340 lines
13 KiB
PHP
340 lines
13 KiB
PHP
<?php
|
||
|
||
namespace app\common;
|
||
|
||
use think\Env;
|
||
|
||
/**
|
||
* 推广邮件 LLM 服务
|
||
*
|
||
* 作用：基于 expert 的代表作 (paper_title)、expert 的研究领域、期刊信息 (name / scope / fields 等)，
|
||
* 通过一次 LLM 调用同时生成两段邮件内容：
|
||
* - description 个性化赞美 + 邀稿段落（对应模板变量 {{ai_content_analysis}} / {{llm_description}}）
|
||
* - advised_topics "我们特别关注 X / Y / Z 领域" 段落（对应模板变量 {{ai_advised_topics}}）
|
||
*
|
||
* 单次调用返回 JSON，避免两次 LLM 请求导致的延迟翻倍；任一段失败可独立兜底。
|
||
*
|
||
* 配置（.env 的 [promotion] 段）：
|
||
* PROMOTION_LLM_URL chat/completions 接口地址
|
||
* PROMOTION_LLM_MODEL 模型名
|
||
* PROMOTION_LLM_TIMEOUT 超时时间(秒)，默认 30
|
||
* PROMOTION_LLM_FALLBACK description 兜底文案
|
||
* PROMOTION_LLM_ADVISED_FALLBACK advised_topics 兜底文案
|
||
*
|
||
* 状态约定：
|
||
* 1 = LLM 成功生成
|
||
* 2 = LLM 调用失败 / 解析失败，使用兜底
|
||
* 3 = 前置条件不足（缺代表作、缺交集等），使用兜底
|
||
*/
|
||
class PromotionLlmService
|
||
{
|
||
private $url;
|
||
private $model;
|
||
private $timeout;
|
||
private $apiKey;
|
||
private $fallback;
|
||
private $advisedFallback;
|
||
|
||
public function __construct()
|
||
{
|
||
$this->url = trim((string)Env::get('promotion.promotion_llm_url', ''));
|
||
$this->model = trim((string)Env::get('promotion.promotion_llm_model', ''));
|
||
$this->timeout = max(5, intval(Env::get('promotion.promotion_llm_timeout', 30)));
|
||
$this->apiKey = trim((string)Env::get('promotion.promotion_llm_api_key', ''));
|
||
$this->fallback = trim((string)Env::get('promotion.promotion_llm_fallback',
|
||
'Your recent work aligns closely with the scope of our journal, and we would be honored to consider a contribution from you.'));
|
||
$this->advisedFallback = trim((string)Env::get('promotion.promotion_llm_advised_fallback',
|
||
'We are especially interested in the research directions that align with your expertise, and warmly welcome your future submissions in these areas.'));
|
||
}
|
||
|
||
/**
|
||
* 一次 LLM 调用生成邮件两段内容。
|
||
*
|
||
* @param array $expert expert 行（含 name / representative_work_title / fields 等）
|
||
* @param array $journal journal 行（含 title / aims / databases 等）
|
||
* @param array $overlapFields 预先计算的 expert & journal 领域交集（可能为空）
|
||
* @param array $journalFields journal（或 task/工厂）的目标领域
|
||
* @param array $expertFields expert 的研究领域
|
||
* @return array [
|
||
* 'description' => string,
|
||
* 'description_status' => 1|2|3,
|
||
* 'advised_topics' => string,
|
||
* 'advised_topics_status' => 1|2|3,
|
||
* ]
|
||
*/
|
||
public function generateEmailContent(
|
||
array $expert,
|
||
array $journal,
|
||
array $overlapFields = [],
|
||
array $journalFields = [],
|
||
array $expertFields = []
|
||
): array {
|
||
$paperTitle = trim((string)($expert['representative_work_title'] ?? ''));
|
||
$expertName = trim((string)($expert['name'] ?? ''));
|
||
$journalName = trim((string)($journal['title'] ?? ''));
|
||
|
||
$overlapList = $this->cleanList($overlapFields);
|
||
$journalList = $this->cleanList($journalFields);
|
||
$expertList = $this->cleanList($expertFields);
|
||
|
||
$hasDescInput = ($paperTitle !== '' && $journalName !== '');
|
||
$hasAdvisedInput = (!empty($overlapList) || (!empty($journalList) && !empty($expertList)));
|
||
|
||
// 两段都缺输入时直接走双兜底
|
||
if (!$hasDescInput && !$hasAdvisedInput) {
|
||
return $this->allFallback(3, 3);
|
||
}
|
||
|
||
// LLM 未配置
|
||
if ($this->url === '' || $this->model === '') {
|
||
return $this->allFallback(
|
||
$hasDescInput ? 2 : 3,
|
||
$hasAdvisedInput ? 2 : 3
|
||
);
|
||
}
|
||
|
||
$expertField = trim((string)($expert['fields'] ?? ($expert['field'] ?? '')));
|
||
$journalAims = trim((string)($journal['aims'] ?? ''));
|
||
$journalDbs = trim((string)($journal['databases'] ?? ''));
|
||
|
||
// advised_topics 目标数量：期望邮件里总是体现 3 个推荐方向
|
||
$targetTopicCount = 3;
|
||
$overlapCount = count($overlapList);
|
||
$needFill = max(0, $targetTopicCount - $overlapCount);
|
||
|
||
$system = 'You are an academic editorial assistant. '
|
||
. 'You will receive context about an author, their recent paper, and a target journal, '
|
||
. 'and you must produce TWO English paragraphs for an invitation email. '
|
||
. 'Output STRICT MINIFIED JSON ONLY with exactly these keys:'
|
||
. '{"description":"...","advised_topics":"..."} '
|
||
. 'Rules for "description": 2-3 sentences, <=50 words, warm and professional; '
|
||
. '(a) briefly appreciate the author\'s recent paper, '
|
||
. '(b) explain why it fits the journal\'s scope, '
|
||
. '(c) gently invite a future submission. '
|
||
. 'Rules for "advised_topics": 1-2 sentences, <=60 words; '
|
||
. 'Must recommend EXACTLY ' . $targetTopicCount . ' research directions the journal is particularly interested in, '
|
||
. 'and explicitly list these ' . $targetTopicCount . ' topics in the sentence. '
|
||
. 'Topic selection rules, in order: '
|
||
. '(i) include all items from "Overlap topics (exact match)" first, preserving their order; '
|
||
. '(ii) if overlap has fewer than ' . $targetTopicCount . ' items, fill the remaining slots '
|
||
. 'with topics that are semantically close to BOTH the journal\'s focus fields and the author\'s research fields '
|
||
. '(prefer concrete sub-topics over generic umbrella terms; '
|
||
. 'do NOT invent topics unrelated to either list); '
|
||
. '(iii) never repeat topics, keep wording concise (2-4 words each). '
|
||
. 'End the paragraph by inviting contributions leaning toward those directions. '
|
||
. 'No greetings, no signatures, no placeholders, no markdown, no code fences. '
|
||
. 'If a section genuinely cannot be produced, return an empty string for that key.';
|
||
|
||
$userLines = [];
|
||
$userLines[] = 'Author name: ' . ($expertName !== '' ? $expertName : '(unknown)');
|
||
if ($expertField !== '') {
|
||
$userLines[] = 'Author research field (raw): ' . $expertField;
|
||
}
|
||
if (!empty($expertList)) {
|
||
$userLines[] = 'Author research fields (list): ' . implode(', ', $expertList);
|
||
}
|
||
$userLines[] = 'Recent paper title: ' . ($paperTitle !== '' ? $paperTitle : '(none)');
