关于「AI 销售智能体何时交给人:吉廷斯指数与增量排序」,《成交对话、异议与人机交接》给出的定量结论是什么?
结论:第五章用吉廷斯指数在广告来源之间分配人工时间(新来源的探索奖励 +0.102),并发现按「最热」交接只用上人工潜力的 55%。
数据口径:书中的先验、回答概率、成交率、退款率与成本均为示意或合成模型;全部数据由书中程序生成;本书不是法律意见,也不提供任何操纵买家的话术。 书中以标注框区分已发表的证据、可运行的 Python 计算(16 段程序)、原典与作者的假说。
对照数据表
下表数字由本章 Python 程序原样打印,可重新运行复现。 程序只用 Python 标准库与结论吻合的打印值: 0.102
| source history | mean | Gittins index | exploration bonus |
|---|---|---|---|
| new (1 of 5) | 0.200 | 0.302 | +0.102 |
| 2 of 10 | 0.200 | 0.257 | +0.057 |
| 4 of 20 | 0.200 | 0.230 | +0.030 |
| 10 of 50 | 0.200 | 0.213 | +0.013 |
| 3 of 10 | 0.300 | 0.365 | +0.065 |
| 6 of 40 | 0.150 | 0.164 | +0.014 |
查看完整验算程序
# Chapter 5. p09: Gittins indices for routing scarce human time. Leads come
# from several sources (campaigns, channels); each source has an unknown
# rate at which an escalated lead closes with a human closer. Each
# escalation is one pull of a Bernoulli arm with a Beta(a, b) posterior;
# rewards are discounted by 0.9 per escalation. The Gittins index is the
# retirement reward per step that makes stopping and continuing equally
# good (calibration by bisection, value iteration truncated at depth 80).
from functools import lru_cache
BETA, DEPTH = 0.9, 80
def index(a, b):
lo, hi = 0.0, 1.0
for _ in range(30):
lam = (lo + hi) / 2
ret = lam / (1 - BETA)
@lru_cache(maxsize=None)
def V(x, y):
p = x / (x + y)
if x + y - a - b >= DEPTH:
return max(ret, p / (1 - BETA))
go = p * (1 + BETA * V(x + 1, y)) + (1 - p) * BETA * V(x, y + 1)
return max(ret, go)
p = a / (a + b)
go = p * (1 + BETA * V(a + 1, b)) + (1 - p) * BETA * V(a, b + 1)
if go > ret + 1e-12:
lo = lam
else:
hi = lam
return (lo + hi) / 2
if __name__ == "__main__":
print(" source history mean Gittins index exploration bonus")
for a, b, label in ((1, 4, "new (1 of 5)"), (2, 8, "2 of 10"),
(4, 16, "4 of 20"), (10, 40, "10 of 50"),
(3, 7, "3 of 10"), (6, 34, "6 of 40")):
g = index(a, b)
m = a / (a + b)
print(" {:<16} {:5.3f} {:13.3f} {:+.3f}".format(
label, m, g, g - m))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《对话式成交自动机、异议消解信息增益与高客单销售动力学》第 5 章「AI 销售智能体何时交给人:吉廷斯指数与增量排序」(版本 1.0.0). 5D Library. https://doi.org/10.5281/zenodo.24090221
DOI: 10.5281/zenodo.24090221 · 阅读本章所在专著 · 5DL-B-084 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026084,
author = {Fan, Yafu},
title = {Conversational Closing Automata, Objection-Handling Information Gain and High-Ticket Sales Kinetics},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
doi = {10.5281/zenodo.24090221},
url = {https://doi.org/10.5281/zenodo.24090221}
}