module 5 is connected to the main control module 2 and is used to provide innovation consulting services to users based on the evaluation results of their innovation literacy and their innovation needs and interests;

[0153] Innovation Consulting Module 5 uses the KNN algorithm matching system to provide personalized innovation consulting based on the user's innovation literacy assessment results; generates consulting content through the generative language model interface GPT-4

[0154] Matching algorithm: Based on the user's innovation literacy score and interest tags, the K nearest neighbor algorithm is used to match appropriate innovation consulting content;

[0155] Consulting services: Generate personalized innovation suggestions and guidance using generative language models; support multiple consulting methods such as text, voice, and video;

[0156] Innovation Consulting Module 5 Consulting Methods:

[0157] Through this module, users can provide themselves with innovation consulting services based on their innovation literacy assessment results, as well as their innovation needs and interests, including innovation theme recommendation, innovation point mining, innovation solution generation, innovation case display and other functions; this module will use the big data processing module 7 and the generative language model module 8 to provide users with the following services:

[0158] Innovation topic recommendation: This module will recommend some innovative topics to users based on their innovation interests and the platform's innovation data, such as technology, education, environmental protection, medical care, art, etc., as well as related sub-topics such as artificial intelligence, online education, renewable energy, telemedicine, digital art, etc., to help users find the innovation fields and directions they are interested in;

[0159] Innovation point mining: This module will mine some innovation points for users, such as problems, needs, opportunities, trends, challenges, etc., based on the innovation theme selected by the user and the innovation data of the platform, to help users find where and how they can innovate;

[0160] Innovative solution generation: This module will generate some innovative solutions for users, such as products, services, models, methods, concepts, etc., based on the innovation points selected by users and the innovation data of the platform, to help users form their own innovative ideas and solutions;

[0161] Innovation Case Display: This module will display some innovation cases for users based on the innovation solutions selected by users and the innovation data of the platform, such as innovation projects, innovative enterprises, innovative people, innovation awards, etc., to help users understand the feasibility, advantages, limitations, and improvements of their own innovation solutions;

[0162] Through this module, users can interact with the platform in a natural, fluent, intelligent and interesting way and obtain innovative consulting services, thereby improving their innovative thinking, innovative methods, innovative ability, innovative attitude and other aspects of their innovative qualities.

[0163] Patent consulting module 6, connected to main control module 2, for providing patent consulting services to users based on the patent literacy assessment results of users, as well as the patent needs and interests of users;

[0164] Patent consultation module 6 uses a collaborative filtering algorithm system to provide personalized patent consultation based on the user's patent literacy assessment results; it generates consultation content through a generative language model interface;

[0165] Matching algorithm: Based on the user's patent literacy score and patent needs, a collaborative filtering algorithm is used to recommend appropriate patent consulting content;

[0166] Consulting services: Generate personalized patent application guidance and intellectual property protection suggestions using generative language models, supporting text, voice, and video consultation methods;

[0167] Patent Consulting Module 6 Consulting Methods:

[0168] Through this module, users can provide themselves with patent consulting services based on their patent literacy assessment results, as well as their patent needs and interests, including patent topic recommendation, patent search, patent analysis, patent writing, patent application and other functions; this module will use the big data processing module 7 and the generative language model module 8 to provide users with the following services:

[0169] Patent topic recommendation: This module will recommend some patent topics such as electronics, machinery, chemical engineering, biology, software, etc., and related sub-topics such as smartphones, robots, nanomaterials, gene editing, artificial intelligence, etc. to users based on their patent interests and the platform's patent data, to help users find patent fields and directions of their interest;

[0170] Patent search: This module will search for relevant patent documents for users based on the patent keywords entered by users and the patent data of the platform, such as patent name, patent abstract, patent claims, patent specification, etc., and provide relevant patent information, such as patent number, patent application date, patent publication date, patent applicant, patent inventor, patent classification number, patent citation, etc., to help users understand the existing technology and technical level of their patent subject;

[0171] Patent analysis: This module will analyze some patent features for users based on the patent documents selected by users and the patent data of the platform, such as the patent's innovation, practicality, novelty, legality, value, risk, etc., and provide relevant patent suggestions, such as patent improvement points, patent optimization solutions, patent protection strategies, patent transformation paths, etc., to help users evaluate the feasibility, advantages, limitations, improvements, etc. of their own patent themes;

[0172] Patent writing: This module will write a patent document for the user based on the patent subject entered by the user and the patent data of the platform, including the patent name, patent abstract, patent claims, patent specification, etc., and provide relevant patent formats, such as patent fonts, font sizes, line spacing, page margins, headers, footers, charts, formulas, etc., to help users form their own patent documents;

[0173] Patent application: This module will apply for a patent for the user based on the patent documents generated by the user and the patent data of the platform, including selecting the patent type, filling in the patent application form, uploading the patent documents, paying patent fees, submitting patent applications, querying patent examinations, obtaining patent certificates, etc., and providing relevant patent guidance, such as patent application conditions, application procedures, application precautions, application common problems, etc., to help users complete their patent applications;

[0174] Through this module, users can interact with the platform in a natural, fluent, intelligent and interesting language and obtain patent consulting services, thereby improving their patent literacy in terms of patent knowledge, patent processes, patent skills, patent awareness and other aspects.

