Merge pull request #90 from aws-samples/feature/customer_label

Add: Another call category item, CUST
aws-samples · Mar 5, 2022 · 144174e · 144174e
2 parents 4fd093d + c2eb9bf
commit 144174e
Show file tree

Hide file tree

Showing 6 changed files with 71 additions and 12 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -5,6 +5,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
+- Added call filename regex for CUST metadata, meant to be used as a customer identifier.
 
 ## [0.1.3] - 2022-01-14
 ### Fixed

diff --git a/pca-main.template b/pca-main.template
@@ -245,7 +245,7 @@ Parameters:
       Regular Expression (regex) used to parse call GUID from audio filenames. 
       The GUID value must be matched using one or more parenthesized groups in the regex. 
       Example: the regex '_GUID_(.*?)_' parses
-      the filename: AutoRepairs1_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+      the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
       to extract the GUID value '2a602c1a-4ca3-4d37-a933-444d575c0222'.
 
   FilenameAgentRegex:
@@ -255,9 +255,19 @@ Parameters:
       Regular Expression (regex) used to parse call AGENT from audio filenames. 
       The AGENT value must be matched using one or more parenthesized groups in the regex. 
       Example: the regex '_AGENT_(.*?)_' parses
-      the filename: AutoRepairs1_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+      the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
       to extract the AGENT value 'BobS'. 
-
+
+  FilenameCustRegex:
+    Type: String
+    Default: '_CUST_(.*?)_'
+    Description: >
+      Regular Expression (regex) used to parse Customer from audio filenames. 
+      The customer id value must be matched using one or more parenthesized groups in the regex. 
+      Example: the regex '_CUST_(.*?)_' parses
+      the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+      to extract the Customer value '12345'.
+
   EnableTranscriptKendraSearch:
     Type: String
     Default: 'No'
@@ -336,6 +346,7 @@ Metadata:
                   - FilenameDatetimeFieldMap
                   - FilenameGUIDRegex
                   - FilenameAgentRegex
+                  - FilenameCustRegex
             - Label:
                 default: Transcription
               Parameters:
@@ -630,6 +641,7 @@ Resources:
         FilenameDatetimeFieldMap: !Ref FilenameDatetimeFieldMap
         FilenameGUIDRegex: !Ref FilenameGUIDRegex
         FilenameAgentRegex: !Ref FilenameAgentRegex
+        FilenameCustRegex: !Ref FilenameCustRegex
         KendraIndexId:
           !If
           - ShouldEnableKendraSearch

diff --git a/pca-server/cfn/lib/glue-database.template b/pca-server/cfn/lib/glue-database.template
@@ -42,7 +42,7 @@ Resources:
         StorageDescriptor: 
           Columns: 
             - Name: conversationanalytics
-              Type: struct<guid:string,agent:string,conversationtime:string,conversationlocation:string,processtime:string,languagecode:string,duration:string,speakerlabels:array<struct<speaker:string,displaytext:string>>,sentimenttrends:struct<spk_0:struct<sentimentscore:double,sentimentperquarter:array<struct<quarter:int,score:double,beginoffsetsecs:double,endoffsetsecs:double>>,sentimentchange:double>,spk_1:struct<sentimentscore:double,sentimentperquarter:array<struct<quarter:int,score:double,beginoffsetsecs:double,endoffsetsecs:double>>,sentimentchange:double>>,speakertime:struct<spk_0:struct<totaltimesecs:double>,spk_1:struct<totaltimesecs:double>,nontalktime:struct<instances:array<struct<beginoffsetsecs:double,endoffsetsecs:double,durationsecs:double>>,totaltimesecs:double>>,categoriesdetected:array<string>,issuesdetected:array<struct<text:string,beginoffset:int,endoffset:int>>,customentities:array<struct<name:string,instances:int,values:array<string>>>,sourceinformation:array<struct<transcribejobinfo:struct<transcribeapitype:string,completiontime:string,mediaformat:string,mediasampleratehertz:int,mediaoriginaluri:string,averagewordconfidence:double,mediafileuri:string,transcriptionjobname:string,channelidentification:int>>>,entityrecognizername:string>
+              Type: struct<guid:string,agent:string,cust:string,conversationtime:string,conversationlocation:string,processtime:string,languagecode:string,duration:string,speakerlabels:array<struct<speaker:string,displaytext:string>>,sentimenttrends:struct<spk_0:struct<sentimentscore:double,sentimentperquarter:array<struct<quarter:int,score:double,beginoffsetsecs:double,endoffsetsecs:double>>,sentimentchange:double>,spk_1:struct<sentimentscore:double,sentimentperquarter:array<struct<quarter:int,score:double,beginoffsetsecs:double,endoffsetsecs:double>>,sentimentchange:double>>,speakertime:struct<spk_0:struct<totaltimesecs:double>,spk_1:struct<totaltimesecs:double>,nontalktime:struct<instances:array<struct<beginoffsetsecs:double,endoffsetsecs:double,durationsecs:double>>,totaltimesecs:double>>,categoriesdetected:array<string>,issuesdetected:array<struct<text:string,beginoffset:int,endoffset:int>>,customentities:array<struct<name:string,instances:int,values:array<string>>>,sourceinformation:array<struct<transcribejobinfo:struct<transcribeapitype:string,completiontime:string,mediaformat:string,mediasampleratehertz:int,mediaoriginaluri:string,averagewordconfidence:double,mediafileuri:string,transcriptionjobname:string,channelidentification:int>>>,entityrecognizername:string>
             - Name: speechsegments
               Type: array<struct<segmentstarttime:double,segmentendtime:double,segmentspeaker:string,segmentinterruption:boolean,originaltext:string,displaytext:string,textedited:int,loudnessscores:array<double>,sentimentispositive:int,sentimentisnegative:int,sentimentscore:double,basesentimentscores:struct<positive:double,negative:double,neutral:double>,entitiesdetected:array<struct<score:double,type:string,text:string,beginoffset:int,endoffset:int>>,categoriesdetected:array<string>,followoncategories:array<string>,issuesdetected:array<struct<text:string,beginoffset:int,endoffset:int>>,wordconfidence:array<struct<text:string,confidence:double,starttime:double,endtime:double>>>>
           Compressed: false

