从零到一：如何构建一个基于知识图谱的智能问答助手？

┌────────────────┬──────────────────────────────────────┐
│                │                                      │
│                │  Speech                              │
│     ┌──────────▼──────────┐                           │
│     │            Frontend │   Siwi, /ˈsɪwi/           │
│     │ Web_Speech_API      │   A PoC of                │
│     │                     │   Dialog System           │
│     │ Vue.JS              │   With Graph Database     │
│     │                     │   Backed Knowledge Graph  │
│     └──────────┬──────────┘                           │
│                │  Sentence                            │
│   ┌────────────┼──────────────────────────────┐       │
│   │            │              Backend         │       │
│   │ ┌──────────▼──────────┐                   │       │
│   │ │ Web API, Flask      │   ./app/          │       │
│   │ └──────────┬──────────┘                   │       │
│   │            │  Sentence    ./bot/          │       │
│   │ ┌──────────▼──────────┐                   │       │
│   │ │ Intent matching,    │   ./bot/classifier│       │
│   │ │ Symentic Processing │                   │       │
│   │ └──────────┬──────────┘                   │       │
│   │            │  Intent, Entities            │       │
│   │ ┌──────────▼──────────┐                   │       │
│   │ │ Intent Actor        │   ./bot/actions   │       │
│   └─┴──────────┬──────────┴───────────────────┘       │
│                │  Graph Query                         │
│     ┌──────────▼──────────┐                           │
│     │ Graph Database      │    Nebula Graph           │
│     └─────────────────────┘                           │
└───────────────────────────────────────────────────────┘

┌────────────┼──────────────────────────────┐
│            │              Backend         │
│ ┌──────────▼──────────┐                   │
│ │ Web API, Flask      │   ./app/          │
│ └──────────┬──────────┘                   │
│            │  Sentence    ./bot/          │
│ ┌──────────▼──────────┐                   │
│ │ Intent matching,    │   ./bot/classifier│
│ │ Symentic Processing │                   │
│ └──────────┬──────────┘                   │
│            │  Intent, Entities            │
│ ┌──────────▼──────────┐                   │
│ │ Intent Actor        │   ./bot/actions   │
└─┴──────────┬──────────┴───────────────────┘
             │  Graph Query
  ┌──────────▼──────────┐
  │ Graph Database      │    Nebula Graph
  └─────────────────────┘

#...
from siwi.bot import bot

#...
@app.route("/query", methods=["POST"])
def query():
    request_data = request.get_json()
    question = request_data.get("question", "") # <----- 1.
    if question:
        answer = siwi_bot.query(
            request_data.get("question", ""))   # <----- 2.
    else:
        answer = "Sorry, what did you say?"
    return jsonify({"answer": answer})

from siwi.bot.actions import SiwiActions
from siwi.bot.classifier import SiwiClassifier


class SiwiBot():
    def __init__(self, connection_pool) -> None:
        self.classifier = SiwiClassifier()
        self.actions = SiwiActions()
        self.connection_pool = connection_pool

    def query(self, sentence):
        intent = self.classifier.get(sentence) # <--- a.
        action = self.actions.get(intent)      # <--- b.
        return action.execute(self.connection_pool)

class SiwiClassifier():
    def get(self, sentence: str) -> dict:
        """
        Classify Sentences and Fill Slots.
        This should be done by NLP, here we fake one to demostrate
        the intent Actor --> Graph DB work flow.

        sentense:
          relation:
            - What is the relationship between Yao Ming and Lakers?
            - How does Tracy McGrady and Lakers connected?
          serving:
            - Which team had Jonathon Simmons served?
          friendship:
            - Whom does Tim Duncan follow?
            - Who are Tracy McGrady's friends?

        returns:
        {
            "entities": entities,
            "intents": intents
        }
        """
        entities = self.get_matched_entities(sentence)
        intents = self.get_matched_intents(sentence)
        return {
            "entities": entities,
            "intents": intents
        }

---
intents:
  fallback:
    action:
      FallbackAction
    keywords: []
  relationship:
    action:
      RelationshipAction
    keywords:
      - between
      - relation
      - relationship
      - related
      - connect
      - correlate
  serve:
    action:
      ServeAction
    keywords:
      - serve
      - served
      - serving
  friend:
    action:
      FollowAction
    keywords:
      - follows
      - followed
      - follow
      - friend
      - friends

def setup_entity_tree(self) -> None:
    self.entity_type_map.update({
        key: "player" for key in self.players.keys()
        })
    self.entity_type_map.update({
        key: "team" for key in self.teams.keys()
        })

    self.entity_tree = ahocorasick.Automaton()
    for index, entity in enumerate(self.entity_type_map.keys()):
        self.entity_tree.add_word(entity, (index, entity))
    self.entity_tree.make_automaton()

#...

def get_matched_entities(self, sentence: str) -> dict:
    """
    Consume a sentence to be matched with ahocorasick
    Returns a dict: {entity: entity_type}
    """
    _matched = []
    for item in self.entity_tree.iter(sentence):
        entities_matched.append(item[1][1])
    return {
        entity: self.entity_type_map[entity] for entity in _matched
    }

class SiwiActions():
    def __init__(self) -> None:
        self.intent_map = {}
        self.load_data()

    def load_data(self) -> None:
        # load data from yaml files
        module_path = f"{ siwi.__path__[0] }/bot/test/data"

        with open(f"{ module_path }/intents.yaml", "r") as file:
            self.intent_map = yaml.safe_load(file)["intents"]

    def get(self, intent: dict):
        """
        returns SiwiActionBase
        """
        if len(intent["intents"]) > 0:
            intent_name = intent["intents"][0]
        else:
            intent_name = "fallback"

