requirements.txt

@@ -2,5 +2,5 @@ flair==0.13.1
 conllu==4.5.3
 pandas==1.5.3
 numpy==1.26.4
-torch==2.3.0
+torch==1.13
 convlab==3.0.2a0

src/service/data/restaurant/db/confirm_db.json

@@ -0,0 +1,4 @@
+[
+  "true",
+  "false"
+]

src/service/data/restaurant/db/dough_db.json

@@ -0,0 +1,5 @@
+[
+    "pepsi", 
+    "cola", 
+    "water"
+]

src/service/data/restaurant/db/drink_db.json

@@ -0,0 +1,11 @@
+[
+    {
+        "name":"pepsi"
+    },
+    {
+        "name":"cola"
+    },
+    {
+        "name":"water"
+    }
+]

src/service/data/restaurant/db/food_db.json

@@ -0,0 +1,3 @@
+[
+    "pizza"
+]

src/service/data/restaurant/db/meat_db.json

@@ -0,0 +1,5 @@
+[
+    "chicken", 
+    "ham", 
+    "tuna"
+]

src/service/data/restaurant/db/menu_db.json

@@ -0,0 +1,7 @@
+[
+    "capri", 
+    "margarita",
+    "hawajska",
+    "barcelona",
+    "tuna"
+]

src/service/data/restaurant/db/pizza_db.json

@@ -0,0 +1,51 @@
+[
+    {
+        "name": "capri",
+        "ingredient": [
+            "tomato",
+            "ham",
+            "mushrooms",
+            "cheese"
+        ],
+        "price": 25
+    },
+    {
+        "name": "margarita",
+        "ingredient": [
+            "tomato",
+            "cheese"
+        ],
+        "price": 20
+    },
+    {
+        "name": "hawajska",
+        "ingredient": [
+            "tomato",
+            "pineapple",
+            "chicken",
+            "cheese"
+        ],
+        "price": 30
+    },
+    {
+        "name": "barcelona",
+        "ingredient": [
+            "tomato",
+            "onion",
+            "ham",
+            "pepper",
+            "cheese"
+        ],
+        "price": 40
+    },
+    {
+        "name": "tuna",
+        "ingredient": [
+            "tomato",
+            "tuna",
+            "onion",
+            "cheese"
+        ],
+        "price": 40
+    }
+]

src/service/data/restaurant/db/sauce_db.json

@@ -0,0 +1,4 @@
+[
+    "garlic", 
+    "1000w"
+]

src/service/data/restaurant/db/size_db.json

@@ -0,0 +1,14 @@
+[
+    {
+        "size": "m",
+        "price_multiplier": 1
+    },
+    {
+        "size": "l",
+        "price_multiplier": 1.2
+    },
+    {
+        "size": "xl",
+        "price_multiplier": 1.4
+    }
+]

