- JSON representation
- CallMetadata
- ConversationDataSource
- GcsSource
- DialogflowSource
- QualityMetadata
- AgentInfo
- Transcript
- TranscriptSegment
- WordInfo
- ConversationParticipant
- DialogflowSegmentMetadata
- ConversationSummarizationSuggestionData
- RuntimeAnnotation
- FaqAnswerData
- SmartReplyData
- SmartComposeSuggestionData
- DialogflowInteractionData
- UserInput
- DialogflowIntent
- DialogflowCxConversationData
- QueryInputStats
- MatchTypeStats
The conversation resource.
JSON representation |
---|
{ "name": string, "dataSource": { object ( |
Fields | |
---|---|
name |
Immutable. The resource name of the conversation. Format: projects/{project}/locations/{location}/conversations/{conversation} |
data |
The source of the audio and transcription for the conversation. |
create |
Output only. The time at which the conversation was created. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
update |
Output only. The most recent time at which the conversation was updated. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
start |
The time at which the conversation started. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
language |
A user-specified language code for the conversation. |
agent |
An opaque, user-specified string representing the human agent who handled the conversation. |
customer |
An opaque, user-specified string representing the customer identifier. |
labels |
A map for the user to specify any custom fields. A maximum of 20 labels per conversation is allowed, with a maximum of 256 characters per entry. An object containing a list of |
quality |
Conversation metadata related to quality management. |
metadata |
Input only. JSON metadata encoded as a string. This field is primarily used by Insights integrations with various telphony systems and must be in one of Insight's supported formats. |
transcript |
Output only. The conversation transcript. |
medium |
Immutable. The conversation medium, if unspecified will default to PHONE_CALL. |
duration |
Output only. The duration of the conversation. A duration in seconds with up to nine fractional digits, ending with ' |
turn |
Output only. The number of turns in the conversation. |
latest |
Output only. The conversation's latest analysis, if one exists. |
latest |
Output only. Latest summary of the conversation. |
runtime |
Output only. The annotations that were generated during the customer and agent interaction. |
dialogflow |
Output only. All the matched Dialogflow intents in the call. The key corresponds to a Dialogflow intent, format: projects/{project}/agent/{agent}/intents/{intent} An object containing a list of |
obfuscated |
Obfuscated user ID which the customer sent to us. |
dialogflow |
The Dialogflow conversation raw data. It will only be populated when ConversationView is DF_CONVERSATION_BASIC or DF_CONVERSATION_FULL. |
Union field metadata . Metadata that applies to the conversation. metadata can be only one of the following: |
|
call |
Call-specific metadata. |
Union field expiration . A time to live expiration setting, can be either a specified timestamp or a duration from the time that the conversation creation request was received. Conversations with an expiration set will be removed up to 24 hours after the specified time. expiration can be only one of the following: |
|
expire |
The time at which this conversation should expire. After this time, the conversation data and any associated analyses will be deleted. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
ttl |
Input only. The TTL for this resource. If specified, then this TTL will be used to calculate the expire time. A duration in seconds with up to nine fractional digits, ending with ' |
CallMetadata
Call-specific metadata.
JSON representation |
---|
{ "customerChannel": integer, "agentChannel": integer } |
Fields | |
---|---|
customer |
The audio channel that contains the customer. |
agent |
The audio channel that contains the agent. |
ConversationDataSource
The conversation source, which is a combination of transcript and audio.
JSON representation |
---|
{ // Union field |
Fields | |
---|---|
Union field source . The source of the conversation. source can be only one of the following: |
|
gcs |
A Cloud Storage location specification for the audio and transcript. |
dialogflow |
The source when the conversation comes from Dialogflow. |
GcsSource
A Cloud Storage source of conversation data.
JSON representation |
---|
{ "audioUri": string, "transcriptUri": string, "metadataUri": string } |
Fields | |
---|---|
audio |
Cloud Storage URI that points to a file that contains the conversation audio. |
transcript |
Immutable. Cloud Storage URI that points to a file that contains the conversation transcript. |
metadata |
Cloud Storage URI that points to a file that contains the conversation metadata. |
DialogflowSource
A Dialogflow source of conversation data.