        cls_name = self.intent_map.get(
            intent_name).get("action") #-------> 1.
        action_cls = getattr(          #-------> 2.
            importlib.import_module("siwi.bot.actions"), cls_name)
        action = action_cls(intent)
        return action

class RelationshipAction(SiwiActionBase):
    """
    USE basketballplayer;
    FIND NOLOOP PATH
    FROM "player100" TO "team204" OVER * BIDIRECT UPTO 4 STEPS;
    """
    def __init__(self, intent):
        print(f"[DEBUG] RelationshipAction intent: { intent }")
        super().__init__(intent)
        try:
            self.entity_left, self.entity_right = intent["entities"]
            self.left_vid = self._vid(self.entity_left)
            self.right_vid = self._vid(self.entity_right)
        except Exception:
            print(
                f"[WARN] RelationshipAction entities recognition Failure "
                f"will fallback to FallbackAction, "
                f"intent: { intent }"
                )
            self.error = True

    def execute(self, connection_pool) -> str:
        self._error_check()
        query = (
            f'USE basketballplayer;'
            f'FIND NOLOOP PATH '
            f'FROM "{self.left_vid}" TO "{self.right_vid}" '
            f'OVER * BIDIRECT UPTO 4 STEPS;'
            )
        print(
            f"[DEBUG] query for RelationshipAction :\n\t{ query }"
            )
        with connection_pool.session_context("root", "nebula") as session:
            result = session.execute(query)        #--------------------> 1.

        if not result.is_succeeded():
            return (
                f"Something is wrong on Graph Database connection when query "
                f"{ query }"
                )

        if result.is_empty():
            return (
                f"There is no relationship between "
                f"{ self.entity_left } and { self.entity_right }"
                )
        path = result.row_values(0)[0].as_path()    #-------------------> 2.
        relationships = path.relationships()
        relations_str = self._name(
            relationships[0].start_vertex_id().as_string())
        for rel_index in range(path.length()):
            rel = relationships[rel_index]
            relations_str += (
                f" { rel.edge_name() }s "
                f"{ self._name(rel.end_vertex_id().as_string()) }")
        return (
            f"There are at least { result.row_size() } relations between "
            f"{ self.entity_left } and { self.entity_right }, "
            f"one relation path is: { relations_str }."
            )

cd nebula-siwi

# Install dependencies
python3 -m pip install -r src/requirements.txt

# Install siwi backend
python3 -m build

# Configure Nebula Graph Endpoint
export NG_ENDPOINTS=127.0.0.1:9669

# Run Backend API server
gunicorn --bind :5000 wsgi --workers 1 --threads 1 --timeout 60

<template>
  <div id="app">
    <VueBotUI
      :messages="msg"
      :options="botOptions"
      :bot-typing="locking"
      :input-disable="locking"
      @msg-send="msgSender"
    />
  </div>
</template>
<script>
import { VueBotUI } from 'vue-bot-ui'

<template>
  <div id="app">

     <VueBotUI
      :messages="msg"
      :options="botOptions"
      :bot-typing="locking"
      :input-disable="locking"
      @msg-send="msgSender"         ---------------- 1.
    />
  </div>
</template>

<script>
import { VueBotUI } from 'vue-bot-ui'
import axios from "axios";

export default {
  name: 'App',
  components: {
    VueBotUI,
  },
  methods: {
    msgSender(data) {
      this.msg.push({
        agent: "user",
        type: "text",
        text: data.text,
      });

      this.locking = true;

      axios.post(this.apiEndpoint, { "question": data.text }).then((response) => {
        console.log(response);   ----------------- 2.

        this.msg.push({          ----------------- 3.
          agent: "bot",
          type: "text",
          text: response.data.answer,
        });

        this.synthText = response.data.answer;
        this.agentSpeak = true;

        this.locking = false;
      });
    },
  }
}

<template>
  <div id="app">
    <button id="mic_btn" @click="record = !record">
        {{record?'👂':'🎙️'}}      --------------------------> 1.
    </button>

    <vue-web-speech
      v-model="record"
      @results="onResults"       --------------------------> 1.
      @unrecognized="unrecognized"
    >
    </vue-web-speech>

...
    <vue-web-speech-synth
      v-model="agentSpeak"
      :voice="synthVoice"
      :text="synthText"
      @list-voices="listVoices"  --------------------------> 4.
    />

  </div>
</template>

<script>
import { VueBotUI } from 'vue-bot-ui'
import axios from "axios";

export default {
  name: 'App',
  components: {
    VueBotUI,
  },
  onResults (data) {             -------------------------> 2.
      this.results = data;
      this.locking = true;

      this.msg.push({
        agent: "user",
        type: "text",
        text: data[0],
      });

      this.locking = true;
      console.log(data[0]);
      axios.post(this.apiEndpoint, { "question": data[0] }).then((response) => {
        console.log(response.data);

        this.msg.push({
          agent: "bot",
          type: "text",
          text: response.data.answer,
        });

        this.synthText = response.data.answer;  ----------> 3.
        this.agentSpeak = true;
      });
      this.locking = false;
    },
  }
}
</script>

.
├── README.md
├── src
│   ├── siwi                        # Siwi-API Backend
│   │   ├── app                     # Web Server, take HTTP requests and calls Bot API
│   │   └── bot                     # Bot API
│   │       ├── actions             # Take Intent, Slots, Query Knowledge Graph here
│   │       ├── bot                 # Entrypoint of the Bot API
│   │       ├── classifier          # Symentic Parsing, Intent Matching, Slot Filling
│   │       └── test                # Example Data Source as equivalent/mocked module
│   └── siwi_frontend               # Browser End
│       ├── README.md
│       ├── package.json
│       └── src
│           ├── App.vue             # Listening to user and pass Questions to Siwi-API
│           └── main.js
└── wsgi.py