diff --git a/pca-server/src/pca/pca-aws-sf-process-turn-by-turn.py b/pca-server/src/pca/pca-aws-sf-process-turn-by-turn.py
@@ -68,6 +68,7 @@ def __init__(self, min_sentiment_pos, min_sentiment_neg, custom_entity_endpoint)
         self.comprehendLanguageCode = ""
         self.guid = ""
         self.agent = ""
+        self.cust = ""
         self.conversationTime = ""
         self.conversationLocation = ""
         self.speechSegmentList = []
@@ -212,6 +213,7 @@ def create_output_conversation_analytics(self):
         # but to default this to the current processing time.
         resultsHeaderInfo["GUID"] = self.guid
         resultsHeaderInfo["Agent"] = self.agent
+        resultsHeaderInfo["Cust"] = self.cust
         resultsHeaderInfo["ConversationTime"] = self.conversationTime
         resultsHeaderInfo["ConversationLocation"] = self.conversationLocation
         resultsHeaderInfo["ProcessTime"] = str(datetime.now())
@@ -1271,7 +1273,7 @@ def set_guid(self, filename):
         Tries to parse a GUID for the call from the filename using a configurable Regular Expression.
         The GUID value must be matched using one or more parenthesized groups in the regex. 
         Example: the regex '_GUID_(.*?)_' parses
-        the filename: AutoRepairs1_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+        the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
         to extract the GUID value '2a602c1a-4ca3-4d37-a933-444d575c0222'.        
         '''
         regex = cf.appConfig[cf.CONF_FILENAME_GUID_REGEX]
@@ -1290,7 +1292,7 @@ def set_agent(self, filename):
         Tries to parse an Agent name or ID from the filename using a configurable Regular Expression.
         The AGENT value must be matched using one or more parenthesized groups in the regex. 
         Example: the regex '_AGENT_(.*?)_' parses
-        the filename: AutoRepairs1_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+        the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
         to extract the Agent value 'BobS'.        
         '''
         regex = cf.appConfig[cf.CONF_FILENAME_AGENT_REGEX]
@@ -1304,6 +1306,25 @@ def set_agent(self, filename):
             agent='None'
         self.agent = agent
 
+    def set_cust(self, filename):
+        '''
+        Regular Expression (regex) used to parse Customer from audio filenames. 
+        The customer id value must be matched using one or more parenthesized groups in the regex. 
+        Example: the regex '_CUST_(.*?)_' parses
+        the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+        to extract the Customer value '12345'.        
+        '''
+        regex = cf.appConfig[cf.CONF_FILENAME_CUST_REGEX]
+        print(f"INFO: Parsing CUST from filename '{filename}' using regex: '{regex}'.")
+        try:
+            match = re.search(regex, filename)
+            cust = " ".join(match.groups()) or 'None'
+            print(f"INFO: Parsed CUST: '{cust}'")
+        except:
+            print(f"WARNING: Unable to parse CUST name/ID from filename {filename}, using regex: '{regex}'. Defaulting to 'None'.")
+            cust='None'
+        self.cust = cust
+
     def load_simple_entity_string_map(self):
         """
         Loads in any defined simple entity map for later use - this must be a CSV file, but it will be defined
@@ -1463,6 +1484,7 @@ def parse_transcribe_file(self, sf_event):
         # Parse Call GUID and Agent Name/ID from filename if possible
         self.set_guid(job_name)
         self.set_agent(job_name)
+        self.set_cust(job_name)
 
