CRFEntityExtractor extractor entities failed in Chinese

configs.yaml:

language: "zh"

pipeline:
- name: "JiebaTokenizer"  # 使用jieba分词
- name: "RegexFeaturizer"
- name: "CRFEntityExtractor"
- name: "EntitySynonymMapper"
- name: "CountVectorsFeaturizer"
- name: "CountVectorsFeaturizer"
  analyzer: "char_wb"
  min_ngram: 1
  max_ngram: 4
- name: "EmbeddingIntentClassifier"

nlu.md

## intent:request_phone_business
- 我想查电话号码[19860618422](phone_number)的[账户余额](business)
- 我要查下[19822618425](phone_number)的[机主](business)是谁
- 你好!请帮我查询一下电话[12260618425](phone_number)的[账户余额](business)
- 查一下手机号码[19862228425](phone_number)的[机主信息](business)
- 帮我查个手机号[19860612222](phone_number)的[余额](business)
- [19860222425](phone_number)是[谁的](business)

## synonym:机主
- 机主信息
- 机主
- 拥有者
- 谁的
- 属于谁

## synonym:余额
- 余额
- 话费
- 话费余额
- 账户余额

result:

Received user message '"138383834381这个号码是谁的"' with 
intent '{'name': 'request_phone_business', 'confidence': 0.9999682903289795}' 
and entities []

Can anyone help?Tks!