# 老军AI玩短视频 (@882306432) on xiaohongshu

- id: koinon:creator:xiaohongshu_882306432
- url: https://koinonlink.com/kol/xiaohongshu/882306432
- schema_version: 1.3

## Identity
- platform: xiaohongshu
- handle: 882306432
- platform_url: https://www.xiaohongshu.com/user/profile/5f6b2bea00000000010063ea
- website: xhsdiscover://message/userPublicGroupList?user_id=5f6b2bea00000000010063ea&username=TA
- country: China
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 17300
- posts_observed: 5
- verified: false
- size_tier: koc

## Engagement
- status: peak_post_only
- peak_post_engagement_rate: 2.13035
- best_post_interactions: 36855
- measurement_source: cn_posts_max
- measurement_formula: likes + comments + shares (douyin) or likes + comments + collects (xiaohongshu), max over observed posts
- comparable_pool: peak_interactions
- status_note: We have only the single best observed post, so no mean exists. peak_post_engagement_rate is an UPPER BOUND, systematically higher than an average — never compare it against an average rate.
- unit_note: engagement_rate and peak_post_engagement_rate are ratios (0-1); avg_interactions_per_post and best_post_interactions are absolute counts. Read status before reading any number: a null rate has several different causes and status says which one applies here.

## Content
- category: software
- subcategory: ai_tools
- category_confidence: 0.9
- category_source: derived_from_recent_content
- topics: Codex安装与使用教程, AI做PPT与职场效率, AI辅助外贸获客, 用Codex无代码开发软件/系统, 提示词与Skill优化技巧
- bio: ☸️惠州本地的80后大叔，不会写代码也能做软件
🔯23年All in AI，分享AI实战案例与技巧
☮️用AI做工厂系统、用AI提高牛马工作效率
✡️拒绝白嫖

## Audience (inferred)
- status: present
- description: foreign trade professionals, career newcomers, and doers who want to leverage AI without coding, primarily using tools like Codex for creating presentations, building systems, and acquiring customers
- roles: automation
- seniority: practitioner
- pain_points: Codex is hard to use effectively, unsure of good prompts and practical skills, Want to use AI for foreign trade lead generation but lack actionable strategies, Spending too much time on PPTs and want to quickly generate high-quality, compelling versions, Want low-cost ERP or management systems but don’t know how to code
- posts_analysed: 44
- confidence: 0.75

## Commercial (inferred)
- audience_buyer_fit: 0.8
- promotion_intent: 0.9
- open_to_collaboration: false
- contact: Koinon does not publish creator contact details.

## Quality signals
- authenticity_score: 70
- authenticity_basis: engagement_observed
- credibility_score: 55
- flagged_for_review: false
- koinon_bd_grade: A — measures Koinon partner-outreach fit, not creator quality
- interpretation: Signals for triage, not verdicts. A flag means the profile is worth a manual check.

## Evidence
- [xiaohongshu_882306432#8efd55c4] deepseek做PPT / deepseek+Kimi快速生成高质量PPT#deepseek[话题]# #deepseek做PPT[话题]# #deepseek应用[话题]# #kimi[话题]# / AI让你的PPT会说话 / deepseek的浪潮下，AI各种用法，你会让PPT说话吗？#deepseek[话题]# #AI[话题]# #职场[话题]# #PPT[话题]# #PPT会说话[话题]# / Claude Code 和 Codex 谁更适合小白 / 我把同一个需求，分别交给 Claude Code 和 Code (https://www.xiaohongshu.com/user/profile/5f6b2bea00000000010063ea)
- [xiaohongshu_882306432#90d88ddc] 不讲复杂参数，直接看两个AI做出来的实际成品。哪个更适合不懂编程的小白？
- [xiaohongshu_882306432#6608ac82] #ClaudeCode[ / 给哈尔滨粉丝配了一台拿到就能用的 AI 主机 / 之前帮哈尔滨的一位粉丝淘了一台 Mac mini，这次我把电脑、Codex、龙虾等常用的 AI 应用全部安装调试好。
- [xiaohongshu_882306432#68cb359c] 还专门给他配了一块非常小巧的便携显示屏，一根线连接 Mac mini 就能使用，不 / 帮粉丝淘台 Macmini，我跑进了深圳龙岗出租 / 一位哈尔滨的粉丝让我买台 Mac mini并部署好AI 给他开机即用。 #Macmini[话题]#  #苹果电脑[话题]#  #AI工具[话题]#  #codex安装[话题]#  #粉丝故事[话题]# / MacBook Air 太难用 / 小白玩ai用苹果系统还是windows #codex[话题]# #vibecoding[话题]# #codex安装[话题]# #macbook[话题]# #开学季笔记本电脑怎么

## Provenance
Every inferred field below carries how it was produced. Facts stay facts; inferences stay inferences.

- audience.description: source_type=ai_inferred, confidence=0.75, freshness_days=34, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.75, freshness_days=34, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.75, freshness_days=34, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=0, method=llm_scorer — Relative signal within Koinon indexing, not a market-wide score.
- commercial.promotion_intent: source_type=ai_inferred, confidence=0.6, freshness_days=0, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=51, method=profile_snapshot_and_engagement_ratio_heuristic — Means "worth a manual check", NOT confirmed fraud. Flags can be wrong and are not a verdict about the person.
- quality.authenticity_score: source_type=heuristic, confidence=0.5, freshness_days=0, method=Starts at 60; interactions-per-follower on collected posts then adds or subtracts (large following with near-zero engagement is penalised heavily). — The input set differs by platform; do not compare this score across platforms.
- quality.koinon_bd_grade: source_type=ai_inferred, confidence=0.5, freshness_days=51, method=llm_partner_fit_classifier + authenticity >= 55 AND fit_score >= 0.45 => A; authenticity >= 40 AND fit_score >= 0.3 => B; else C. authenticity < 30 or a promotional-pattern flag => quarantine. — Koinon partner-outreach fit, not creator quality.
- reach.followers: source_type=observed, confidence=0.95, freshness_days=51, method=platform_profile

## Freshness
- profile_checked_days_ago: 51
- content_analysed_days_ago: 0
- audience_updated_days_ago: 34

## AI retrieval
- indexing_requests: 1
- user_triggered_requests: 0
- note: Being indexed in bulk is not the same as being retrieved to answer a question.

## This profile
- Claim or correct: https://koinonlink.com/claim?k=xiaohongshu_882306432
- Request removal: https://koinonlink.com/claim?k=xiaohongshu_882306432
- Terms: https://koinonlink.com/for-ai