[0175] The big data processing module 7 is connected to the main control module 2 and is used to collect, store, process, analyze and mine various types of data on the platform;

[0176] Big data processing module 7 is responsible for collecting, storing, processing, analyzing and mining various data on the platform, including Apache Kafka, Hadoop HDFS, Apache Spark and cluster analysis technologies;

[0177] Data collection: Use Apache Kafka for real-time data collection;

[0178] Data storage: Use Hadoop HDFS to store big data;

[0179] Data processing and analysis: Use Apache Spark to process and analyze big data to extract useful information and patterns;

[0180] Data mining: Use data mining to discover user behavior patterns and interest trends;

[0181] Machine learning algorithms include cluster analysis and association rules;

[0182] like Figure 5 As shown, the processing method of the big data processing module 7 is:

[0183] This module is used to collect, store, process, analyze, and mine various types of data on the platform, including user data, innovation data, patent data, etc., and to provide data support and feedback for other modules. This module will use big data technologies such as cloud computing, distributed storage, data mining, machine learning, etc. to achieve the following functions:

[0184] S201. Data collection:

[0185] This module will collect various data, such as user registration information, login information, usage information, evaluation information, consultation information, feedback information, etc., as well as the theme, point, scheme, case, etc. of innovation, as well as patent literature, information, analysis, writing, application, etc., through the platform's webpage or mobile terminal, as well as other data sources, such as patent databases, innovation databases, social media, web crawlers, etc.;

[0186] S202, data storage:

[0187] This module will store the collected data through distributed storage systems, such as Hadoop and MongoDB, and perform operations such as backing up, compressing, and encrypting the data to ensure the security, integrity, and availability of the data;

[0188] S203, data processing:

[0189] This module will clean, convert, integrate, and standardize the stored data through data processing systems such as Spark and Storm to ensure the quality, consistency, and effectiveness of the data;

[0190] S204, Data Analysis:

[0191] This module will use data analysis systems such as Hive and Pig to perform statistics, aggregation, classification, clustering, association, regression and other operations on the processed data to extract data features, rules, patterns, trends, etc.

[0192] S205. Data mining:

[0193] This module will mine the analyzed data through data mining systems such as TensorFlow and PyTorch, and use machine learning, deep learning, natural language processing and other technologies to build data models, algorithms, applications, etc. to achieve intelligent, valuable and innovative data.

[0194] This module will provide data support and feedback to other modules according to their needs, such as providing user portraits for user registration and login module 1, providing evaluation data for innovation literacy assessment module 3 and patent literacy assessment module 4, providing consulting data for innovation consulting module 5 and patent consulting module 6, and providing language data for generative language model module 8, etc.

[0195] The generative language model module 8 is connected to the main control module 2 and is used to use the generative language model, such as GPT-4, to provide language generation, understanding, interaction, optimization and other functions for other modules, and to provide users with natural, fluent, intelligent and interesting language services;

[0196] Generative language model module 8 integrates OpenAI API, uses generative language models such as GPT-4 to provide language generation, understanding, interaction and optimization services, and uses the Transformer architecture and reinforcement learning algorithm PPO to improve the performance of the language model;

[0197] Model integration: Use OpenAI API to integrate the GPT-4 model to handle natural language generation and understanding tasks;

[0198] Language services: Provide text generation, dialogue, translation and other language services. Use the Transformer architecture to optimize the language model and improve the fluency and accuracy of language generation.

[0199] Interaction optimization: Combine user feedback and continuously optimize the interaction effect of the language model through reinforcement learning algorithms;

[0200] Generative Language Model Module 8 Application Method:

[0201] Language generation: This module will generate language content for users based on the needs of other modules and the data of the platform, such as innovation plans, patent writing, patent applications, etc., and provide relevant language formats, such as grammar, spelling, punctuation, paragraphs, titles, etc., to ensure that the language content is complete, correct and standardized;

[0202] Language understanding: This module will understand the user's language content based on the user's input and the platform's data, such as identifying the user's language type, language intention, language emotion, language needs, language interests, etc., and provide relevant language feedback, such as language response, language confirmation, language prompts, language guidance, etc., to ensure that the language content is clear, accurate and effective;

