关于「三因子相乘:相关性、距离与知名度的乘积结构」,《地图排名与同城承接》给出的定量结论是什么?

结论:第一、二章讲三因子的乘积结构、赫夫引力与距离衰减,以及 5 × 5 方格名次图的读法与扫描噪声。

数据口径:本书把三因子写成乘积式示意打分,全部权重都是示意参数,不是谷歌真实权重:一家距离两公里、类目登记错误的示意门店,要靠评论追平改对主类目的效果,需要 8,511 条评论。 书中参数为示意,全部计算由书中程序生成。

English version

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

A. own Huff share by distance and attractiveness S
  d km   S=100    S=200    S=400
   0.5  0.6221   0.7671   0.8682
   1.0  0.2916   0.4515   0.6221
   1.5  0.1547   0.2679   0.4226
   2.0  0.0933   0.1707   0.2916
   3.0  0.0437   0.0838   0.1547
   4.0  0.0251   0.0489   0.0933
B. S multiplier that offsets a longer distance
  distance x1.5: S x 2.25
  distance x2.0: S x 4.00
  distance x3.0: S x 9.00
C. same question under exp(-d / d0), d0 = 1.5 km
  +0.5 km: S x 1.396
  +1.0 km: S x 1.948
  +2.0 km: S x 3.794
查看完整验算程序
# Chapter 1. p11: Huff gravity shares, distance against attractiveness.
# Model (Huff 1963): a searcher at the origin picks store j with
# probability S_j^alpha / T_j^beta, normalised over all stores.
# S is an attractiveness index, T the distance in km. alpha = 1 and
# beta = 2 are illustrative, not estimates for any real market and
# not Google weights. Three rival stores sit at 1.0, 1.5 and 2.5 km.
import math

ALPHA, BETA = 1.0, 2.0
RIVALS = [(100.0, 1.0), (300.0, 1.5), (60.0, 2.5)]


def huff_share(s_own, d_own, rivals=RIVALS, a=ALPHA, b=BETA):
    own = s_own ** a / d_own ** b
    rest = [s ** a / d ** b for s, d in rivals]
    return own / math.fsum([own] + rest)


def offset_multiplier(dist_ratio, a=ALPHA, b=BETA):
    # attractiveness factor that exactly offsets a distance ratio
    return dist_ratio ** (b / a)


if __name__ == "__main__":
    print("A. own Huff share by distance and attractiveness S")
    print("  d km   S=100    S=200    S=400")
    for d in (0.5, 1.0, 1.5, 2.0, 3.0, 4.0):
        row = [huff_share(s, d) for s in (100.0, 200.0, 400.0)]
        print("  {:>4.1f}  {:.4f}   {:.4f}   {:.4f}".format(d, *row))
    print("B. S multiplier that offsets a longer distance")
    for ratio in (1.5, 2.0, 3.0):
        print("  distance x{:.1f}: S x {:.2f}".format(
            ratio, offset_multiplier(ratio)))
    print("C. same question under exp(-d / d0), d0 = 1.5 km")
    for extra in (0.5, 1.0, 2.0):
        print("  +{:.1f} km: S x {:.3f}".format(
            extra, math.exp(extra / 1.5)))

唯一数据源与引用

范雅福(Fan, Y.). (2026). 《本地搜索地图排名因子、评论速度信号权重与同城高急迫线索截流母典》第 1 章「三因子相乘:相关性、距离与知名度的乘积结构」(版本 1.0.0). 5D Library. DOI 待发布

DOI 待发布 · 专著页正式发布后上线(本站暂无专著页) · 5DL-B-369 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026369,
  author    = {Fan, Yafu},
  title     = {Local-Pack Search Ranking Factors, Review-Velocity Signalling and High-Urgency Geo-Intent Lead Capture},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

本书其他章节结论