从提示到推荐：AI搜索中品牌可见性的拟合阶段模型
From Prompt to Recommendation: A Fitted Stage Model of Brand Visibility in AI Search
浏览论文内容
中文总结 AI 辅助
本研究通过分析34,960条提示观测数据，提出拟合阶段模型，揭示自有域名曝光和品牌扇出对AI搜索中品牌提及率的显著影响，并验证了模型的高预测性能。
中文摘要 AI 辅助
我们分析了来自75个匿名Aiso项目的34,960条无品牌提示工程观测数据，覆盖2,854个不同的受监控提示，以及2026年6月至9月期间重复的GPT和Gemini运行。当目标品牌及其自有域名均未出现在可观测的实时检索路径中时，GPT的目标提及率为2.8%，Gemini为3.8%。当存在自有域名引用但无品牌扇出时，提及率分别上升至49.0%和58.4%。当自有域名曝光和品牌扇出同时发生时，提及率达到91.4%和100%。在重复运行中，同一项目、提示和引擎内该关系持续存在：在品牌扇出缺失的情况下，提示单元中自有域名曝光的变化与GPT上平均提及率增加40.2个百分点、Gemini上增加49.0个百分点相关。先前的可见性独立地具有持续性。先前未提及且当前无自有域名曝光时，下一轮提及率为1.6%和1.9%；先前提及且当前有曝光时，提及率为80.5%和83.7%。我们使用先前运行历史和同期检索指标拟合了一个时间顺序诊断模型：$ \operatorname{logit}P(M_t=1)=\alpha_e+\beta_e\operatorname{logit}(\widetilde P_{t-1})+\gamma_e E_t+\delta_e F_t+\theta_e^\top X. $ 在最新的30%留出集上，完整模型在GPT上达到AUC 0.963，在Gemini上达到0.942，而仅使用先前历史的AUC为0.937/0.917，仅使用实时信号的AUC为0.880/0.840。人工策划的提示敏感性给出了几乎相同的AUC（0.960和0.943）。一个单独的199提示页面语料验证发现，提示-页面匹配预测Gemini曝光（AUC 0.641）比GPT曝光（0.545）更清晰，将相关性置于更大的引擎中介曝光效应上游。该方程是预测性和观测性的，而非对专有引擎内部机制的因果描述。
英文摘要
We analyze 34,960 unbranded prompt-engine observations from 75 anonymized Aiso projects, covering 2,854 distinct monitored prompts and repeated GPT and Gemini runs from June-September 2026. When neither the target brand nor its own domain appears in the observable live retrieval path, target mention rates are 2.8% for GPT and 3.8% for Gemini. With an own-domain citation but no branded fan-out, they rise to 49.0% and 58.4%. When both own-domain exposure and a branded fan-out occur, mention rates reach 91.4% and 100%. The relationship persists within the same project, prompt, and engine across repeated runs: among prompt cells that vary in own-domain exposure while holding branded fan-out absent, exposure is associated with a mean mention-rate increase of 40.2 percentage points on GPT and 49.0 points on Gemini. Prior visibility is independently persistent. A previous non-mention plus no current own-domain exposure yields next-run mention rates of 1.6% and 1.9%; previous mention plus current exposure yields 80.5% and 83.7%. We fit a chronological diagnostic model using prior-run history and contemporaneous retrieval indicators: $ \operatorname{logit}P(M_t=1)=α_e+β_e\operatorname{logit}(\widetilde P_{t-1})+γ_e E_t+δ_e F_t+θ_e^\top X. $ On the latest 30% holdout, the full model achieves AUC 0.963 on GPT and 0.942 on Gemini, compared with 0.937/0.917 for prior history alone and 0.880/0.840 for live signals alone. A manually curated prompt sensitivity gives nearly identical AUCs (0.960 and 0.943). A separate 199-prompt page-corpus validation finds that prompt-page match predicts Gemini exposure (AUC 0.641) more clearly than GPT exposure (0.545), placing relevance upstream of a larger engine-mediated exposure effect. The equation is predictive and observational, not a causal description of proprietary engine internals.
发表机构
- Aiso Boost Ltd.（Aiso Boost有限公司）
机构由 AI 辅助整理，请以论文原文为准。
