钟小波
Character Mentor for Ages 0-3
Based on the child's age (0-3 years), using the emotional guidance method, it provides parents and early childhood educators with scientific, specific, and actionable character word teaching plans, helping children naturally acquire core virtues such as patience, bravery, sharing, and perseverance in everyday situations.
Proposal,Midterm,Defense PPT
An AI presentation generation system designed specifically for thesis defense/report defense scenarios—converts academic documents such as papers, research reports, and proposal reports into native editable PowerPoint. Strictly follows the 7x7 rule (≤7 lines per page, ≤7 words per line), adopts standard academic defense structure, outputs real DrawingML shapes instead of images, supports formula rendering, data charts, and animation transitions.
Technical Roadmap Generator
Upload papers or research materials to automatically read, understand, and extract research logic, generating academic-standard technical roadmap diagrams (HTML/SVG vector graphics). It supports six major discipline categories, five layout styles, special element annotation, and quality self-checks.
AI Job Search Assistant
Full-stack job search assistant covering the complete closed loop from profile creation, job search, fit assessment, CV/cover letter customization, interview preparation, to result tracking. Based on the AFP architecture, it employs a draft-review dual-agent adversarial mechanism, with built-in honesty guardrails (no fabricated skills/experience), ATS keyword compliance checks, relevance-weighted CV trimming, and supports back-calibrating the evaluation framework from actual application outcomes.
Stock Investment Advisor
An AI stock investment analysis advisor based on a five-dimensional analysis framework (fundamentals, capital flow, technicals, sentiment, and news). Supports A-shares, Hong Kong stocks, and US stocks. Provides multi-dimensional cross-validation, risk warnings, and comprehensive assessment reports.
Expert Productization Workflow
End-to-end process for productizing professional experience and turning it into personal IP content and skill delivery: demand trust diagnosis → IP anchor → minimum viable distributable product → content master draft → multi-platform tailoring → distribution skill configuration → launch verification → optional visual output. Suitable for experts such as lawyers, consultants, teachers, researchers, etc. who want to turn their professional capabilities into content, products, skills, and monetization paths.
Speech Coach
From scene analysis, script construction to voice and body optimization, an all-in-one speech coach.
Lesson Prep Script V1.0
Helps instructors/knowledge IPs directly turn lesson preparation topics into a ready-to-use 30-minute spoken-word script—just pick it up and read, not secondary prompts. What it solves Traditional lesson preparation requires instructors to go through "ideation → break into modules → write script → mark pacing → design interactions", which is time-consuming and easy to miss details. This Skill compresses this process into a 5-step interaction. Instructors only need to provide the topic and key knowledge points, and the rest is automated. Core capabilities ① Five-step structured interaction: Select lesson type → Receive preparation content → Deep analysis with option presentation → Ask for style preference → Directly generate a complete spoken-word script. Each step waits for user confirmation before proceeding. ② CXO three-dimensional teaching verification: Each module is annotated with teaching dimensions — C (Content/Knowledge), X (Experience/Practice), O (Objective/Output), ensuring full coverage throughout. ③ Spoken-word script template: Each segment follows the framework of Hook → Key Point → Structure → Call to Action. The structure supports four modes: reason, method, situation/reaction, and chronological order. ④ Complete output includes: 7 modules totaling approximately 7,900 words of spoken text + tone cues (【Pause 2 seconds】【Emphasis】) + audience interaction instructions + CXO paragraph annotations + full statistics. ⑤ Seven-dimensional quality check: Word count deviation / Spoken style / Template completeness / CXO coverage / Logical coherence / Pacing / Reusability — each dimension is checked, and if any fails, it is corrected and regenerated.
