def __init__(self, query_data, dependency=None):
logger.info('Query Parsing...')
self.relation = query_data.setdefault('relation', list())
self.entity = query_data.setdefault('entity', list())
self.intent = query_data['intent']
self.dependency = dependency
self.relation_component_list = list()
self.entity_component_list = list()
# 获取实体和关系对应的子图组件
self.init_relation_component()
self.init_entity_component()
# 若有依存分析，根据依存分析来获取组件图
if self.dependency and len(self.dependency) > 0:
logger.info('dependency exist.')
print('dependency exist.')
dm = DepMap(query_data['dependency'], self.relation_component_list,
self.entity_component_list)
if dm.check_dep():
# 使用依存分析，获取self.component_graph
if nx.algorithms.is_weakly_connected(dm.dep_graph):
self.query_graph = dm.dep_graph
self.determine_intention()
return
else:
logger.info('dependency wrong!')
# 得到子图组件构成的集合，用图表示
self.component_graph = nx.disjoint_union_all(
self.relation_component_list + self.entity_component_list)
self.query_graph = copy.deepcopy(self.component_graph)
self.query_graph = Graph(self.query_graph)
self.old_query_graph = copy.deepcopy(self.component_graph)
self.node_type_dict = self.query_graph.node_type_statistic()
self.component_assemble()
while len(self.query_graph.nodes) != len(self.old_query_graph.nodes) \
and not nx.algorithms.is_weakly_connected(self.query_graph):
# 节点一样多说明上一轮没有合并
# 图已连通也不用合并
self.old_query_graph = copy.deepcopy(self.query_graph)
self.node_type_dict = self.query_graph.node_type_statistic()
self.component_assemble()
while not nx.algorithms.is_weakly_connected(self.query_graph):
# 若不连通则在联通分量之间添加默认边
flag = self.add_default_edge()
if not flag:
logger.info('default edge missing!')
# 未添加上说明缺少默认边
break
# 经过上面两个循环，得到连通的图，下面确定意图
self.determine_intention()
def add_default_edge(self):
flag = False
components_set = self.query_graph.get_connected_components_subgraph()
d0 = Graph(components_set[0]).node_type_statistic()
d1 = Graph(components_set[1]).node_type_statistic()
candidates = itertools.product(d0.keys(), d1.keys())
candidates = list(candidates)
for key, edge in DEFAULT_EDGE.items():
for c in candidates:
if c[0] == edge['domain'] and c[1] == edge['range']:
node_0 = d0[edge['domain']][0]
node_1 = d1[edge['range']][0]
self.query_graph.add_edge(node_0, node_1, key)
flag = True
return flag
elif c[1] == edge['domain'] and c[0] == edge['range']:
node_0 = d1[edge['domain']][0]
node_1 = d0[edge['range']][0]
self.query_graph.add_edge(node_0, node_1, key)
flag = True
return flag
return flag
def add_default_edge_between_components(self, components_set, c1, c2):
"""
在两个连通分量之间添加默认边
:param components_set:
:param c1:
:param c2:
:return:
"""
flag = False
d0 = Graph(components_set[c1]).node_type_statistic()
d1 = Graph(components_set[c2]).node_type_statistic()
candidates = itertools.product(d0.keys(), d1.keys())
candidates = list(candidates)
trick_index = 0
for key, edge in DEFAULT_EDGE.items():
for c in candidates:
if c[0] == edge['domain'] and c[1] == edge['range']:
node_0 = d0[edge['domain']][trick_index]
node_1 = d1[edge['range']][trick_index]
self.query_graph.add_edge(node_0,
node_1,
key,
type=key,
value=edge['value'])
flag = True
return flag
elif c[1] == edge['domain'] and c[0] == edge['range']:
node_0 = d1[edge['domain']][trick_index]
node_1 = d0[edge['range']][trick_index]
self.query_graph.add_edge(node_0,
node_1,
key,
type=key,
value=edge['value'])
