235 lines
10 KiB
C#
235 lines
10 KiB
C#
using CloudBuilder.AI.Entity;
|
||
using CloudBuilder.Core.DatabaseAccessor.Entity;
|
||
using CloudBuilder.Topshelf.Python;
|
||
using System;
|
||
using System.Collections.Generic;
|
||
using System.Diagnostics.Eventing.Reader;
|
||
using System.Linq;
|
||
using System.Reflection.Metadata;
|
||
using System.Text;
|
||
using System.Text.RegularExpressions;
|
||
using System.Threading.Tasks;
|
||
using static System.Net.Mime.MediaTypeNames;
|
||
|
||
namespace CloudBuilder.Topshelf.Utility
|
||
{
|
||
public class SpeakerAnalysisHelper
|
||
{
|
||
public string GetPerson(Hanlp2 hanlp, string text)
|
||
{
|
||
string depRoot = hanlp.GetDepRoot(text);
|
||
|
||
List<NamedEntity> ners = hanlp.GetHanlpNer(text);
|
||
|
||
List<List<MeaningRepresentationParsingEntity>> srls = hanlp.GetHanlpSrl(text);
|
||
|
||
List<HanlpConstituencyNode> cons = hanlp.GetHanlpCon(text);
|
||
|
||
SpeakerAnalysisHelper speakerFeatureLearner = new SpeakerAnalysisHelper();
|
||
|
||
List<string> ps = new List<string>();
|
||
|
||
string arg1 = string.Empty;
|
||
|
||
string person = GetArg0(hanlp, depRoot, ners, srls, cons, ref arg1);
|
||
|
||
//同边同时有的，放在最前面
|
||
if (!string.IsNullOrEmpty(person) && ners != null && ners.Where(x => x.Type.Contains("PERSON")).Count() > 0)
|
||
{
|
||
if (ners.Where(x => x.Text.Contains(person)).Any()) ps.Add(person);
|
||
}
|
||
//如果前面的不一样，那么加入人名
|
||
if (ners != null && ners.Where(x => x.Type.Contains("PERSON")).Count() > 0)
|
||
{
|
||
foreach (string namedEntity in ners.Where(x => x.Type.Contains("PERSON")).Select(x => x.Text).Distinct().ToArray())
|
||
{
|
||
if (namedEntity.Length > 1)
|
||
{
|
||
if (!ps.Contains(namedEntity))
|
||
ps.Add(namedEntity);
|
||
}
|
||
else
|
||
{
|
||
HanlpConstituencyNode[] nodes;
|
||
HanlpConstituencyNode nodef;
|
||
string feature = null;
|
||
|
||
nodes = HanlpResultHelper.GetNodeByLabel(cons, namedEntity);
|
||
if (nodes == null || nodes.Length == 0) continue;
|
||
|
||
string[] nps = new string[] { "NP", "DNP" };
|
||
//如果存在，找到父节点上的NP
|
||
foreach (HanlpConstituencyNode node in nodes)
|
||
{
|
||
nodef = HanlpResultHelper.GetNodeTopLabelById(cons, node.FatherId, nps);
|
||
if (nodef != null)
|
||
{
|
||
feature = HanlpResultHelper.GetNodeBottomLabelById(cons, nodef.ItemId, nps);
|
||
|
||
if (string.IsNullOrEmpty(feature)) continue;
|
||
}
|
||
else if (string.IsNullOrEmpty(feature))
|
||
{
|
||
feature = node.Label;
|
||
}
|
||
//如果下一个是“NP、DNP”，可以串起来，跟上面的GetNodeBottomLabelById类似
|
||
if (feature.Length == 1)
|
||
{
|
||
HanlpConstituencyNode[] nodesSon;
|
||
nodef = HanlpResultHelper.GetNodeById(cons, node.ItemId + 1);
|
||
if (nps.Contains(nodef.Label))
|
||
{
|
||
nodesSon = HanlpResultHelper.GetNodeSonById(cons, nodef.ItemId);
|
||
if (nodesSon != null && nodesSon.Where(x => x.Children == 0).Any())
|
||
{
|
||
feature += string.Concat(nodesSon.Select(x => x.Label));
|
||
}
|
||
}
|
||
}
|
||
|
||
if (feature.Length == 1)
|
||
{
|
||
var bs = HanlpResultHelper.GetNodeBrothersById(cons, node.ItemId);
|
||
|
||
if (bs != null && bs.Where(x => x.Children == 0).Any())
|
||
{
|
||
feature += string.Concat(bs.Select(x => x.Label));
|
||
}
|
||
}
|
||
|
||
if (feature.Contains(namedEntity) && !ps.Contains(feature)) ps.Add(feature);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
//如果主语==动作发出者
|
||
//if (!string.IsNullOrEmpty(person) && !ps.Contains(person) && !ps.Contains(string.Format("[{0}]", person))) ps.Add(string.Format("[{0}]", person));
|
||
//动作接受者
|
||
//if (!string.IsNullOrEmpty(arg1) && !ps.Contains(arg1)) ps.Add(arg1);
|
||
|
||
person = QuotedString.ToDelimiteredList(ps.ToArray());
|
||
|
||
return person;
|
||
}
|
||
|
||
public string GetAgr0(Hanlp2 hanlp, string text)
|
||
{
|
||
string depRoot = hanlp.GetDepRoot(text);
|
||
|
||
List<NamedEntity> ners = hanlp.GetHanlpNer(text);
|
||
|
||