Grant Proposal Review PRO V2.0
🎯 Core Functionality Overview This is an intelligent review and optimization system specially designed for national social science, education ministry, and provincial grant applications. It simulates the thinking mode of a senior review expert with 15 years of experience, ensuring academic rigor and competitiveness through three core mechanisms. 🔧 Three Core Mechanisms 1️⃣ 12-Step Structured Methodology Covers the full lifecycle of grant proposal review: Phase 1-3: Basic Diagnosis - In-depth analysis of announcement (funding priorities, review criteria, application requirements) - Cross-disciplinary type judgment (precise identification of 8 types) - Research GAP five-dimension identification (theory/methodology/empirical/policy/technology) Phase 4-7: Core Element Review - Research question TMAQ model analysis (theory/methodology/approach/question four dimensions) - Research objective SMART principle test - Research content framework completeness assessment - Research approach type matching (6 types) Phase 8-10: Deep Quality Enhancement - Precise extraction of key difficulties (distinguish criteria + breakthrough paths) - Innovation point seven-dimension mining - Feasibility seven-dimension argumentation Phase 11-12: Overall Optimization - Nine-dimension quality check (academic rigor, innovativeness, feasibility, etc.) - Comprehensive optimization suggestions and final report 2️⃣ Dual-Core Adversarial Mechanism (Builder vs Supervisor) Working Principle: - Builder (academic writer): Generates optimization plans based on user materials - Supervisor (top journal reviewer): Challenges Builder's plans with the strictest standards - Adversarial iteration: 3 rounds of confrontation to ensure plans are robust Application Scenarios: - Innovation point mining: Builder proposes innovation points → Supervisor questions novelty → iterative optimization - Feasibility argumentation: Builder designs plan → Supervisor challenges feasibility → supplementary argumentation - Literature citation: Builder cites literature → Supervisor verifies authenticity → ensure academic standards 3️⃣ Literature Authenticity Verification Mechanism Two working modes: Mode A: Placeholder Mode (Default) - Use markers like [Literature Placeholder-001] in place of specific references - Output a Literature Requirement List specifying search requirements for each placeholder - User searches and fills in real references Mode B: Real-Time Verification Mode - Call Google Scholar to verify literature authenticity in real time - Generate Literature Verification Report (authenticity/relevance/authority scores) - Ensure every citation is traceable Preventing AI Hallucination: - Prohibits fabricating authors, journals, DOIs - All references must be verified or marked as placeholders - Guarantees academic integrity bottom line 💡 Core Value and Applicable Scenarios ✅ Key Pain Points Addressed 1. Academic sloppiness: AI-generated content often includes fake references, logical gaps 2. Insufficient innovation: Difficulty uncovering true academic innovation points 3. Weak feasibility: Research plans lack systematic argumentation 4. Cross-disciplinary difficulty: Interdisciplinary topics often fall between two stools 🎓 Target Users - University faculty (social sciences, education, humanities) - Researchers (applying for national and provincial grants) - Academic teams (needing systematic review processes) 📋 Typical Workflow 1. Input: Upload announcement + proposal draft 2. Review: System executes 12-step structured analysis 3. Adversarial: Dual-core mechanism iteratively optimizes key sections 4. Verification: Literature authenticity check 5. Output: Complete review report + optimization suggestions + literature list 🔍 Differences from Traditional Review | Dimension | Traditional Human Review | Expert Review System | |-----------|------------------------|----------------------| | Review depth | Depends on personal experience | 12-step structured + 9D QC | | Academic rigor | Hard to fully audit | Literature verification + dual-core adversarial | | Innovation mining | Subjective judgment | 7-dimension systematic analysis | | Feasibility argumentation | Experience-driven | 7-dimension item-by-item argumentation | | Consistency | Varies by individual | Standardized process | | Efficiency | Days to weeks | 1-2 hours for initial review | The core advantage of this system is: it makes the tacit knowledge of a 15-year senior review expert explicit, structured, and replicable, enabling every user to receive top-level expert review services.
