- JSON representation
- AnalysisResult
- CallAnalysisMetadata
- CallAnnotation
- InterruptionData
- SilenceData
- HoldData
- EntityMentionData
- IntentMatchData
- PhraseMatchData
- IssueMatchData
- IssueAssignment
- Entity
- ConversationLevelSentiment
- ConversationLevelSilence
- Intent
- IssueModelResult
- SemanticMatchMetadata
- QaScorecardResult
- QaAnswer
- AnswerSource
- QaTagResult
- ScoreSource
The analysis resource.
JSON representation |
---|
{ "name": string, "requestTime": string, "createTime": string, "analysisResult": { object ( |
Fields | |
---|---|
name |
Immutable. The resource name of the analysis. Format: projects/{project}/locations/{location}/conversations/{conversation}/analyses/{analysis} |
requestTime |
Output only. The time at which the analysis was requested. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
createTime |
Output only. The time at which the analysis was created, which occurs when the long-running operation completes. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
analysisResult |
Output only. The result of the analysis, which is populated when the analysis finishes. |
annotatorSelector |
To select the annotators to run and the phrase matchers to use (if any). If not specified, all annotators will be run. |
AnalysisResult
The result of an analysis.
JSON representation |
---|
{ "endTime": string, // Union field |
Fields | |
---|---|
endTime |
The time at which the analysis ended. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
Union field metadata . Metadata discovered during analysis. metadata can be only one of the following: |
|
callAnalysisMetadata |
Call-specific metadata created by the analysis. |
CallAnalysisMetadata
Call-specific metadata created during analysis.
JSON representation |
---|
{ "annotations": [ { object ( |
Fields | |
---|---|
annotations[] |
A list of call annotations that apply to this call. |
entities |
All the entities in the call. An object containing a list of |
sentiments[] |
Overall conversation-level sentiment for each channel of the call. |
silence |
Overall conversation-level silence during the call. |
intents |
All the matched intents in the call. An object containing a list of |
phraseMatchers |
All the matched phrase matchers in the call. An object containing a list of |
issueModelResult |
Overall conversation-level issue modeling result. |
semanticMatchMetadata |
Metadata used in the semantic match. |
qaScorecardResults[] |
Results of scoring QaScorecards. |
CallAnnotation
A piece of metadata that applies to a window of a call.
JSON representation |
---|
{ "channelTag": integer, "annotationStartBoundary": { object ( |
Fields | |
---|---|
channelTag |
The channel of the audio where the annotation occurs. For single-channel audio, this field is not populated. |
annotationStartBoundary |
The boundary in the conversation where the annotation starts, inclusive. |
annotationEndBoundary |
The boundary in the conversation where the annotation ends, inclusive. |
Union field data . The data in the annotation. data can be only one of the following: |
|
interruptionData |
Data specifying an interruption. |
sentimentData |
Data specifying sentiment. |
silenceData |
Data specifying silence. |
holdData |
Data specifying a hold. |
entityMentionData |
Data specifying an entity mention. |
intentMatchData |
Data specifying an intent match. |
phraseMatchData |
Data specifying a phrase match. |
issueMatchData |
Data specifying an issue match. |
InterruptionData
This type has no fields.
The data for an interruption annotation.
SilenceData
This type has no fields.
The data for a silence annotation.
HoldData
This type has no fields.
The data for a hold annotation.
EntityMentionData
The data for an entity mention annotation. This represents a mention of an Entity
in the conversation.
JSON representation |
---|
{ "entityUniqueId": string, "type": enum ( |
Fields | |
---|---|
entityUniqueId |
The key of this entity in conversation entities. Can be used to retrieve the exact |
type |
The type of the entity mention. |
sentiment |
Sentiment expressed for this mention of the entity. |
IntentMatchData
The data for an intent match. Represents an intent match for a text segment in the conversation. A text segment can be part of a sentence, a complete sentence, or an utterance with multiple sentences.
JSON representation |
---|
{ "intentUniqueId": string } |
Fields | |
---|---|
intentUniqueId |
The id of the matched intent. Can be used to retrieve the corresponding intent information. |
PhraseMatchData
The data for a matched phrase matcher. Represents information identifying a phrase matcher for a given match.
JSON representation |
---|
{ "phraseMatcher": string, "displayName": string } |
Fields | |
---|---|
phraseMatcher |
The unique identifier (the resource name) of the phrase matcher. |
displayName |
The human-readable name of the phrase matcher. |
IssueMatchData
The data for an issue match annotation.
JSON representation |
---|
{
"issueAssignment": {
object ( |
Fields | |
---|---|
issueAssignment |
Information about the issue's assignment. |
IssueAssignment
Information about the issue.
JSON representation |
---|
{ "issue": string, "score": number, "displayName": string } |
Fields | |
---|---|
issue |
Resource name of the assigned issue. |
score |
Score indicating the likelihood of the issue assignment. currently bounded on [0,1]. |
displayName |
Immutable. Display name of the assigned issue. This field is set at time of analyis and immutable since then. |
Entity
The data for an entity annotation. Represents a phrase in the conversation that is a known entity, such as a person, an organization, or location.