|
||
$userLines[] = 'Target journal: ' . ($journalName !== '' ? $journalName : '(unknown)');
|
||
if (!empty($journalList)) {
|
||
$userLines[] = 'Journal focus fields: ' . implode(', ', $journalList);
|
||
}
|
||
if (!empty($overlapList)) {
|
||
$userLines[] = 'Overlap topics (exact match): ' . implode(', ', $overlapList)
|
||
. ' [count=' . $overlapCount . ', need_fill=' . $needFill . ']';
|
||
} else {
|
||
$userLines[] = 'Overlap topics (exact match): (none) '
|
||
. '[count=0, need_fill=' . $targetTopicCount
|
||
. '; please pick ' . $targetTopicCount
|
||
. ' semantically related topics from the two field lists above]';
|
||
}
|
||
if ($journalAims !== '') {
|
||
$userLines[] = 'Journal aims & scope: ' . mb_substr($journalAims, 0, 500);
|
||
}
|
||
if ($journalDbs !== '') {
|
||
$userLines[] = 'Journal indexing: ' . mb_substr($journalDbs, 0, 200);
|
||
}
|
||
$userLines[] = 'Advised topics required count: ' . $targetTopicCount;
|
||
$userLines[] = 'Return only minified JSON {"description":"...","advised_topics":"..."}.';
|
||
$user = implode("\n", $userLines);
|
||
|
||
$payload = [
|
||
'model' => $this->model,
|
||
'temperature' => 0.4,
|
||
'messages' => [
|
||
['role' => 'system', 'content' => $system],
|
||
['role' => 'user', 'content' => $user],
|
||
],
|
||
];
|
||
|
||
$content = $this->postChat($payload);
|
||
if ($content === null) {
|
||
return $this->allFallback(
|
||
$hasDescInput ? 2 : 3,
|
||
$hasAdvisedInput ? 2 : 3
|
||
);
|
||
}
|
||
|
||
$parsed = $this->parseJson($content);
|
||
if ($parsed === null) {
|
||
return $this->allFallback(
|
||
$hasDescInput ? 2 : 3,
|
||
$hasAdvisedInput ? 2 : 3
|
||
);
|
||
}
|
||
|
||
$desc = $this->cleanContent((string)($parsed['description'] ?? ''));
|
||
$advised = $this->cleanContent((string)($parsed['advised_topics'] ?? ''));
|
||
|
||
$descStatus = 1;
|
||
if ($desc === '') {
|
||
$desc = $this->fallback;
|
||
$descStatus = $hasDescInput ? 2 : 3;
|
||
}
|
||
|
||
$advisedStatus = 1;
|
||
if ($advised === '') {
|
||
$advised = $this->advisedFallback;
|
||
$advisedStatus = $hasAdvisedInput ? 2 : 3;
|
||
}
|
||
|
||
return [
|
||
'description' => $desc,
|
||
'description_status' => $descStatus,
|
||
'advised_topics' => $advised,
|
||
'advised_topics_status' => $advisedStatus,
|
||
];
|
||
}
|
||
|
||
/**
|
||
* 兼容旧接口：单段 description 生成（仍走 generateEmailContent，取第一段）
|
||
*
|
||
* @return array ['status' => 1|2|3, 'text' => string]
|
||
*/
|
||
public function generateDescription(array $expert, array $journal): array
|
||
{
|
||
$r = $this->generateEmailContent($expert, $journal);
|
||
return [
|
||
'status' => intval($r['description_status']),
|
||
'text' => (string)$r['description'],
|
||
];
|
||
}
|
||
|
||
/**
|
||
* 调用 chat/completions 接口，返回 content 字符串；失败返回 null。
|
||
*/
|
||
private function postChat(array $payload)
|
||
{
|
||
$ch = curl_init();
|
||
curl_setopt($ch, CURLOPT_URL, $this->url);
|
||
curl_setopt($ch, CURLOPT_POST, true);
|