JSON representation |
---|
{ "dialogflowConversation": string, "audioUri": string } |
Fields | |
---|---|
dialogflow |
Output only. The name of the Dialogflow conversation that this conversation resource is derived from. Format: projects/{project}/locations/{location}/conversations/{conversation} |
audio |
Cloud Storage URI that points to a file that contains the conversation audio. |
QualityMetadata
Conversation metadata related to quality management.
JSON representation |
---|
{
"customerSatisfactionRating": integer,
"waitDuration": string,
"menuPath": string,
"agentInfo": [
{
object ( |
Fields | |
---|---|
customer |
An arbitrary integer value indicating the customer's satisfaction rating. |
wait |
The amount of time the customer waited to connect with an agent. A duration in seconds with up to nine fractional digits, ending with ' |
menu |
An arbitrary string value specifying the menu path the customer took. |
agent |
Information about agents involved in the call. |
AgentInfo
Information about an agent involved in the conversation.
JSON representation |
---|
{ "agentId": string, "displayName": string, "team": string, "dispositionCode": string } |
Fields | |
---|---|
agent |
A user-specified string representing the agent. |
display |
The agent's name. |
team |
A user-specified string representing the agent's team. |
disposition |
A user-provided string indicating the outcome of the agent's segment of the call. |
Transcript
A message representing the transcript of a conversation.
JSON representation |
---|
{
"transcriptSegments": [
{
object ( |
Fields | |
---|---|
transcript |
A list of sequential transcript segments that comprise the conversation. |
TranscriptSegment
A segment of a full transcript.
JSON representation |
---|
{ "messageTime": string, "text": string, "confidence": number, "words": [ { object ( |
Fields | |
---|---|
message |
The time that the message occurred, if provided. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
text |
The text of this segment. |
confidence |
A confidence estimate between 0.0 and 1.0 of the fidelity of this segment. A default value of 0.0 indicates that the value is unset. |
words[] |
A list of the word-specific information for each word in the segment. |
language |
The language code of this segment as a BCP-47 language tag. Example: "en-US". |
channel |
For conversations derived from multi-channel audio, this is the channel number corresponding to the audio from that channel. For audioChannelCount = N, its output values can range from '1' to 'N'. A channel tag of 0 indicates that the audio is mono. |
segment |
The participant of this segment. |
dialogflow |
CCAI metadata relating to the current transcript segment. |
sentiment |
The sentiment for this transcript segment. |
WordInfo
Word-level info for words in a transcript.
JSON representation |
---|
{ "startOffset": string, "endOffset": string, "word": string, "confidence": number } |
Fields | |
---|---|
start |
Time offset of the start of this word relative to the beginning of the total conversation. A duration in seconds with up to nine fractional digits, ending with ' |
end |
Time offset of the end of this word relative to the beginning of the total conversation. A duration in seconds with up to nine fractional digits, ending with ' |
word |
The word itself. Includes punctuation marks that surround the word. |
confidence |
A confidence estimate between 0.0 and 1.0 of the fidelity of this word. A default value of 0.0 indicates that the value is unset. |
ConversationParticipant
The call participant speaking for a given utterance.
JSON representation |
---|
{ "dialogflowParticipant": string, "obfuscatedExternalUserId": string, "role": enum ( |
Fields | |
---|---|
dialogflowParticipant |
Deprecated. Use |
obfuscated |
Obfuscated user ID from Dialogflow. |
role |
The role of the participant. |
Union field
|
|
dialogflow |
The name of the participant provided by Dialogflow. Format: projects/{project}/locations/{location}/conversations/{conversation}/participants/{participant} |
user |
A user-specified ID representing the participant. |
DialogflowSegmentMetadata
Metadata from Dialogflow relating to the current transcript segment.
JSON representation |
---|
{ "smartReplyAllowlistCovered": boolean } |
Fields | |
---|---|
smart |
Whether the transcript segment was covered under the configured smart reply allowlist in Agent Assist. |
ConversationSummarizationSuggestionData
Conversation summarization suggestion data.