[0203] Language interaction: This module will interact with users based on their input and output, as well as platform data, such as establishing the user's language context, language relationship, language collaboration, language dialogue, etc., and provide relevant language strategies, such as language adaptation, language recommendation, language guidance, language motivation, etc., to ensure that the language content is coherent, fluent, friendly, and interesting;

[0204] Language optimization: This module will optimize the user's language content based on the user's input and output, as well as the platform's data, such as detecting the user's language errors, language defects, language redundancy, language deficiencies, etc., and provide relevant language suggestions, such as language modification, language improvement, language supplement, language evaluation, etc., to ensure the optimization, improvement, perfection and innovation of language content;

[0205] This module will provide language services to other modules according to their needs, such as providing language generation, understanding, interaction, optimization and other functions for the innovation consulting module 5 and the patent consulting module 6, providing users with natural, fluent, intelligent and interesting language services, thereby improving users' innovation and patent literacy;

[0206] Language optimization method:

[0207] This module will optimize the user's language content based on the user's input and output, as well as the platform's data, such as detecting the user's language errors, language defects, language redundancy, language deficiencies, etc., and provide relevant language suggestions, such as language modification, language improvement, language supplement, language evaluation, etc., to ensure the optimization, improvement, perfection and innovation of the language content.

[0208] Innovation Cultivation Module 9 is used to cultivate college students' innovation ability, including:

[0209] Guiding innovative ideas: Provide innovative ideas, innovative thinking methods and other aspects through generative language models to guide students to form innovative thinking habits.

[0210] Sharing of innovation cases: Integrate historical and current successful innovation cases and present them in the form of cases to facilitate students' intuitive understanding and absorption.

[0211] Innovative practice guidance: Use generative language models to answer questions students encounter in innovative practice and provide targeted guidance and suggestions.

[0212] like Figure 4 As shown, the present invention discloses a second implementation method: a method for using a college student innovation and patent literacy consulting service platform based on a large language model, comprising the following steps:

[0213] S101: Register and log in through the platform's webpage or mobile terminal, and set personal information and preferences, such as name, gender, age, school, major, innovation interests, patent interests, etc.; the platform will generate a personalized user profile for you based on your information and preferences, as well as an initial evaluation result of your innovation literacy and patent literacy, which will serve as the basis for your use of the platform;

[0214] S102: Through the Innovation Literacy Assessment Module 3 and Patent Literacy Assessment Module 4, you can assess your innovation literacy and patent literacy, including innovative thinking, innovative methods, innovative ability, innovative attitude, patent knowledge, patent process, patent skills, patent awareness, etc., and give corresponding scores and suggestions; you can test your innovation and patent literacy level by answering a series of innovation and patent-related questions, and obtain corresponding feedback and guidance;

[0215] S103: Through the innovation consultation module 5 and the patent consultation module 6, according to the evaluation results of their own innovation literacy and patent literacy, as well as their own innovation needs and interests, they can provide themselves with innovation and patent consulting services, including innovation theme recommendation, innovation point mining, innovation plan generation, innovation case display, patent theme recommendation, patent search, patent analysis, patent writing, patent application and other functions; users can obtain innovation and patent consulting services through natural, fluent, intelligent and interesting language interaction with the platform, thereby improving their own innovation and patent literacy;

[0216] S104: Use the feedback function of the platform to evaluate the platform's services, put forward opinions and suggestions, share your own innovations and patent achievements, and communicate and interact with other users.

[0217] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0218] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0219] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0220] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A consulting service platform for college students' innovation and patent literacy based on a large language model, characterized by: include: User registration and login module, used to collect and encrypt user information, complete user identity authentication, and store user information in the user database; The main control module is used to coordinate the workflow of each module and manage data interaction and signal transmission; The innovation literacy assessment module and the patent literacy assessment module are used to collect user data through questionnaires and tests respectively, and use the big data processing module and the generative language model module to perform data analysis to generate assessment reports on user innovation literacy and patent literacy; The innovation consulting module and patent consulting module are used to generate personalized suggestions and solutions based on the evaluation results and user needs using the generative language model, and feed back the consulting results to the user and store them in the user history records; Big data processing module, which is used to collect, store, process and analyze all data on the platform to support the normal operation of other modules; Generative language model module, which is used to provide language generation and understanding functions to optimize the user's interactive experience; The innovation training module is used to formulate personalized innovation training plans based on the user's evaluation results, provide online courses, practical projects and other resources to help users improve their innovation, and provide feedback on the training results to users, which are also stored in the user's history records; The system achieves collaborative work through efficient signal and data processing processes between modules, jointly promoting the improvement of college students' innovation and patent literacy.

