【摘要】：本課題為基于深度學(xué)習(xí)的司法智能研究,任務(wù)主要以司法領(lǐng)域的自動量刑、相關(guān)法條預(yù)測和相似案例推薦為主。旨在以深度學(xué)習(xí)技術(shù)為主,解決司法領(lǐng)域智慧化問題,開展人工智能與法律領(lǐng)域的結(jié)合。在研究過程中,以單人單罪的刑事案件作為實驗數(shù)據(jù)。自動量刑指的是在給定案情描述的情況下,預(yù)測案件的罪名、刑期和罰金。在實驗中分別采用詞袋模型、fast Text和卷積神經(jīng)網(wǎng)絡(luò)模型,對刑期和罰金任務(wù),對比使用了預(yù)測值變換和數(shù)字離散化等方法。罪名預(yù)測上卷積神經(jīng)網(wǎng)絡(luò)模型效果最好,準確率為96.22%。刑期預(yù)測上,最好結(jié)果為平均絕對誤差5.42個月,平均絕對比例誤差36.60%,一致率43.04%。罰金預(yù)測上,最好結(jié)果為平均絕對誤差5199元,平均絕對比例誤差52.36%,一致率34.06%。相關(guān)法條預(yù)測指的是在給定案情描述的情況下,預(yù)測案件引用的法條信息。在實驗中分別嘗試了多種實驗思路,如比照法條文本、多標簽分類和通過相似案件的法條預(yù)測。同時也嘗試了融合更多信息的模型,如罪名預(yù)測結(jié)果和案件要素抽取結(jié)果。其中以融合更多信息的多標簽分類結(jié)果最好,在平均覆蓋率@5上結(jié)果為92.34%,宏平均準確率為89.43%,宏平均召回率為87.02%,宏平均F1值為88.21%,微平均準確率為88.08%,微平均召回率為84.23%,微平均F1值為86.11%。相似案件推薦指的是在給定案情描述情況下,通過文本相似度的計算在已有的案件庫中推薦部分相似案件。在研究中分別嘗試了詞頻-逆向文件詞頻、doc2vec、詞頻-逆向文件詞頻和word2vec融合等方法,其中詞頻-逆向文件詞頻和word2vec融合的效果最好。在模型評估上,通過采用人工打分的方法,以avgDCG@5作為評價指標,最好結(jié)果為18.51。
[Abstract]:The task of this paper is to study judicial intelligence based on deep learning. The main tasks are the automatic sentencing in the judicial field, the prediction of relevant laws and the recommendation of similar cases. The purpose of this paper is to solve the problem of wisdom in judicial field and to combine artificial intelligence with law field. In the course of the study, single-person single-crime criminal cases as experimental data. Automatic sentencing refers to the prediction of charges, sentences, and fines given a description of the case. In the experiment, word bag model, fast Text and convolution neural network model are used to compare the term of imprisonment and the task of fine by using the methods of predictive value transformation and numerical discretization. Convolution neural network model is the best in charge prediction, and the accuracy is 96.22. The best result is the average absolute error of 5.42 months, the average absolute proportion error of 36.60 and the consistent rate of 43.04. In the prediction of fine, the best result is the average absolute error of 5199 yuan, the average absolute proportion error of 52.36 and the consistent rate of 34.06. The relevant law prediction refers to the law information quoted in the case given the case description. In the experiment, we try many kinds of experimental ideas, such as comparing the text of the law, classifying the multi-label and forecasting the similar cases. At the same time, we try to integrate more information models, such as the result of charge prediction and the result of case element extraction. The results of multi-label classification with more information are the best, with 92.34 on the average coverage @ 5, 89.43 on the average accuracy of macros, 87.02 on the average recall of macros, 88.21 on the average F1 values of macros. The average accuracy was 88.08, the recall rate was 84.23, and the F1 value was 86.11. Similar case recommendation refers to the recommendation of some similar cases in the existing case base through the calculation of text similarity under the given case description. The methods of word frequency-reverse file word frequency, doc2vec, word frequency-reverse file word frequency and word2vec fusion are tried respectively in the research. Among them, word frequency-reverse file word frequency and word2vec fusion are the best. In model evaluation, the best result is 18.51 by using artificial scoring method and avgDCG@5 as evaluation index.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：D926;TP18

【參考文獻】

相關(guān)碩士學(xué)位論文 前1條

1 高菲;基于機器學(xué)習(xí)的計算機輔助量刑初探[D];華東政法學(xué)院;2005年

，

本文編號：2352014