offer-puplayer / backend /app /services /job_service.py
tryprogram's picture
Upload 46 files
61fd574 verified
Raw History Blame Contribute Delete
9.51 kB
import json
import os
import logging
import httpx
from app import database
logger = logging.getLogger(__name__)
_985_UNIVERSITIES = {
"清华大学","北京大学","复旦大学","上海交通大学","浙江大学","南京大学","中国科学技术大学",
"哈尔滨工业大学","西安交通大学","武汉大学","华中科技大学","中山大学","四川大学","南开大学",
"天津大学","山东大学","东南大学","吉林大学","厦门大学","同济大学","北京师范大学",
"国防科技大学","中国人民大学","北京航空航天大学","北京理工大学","中国农业大学",
"中央民族大学","华东师范大学","兰州大学","西北工业大学","电子科技大学",
"重庆大学","湖南大学","中南大学","大连理工大学","东北大学","华南理工大学"
}
_211_UNIVERSITIES = _985_UNIVERSITIES | {
"北京科技大学","北京交通大学","北京邮电大学","北京林业大学","北京外国语大学",
"中国传媒大学","中央财经大学","对外经济贸易大学","北京体育大学","中国政法大学",
"华北电力大学","河北工业大学","太原理工大学","内蒙古大学","辽宁大学","大连海事大学",
"延边大学","东北师范大学","哈尔滨工程大学","东北农业大学","华东理工大学","东华大学",
"上海外国语大学","上海财经大学","上海大学","苏州大学","南京航空航天大学","南京理工大学",
"中国矿业大学","河海大学","江南大学","南京农业大学","中国药科大学","南京师范大学",
"安徽大学","合肥工业大学","福州大学","南昌大学","中国石油大学","郑州大学",
"中国地质大学","武汉理工大学","华中农业大学","华中师范大学","中南财经政法大学",
"湖南师范大学","暨南大学","华南师范大学","广西大学","海南大学","西南交通大学",
"西南大学","西南财经大学","贵州大学","云南大学","西藏大学","西北大学",
"西安电子科技大学","长安大学","陕西师范大学","青海大学","宁夏大学","石河子大学",
"新疆大学","北京工业大学","天津医科大学","南京信息工程大学","南方科技大学",
"上海科技大学","中国社科院大学","中国科学院大学"
}
def _get_school_tier(school: str) -> int:
if not school:
return 0
if school in _985_UNIVERSITIES:
return 2
if school in _211_UNIVERSITIES:
return 1
return 0
def _build_resume_text(resume_data: dict) -> str:
skills = " ".join(s.lower().strip() for s in resume_data.get("skills", []))
projects = " ".join(
p if isinstance(p, str) else (p.get("name", "") + " " + p.get("description", ""))
for p in resume_data.get("projects", [])
)
parts = [
resume_data.get("summary") or "",
projects,
resume_data.get("experience") or "",
resume_data.get("education") or "",
resume_data.get("major") or "",
skills,
]
return " ".join(parts)
def _calc_match_rate(resume_data: dict, job: dict, tag_score: float, edu_score: float, vec_score: float) -> float:
final_score = vec_score * 0.35 + tag_score * 0.45 + edu_score * 0.20
return round(min(final_score, 1.0), 4)
def _calc_tag_score(resume_data: dict, job: dict) -> float:
skills = [s.lower().strip() for s in resume_data.get("skills", [])]
tags = [t.lower().strip() for t in job.get("tags", [])]
if not tags:
return 0.0
matched = sum(1 for t in tags if t in skills)
return matched / len(tags)
def _calc_edu_score(resume_data: dict, job: dict) -> float:
school = (resume_data.get("school") or "")
grade = (resume_data.get("grade") or "").lower()
jd_requirements = (job.get("requirements") or "").lower()
score = 0.4
tier = _get_school_tier(school)
if tier >= 2:
score = 1.0
elif tier >= 1:
score = 0.8
elif school:
score = 0.5
if ("硕士" in grade or "博士" in grade or "研" in grade) and "硕士" in jd_requirements:
score = min(score + 0.15, 1.0)
return score
def recommend_jobs(resume_data: dict) -> list[dict]:
if not resume_data or not resume_data.get("skills"):
return []
conn = database.get_conn()
rows = conn.execute("SELECT * FROM jobs ORDER BY job_id").fetchall()
conn.close()
jobs = []
for r in rows:
embedding_raw = r["embedding"] if "embedding" in r.keys() else ""
jobs.append({
"job_id": r["job_id"],
"name": r["name"],
"company": r["company"],
"city": r["city"],