2. The college students' innovation and patent literacy consulting service platform based on a large language model according to claim 1 is characterized by: The user registration and login module is responsible for user registration and login, including OAuth2.0 authentication service and user information database; Registration and login use OAuth2.0 protocol for security authentication, supporting multiple login methods, including email registration and social media login. User information is stored in an encrypted database, and passwords are encrypted using SHA-256 algorithm. User information and preferences: Users fill in personal information and preferences and submit data through forms; data is stored in a relational database.

3. The college students' innovation and patent literacy consulting service platform based on a large language model according to claim 1 is characterized by: The main control module controls the operation of the entire system, manages permissions and implements communication between modules through message queues; Scheduling and management: Use the SpringBoot framework to build the main control module, implement communication and coordination between modules, and use the message queue RabbitMQ to implement asynchronous communication between modules; Permission management: Use the role-based access control (RBAC) model to manage different permissions for users and administrators.

4. The college student innovation and patent literacy consulting service platform based on a large language model according to claim 1 is characterized by: The innovation literacy assessment module includes a questionnaire system LimeSurvey and a hierarchical analysis method AHP, which are used to assess the user's innovation literacy; Questionnaire evaluation: Design a questionnaire that includes innovative thinking, problem-solving ability, and creative expression. Use the LimeSurvey tool to manage the questionnaire. The evaluation results are quantified through a scoring system and stored in a database. Hierarchical analysis: The analytic hierarchy process (AHP) was used to comprehensively evaluate the questionnaire results and obtain the innovation literacy score.

5. The college student innovation and patent literacy consulting service platform based on a large language model according to claim 1 is characterized by: The patent literacy assessment module includes an online testing system and a fuzzy comprehensive evaluation method FCE, which are used to assess the patent literacy of users; Knowledge test: Design online tests covering basic patent knowledge, patent application process, and intellectual property protection. Test results are automatically scored and stored in the database; Evaluation algorithm: Use fuzzy comprehensive evaluation method to evaluate the test results and obtain the patent literacy score.

6. The college student innovation and patent literacy consulting service platform based on a large language model according to claim 1 is characterized by: The innovation consulting module uses the KNN algorithm matching system to provide personalized innovation consulting based on the user's innovation literacy assessment results; the consulting content is generated through the generative language model interface GPT-4 Matching algorithm: Based on the user's innovation literacy score and interest tags, the K nearest neighbor algorithm is used to match appropriate innovation consulting content; Consulting services: Generate personalized innovation recommendations and guidance using generative language models; Supports multiple consultation methods such as text, voice, and video.

7. The college student innovation and patent literacy consulting service platform based on a large language model according to claim 1 is characterized by: The patent consultation module uses a collaborative filtering algorithm system to provide personalized patent consultation based on the user's patent literacy assessment results; and generates consultation content through a generative language model interface; Matching algorithm: Based on the user's patent literacy score and patent needs, a collaborative filtering algorithm is used to recommend appropriate patent consulting content; Consulting services: Generate personalized patent application guidance and intellectual property protection suggestions using generative language models, supporting multiple consultation methods such as text, voice, and video.

8. The college student innovation and patent literacy consulting service platform based on a large language model according to claim 1 is characterized by: The big data processing module is responsible for collecting, storing, processing, analyzing and mining various types of data on the platform, including Apache Kafka, Hadoop HDFS, Apache Spark and cluster analysis technology; Data collection: Use Apache Kafka for real-time data collection; Data storage: Use Hadoop HDFS to store big data; Data processing and analysis: Use Apache Spark to process and analyze big data to extract useful information and patterns; Data mining: Use data mining to discover user behavior patterns and interest trends; Machine learning algorithms include cluster analysis and association rules.

9. The college student innovation and patent literacy consulting service platform based on a large language model according to claim 1 is characterized by: The generative language model module integrates OpenAI API, uses GPT-4 generative language model to provide language generation, understanding, interaction and optimization services, and uses Transformer architecture and reinforcement learning algorithm PPO to improve the performance of the language model; Model integration: Use OpenAI API to integrate the GPT-4 model to handle natural language generation and understanding tasks; Language services: Provide text generation, dialogue, translation and other language services. Use the Transformer architecture to optimize the language model and improve the fluency and accuracy of language generation. Interaction optimization: Combined with user feedback, the interaction effect of the language model is continuously optimized through reinforcement learning algorithms.

10. The college student innovation and patent literacy consulting service platform based on a large language model according to claim 1 is characterized in that: The innovation training module specifically includes: Guidance on innovative concepts: Provide content on innovative concepts and innovative thinking methods through generative language models to guide students to form innovative thinking habits. Sharing of innovation cases: Integrate historical and current successful innovation cases and present them in the form of cases to facilitate students' intuitive understanding and absorption. Innovative practice guidance: Use generative language models to answer questions students encounter in innovative practice and provide targeted guidance and suggestions.