||
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload, JSON_UNESCAPED_UNICODE));
|
||
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
|
||
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, min(10, $this->timeout));
|
||
curl_setopt($ch, CURLOPT_TIMEOUT, $this->timeout);
|
||
|
||
$headers = ['Content-Type: application/json'];
|
||
if ($this->apiKey !== '') {
|
||
$headers[] = 'Authorization: Bearer ' . $this->apiKey;
|
||
}
|
||
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
|
||
|
||
$raw = curl_exec($ch);
|
||
if ($raw === false) {
|
||
curl_close($ch);
|
||
return null;
|
||
}
|
||
$httpCode = intval(curl_getinfo($ch, CURLINFO_HTTP_CODE));
|
||
curl_close($ch);
|
||
if ($httpCode < 200 || $httpCode >= 300) {
|
||
return null;
|
||
}
|
||
|
||
$data = json_decode($raw, true);
|
||
if (!is_array($data)) return null;
|
||
|
||
if (isset($data['choices'][0]['message']['content'])) {
|
||
return (string)$data['choices'][0]['message']['content'];
|
||
}
|
||
if (isset($data['content'])) {
|
||
return (string)$data['content'];
|
||
}
|
||
return null;
|
||
}
|
||
|
||
/**
|
||
* 从模型原始输出里提取 JSON 对象；失败返回 null。
|
||
*/
|
||
private function parseJson(string $raw)
|
||
{
|
||
$raw = trim($raw);
|
||
if ($raw === '') return null;
|
||
$raw = preg_replace('/^```[a-zA-Z]*\s*|```$/m', '', $raw);
|
||
$raw = trim($raw);
|
||
|
||
// 直接 decode
|
||
$obj = json_decode($raw, true);
|
||
if (is_array($obj)) return $obj;
|
||
|
||
// 抓出第一个 {...} 块再 decode
|
||
if (preg_match('/\{.*\}/s', $raw, $m)) {
|
||
$obj = json_decode($m[0], true);
|
||
if (is_array($obj)) return $obj;
|
||
}
|
||
return null;
|
||
}
|
||
|
||
/**
|
||
* 清洗 LLM 输出：去除 markdown 包裹、多余空白、首尾引号、过长截断。
|
||
*/
|
||
private function cleanContent(string $text): string
|
||
{
|
||
$text = trim($text);
|
||
$text = preg_replace('/^```[a-zA-Z]*\s*|```$/m', '', $text);
|
||
$text = trim($text);
|
||
$text = trim($text, "\"' \t\n\r\0\x0B");
|
||
$text = preg_replace('/\s+/', ' ', $text);
|
||
if (mb_strlen($text) > 800) {
|
||
$text = mb_substr($text, 0, 800);
|
||
}
|
||
return trim($text);
|
||
}
|
||
|
||
/**
|
||
* 对领域列表做 trim / 去空 / 去重，保留首次出现顺序。
|
||
*/
|
||
private function cleanList(array $list): array
|
||
{
|
||
$out = [];
|
||
$seen = [];
|
||
foreach ($list as $item) {
|
||
$v = trim((string)$item);
|
||
if ($v === '') continue;
|
||
$key = strtolower($v);
|
||
if (isset($seen[$key])) continue;
|
||
$seen[$key] = true;
|
||
$out[] = $v;
|
||
}
|
||
return $out;
|
||
}
|
||
|
||
private function allFallback(int $descStatus, int $advisedStatus): array
|
||
{
|
||
return [
|
||
'description' => $this->fallback,
|
||
'description_status' => $descStatus,
|
||
'advised_topics' => $this->advisedFallback,
|
||
'advised_topics_status' => $advisedStatus,
|
||
];
|
||
}
|
||
|
||
public function getFallback(): string
|
||
{
|
||
return $this->fallback;
|
||
}
|
||
|
||
public function getAdvisedFallback(): string
|
||
{
|
||
return $this->advisedFallback;
|
||
}
|
||
}
|