flag = True
return flag
return flag
def init_dep_graph(self):
for item in self.dependency:
f = item['from']
t = item['to']
if f['type'] == 'entity' and t['type'] == 'relation':
temp_graph = self.from_ent_to_rel(f['value'], t['value'])
self.dep_graph_list.append(temp_graph)
elif f['type'] == 'relation' and t['type'] == 'entity':
temp_graph = self.from_rel_to_ent(f['value'], t['value'])
self.dep_graph_list.append(temp_graph)
self.dep_graph = nx.disjoint_union_all(self.dep_graph_list)
mapping = dict()
for i, n in enumerate(self.dep_graph.nodes):
mapping[n] = i
nx.relabel_nodes(self.dep_graph, mapping, copy=False)
self.dep_graph = Graph(self.dep_graph)
def __init__(self, graph, query):
self.graph = nx.convert_node_labels_to_integers(graph)
self.graph = Graph(self.graph)
self.query = query
# 用于指出查询意图为某归属属性的情况
self.intention_tail = ''
self.entities = dict()
self.init_entities()
self.rels = list()
self.init_rels()
self.intentions = list()
self.init_intention()
self.query_dict = dict()
self.serial_process()
self.add_rels_to_entities()
self.final_delete()
self.init_query_dict()
def __init__(self, query_data, dependency=None):
logger.info('Query Graph Parsing...')
self.error_info = None
# print('Query Graph Parsing...')
self.relation = query_data.setdefault('relation', list())
self.entity = query_data.setdefault('entity', list())
self.pre_process()
self.intent = query_data['intent']
self.dependency = dependency
self.relation_component_list = list()
self.entity_component_list = list()
# 获取实体和关系对应的子图组件
self.init_relation_component()
self.init_entity_component()
# 若有依存分析，根据依存分析来获取组件图
if self.dependency and len(self.dependency) > 0:
logger.info('dependency exist.')
# print('dependency exist.')
dm = DepMap(self.dependency, self.relation_component_list,
self.entity_component_list)
if dm.check_dep(
) and dm.dep_graph and nx.algorithms.is_weakly_connected(
dm.dep_graph):
self.query_graph = dm.dep_graph
self.query_graph = None
# 得到子图组件构成的集合，用图表示
# self.component_graph = nx.disjoint_union_all(self.relation_component_list + self.entity_component_list)
# self.component_graph的顺序决定了节点合并顺序，对最终构建的图有很大影响
self.component_graph = my_disjoint_union_all(
self.entity_component_list + self.relation_component_list)
self.query_graph = copy.deepcopy(self.component_graph)
self.query_graph = Graph(self.query_graph)
self.old_query_graph = copy.deepcopy(self.component_graph)
self.node_type_dict = self.query_graph.node_type_statistic()
self.component_assemble()
while len(self.query_graph.nodes) != len(self.old_query_graph.nodes) \
and not nx.algorithms.is_weakly_connected(self.query_graph):
# 节点一样多说明上一轮没有合并
# 图已连通也不用合并
self.old_query_graph = copy.deepcopy(self.query_graph)
self.node_type_dict = self.query_graph.node_type_statistic()
self.component_assemble()
if not self.query_graph:
self.error_info = '问句缺失必要实体'
return
while not nx.algorithms.is_weakly_connected(self.query_graph):
# 若不连通则在联通分量之间添加默认边
flag = self.add_default_edge()
if not flag:
logger.info('default edge missing!')
logger.info('graph is not connected!')
self.error_info = 'graph is not connected!'
# 未添加上说明缺少默认边
return
# 经过上面两个循环，得到连通的图，下面确定意图
logger.info('connected graph is already')
self.query_graph = nx.convert_node_labels_to_integers(self.query_graph)
self.query_graph = Graph(self.query_graph)
self.query_graph.show_log()
logger.info('next is determine intention')
self.determine_intention()