关于「字形远、读音近:编辑距离、音骨架与混淆的通道」,《品牌撞名三维预检》给出的定量结论是什么?
结论:先看最上面一行:声音通道占比为零,混淆全部来自文字,这时视觉尺子的 AUC 是 0.906,普通字母编辑距离是 0.880,音码只有 0.683。再看最下面一行:混淆全部来自声音,音码的 AUC 升到 0.893,字母编辑距离降到 0.789,视觉尺子降到 0.767。两条线在中间交叉:声音占比 0.5 时,音码为 0.789,字母距离为 0.825,视觉为 0.826,字形一侧仍略占上风;声音占比 0.8 时,音码以 0.851 超过字母距离的 0.817。
数据口径:在一个示意模型中,声音通道占八成时音码的 AUC 为 0.851,高于字母编辑距离的 0.817。 书中参数为示意;全部计算由书中程序生成;本书是非个人化法律建议,商标近似判断以各地官方检索与专业代理意见为准。
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: 0.5, 0.683, 0.767, 0.789, 0.8, 0.817
| pairs 2400 | (600 bases x 4 comparison names) | |||||
| spoken | conf | letter soundex | sound | visual | max(s,v) | |
| 0.0 | 1317 | 0.880 | 0.597 | 0.683 | 0.906 | 0.709 |
| 0.2 | 1340 | 0.849 | 0.610 | 0.712 | 0.868 | 0.732 |
| 0.5 | 1368 | 0.825 | 0.654 | 0.789 | 0.826 | 0.791 |
| 0.8 | 1456 | 0.817 | 0.678 | 0.851 | 0.806 | 0.840 |
| 1.0 | 1451 | 0.789 | 0.717 | 0.893 | 0.767 | 0.867 |
查看完整验算程序
# Chapter 1. p12: which distance predicts confusion depends on channel.
# Model: 600 random invented base names; each gets four comparison
# names: a respelling that keeps the sound (S), a look-alike letter
# swap that changes the sound (V), one random letter change (N) and
# an unrelated name (U). A confusion happens through a spoken channel
# with probability s, else a written one; logit P = -6 + 9 * sim,
# where sim is 1 - sound distance (spoken) or 1 - visual distance
# (written). Distances as in p11. AUC = Mann-Whitney probability with
# mid-ranks for ties. Channel model and constants are illustrative.
import math
import random
import re
SKEL = ((r"ch", "tsh"), (r"ph", "f"), (r"gh", "g"), (r"ck", "k"),
(r"qu", "kw"),
(r"q", "k"), (r"x", "ks"), (r"z", "s"), (r"y", "i"),
(r"ee", "i"), (r"oo", "u"), (r"c(?=[ei])", "s"), (r"c", "k"))
VMULTI = (("rn", "m"), ("cl", "d"), ("vv", "w"))
VPAIRS = {frozenset(p) for p in ("il", "ij", "lt", "nh", "uv", "vy",
"ce", "co", "oa", "bd", "pq", "ft")}
CODE = {c: d for d, g in (("1", "bfpv"), ("2", "cgjkqsxz"), ("3", "dt"),
("4", "l"), ("5", "mn"), ("6", "r")) for c in g}
SOUND_OPS = ((r"f", "ph"), (r"k(?=[aou])", "c"), (r"s", "z"),
(r"i", "y"), (r"([bdlmnprt])", r"\1\1"), (r"u", "oo"))
LOOK_OPS = (("n", "h"), ("h", "n"), ("c", "e"), ("e", "c"), ("a", "o"),
("o", "a"), ("l", "t"), ("t", "l"), ("b", "d"), ("d", "b"),
("m", "rn"), ("d", "cl"))
def lev(a, b, sub=None):
prev = [float(j) for j in range(len(b) + 1)]
for i, x in enumerate(a, 1):
cur = [float(i)]
for j, y in enumerate(b, 1):
c = 0.0 if x == y else (sub(x, y) if sub else 1.0)
cur.append(min(prev[j] + 1.0, cur[j - 1] + 1.0,
prev[j - 1] + c))
prev = cur
return prev[-1]
def skeleton(s):
for pat, rep in SKEL:
s = re.sub(pat, rep, s)
if len(s) > 3 and s.endswith("e") and s[-2] not in "aeiou":
s = s[:-1]
return re.sub(r"(.)\1+", r"\1", s)
def vsub(x, y):
