Google Cloud Dialogflow V2 Client - Class ConversationModelEvaluation (1.2.0)

Reference documentation and code samples for the Google Cloud Dialogflow V2 Client class ConversationModelEvaluation.

Represents evaluation result of a conversation model.

Generated from protobuf message google.cloud.dialogflow.v2.ConversationModelEvaluation

Methods

__construct

Constructor.

Parameters
NameDescription
data array

Optional. Data for populating the Message object.

↳ name string

The resource name of the evaluation. Format: projects/<Project ID>/conversationModels/<Conversation Model ID>/evaluations/<Evaluation ID>

↳ display_name string

Optional. The display name of the model evaluation. At most 64 bytes long.

↳ evaluation_config Google\Cloud\Dialogflow\V2\EvaluationConfig

Optional. The configuration of the evaluation task.

↳ create_time Google\Protobuf\Timestamp

Output only. Creation time of this model.

↳ smart_reply_metrics Google\Cloud\Dialogflow\V2\SmartReplyMetrics

Output only. Only available when model is for smart reply.

↳ raw_human_eval_template_csv string

Output only. Human eval template in csv format. It tooks real-world conversations provided through input dataset, generates example suggestions for customer to verify quality of the model. For Smart Reply, the generated csv file contains columns of Context, (Suggestions,Q1,Q2)*3, Actual reply. Context contains at most 10 latest messages in the conversation prior to the current suggestion. Q1: "Would you send it as the next message of agent?" Evaluated based on whether the suggest is appropriate to be sent by agent in current context. Q2: "Does the suggestion move the conversation closer to resolution?" Evaluated based on whether the suggestion provide solutions, or answers customer's question or collect information from customer to resolve the customer's issue. Actual reply column contains the actual agent reply sent in the context.

getName

The resource name of the evaluation. Format: projects/<Project ID>/conversationModels/<Conversation Model ID>/evaluations/<Evaluation ID>

Returns
TypeDescription
string

setName

The resource name of the evaluation. Format: projects/<Project ID>/conversationModels/<Conversation Model ID>/evaluations/<Evaluation ID>

Parameter
NameDescription
var string
Returns
TypeDescription
$this

getDisplayName

Optional. The display name of the model evaluation. At most 64 bytes long.

Returns
TypeDescription
string

setDisplayName

Optional. The display name of the model evaluation. At most 64 bytes long.

Parameter
NameDescription
var string
Returns
TypeDescription
$this

getEvaluationConfig

Optional. The configuration of the evaluation task.

Returns
TypeDescription
Google\Cloud\Dialogflow\V2\EvaluationConfig|null

hasEvaluationConfig

clearEvaluationConfig

setEvaluationConfig

Optional. The configuration of the evaluation task.

Parameter
NameDescription
var Google\Cloud\Dialogflow\V2\EvaluationConfig
Returns
TypeDescription
$this

getCreateTime

Output only. Creation time of this model.

Returns
TypeDescription
Google\Protobuf\Timestamp|null

hasCreateTime

clearCreateTime

setCreateTime

Output only. Creation time of this model.

Parameter
NameDescription
var Google\Protobuf\Timestamp
Returns
TypeDescription
$this

getSmartReplyMetrics

Output only. Only available when model is for smart reply.

Returns
TypeDescription
Google\Cloud\Dialogflow\V2\SmartReplyMetrics|null

hasSmartReplyMetrics

setSmartReplyMetrics

Output only. Only available when model is for smart reply.

Parameter
NameDescription
var Google\Cloud\Dialogflow\V2\SmartReplyMetrics
Returns
TypeDescription
$this

getRawHumanEvalTemplateCsv

Output only. Human eval template in csv format.

It tooks real-world conversations provided through input dataset, generates example suggestions for customer to verify quality of the model. For Smart Reply, the generated csv file contains columns of Context, (Suggestions,Q1,Q2)*3, Actual reply. Context contains at most 10 latest messages in the conversation prior to the current suggestion. Q1: "Would you send it as the next message of agent?" Evaluated based on whether the suggest is appropriate to be sent by agent in current context. Q2: "Does the suggestion move the conversation closer to resolution?" Evaluated based on whether the suggestion provide solutions, or answers customer's question or collect information from customer to resolve the customer's issue. Actual reply column contains the actual agent reply sent in the context.

Returns
TypeDescription
string

setRawHumanEvalTemplateCsv

Output only. Human eval template in csv format.

It tooks real-world conversations provided through input dataset, generates example suggestions for customer to verify quality of the model. For Smart Reply, the generated csv file contains columns of Context, (Suggestions,Q1,Q2)*3, Actual reply. Context contains at most 10 latest messages in the conversation prior to the current suggestion. Q1: "Would you send it as the next message of agent?" Evaluated based on whether the suggest is appropriate to be sent by agent in current context. Q2: "Does the suggestion move the conversation closer to resolution?" Evaluated based on whether the suggestion provide solutions, or answers customer's question or collect information from customer to resolve the customer's issue. Actual reply column contains the actual agent reply sent in the context.

Parameter
NameDescription
var string
Returns
TypeDescription
$this

getMetrics

Returns
TypeDescription
string