JSON representation |
---|
{ "text": string, "textSections": { string: string, ... }, "confidence": number, "metadata": { string: string, ... }, "answerRecord": string, "conversationModel": string } |
Fields | |
---|---|
text |
The summarization content that is concatenated into one string. |
text |
The summarization content that is divided into sections. The key is the section's name and the value is the section's content. There is no specific format for the key or value. An object containing a list of |
confidence |
The confidence score of the summarization. |
metadata |
A map that contains metadata about the summarization and the document from which it originates. An object containing a list of |
answer |
The name of the answer record. Format: projects/{project}/locations/{location}/answerRecords/{answerRecord} |
conversation |
The name of the model that generates this summary. Format: projects/{project}/locations/{location}/conversationModels/{conversationModel} |
RuntimeAnnotation
An annotation that was generated during the customer and agent interaction.
JSON representation |
---|
{ "annotationId": string, "createTime": string, "startBoundary": { object ( |
Fields | |
---|---|
annotation |
The unique identifier of the annotation. Format: projects/{project}/locations/{location}/conversationDatasets/{dataset}/conversationDataItems/{data_item}/conversationAnnotations/{annotation} |
create |
The time at which this annotation was created. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
start |
The boundary in the conversation where the annotation starts, inclusive. |
end |
The boundary in the conversation where the annotation ends, inclusive. |
answer |
The feedback that the customer has about the answer in |
user |
Explicit input used for generating the answer |
Union field data . The data in the annotation. data can be only one of the following: |
|
article |
Agent Assist Article Suggestion data. |
faq |
Agent Assist FAQ answer data. |
smart |
Agent Assist Smart Reply data. |
smart |
Agent Assist Smart Compose suggestion data. |
dialogflow |
Dialogflow interaction data. |
conversation |
Conversation summarization suggestion data. |
FaqAnswerData
Agent Assist frequently-asked-question answer data.
JSON representation |
---|
{ "answer": string, "confidenceScore": number, "question": string, "metadata": { string: string, ... }, "queryRecord": string, "source": string } |
Fields | |
---|---|
answer |
The piece of text from the |
confidence |
The system's confidence score that this answer is a good match for this conversation, ranging from 0.0 (completely uncertain) to 1.0 (completely certain). |
question |
The corresponding FAQ question. |
metadata |
Map that contains metadata about the FAQ answer and the document that it originates from. An object containing a list of |
query |
The name of the answer record. Format: projects/{project}/locations/{location}/answerRecords/{answerRecord} |
source |
The knowledge document that this answer was extracted from. Format: projects/{project}/knowledgeBases/{knowledgeBase}/documents/{document}. |
SmartReplyData
Agent Assist Smart Reply data.
JSON representation |
---|
{ "reply": string, "confidenceScore": number, "metadata": { string: string, ... }, "queryRecord": string } |
Fields | |
---|---|
reply |
The content of the reply. |
confidence |
The system's confidence score that this reply is a good match for this conversation, ranging from 0.0 (completely uncertain) to 1.0 (completely certain). |
metadata |
Map that contains metadata about the Smart Reply and the document from which it originates. An object containing a list of |
query |
The name of the answer record. Format: projects/{project}/locations/{location}/answerRecords/{answerRecord} |
SmartComposeSuggestionData
Agent Assist Smart Compose suggestion data.
JSON representation |
---|
{ "suggestion": string, "confidenceScore": number, "metadata": { string: string, ... }, "queryRecord": string } |
Fields | |
---|---|
suggestion |
The content of the suggestion. |
confidence |
The system's confidence score that this suggestion is a good match for this conversation, ranging from 0.0 (completely uncertain) to 1.0 (completely certain). |
metadata |
Map that contains metadata about the Smart Compose suggestion and the document from which it originates. An object containing a list of |
query |
The name of the answer record. Format: projects/{project}/locations/{location}/answerRecords/{answerRecord} |
DialogflowInteractionData
Dialogflow interaction data.