JSON representation |
---|
{ "displayName": string, "type": enum ( |
Fields | |
---|---|
displayName |
The representative name for the entity. |
type |
The entity type. |
metadata |
Metadata associated with the entity. For most entity types, the metadata is a Wikipedia URL ( An object containing a list of |
salience |
The salience score associated with the entity in the [0, 1.0] range. The salience score for an entity provides information about the importance or centrality of that entity to the entire document text. Scores closer to 0 are less salient, while scores closer to 1.0 are highly salient. |
sentiment |
The aggregate sentiment expressed for this entity in the conversation. |
ConversationLevelSentiment
One channel of conversation-level sentiment data.
JSON representation |
---|
{
"channelTag": integer,
"sentimentData": {
object ( |
Fields | |
---|---|
channelTag |
The channel of the audio that the data applies to. |
sentimentData |
Data specifying sentiment. |
ConversationLevelSilence
Conversation-level silence data.
JSON representation |
---|
{ "silenceDuration": string, "silencePercentage": number } |
Fields | |
---|---|
silenceDuration |
Amount of time calculated to be in silence. A duration in seconds with up to nine fractional digits, ending with ' |
silencePercentage |
Percentage of the total conversation spent in silence. |
Intent
The data for an intent. Represents a detected intent in the conversation, for example MAKES_PROMISE.
JSON representation |
---|
{ "id": string, "displayName": string } |
Fields | |
---|---|
id |
The unique identifier of the intent. |
displayName |
The human-readable name of the intent. |
IssueModelResult
Issue Modeling result on a conversation.
JSON representation |
---|
{
"issueModel": string,
"issues": [
{
object ( |
Fields | |
---|---|
issueModel |
Issue model that generates the result. Format: projects/{project}/locations/{location}/issueModels/{issueModel} |
issues[] |
All the matched issues. |
SemanticMatchMetadata
Semantic match metadata used in an analysis.
JSON representation |
---|
{ "issueModel": string } |
Fields | |
---|---|
issueModel |
Issue model that's used in the semantic match. Format: projects/{project}/locations/{location}/issueModels/{issueModel} |
QaScorecardResult
The results of scoring a single conversation against a QaScorecard. Contains a collection of QaAnswers and aggregate score.
JSON representation |
---|
{ "name": string, "qaScorecardRevision": string, "conversation": string, "createTime": string, "agentId": string, "qaAnswers": [ { object ( |
Fields | |
---|---|
name |
Identifier. The name of the scorecard result. Format: projects/{project}/locations/{location}/qaScorecardResults/{qa_scorecard_result} |
qaScorecardRevision |
The QaScorecardRevision scored by this result. |
conversation |
The conversation scored by this result. |
createTime |
Output only. The timestamp that the revision was created. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
agentId |
ID of the agent that handled the conversation. |
qaAnswers[] |
Set of QaAnswers represented in the result. |
score |
The overall numerical score of the result, incorporating any manual edits if they exist. |
potentialScore |
The maximum potential overall score of the scorecard. Any questions answered using |
normalizedScore |
The normalized score, which is the score divided by the potential score. Any manual edits are included if they exist. |
qaTagResults[] |
Collection of tags and their scores. |
scoreSources[] |
List of all individual score sets. |
QaAnswer
An answer to a QaQuestion.
JSON representation |
---|
{ "qaQuestion": string, "conversation": string, "questionBody": string, "answerValue": { object ( |
Fields | |
---|---|
qaQuestion |
The QaQuestion answered by this answer. |
conversation |
The conversation the answer applies to. |
questionBody |
Question text. E.g., "Did the agent greet the customer?" |
answerValue |
The main answer value, incorporating any manual edits if they exist. |
potentialScore |
The maximum potential score of the question. If the question was answered using |
tags[] |
User-defined list of arbitrary tags. Matches the value from QaScorecard.ScorecardQuestion.tags. Used for grouping/organization and for weighting the score of each answer. |
answerSources[] |
List of all individual answers given to the question. |
AnswerSource
A question may have multiple answers from varying sources, one of which becomes the "main" answer above. AnswerSource represents each individual answer.
JSON representation |
---|
{ "sourceType": enum ( |
Fields | |
---|---|
sourceType |
What created the answer. |
answerValue |
The answer value from this source. |
QaTagResult
Tags and their corresponding results.
JSON representation |
---|
{ "tag": string, "score": number, "potentialScore": number, "normalizedScore": number } |
Fields | |
---|---|
tag |
The tag the score applies to. |
score |
The score the tag applies to. |
potentialScore |
The potential score the tag applies to. |
normalizedScore |
The normalized score the tag applies to. |
ScoreSource
A scorecard result may have multiple sets of scores from varying sources, one of which becomes the "main" answer above. A ScoreSource represents each individual set of scores.
JSON representation |
---|
{ "sourceType": enum ( |
Fields | |
---|---|
sourceType |
What created the score. |
score |
The overall numerical score of the result. |
potentialScore |
The maximum potential overall score of the scorecard. Any questions answered using |
normalizedScore |
The normalized score, which is the score divided by the potential score. |
qaTagResults[] |
Collection of tags and their scores. |