List<List<MeaningRepresentationParsingEntity>> srls = hanlp.GetHanlpSrl(text);
|
||
|
||
List<HanlpConstituencyNode> cons = hanlp.GetHanlpCon(text);
|
||
|
||
SpeakerAnalysisHelper speakerFeatureLearner = new SpeakerAnalysisHelper();
|
||
|
||
List<string> ps = new List<string>();
|
||
|
||
string arg1 = string.Empty;
|
||
|
||
return GetArg0(hanlp, depRoot, ners, srls, cons, ref arg1);
|
||
}
|
||
|
||
public string GetArg0(Hanlp2 hanlp, string depRoot, List<NamedEntity> ners, List<List<MeaningRepresentationParsingEntity>> srls, List<HanlpConstituencyNode> cons, ref string arg1)
|
||
{
|
||
string arg0 = string.Empty;
|
||
|
||
if (!string.IsNullOrEmpty(depRoot) && srls != null && srls.Count() > 0)
|
||
{
|
||
foreach (var srl in srls)
|
||
{
|
||
if (srl.Where(x => x.Text == depRoot).Any())
|
||
{
|
||
foreach (var mrp in srl)
|
||
{
|
||
if (mrp.Type.ToUpper() != "ARG0") continue;
|
||
|
||
if (ners != null && ners.Where(x => mrp.Text.Contains(x.Text)).Any() &&
|
||
ners.Where(x => mrp.Text.Contains(x.Text)).FirstOrDefault().Text.Length > 1)
|
||
return ners.Where(x => mrp.Text.Contains(x.Text)).FirstOrDefault().Text;
|
||
|
||
if (mrp.Text.Length > 4)
|
||
{
|
||
arg0 = GetAgr0(hanlp, mrp.Text);
|
||
}
|
||
else if (mrp.Text.Length > 1)
|
||
{
|
||
if (ners == null || ners.Where(x => x.Type.Contains("PERSON")).Count() == 0)
|
||
return mrp.Text;
|
||
}
|
||
}
|
||
}
|
||
|
||
foreach (var mrp in srl)
|
||
{
|
||
if (mrp.Type.ToUpper() != "ARG0") continue;
|
||
if (mrp.Text.Length > 4)
|
||
{
|
||
var temp = GetAgr0(hanlp, mrp.Text);
|
||
if (!string.IsNullOrEmpty(temp))
|
||
{
|
||
arg1 = temp;
|
||
return arg0;
|
||
}
|
||
}
|
||
else
|
||
{
|
||
arg1 = mrp.Text;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
return arg0;
|
||
}
|
||
|
||
public void MatchPerson(AiSentenceViewEntity[] aiSentences, IRepository<AiSentenceEntity> repositoryAiSentenceEntity)
|
||
{
|
||
if (AiChapterPersons == null || AiChapterPersons.Length == 0) return;
|
||
|
||
AiSentenceEntity aiSentence;
|
||
string dialogueName = string.Empty;
|
||
foreach (AiSentenceViewEntity aiSentenceView in aiSentences)
|
||
{
|
||
dialogueName= string.Empty;
|
||
if (aiSentenceView.DialogueIndc != YesNoPolicy.YES) continue;
|
||
|
||
if (aiSentences.Where(x => x.ChapterId == aiSentenceView.ChapterId && x.ParagraphId == aiSentenceView.ParagraphId).Count() > 1)
|
||
{
|
||
if (AiChapterPersons.Where(x => x.ChapterId == aiSentenceView.ChapterId && x.ParagraphIndex == aiSentenceView.ParagraphId && aiSentenceView.SentenceIndex == x.SentenceIndex).Any())
|
||
{
|
||
dialogueName = AiChapterPersons.Where(x => x.ChapterId == aiSentenceView.ChapterId && x.ParagraphIndex == aiSentenceView.ParagraphId && aiSentenceView.SentenceIndex == x.SentenceIndex).FirstOrDefault().PersonName;
|
||
}
|
||
|
||
if (AiChapterPersons.Where(x => x.ChapterId == aiSentenceView.ChapterId && x.ParagraphIndex == aiSentenceView.ParagraphId && aiSentenceView.SentenceIndex != x.SentenceIndex && x.PersonName != dialogueName).Any())
|
||
{
|
||
aiSentenceView.PersonName = AiChapterPersons.Where(x =>x.ChapterId==aiSentenceView.ChapterId && x.ParagraphIndex == aiSentenceView.ParagraphId && aiSentenceView.SentenceIndex != x.SentenceIndex && x.PersonName != dialogueName).OrderBy(x => x.OrderIndex).FirstOrDefault().PersonName;
|
||
}
|
||
}
|
||
|
||
aiSentence = new AiSentenceEntity();
|
||
ObjectCopyHelper.Copy(aiSentenceView, aiSentence);
|
||
repositoryAiSentenceEntity.UpdateNow(aiSentence);
|
||
}
|
||
}
|
||
|
||
public AiSentenceEntity[] AiSentences { get; set; }
|
||
|
||
public AiChapterPersonEntity[] AiChapterPersons { get; set; }
|
||
}
|
||
}
|
||
/*
|
||
“文本解析→人物提取→上下文匹配→结果输出”
|
||
|
||
graph TD
|
||
A[对话行] --> B{规则1：文本特征匹配};
|
||
B -->|匹配成功| C[直接赋值说话者];
|
||
B -->|匹配失败| D{规则2：紧邻旁白匹配};
|
||
D -->|匹配成功| C;
|
||
D -->|匹配失败| E{规则3：段落内最近人物};
|
||
E -->|匹配成功| C;
|
||
E -->|匹配失败| F[赋值默认值+标记异常];
|
||
|
||
*/ |