如何从海量文本中快速提炼核心信息？donatello-za/rake-php-plus助你实现智能关键词提取

<pre class="brush:php;toolbar:false;"># 推荐安装最新版本，支持 PHP 7.4 到 8.3
composer require donatello-za/rake-php-plus:^2.0

# 如果需要支持更老的 PHP 版本 (5.4 到 8.3)
# composer require donatello-za/rake-php-plus:^1.0

<pre class="brush:php;toolbar:false;"><?php
require 'vendor/autoload.php';

use DonatelloZa\RakePlus\RakePlus;

// 示例文本
$text = "Criteria of compatibility of a system of linear Diophantine equations, " .
    "strict inequations, and nonstrict inequations are considered. Upper bounds " .
    "for components of a minimal set of solutions and algorithms of construction " .
    "of minimal generating sets of solutions for all types of systems are given.";

// 1. 提取关键短语（默认英语）
$phrases = RakePlus::create($text)->get();
echo "--- 提取的关键短语 ---\n";
print_r($phrases);
/*
Array
(
    [0] => criteria
    [1] => compatibility
    [2] => system
    [3] => linear diophantine equations
    [4] => strict inequations
    [5] => nonstrict inequations
    [6] => considered
    [7] => upper bounds
    [8] => components
    [9] => minimal set
    [10] => solutions
    [11] => algorithms
    [12] => construction
    [13] => minimal generating sets
    [14] => types
    [15] => systems
)
*/

// 2. 提取独立关键词
$keywords = RakePlus::create($text)->keywords();
echo "\n--- 提取的独立关键词 ---\n";
print_r($keywords);
/*
Array
(
    [0] => criteria
    [1] => compatibility
    [2] => system
    [3] => linear
    [4] => diophantine
    [5] => equations
    ...
)
*/

// 3. 按分数降序排列短语，并获取分数
$rake = RakePlus::create($text, 'en_US'); // 明确指定语言
$phrase_scores = $rake->sortByScore('desc')->scores();
echo "\n--- 按分数排序的关键短语及分数 ---\n";
print_r($phrase_scores);
/*
Array
(
    [linear diophantine equations] => 9
    [minimal generating sets] => 8.5
    [minimal set] => 4.5
    [strict inequations] => 4
    [nonstrict inequations] => 4
    [upper bounds] => 4
    [criteria] => 1
    [compatibility] => 1
    [system] => 1
    [considered] => 1
    [components] => 1
    [solutions] => 1
    [algorithms] => 1
    [construction] => 1
    [types] => 1
    [systems] => 1
)
*/

// 4. 处理新文本，复用 RakePlus 实例更高效
$newText = "A fast Fourier transform (FFT) algorithm computes...";
$newPhrases = $rake->extract($newText)->sort()->get();
echo "\n--- 处理新文本后的关键短语 ---\n";
print_r($newPhrases);
/*
Array
(
    [0] => algorithm computes
    [1] => fast fourier transform
    [2] => fft
)
*/

// 5. 自定义停用词或指定语言
// 你可以直接传递一个停用词数组
$customStopwords = ['a', 'an', 'the', 'of', 'for'];
$rakeWithCustomStopwords = RakePlus::create("This is a test sentence for custom stopwords.", $customStopwords);
print_r($rakeWithCustomStopwords->get());

// 或者指定支持的语言代码，例如中文（如果它被官方支持或你添加了停用词文件）
// $chineseText = "这是一个关于人工智能的中文文本。";
// $rakeChinese = RakePlus::create($chineseText, 'zh_CN'); // 假设 zh_CN 已被支持或配置
// print_r($rakeChinese->get());