return 0.3 if frozenset((x, y)) in VPAIRS else 1.0
def vskel(s):
for pat, rep in VMULTI:
s = s.replace(pat, rep)
return s
def soundex(s):
last, out = CODE.get(s[0], ""), []
for c in s[1:]:
d = CODE.get(c, "")
if d and d != last:
out.append(d)
if c not in "hw":
last = d
return (s[0] + "".join(out) + "000")[:4]
def nd(a, b, sub=None):
return lev(a, b, sub) / max(len(a), len(b), 1)
def make_name(rng):
syl = [rng.choice("bdfgklmnprstvz") + rng.choice("aeiou")
for _ in range(rng.choice((2, 3)))]
return "".join(syl)
def apply_op(rng, name, ops, regex):
order = list(ops)
rng.shuffle(order)
for pat, rep in order:
hits = ([m.start() for m in re.finditer(pat, name)] if regex
else [m.start() for m in re.finditer(re.escape(pat), name)])
if hits:
k = rng.choice(hits)
if regex:
return name[:k] + re.sub(pat, rep, name[k:], count=1)
return name[:k] + rep + name[k + len(pat):]
return name
def auc(pos, neg):
allv = sorted([(v, 1) for v in pos] + [(v, 0) for v in neg])
ranks, i = [], 0
while i < len(allv):
j = i
while j < len(allv) and allv[j][0] == allv[i][0]:
j += 1
mid = (i + 1 + j) / 2.0
ranks.extend(mid for k in range(i, j) if allv[k][1] == 1)
i = j
n1, n0 = len(pos), len(neg)
return (math.fsum(ranks) - n1 * (n1 + 1) / 2.0) / (n1 * n0)
if __name__ == "__main__":
rng = random.Random(20261113)
rows = []
for _ in range(600):
a = make_name(rng)
s1 = apply_op(rng, apply_op(rng, a, SOUND_OPS, True),
SOUND_OPS, True)
v1 = apply_op(rng, a, LOOK_OPS, False)
k = rng.randrange(len(a))
n1 = a[:k] + rng.choice("abdeiklmnorstu") + a[k + 1:]
for b in (s1, v1, n1, make_name(rng)):
ka, kb = skeleton(a), skeleton(b)
sp = 1.0 - nd(ka, kb)
sv = 1.0 - nd(vskel(a), vskel(b), vsub)
sl = 1.0 - nd(a, b)
sx = 1.0 if soundex(a) == soundex(b) else 0.0
rows.append((sl, sx, sp, sv, max(sp, sv)))
print("pairs {} (600 bases x 4 comparison names)".format(len(rows)))
print("spoken conf letter soundex sound visual max(s,v)")
for share in (0.0, 0.2, 0.5, 0.8, 1.0):
lab = []
for sl, sx, sp, sv, mx in rows:
sim = sp if rng.random() < share else sv
p = 1.0 / (1.0 + math.exp(6.0 - 9.0 * sim))
lab.append(rng.random() < p)
cols = []
for c in range(5):
pos = [r[c] for r, y in zip(rows, lab) if y]
neg = [r[c] for r, y in zip(rows, lab) if not y]
cols.append(auc(pos, neg))
print("{:5.1f} {:6d} {:6.3f} {:7.3f} {:6.3f} {:7.3f} {:9.3f}"
.format(share, lab.count(True), *cols))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《商标音近形近义近三维距离、从反切到音码的品牌撞名预检母典》第 1 章「字形远、读音近:编辑距离、音骨架与混淆的通道」(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-317 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026317,
author = {Fan, Yafu},
title = {Phonetic, Graphic and Semantic Distance between Trademarks: Pre-Screening Brand-Name Collisions from Fanqie Spellings to Sound Codes},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}