         # Work out the conversation time and set the language code
         self.calculate_transcribe_conversation_time(job_name)

diff --git a/pca-server/src/pca/pcaconfiguration.py b/pca-server/src/pca/pcaconfiguration.py
@@ -36,6 +36,7 @@
 CONF_FILENAME_DATETIME_FIELDMAP = "FilenameDatetimeFieldMap"
 CONF_FILENAME_GUID_REGEX = "FilenameGUIDRegex"
 CONF_FILENAME_AGENT_REGEX = "FilenameAgentRegex"
+CONF_FILENAME_CUST_REGEX = "FilenameCustRegex"
 CONF_FILTER_MODE = "VocabFilterMode"
 CONF_FILTER_NAME = "VocabFilterName"
 CONF_KENDRA_INDEX_ID = "KendraIndexId"
@@ -122,8 +123,8 @@ def loadConfiguration():
                                                CONF_FILTER_MODE, CONF_FILTER_NAME, 
                                                CONF_FILENAME_DATETIME_REGEX, CONF_FILENAME_DATETIME_FIELDMAP,
                                                CONF_FILENAME_GUID_REGEX, CONF_FILENAME_AGENT_REGEX,
-                                               CONF_KENDRA_INDEX_ID])
-    fullParamList4 = ssm.get_parameters(Names=[CONF_WEB_URI, CONF_TRANSCRIBE_API, CONF_REDACTION_TRANSCRIPT,
+                                               CONF_FILENAME_CUST_REGEX])
+    fullParamList4 = ssm.get_parameters(Names=[CONF_KENDRA_INDEX_ID, CONF_WEB_URI, CONF_TRANSCRIBE_API, CONF_REDACTION_TRANSCRIPT,
                                                CONF_REDACTION_AUDIO])
 
     # Extract our parameters into our config

diff --git a/pca-ssm/cfn/ssm.template b/pca-ssm/cfn/ssm.template
@@ -200,7 +200,7 @@ Parameters:
       Regular Expression (regex) used to parse call GUID from audio filenames. 
       The GUID value must be matched using a parenthesized group in the regex. 
       Example: the regex '_GUID_(.*?)_' parses
-      the filename: AutoRepairs1_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+      the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
       to extract the GUID value '2a602c1a-4ca3-4d37-a933-444d575c0222'.
 
   FilenameAgentRegex:
@@ -210,9 +210,19 @@ Parameters:
       Regular Expression (regex) used to parse call AGENT from audio filenames. 
       The AGENT value must be matched using a parenthesized group in the regex. 
       Example: the regex '_AGENT_(.*?)_' parses
-      the filename: AutoRepairs1_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+      the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
       to extract the AGENT value 'BobS'.  
 
+  FilenameCustRegex:
+    Type: String
+    Default: '_CUST_(.*?)_'
+    Description: >
+      Regular Expression (regex) used to parse Customer from audio filenames. 
+      The customer id value must be matched using one or more parenthesized groups in the regex. 
+      Example: the regex '_CUST_(.*?)_' parses
+      the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+      to extract the Customer value '12345'.
+
   KendraIndexId:
     Type: String
     Description: Kendra Index ID, or empty string if call transcription indexing is not enabled 
@@ -520,7 +530,7 @@ Resources:
         Regular Expression (regex) used to parse call GUID from audio filenames. 
         The GUID value must be matched using one or more parenthesized groups in the regex. 
         Example: the regex '_GUID_(.*?)_' parses
-        the filename: AutoRepairs1_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+        the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
         to extract the GUID value '2a602c1a-4ca3-4d37-a933-444d575c0222'.
 
   FilenameAgentRegexParameter:
@@ -533,9 +543,22 @@ Resources:
         Regular Expression (regex) used to parse call AGENT from audio filenames. 
         The AGENT value must be matched using one or more parenthesized groups in the regex. 
         Example: the regex '_AGENT_(.*?)_' parses
-        the filename: AutoRepairs1_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+        the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
         to extract the AGENT value 'BobS'.
 
+  FilenameCustRegexParameter:
+    Type: "AWS::SSM::Parameter"
+    Properties:
+      Name: FilenameCustRegex
+      Type: String
+      Value: !Ref FilenameCustRegex
+      Description: >
+        Regular Expression (regex) used to parse Customer from audio filenames. 
+        The customer id value must be matched using one or more parenthesized groups in the regex. 
+        Example: the regex '_CUST_(.*?)_' parses
+        the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
+        to extract the Customer value '12345'.
+
   KendraIndexIdParameter:
     Type: "AWS::SSM::Parameter"
     Properties: