组合评分
把一个复杂的判断拆成若干原子评分,再用你在代码中掌控的权重把它们组合起来。
我们常常希望同时基于多个标准来给一组条目排序。组合评分是一种便于思考的做法:把判断拆成相互独立的维度,分别给每个维度评分,再用你在代码中掌控的权重把它们组合起来。
示例:简历筛选
设想你正在处理工程岗位的简历。你希望基于多个标准给候选人排序,并最终选出排名前 X 的候选人进入下一轮评审。
%%{init: {"fontFamily": "Inter, sans-serif", "flowchart": {"rankSpacing": 35, "wrappingWidth": 300, "subGraphTitleMargin": {"top": 12, "bottom": 36}}}}%%
flowchart LR
resume["候选人简历"]
subgraph req["TypeSafe 并行<br/>评估各个问题"]
direction TB
py["<b>Score:</b> Python 深度"]
lead["<b>Score:</b> 团队领导力"]
arch["<b>Score:</b> 系统设计"]
general["<b>Score:</b> 通才程度"]
%% Invisible links stack the questions; they are answered in parallel.
py ~~~ lead ~~~ arch ~~~ general
end
resume -- "一次请求<br/>简历 + 4 个问题" --> req
req -- "一次响应<br/>4 个评分答案" --> normalize["<b>把评分归一化到 0–1</b><br/>在你的代码中每项除以 4"]
normalize --> ic["<b>资深个人贡献者权重</b><br/>40% Python + 10% 领导力<br/>40% 设计 + 10% 通才"]
normalize --> em["<b>工程经理权重</b><br/>15% Python + 40% 领导力<br/>20% 设计 + 25% 通才"]
ic --> rank["给候选人排序<br/>针对每个角色"]
em --> rank
第 1 步:独立地给每个维度评分
{
"questions": {
"python_depth": {
"type": "score",
"instructions": "How much depth of python experience does this candidate have, based on the supplied resume?",
"criteria": [
"No Python experience mentioned",
"Mentioned but no detail",
"Used in projects, some specifics",
"Primary language, multiple projects",
"Deep expertise: architecture, performance, libraries"
]
},
"team_leadership": {
"type": "score",
"instructions": "How much experience does this candidate have managing or leading engineering teams?",
"criteria": [
"No management experience mentioned",
"Informal mentorship or tech lead role",
"Led a small team or project",
"Managed a team with direct reports",
"Managed multiple teams or an engineering org"
]
},
"system_design": {
"type": "score",
"instructions": "How much experience does this candidate have designing large-scale or distributed systems?",
"criteria": [
"No architecture work mentioned",
"Contributed to design discussions",
"Designed components of a larger system",
"Owned architecture of a significant system",
"Designed systems at scale across multiple domains"
]
},
"generalist": {
"type": "score",
"instructions": "How much evidence is there that this candidate picks up unfamiliar tools, roles, or domains outside their core specialty?",
"criteria": [
"Only one domain or role mentioned",
"Some variety but within a narrow field",
"Worked across a few different areas or tech stacks",
"Regularly moved between domains, wore many hats",
"Track record of ramping up in unfamiliar areas and delivering"
]
}
}
}
这个示例是可交互的;到官网原页面可以直接在 Playground 里运行。
第 2 步:用权重组合
每个维度都会被归一化到 0–1 并赋予权重。权重让你可以方便地调整每个维度的相对重要性,同时不会丢失任何单项评分中的细微差别。
py = response.answers["python_depth"].score / 4
lead = response.answers["team_leadership"].score / 4
arch = response.answers["system_design"].score / 4
general = response.answers["generalist"].score / 4
# Senior IC
ic_score = (0.40 * py) + (0.10 * lead) + (0.40 * arch) + (0.10 * general)
# Engineering Manager
em_score = (0.15 * py) + (0.40 * lead) + (0.20 * arch) + (0.25 * general)
这样你就能基于组合评分给候选人排序。但更重要的是,它让你能看清最终评分究竟是如何计算出来的。如果排名最高的候选人并不符合你的预期,你可以调整权重来找到合适的平衡点。