src/service/dbquery.py

@@ -0,0 +1,91 @@
+"""
+"""
+import json
+import os
+import random
+from fuzzywuzzy import fuzz
+from itertools import chain
+from copy import deepcopy
+
+
+class Database(object):
+    def __init__(self):
+        super(Database, self).__init__()
+        # loading databases
+        domains = ['restaurant', 'hotel', 'attraction', 'train', 'hospital', 'taxi', 'police']
+        self.dbs = {}
+        for domain in domains:
+            with open(os.path.join(os.path.dirname(
+                    os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))),
+                    'data/restaurant/db/{}_db.json'.format(domain))) as f:
+                self.dbs[domain] = json.load(f)
+
+    def query(self, domain, constraints, ignore_open=False, soft_contraints=(), fuzzy_match_ratio=60):
+        """Returns the list of entities for a given domain
+        based on the annotation of the belief state"""
+        # query the db
+        if domain == 'taxi':
+            return [{'taxi_colors': random.choice(self.dbs[domain]['taxi_colors']),
+            'taxi_types': random.choice(self.dbs[domain]['taxi_types']),
+            'taxi_phone': ''.join([str(random.randint(1, 9)) for _ in range(11)])}]
+        if domain == 'police':
+            return deepcopy(self.dbs['police'])
+        if domain == 'hospital':
+            department = None
+            for key, val in constraints:
+                if key == 'department':
+                    department = val
+            if not department:
+                return deepcopy(self.dbs['hospital'])
+            else:
+                return [deepcopy(x) for x in self.dbs['hospital'] if x['department'].lower() == department.strip().lower()]
+        constraints = list(map(lambda ele: ele if not(ele[0] == 'area' and ele[1] == 'center') else ('area', 'centre'), constraints))
+
+        found = []
+        for i, record in enumerate(self.dbs[domain]):
+            constraints_iterator = zip(constraints, [False] * len(constraints))
+            soft_contraints_iterator = zip(soft_contraints, [True] * len(soft_contraints))
+            for (key, val), fuzzy_match in chain(constraints_iterator, soft_contraints_iterator):
+                if val == "" or val == "dont care" or val == 'not mentioned' or val == "don't care" or val == "dontcare" or val == "do n't care":
+                    pass
+                else:
+                    try:
+                        record_keys = [k.lower() for k in record]
+                        if key.lower() not in record_keys:
+                            continue
+                        if key == 'leaveAt':
+                            val1 = int(val.split(':')[0]) * 100 + int(val.split(':')[1])
+                            val2 = int(record['leaveAt'].split(':')[0]) * 100 + int(record['leaveAt'].split(':')[1])
+                            if val1 > val2:
+                                break
+                        elif key == 'arriveBy':
+                            val1 = int(val.split(':')[0]) * 100 + int(val.split(':')[1])
+                            val2 = int(record['arriveBy'].split(':')[0]) * 100 + int(record['arriveBy'].split(':')[1])
+                            if val1 < val2:
+                                break
+                        # elif ignore_open and key in ['destination', 'departure', 'name']:
+                        elif ignore_open and key in ['destination', 'departure']:
+                            continue
+                        elif record[key].strip() == '?':
+                            # '?' matches any constraint
+                            continue
+                        else:
+                            if not fuzzy_match:
+                                if val.strip().lower() != record[key].strip().lower():
+                                    break
+                            else:
+                                if fuzz.partial_ratio(val.strip().lower(), record[key].strip().lower()) < fuzzy_match_ratio:
+                                    break
+                    except:
+                        continue
+            else:
+                res = deepcopy(record)
+                res['Ref'] = '{0:08d}'.format(i)
+                found.append(res)
+
+        return found
+
+
+if __name__ == '__main__':
+    db = Database()
+    print(db.query("train", [['departure', 'cambridge'], ['destination','peterborough'], ['day', 'tuesday'], ['arriveBy', '11:15']]))

src/service/dialog_policy.py

@@ -1,8 +1,59 @@
-from model.frame import Frame
+from collections import defaultdict
+import copy
+import json
+from copy import deepcopy
 
-class DialogPolicy:
+from convlab.policy.policy import Policy
-    def next_dialogue_act(self, frames: list[Frame]) -> Frame:
+from dbquery import Database
-        if frames[-1].act == "welcomemsg":
+
-            return Frame("system", "welcomemsg", [])
+class SimpleRulePolicy(Policy):
-        else:
+    def __init__(self):
-            return Frame("system", "canthelp", [])
+        Policy.__init__(self)
+        self.db = Database()
+
+    def predict(self, state):
+        self.results = []
+        system_action = defaultdict(list)
+        user_action = defaultdict(list)
+
+        for intent, domain, slot, value in state['user_action']:
+            user_action[(domain.lower(), intent.lower())].append((slot.lower(), value))
+
+        for user_act in user_action:
+            self.update_system_action(user_act, user_action, state, system_action)
+
+        # Reguła 3
+        if any(True for slots in user_action.values() for (slot, _) in slots if slot in ['book stay', 'book day', 'book people']):
+            if self.results:
+                system_action = {('Booking', 'Book'): [["Ref", self.results[0].get('Ref', 'N/A')]]}
+
+        system_acts = [[intent, domain, slot, value] for (domain, intent), slots in system_action.items() for slot, value in slots]
+        state['system_action'] = system_acts
+        return system_acts
+
+    def update_system_action(self, user_act, user_action, state, system_action):
+        domain, intent = user_act
+        constraints = [(slot, value) for slot, value in state['belief_state'][domain.lower()].items() if value != '']
+        self.results = deepcopy(self.db.query(domain.lower(), constraints))
+
+        # Reguła 1
+        if intent == 'request':
+            if len(self.results) == 0:
+                system_action[(domain, 'NoOffer')] = []
+            else:
+                for slot in user_action[user_act]:                  
+                    if slot[0] in self.results[0]:
+                        system_action[(domain, 'Inform')].append([slot[0], self.results[0].get(slot[0], 'unknown')])
+
+        # Reguła 2
+        elif intent == 'inform':
+            if len(self.results) == 0:
+                system_action[(domain, 'NoOffer')] = []
+            else:
+                system_action[(domain, 'Inform')].append(['Choice', str(len(self.results))])
+                choice = self.results[0]
+
+                if domain in ["hotel", "attraction", "police", "restaurant"]:
+                    system_action[(domain, 'Recommend')].append(['Name', choice['name']])
+
+dialogPolicy = SimpleRulePolicy()