這個自然語言處理功能十分強大,對一語話,可以進行類似我們以前的分詞器分詞效果,還能標記出可能傾向的搜索詞.還有就是對語言的情感分析,文章的標簽分類等等在商業場合應用都十分廣泛的,來看這個小例子好像在微信小程序有看到

以上是引自百度的一個ai體驗中心,.....

/** * 詞法分析 */ @Test public void lexer(){JavaAipNlp aipNlp = new JavaAipNlp(); HashMap<String, Object> options = new HashMap<String, Object>(); JSONObject lexer = aipNlp.lexer("好好學習天天向上!", options); System.out.println(lexer.toString()); //{"log_id":664642641923030240,"text":"好好學習天天向上!","items":[ // {"formal":"","loc_details":[],"item":"好好","pos":"d","ne":"","basic_words":["好","好"],"byte_length":4,"byte_offset":0,"uri":""}, // {"formal":"","loc_details":[],"item":"學習","pos":"v","ne":"","basic_words":["學習"],"byte_length":4,"byte_offset":4,"uri":""}, // {"formal":"","loc_details":[],"item":"天天向上","pos":"v","ne":"","basic_words":["天天","向上"],"byte_length":8,"byte_offset":8,"uri":""}, // {"formal":"","loc_details":[],"item":"!","pos":"w","ne":"","basic_words":["!"],"byte_length":1,"byte_offset":16,"uri":""}]} //詞法分析（定制版） @Test public void lexerCustom(){JavaAipNlp aipNlp = new JavaAipNlp(); HashMap<String, Object> options = new HashMap<String, Object>(); JSONObject lexer = aipNlp.lexer("廣東省南山區科苑北清華信息港!", options); System.out.println(lexer.toString()); // {"log_id":2841336793035219062,"text":"廣東省南山區科苑北清華信息港!","items":[ // {"formal":"","loc_details":[],"item":"廣東省","pos":"","ne":"LOC","basic_words":["廣東","省"],"byte_length":6,"byte_offset":0,"uri":""}, // {"formal":"","loc_details":[],"item":"南山區","pos":"","ne":"LOC","basic_words":["南山","區"],"byte_length":6,"byte_offset":6,"uri":""}, // {"formal":"","loc_details":[],"item":"科苑","pos":"n","ne":"","basic_words":["科苑"],"byte_length":4,"byte_offset":12,"uri":""}, // {"formal":"","loc_details":[],"item":"北","pos":"f","ne":"","basic_words":["北"],"byte_length":2,"byte_offset":16,"uri":""}, // {"formal":"","loc_details":[],"item":"清華信息港","pos":"","ne":"ORG","basic_words":["清華","信息","港"],"byte_length":10,"byte_offset":18,"uri":""}, // {"formal":"","loc_details":[],"item":"!","pos":"w","ne":"","basic_words":["!"],"byte_length":1,"byte_offset":28,"uri":""}]} //LOC 地名 //依存法 句法分析 @Test public void depParser (){JavaAipNlp aipNlp = new JavaAipNlp(); HashMap<String, Object> options = new HashMap<String, Object>(); //模型選擇。默認值為0，可選值mode=0（對應web模型）；mode=1（對應query模型 options.put("mode",1); JSONObject lexer = aipNlp.depParser("我不想上班", options); System.out.println(lexer.toString()); //{"log_id":8560515157495529056,"text":"我不想上班","items":[ // {"head":2,"deprel":"SBV","postag":"n","id":1,"word":"我不想"}, // {"head":0,"deprel":"HED","postag":"v","id":2,"word":"上班"}]} } //DNN 語言模型 //中文DNN語言模型接口用于輸出切詞結果并給出每個詞在句子中的概率值,判斷一句話是否符合語言表達習慣。 //ppl float 描述句子通順的值：數值越低，句子越通順 resp_sample: //prob float 該詞在句子中的概率值,取值范圍[0,1] @Test public void dnnlmCn (){// String words = "我上下班飛機在河里漂浮"; String words = "我愛生活!"; JavaAipNlp aipNlp = new JavaAipNlp(); HashMap<String, Object> options = new HashMap<String, Object>(); JSONObject lexer = aipNlp.dnnlmCn(words, options); System.out.println(lexer.toString()); //{"log_id":6371386997672135571,"text":"我上下班飛機在河里漂浮","items":[ // {"prob":0.0161273,"word":"我"}, // {"prob":0.00229803,"word":"上"}, // {"prob":0.00197205,"word":"下班"}, // {"prob":1.35979E-5,"word":"飛機"}, // {"prob":0.0167389,"word":"在"}, // {"prob":3.04629E-4,"word":"河里"}, // {"prob":1.17134E-4,"word":"漂浮"}], // "ppl":1077.36} //===================================================================== // {"log_id":962095172634786721,"text":"我愛生活!","items":[ // {"prob":0.0161273,"word":"我"}, // {"prob":0.0125896,"word":"愛"}, // {"prob":9.05624E-4,"word":"生活"}, // {"prob":0.0197345,"word":"!"}], } //詞義相似度 // 輸入兩個詞，得到兩個詞的相似度結果。 @Test public void wordSimEmbedding (){String words1 = "小"; // 最大64kb String words2 = "小"; JavaAipNlp aipNlp = new JavaAipNlp(); HashMap<String, Object> options = new HashMap<String, Object>(); // options.put("mode", 0); JSONObject lexer = aipNlp.wordSimEmbedding(words1,words2, options); System.out.println(lexer.toString()); //{"log_id":7955806838486346559,"score":1,"words":{"word_1":"小","word_2":"小"}} //score 相似度的分數 1 為完全相似 } //短文本 相似度 // 輸入兩個短文本，得到兩個詞的相似度結果。 @Test public void simnet (){String words1 = "立馬"; String words2 = "馬上"; JavaAipNlp aipNlp = new JavaAipNlp(); HashMap<String, Object> options = new HashMap<String, Object>(); options.put("model", "CNN"); JSONObject lexer = aipNlp.simnet(words1,words2, options); System.out.println(lexer.toString()); //{"log_id":5656570856871633902,"score":0.580114,"texts":{"text_1":"立馬","text_2":"馬上"}} } //評論觀點抽取 // 評論觀點抽取接口用來提取一條評論句子的關注點和評論觀點，并輸出評論觀點標簽及評論觀點極性 /** * Type * 1 - 酒店 2 - KTV3 - 麗人 4 - 美食餐飲 5 - 旅游 6 - 健康 7 - 教育 8 - 商業 9 - 房產 10 - 汽車 11 - 生活 12 - 購物 13 - 3C */ @Test public void commentTag (){JavaAipNlp aipNlp = new JavaAipNlp(); String text = "這家餐館味道很差"; HashMap<String, Object> options = new HashMap<String, Object>(); JSONObject lexer = aipNlp.commentTag(text, ESimnetType.FOOD, options); System.out.println(lexer.toString()); // {"log_id":8456459865047604201,"items":[ // {"sentiment":0,"adj":"差勁","prop":"味道","end_pos":16,"abstract":"這家餐館<span>味道很差<\/span>","begin_pos":8}]} String hotel = "喜來登酒店干凈衛生"; JSONObject result = aipNlp.commentTag(hotel, ESimnetType.HOTEL, options); System.out.println(result.toString()); //prop string 匹配上的屬性詞 //adj string 匹配上的描述詞 // sentiment int 該情感搭配的極性（0表示消極，1表示中性，2表示積極） //begin_pos int 該情感搭配在句子中的開始位置 (干) //end_pos int 該情感搭配在句子中的結束位置 (生) // abstract string 對應于該情感搭配的短句摘要 //{"log_id":6206030619412743250,"items":[ // {"sentiment":2,"adj":"衛生","prop":"干凈","end_pos":18,"abstract":"喜來登酒店<span>干凈衛生<\/span>","begin_pos":10}, // {"sentiment":2,"adj":"干凈","prop":"衛生","end_pos":18,"abstract":"喜來登酒店<span>干凈衛生<\/span>","begin_pos":10}]} } /** * 情感傾向分析 * 對包含主觀觀點信息的文本進行情感極性類別（積極、消極、中性）的判斷，并給出相應的置信度。 */ @Test public void sentimentClassify(){JavaAipNlp aipNlp = new JavaAipNlp(); String text = "淘寶上很多假貨"; HashMap<String, Object> options = new HashMap<String, Object>(); JSONObject lexer = aipNlp.sentimentClassify(text, options); System.out.println(lexer.toString()); // {"log_id":4774610278737884339, //"text":"淘寶上很多假貨", //"items":[{"positive_prob":0.498948,"sentiment":1,"confidence":0.97895,"negative_prob":0.501053}]} /** * +sentiment 是 number 表示情感極性分類結果, 0:負向，1:中性，2:正向 +confidence 是 number 表示分類的置信度 +positive_prob 是 number 表示屬于積極類別的概率 +negative_prob 是 number 表示屬于消極類別的概率 */ } /* 文章標簽 文章標簽服務能夠針對網絡各類媒體文章進行快速的內容理解，根據輸入含有標題的文章，輸出多個內容標簽以及對 應的置信度，用于個性化推薦、相似文章聚合、文內容分析等場景。 */ @Test public void keyword(){ String title = "iphone手機出現“白蘋果”原因及解決辦法，用蘋果手機的可以看下" ; String content = "如果下面的方法還是沒有解決你的問題建議來我們門店看下成都市錦江區紅星路三段99號銀石廣場24層01室。" ; JavaAipNlp aipNlp = new JavaAipNlp() ; HashMap< String , Object> options = new HashMap< String , Object>() ; JSONObject lexer = aipNlp.keyword( title , content , options) ; System. out.println( lexer.toString()) ; /* {"log_id":3274746225884300396,"items":[ {"score":0.99775,"tag":"iphone"}, {"score":0.862602,"tag":"手機"}, {"score":0.845657,"tag":"蘋果"}, {"score":0.837886,"tag":"蘋果公司"}, {"score":0.811601,"tag":"白蘋果"}, {"score":0.797911,"tag":"數碼"}]} +tag 是 string 關注點字符串 +score 是 number 權重(取值范圍0~1) */} /** * 文章分類 對文章按照內容類型進行自動分類，首批支持娛樂、體育、科技等26個主流內容類型，為文章聚類、 文本內容分析等應用提供基礎技術支持。 */ @Test public void topic (){String title = "歐洲冠軍杯足球賽"; String content = "歐洲冠軍聯賽是歐洲足球協會聯盟主辦的年度足球比賽， 代表歐洲俱樂部足球最高榮譽和水平，被認為是全世界最高素質、" +"最具影響力以及最高水平的俱樂部賽事，亦是世界上獎金最高的足球賽事和體育賽事之一。"; JavaAipNlp aipNlp = new JavaAipNlp(); HashMap<String, Object> options = new HashMap<String, Object>(); JSONObject lexer = aipNlp.topic(title,content, options); System.out.println(lexer.toString()); /** * 返回參數說明 * +lv1_tag_list array of objects 一級分類結果 +lv2_tag_list array of objects 二級分類結果 實際返回參數: * {"log_id":6440401236167732852,"item":{"lv2_tag_list":[ * {"score":0.915631,"tag":"足球"}, * {"score":0.803507,"tag":"國際足球"}, * {"score":0.77813,"tag":"英超"}], * "lv1_tag_list":[{"score":0.830915,"tag":"體育"}]}} */ }像百度在大數據,人工智能這一塊的業務做得已經很開了,就像調查問卷,你可以直接根據你想調查的行業和問題調用 他們的接口數據,返回他們的真是調查結果給你.已經很厲害了,只是這個需要一元一份問卷,看似很貴,但是這是他們

多年的數據積累啊.還有就是根據您的視頻可以提取視頻里面精彩部分作為幀圖或者縮略圖,等等很強大的接口,

視頻播放網站上那些我們看到的電影的縮略圖是不是就是這樣來的?

總結

以上是生活随笔為你收集整理的百度云 自然语言处理(Nlp)的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。