一、研究意义
(一)理论意义
新质生产力作为马克思主义生产力理论在新时代的创新发展,为理解数字经济时代的生产力跃迁提供了新的理论框架。本研究从统计学视角切入,具有三方面理论价值:
第一,拓展新质生产力的测度理论。现有研究多停留在概念阐释与定性分析层面,本研究通过构建多维统计测度指标体系,将抽象的理论概念转化为可操作的量化工具,为新质生产力的实证研究提供方法论支撑。这一转化不仅回应了"如何测度新质生产力"这一基础性理论问题,也为后续跨区域比较研究奠定基础。
第二,深化产业新赛道对全要素生产率影响的机制研究。已有研究证实了技术创新与经济增长的正向关系,但对人工智能、低空经济等新兴产业如何通过技术溢出、产业关联、就业创造等路径影响TFP的内在机制,尚缺乏系统的实证检验。本研究运用机器学习算法识别非线性作用机制,突破传统线性回归模型的局限,为生产率理论研究提供新的分析工具。
第三,推动跨学科理论整合。本研究将统计学的测度方法、经济学的生产率理论、体育科学的技术应用场景有机结合,构建"理论框架-测度工具-典型场景-实证评估"的系统分析范式,为跨学科交叉研究提供可复制的理论模型。
(二)实践意义
本研究对广州乃至粤港澳大湾区的产业政策制定具有直接的实践价值:
第一,为区域产业布局提供决策依据。通过实证评估人工智能、低空经济对TFP的贡献度,识别高潜力产业新赛道,帮助政府部门优化资源配置,避免盲目投资与重复建设。研究结果可为广州市"产业科技创新"行动计划、"制造业当家"战略的实施路径提供量化支撑。
第二,推动科技与体育产业深度融合。以AI大模型在竞技体育训练监测、低空经济在无人机竞速等典型场景为切入点,探索科技赋能传统产业的创新路径,为广州打造"科技+体育"融合发展示范区提供实践样本。这一探索对于激活体育产业新动能、培育消费新增长点具有示范意义。
第三,服务粤港澳大湾区协同创新。广州作为大湾区核心引擎城市,其产业新赛道发展经验可为深圳、珠海等城市提供参考,研究成果有助于推动区域产业协同布局,形成"广州研发+周边制造+全域应用"的产业生态。
二、文献综述
(一)新质生产力的理论内涵与测度研究
新质生产力概念自提出以来,学术界围绕其理论内涵展开了广泛讨论。【文献1】【待补充】关于新质生产力理论内涵的研究(建议搜索关键词:新质生产力、理论内涵、生产力跃迁)从马克思主义政治经济学视角,将新质生产力界定为以科技创新为核心驱动、以数字技术为关键要素、以绿色低碳为发展方向的先进生产力形态。【文献2】【待补充】关于新质生产力特征的研究(建议搜索关键词:新质生产力、特征、创新驱动)进一步提炼出创新性、融合性、可持续性三大核心特征。
在测度方法方面,现有研究主要采用两类路径:一是基于投入产出的综合评价法,【文献3】【待补充】关于新质生产力评价指标体系的研究(建议搜索关键词:新质生产力、指标体系、综合评价)构建了涵盖创新投入、数字基础设施、绿色转型等维度的评价体系,运用层次分析法确定权重;二是基于生产函数的计量分析法,【文献4】【待补充】关于新质生产力对经济增长影响的研究(建议搜索关键词:新质生产力、经济增长、实证分析)通过扩展索洛模型,将新质生产力纳入生产函数进行实证检验。
然而,现有测度研究存在两方面不足:其一,指标体系多基于传统统计框架,对人工智能、低空经济等新兴产业的特征指标纳入不足;其二,测度方法以线性模型为主,难以捕捉新质生产力对经济系统的非线性、动态影响。
(二)人工智能对区域经济增长的影响研究
人工智能作为新一轮科技革命的核心技术,其经济效应受到广泛关注。【文献5】【待补充】关于人工智能对全要素生产率影响的研究(建议搜索关键词:人工智能、全要素生产率、技术溢出)基于省级面板数据,证实人工智能通过技术溢出效应显著提升TFP,且这一效应在东部地区更为明显。【文献6】【待补充】关于人工智能产业集聚效应的研究(建议搜索关键词:人工智能、产业集聚、区域经济)发现产业集聚度每提升1个百分点,区域创新产出增加0.8个百分点。
在应用场景研究方面,【文献7】【待补充】关于AI在体育训练中的应用研究(建议搜索关键词:人工智能、体育训练、可穿戴设备)探讨了AI大模型、可穿戴设备在运动员训练监测、伤病预防中的技术路径,但研究多聚焦技术层面,缺乏从产业经济视角评估其对体育产业TFP的贡献。
(三)低空经济的产业发展与应用研究
Proposal Writing & Polish v1.1
Project proposal review and polish expert system. Dual-core adversarial engine real-time checking, literature review mechanism to prevent fabricated citations, three-stage workflow (creation → diagnosis → polish).
一、优化概览
针对《广州新质生产力发展中人工智能等产业新赛道的多维度研究——基于体育科技与统计测度的双重视角》课题申报书，基于课题申报书评审专家的专业评审意见，已完成5大关键优化，解决了评审中发现的6个核心问题。
二、已完成的关键优化
✅ 优化1：文献综述部分——处理文献真实性风险（🔴 致命问题）
原问题：文献综述引用了多篇文献（如"刘伟等（2024）"、"张军扩（2024）"、"Chen et al., 2023"等），但信息不完整，缺少期刊名称、卷期页码，部分文献真实性存疑。
优化措施：
- 删除了所有无法核实的具体作者和年份
- 改为描述性表述："近期有学者..."、"部分研究..."
- 添加明确标注：【待补充：相关领域2020-2025年代表性文献完整引用信息】
- 提醒申请人在正式提交前补充完整文献信息
优化效果：彻底消除了文献虚构风险，避免评审专家的"一票否决"。
✅ 优化2：研究内容部分——强化三条主线的整合逻辑（🟡 重要问题）
原问题：三个研究内容（新质生产力测度、AI训练监测、低空经济产业布局）之间的内在逻辑联系不够紧密，给人"拼盘式"研究的印象。
优化措施： 在"研究内容与方案"开头新增研究整体设计说明段落：
本研究采用"宏观测度-中观应用-微观验证"的三层递进结构，三条研究主线相互支撑、逻辑贯通：研究内容1从宏观层面构建新质生产力的测度体系，识别人工智能等新兴产业对区域经济的拉动机制，为广州产业政策提供量化依据；研究内容2选取竞技体育这一典型垂直场景，验证AI技术作为新质生产力代表的实际应用效果，形成可复制的技术方案；研究内容3聚焦低空经济这一新兴产业形态，探索其在体育领域的产业化路径，为新质生产力的产业落地提供实践样本。三者共同构成"理论测度-技术应用-产业布局"的完整研究链条，既有理论深度，又有实践落地，既服务宏观决策，又提供微观解决方案。
优化效果：明确了三条主线的逻辑关系和研究价值，避免"拼盘研究"印象。
Grant Proposal Reviewer v2.0
A project proposal review expert system built on a super prompt architecture. It supports types such as the National Natural Science Foundation, National Social Science Fund, and provincial and ministerial research projects. Equipped with a built-in dual-core review engine (dual evaluation of academic value and feasibility), multi-dimensional scoring system, problem diagnosis and improvement suggestions, and academic norm checking, it simulates the real expert review process to help applicants identify issues and improve quality before submission.