Dialogflow CX

1. 接口

1. detectIntent, connector -> dialogflow cx

https://cloud.google.com/dialogflow/cx/docs/reference/rest/v3/projects.locations.agents.environments.sessions/detectIntent
 

  • POST https://{endpoint}/v3/{session=projects/*/locations/*/agents/*/environments/*/sessions/*}:detectIntent

request:

{
  "queryParams": {
    object (QueryParameters)
  },
  "queryInput": {
    object (QueryInput)
  },
  "outputAudioConfig": {
    object (OutputAudioConfig)
  }
}

 QueryParameters:

{
  "timeZone": string,
  "geoLocation": {
    object (LatLng)
  },
  "sessionEntityTypes": [
    {
      object (SessionEntityType)
    }
  ],
  "payload": {
    object
  },
  "parameters": {
    object
  },
  "currentPage": string,
  "disableWebhook": boolean,
  "analyzeQueryTextSentiment": boolean,
  "webhookHeaders": {
    string: string,
    ...
  },
  "flowVersions": [
    string
  ],
  "channel": string,
  "sessionTtl": string,
  "endUserMetadata": {
    object
  },
  "searchConfig": {
    object (SearchConfig)
  },
  "populateDataStoreConnectionSignals": boolean
}

object (Struct format)

Additional parameters to be put into [session parameters][SessionInfo.parameters]. To remove a parameter from the session, clients should explicitly set the parameter value to null.

You can reference the session parameters in the agent with the following format: $session.params.parameter-id.

Depending on your protocol or client library language, this is a map, associative array, symbol table, dictionary, or JSON object composed of a collection of (MapKey, MapValue) pairs:

    MapKey type: string
    MapKey value: parameter name
    MapValue type: If parameter's entity type is a composite entity then use map, otherwise, depending on the parameter value type, it could be one of string, number, boolean, null, list or map.
    MapValue value: If parameter's entity type is a composite entity then use map from composite entity property names to property values, otherwise, use parameter value.
 

response:

{
  "responseId": string,
  "queryResult": {
    object (QueryResult)
  },
  "outputAudio": string,
  "outputAudioConfig": {
    object (OutputAudioConfig)
  },
  "responseType": enum (ResponseType),
  "allowCancellation": boolean
}

2. sessions

https://cloud.google.com/dialogflow/cx/docs/reference/rest/v3/projects.locations.agents.environments.sessions

3. webhook, dialogflow cx -> cloud run

https://cloud.google.com/dialogflow/cx/docs/reference/rest/v3/WebhookRequest

{
  "detectIntentResponseId": string,
  "languageCode": string,
  "fulfillmentInfo": {
    object (FulfillmentInfo)
  },
  "intentInfo": {
    object (IntentInfo)
  },
  "pageInfo": {
    object (PageInfo)
  },
  "sessionInfo": {
    object (SessionInfo)
  },
  "messages": [
    {
      object (ResponseMessage)
    }
  ],
  "payload": {
    object
  },
  "sentimentAnalysisResult": {
    object (SentimentAnalysisResult)
  },
  "languageInfo": {
    object (LanguageInfo)
  },

  // Union field query can be only one of the following:
  "text": string,
  "triggerIntent": string,
  "transcript": string,
  "triggerEvent": string,
  "dtmfDigits": string
  // End of list of possible types for union field query.
}

sessionInfo:

{
  "session": string,
  "parameters": {
    string: value,
    ...
  }
}

map (key: string, value: value (Value format))

Optional for WebhookRequest. Optional for WebhookResponse. All parameters collected from forms and intents during the session. Parameters can be created, updated, or removed by the webhook. To remove a parameter from the session, the webhook should explicitly set the parameter value to null in WebhookResponse. The map is keyed by parameters' display names.

An object containing a list of "key": value pairs. Example: { "name": "wrench", "mass": "1.3kg", "count": "3" }.

https://cloud.google.com/dialogflow/cx/docs/reference/rest/v3/WebhookResponse

 WebhookResponse:

{
  "fulfillmentResponse": {
    object (FulfillmentResponse)
  },
  "pageInfo": {
    object (PageInfo)
  },
  "sessionInfo": {
    object (SessionInfo)
  },
  "payload": {
    object
  },

  // Union field transition can be only one of the following:
  "targetPage": string,
  "targetFlow": string
  // End of list of possible types for union field transition.
}

fulfillmentResponse:

{
  "messages": [
    {
      object (ResponseMessage)
    }
  ],
  "mergeBehavior": enum (MergeBehavior)
}

Identity and Access Management (IAM)

TODO:

1. Liveperson UI

2. Add market parameter

Secret Manager:

SYSTEM_CONFIG_DEV

        大写key -> secret_key

config文件:

        大写key -> secret_key

小写key -> handler

小写key -> parameters

大写key -> 小写key

3. skillId adapter

4. Unit Test development

5. Api auth

内容概要:本资源聚焦于配电网在发生故障后的两阶段鲁棒恢复研究,旨在提升电力系统在不确定性条件下的恢复能力与运行可靠性。研究采用两阶段优化方法,第一阶段进行预恢复决策,如网络重构、分布式电源出力调整等,以最小化预期损失;第二阶段则针对实际发生的故障场景实施校正控制,利用鲁棒优化理论应对负荷波动、新能源出力不确定性等因素,确保恢复方案的可行性与强健性。资源提供了完整的Matlab代码实现,复现了相关顶刊研究成果,便于使用者深入理解模型构建、算法求解及仿真分析全过程。; 适合人群:具备电力系统分析、优化理论基础及Matlab编程能力的研究生、科研人员及电力行业工程师。; 使用场景及目标:① 学习并掌握配电网故障恢复的先进优化方法,特别是两阶段鲁棒优化模型的构建与应用;② 复现和验证顶刊论文中的算法,为自身科研工作提供技术参考和代码基础;③ 将所学方法拓展应用于微电网、主动配电网等新型电力系统的可靠性评估与优化调度研究。; 阅读建议:学习者应结合提供的Matlab代码,仔细研读模型的数学公式与求解逻辑,重点关注不确定性建模、两阶段决策变量的设定以及鲁棒对等转换技巧。建议在掌握基础案例后,尝试修改参数或引入新的约束条件进行扩展研究,以深化理解并提升创新能力。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值