"salary": r["salary"],
"tags": json.loads(r["tags"] or "[]"),
"description": r["description"],
"requirements": r["requirements"],
"expectation_signals": json.loads(r["expectation_signals"] or "[]"),
"_embedding": json.loads(embedding_raw) if embedding_raw else None,
})
resume_text = _build_resume_text(resume_data)
resume_vec = None
try:
from app.services.embedding_service import compute_embedding, cosine_similarity
resume_vec = compute_embedding(resume_text)
except Exception as e:
logger.warning("Resume embedding failed: %s", e)
for job in jobs:
tag_score = _calc_tag_score(resume_data, job)
edu_score = _calc_edu_score(resume_data, job)
vec_raw = 0.0
if resume_vec and job["_embedding"]:
vec_raw = cosine_similarity(resume_vec, job["_embedding"])
job["_tag_score"] = tag_score
job["_edu_score"] = edu_score
job["_vec_raw"] = vec_raw
for job in jobs:
job["_vec_score"] = max(0, min((job["_vec_raw"] - 0.30) / 0.40, 1.0))
scored = []
for job in jobs:
match_rate = _calc_match_rate(
resume_data, job,
job["_tag_score"], job["_edu_score"], job["_vec_score"]
)
scored.append({
"job_id": job["job_id"],
"match_rate": match_rate,
"job": job,
})
scored.sort(key=lambda x: x["match_rate"], reverse=True)
top_n = scored
api_key = os.getenv("DEEPSEEK_API_KEY")
if api_key and top_n:
try:
job_summaries = []
for item in top_n:
j = item["job"]
job_summaries.append(
f' {j.get("job_id")}: {j.get("name")} @ {j.get("company")} | '
f'tags={j.get("tags")} | match_rate={item["match_rate"]}'
)
system_prompt = (
"你是一个岗位推荐排序专家。给定候选人的技能列表和全部候选岗位,"
"请根据岗位与候选人的匹配程度重新排序,输出最匹配的岗位ID列表(从最匹配到最不匹配)。"
"输出格式为JSON:{\"ranked_job_ids\": [1, 2, 3, ...]}"
)
user_input = {
"skills": resume_data.get("skills", []),
"candidates": "\n".join(job_summaries),
}
with httpx.Client(timeout=30.0) as client:
resp = client.post(
"https://api.deepseek.com/chat/completions",
headers={
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json",
},
json={
"model": "deepseek-chat",
"response_format": {"type": "json_object"},
"messages": [
{"role": "system", "content": system_prompt},
{"role": "user", "content": json.dumps(user_input, ensure_ascii=False)},
],
},
)
resp.raise_for_status()
body = resp.json()
content = body["choices"][0]["message"]["content"]
llm_result = json.loads(content)
ranked_ids = llm_result.get("ranked_job_ids", [])
id_to_item = {item["job"]["job_id"]: item for item in top_n}
re_ranked = []
for raw_id in ranked_ids:
if raw_id in id_to_item:
re_ranked.append(id_to_item[raw_id])
for item in top_n:
if item["job"]["job_id"] not in ranked_ids:
re_ranked.append(item)
top_n = re_ranked
except Exception as e:
logger.warning("LLM ranking failed: %s", e)
return [
{
"job_id": item["job_id"],
"match_rate": item["match_rate"],
"match_detail": {
"semantic": round(item["job"]["_vec_score"], 4),
"tags": round(item["job"]["_tag_score"], 4),
"education": round(item["job"]["_edu_score"], 4),
},
"name": item["job"].get("name", ""),
"company": item["job"].get("company", ""),
"city": item["job"].get("city", ""),
"salary": item["job"].get("salary", ""),
"tags": item["job"].get("tags", []),
"description": item["job"].get("description", ""),
"requirements": item["job"].get("requirements", ""),
"expectation_signals": item["job"].get("expectation_signals", []),
}
for item in top_n
]