JSON representation |
---|
{ "dialogflowIntentId": string, "confidence": number, "detectIntentRequest": { "@type": string, field1: ..., ... }, "detectIntentResponse": { "@type": string, field1: ..., ... }, "flowId": string, "flowDisplayName": string, "pageId": string, "pageDisplayName": string, "intentId": string, "intentDisplayName": string, "endFlowOrSession": boolean, "liveAgentHandoff": boolean, "inputType": enum ( |
Fields | |
---|---|
dialogflow |
The Dialogflow intent resource path. Format: projects/{project}/agent/{agent}/intents/{intent} |
confidence |
The confidence of the match ranging from 0.0 (completely uncertain) to 1.0 (completely certain). |
detect |
The Dialogflow conversation DetectIntentRequest raw data of this turn. This field will only be populated in the GetConversation response and its data format should be same as Dialogflow [DetectIntentRequest] of Sessions. An object containing fields of an arbitrary type. An additional field |
detect |
The Dialogflow conversation DetectIntentResponse raw data of this turn. This field will only be populated in the GetConversation response and its data format should be same as Dialogflow DetectIntentResponse of Sessions. An object containing fields of an arbitrary type. An additional field |
flow |
The Dialogflow flow id. |
flow |
The Dialogflow flow display name. The Dialogflow environment display name. |
page |
The Dialogflow page ID. |
page |
The Dialogflow page display name. The Dialogflow environment display name. |
intent |
The Dialogflow intent ID. |
intent |
The Dialogflow intent display name. The Dialogflow environment display name. |
end |
The turn reaches END_FLOW or END_SESSION. |
live |
Whether the turn was handed off to a human agent. |
input |
The input type in this turn. |
match |
The match type in this turn. |
UserInput
Explicit input used for generating the answer
JSON representation |
---|
{
"query": string,
"generatorName": string,
"querySource": enum ( |
Fields | |
---|---|
query |
Query text. Article Search uses this to store the input query used to generate the search results. |
generator |
The resource name of associated generator. Format: |
query |
Query source for the answer. |
DialogflowIntent
The data for a Dialogflow intent. Represents a detected intent in the conversation, e.g. MAKES_PROMISE.
JSON representation |
---|
{ "displayName": string } |
Fields | |
---|---|
display |
The human-readable name of the intent. |
DialogflowCxConversationData
The metadata for a Dialogflow CX conversation.
JSON representation |
---|
{ "virtualAgentId": string, "flowIds": [ string ], "flowDisplayNames": [ string ], "pageIds": [ string ], "pageDisplayNames": [ string ], "intentIds": [ string ], "intentDisplayNames": [ string ], "experimentIds": [ string ], "experimentDisplayNames": [ string ], "inputAudioDuration": string, "outputAudioDuration": string, "queryInputStats": { object ( |
Fields | |
---|---|
virtual |
The virtual agent id of this conversation. |
flow |
The deduped flow UUIDs set. |
flow |
The deduped flow display names set. |
page |
The deduped page UUIDs set. |
page |
The deduped page display names set. |
intent |
The deduped intent UUIDs set. |
intent |
The deduped intent display names set. |
experiment |
The deduped experiment UUIDs set. |
experiment |
The deduped experiment display names set. |
input |
The total duration of the user input audio in this conversation. A duration in seconds with up to nine fractional digits, ending with ' |
output |
The total duration of the agent output audio in this conversation. A duration in seconds with up to nine fractional digits, ending with ' |
query |
Query input stats |
match |
Match type stats. |
average |
Average match confidence for all the initent matches in this conversation. |
end |
Whether the conversation reaches END_FLOW or END_SESSION. |
max |
The maximum webhook latency for an individual webhook call in this conversation. A duration in seconds with up to nine fractional digits, ending with ' |
live |
Whether the conversation was handed off to a human agent. |
QueryInputStats
Count by input types in this conversation
JSON representation |
---|
{ "textCount": integer, "intentCount": integer, "audioCount": integer, "eventCount": integer, "dtmfCount": integer } |
Fields | |
---|---|
text |
The number of requests with text input. |
intent |
The number of requests with intent input. |
audio |
The number of requests with audio input. |
event |
The number of requests with event input. |
dtmf |
The number of requests with DTMF input. |
MatchTypeStats
Count by match types in this conversation .
JSON representation |
---|
{ "intentCount": integer, "directIntentCount": integer, "parameterFillingCount": integer, "noMatchCount": integer, "noInputCount": integer, "eventCount": integer } |
Fields | |
---|---|
intent |
The number of responses with match type INTENT. |
direct |
The number of responses with match type DIRECT_INTENT. |
parameter |
The number of responses with match type PARAMETER_FILLING. |
no |
The number of responses with match type NO_MATCH. |
no |
The number of responses with match type NO_INPUT. |
event |
The number of responses with match type EVENT. |