Enlighten AutoSummary

Enlighten AutoSummary 會在傳入和傳出語音互動結束時自動為客服專員產生摘要。 互動結束時，產生的摘要會顯示在CXone Agent 應用程式的備註欄位中。 其可以傳遞給支援的 CRM 管理聯絡人、銷售資訊、支援詳情和案例歷史的第三方系統。 應用程式，讓未來與聯絡人互動的客服專員可以獲得摘要。 摘要資料也可以用於 Interaction Analytics。

AutoSummary 使用 NICE Enlighten AI 對互動進行分析和總結。 摘要能夠擷取有關互動的關鍵資訊，例如

• 互動的目的或意圖 聯絡人所說/所輸入內容背後的含義或目的；聯絡要傳達或實現什麼。
• 互動過程中發生的動作 互動過程中發生的事件或動作，例如退回或完成支付。，例如付款。
• 聯絡人的情緒 透過分析字詞、短語和轉錄內容確定的整體情緒或互動結果。。
• 互動的結果 客服專員或系統在語音（處置方式）或數位（狀態）互動結束時指派的結果。，例如成功解決問題。

AutoSummary 產生的摘要始終簡潔、準確、易讀易懂。 客服專員新增的摘要不一定符合這些標準。 例如，客服專員可能會新增如下摘要：

「CXJames Smith 345456/concerned about missing pymnt/DM researched/no record in acc/informed not posted/prms cb」（CXJames Smith 345456/有關沒有支付的問題/已透過私人訊息交流/帳戶中無記錄/通知未發佈/承諾回呼）。 

由 AutoSummary 為同一互動產生的摘要可能是：

「 Mr. Smith was offered and declined a bill credit. Was given a promised callback."

Agents can modify the generated summary if they need to add or correct details. This allows them to focus on the important parts of the interaction instead of trying to capture the entire interaction themselves.

AutoSummary is an agent assist application that's set up and managed in Agent Assist Hub.

How AutoSummary Works

AutoSummary uses NICE Enlighten AI. It also uses Generative AI, which is based on Large Language Models (LLM) technology. Generative AI models learn patterns and the structure of data during their training. They are then able to generate new data that follows similar patterns.

AutoSummary provides several models that are trained to recognize terminology, intents 聯絡人所說/所輸入內容背後的含義或目的；聯絡要傳達或實現什麼, actions, and outcomes related to various vertical markets. These include markets such as financial services, healthcare, telecommunications, travel and hospitality, and retail. Combined with Generative AI and LLM technology, this allows AutoSummary to produce short, readable, and accurate summaries.

During inbound or outbound voice interactions, audio from the call is captured and transcribed to text. The custom Studio script that routes interactions is configured with an AutoSummary profile. The profile contains settings that determine the model to use and the kind of summary to generate.

AutoSummary applies the profile settings to the transcription. The model identifies the key aspects of the interaction. These include the contact's intent 聯絡人所說/所輸入內容背後的含義或目的；聯絡要傳達或實現什麼, sentiment 透過分析字詞、短語和轉錄內容確定的整體情緒或互動結果。, actions 互動過程中發生的事件或動作，例如退回或完成支付。 that occurred during the interaction, and the interaction's outcome 客服專員或系統在語音（處置方式）或數位（狀態）互動結束時指派的結果。. The result of the analysis is sent to the Generative AI engine for summarization.

AutoSummary delivers the summary to the agent in CXone Agent or one of the other supported 客服專員應用程式s. The resulting summary data can be delivered to a CRM 管理聯絡人、銷售資訊、支援詳情和案例歷史的第三方系統。 or used in Interaction Analytics.

Summary Types

您可以選擇AutoSummary 產生每個AutoSummary設定檔的摘要類型。 所有摘要都是基於互動文字記錄透過 AI 產生的。 類型為：

• 結構化 AI：此類摘要以簡短的短語定義互動的意圖、結果和事件。 範例：

  關於付款的已聯絡客戶。

  客戶的情緒是正面的，問題已解決。

  聯絡期間發生的結果：付款已完成

  動作：已付款、餘額付款已處理、客戶已付款

• Generative AI：此類摘要直接來自 Generative AI LLM 引擎。 它包含互動文字記錄的摘要，總結了互動的意圖、結果和事件。 以下是產生式 AI 摘要的範例：

  客戶嘗試支付帳單，但因路由號碼不正確而遇到問題。 客戶嘗試準時付款。 客服專員向客戶收集正確的路由號碼。 客服專員提出調查付款。 客戶要求協助付款，在整個通話過程中表現出正面情緒。 付款已處理，客戶成功付款。

• 混合：若要建立此類摘要，AutoSummary會將與結構化 AI 摘要相關的語句傳送至產生式 AI 服務。 服務以完整的語句提供摘要。 以下是混合摘要的範例：

  由於路由號碼不正確，客戶在帳單付款時遇到問題。 客服專員確認了正確的路由號碼，並提出調查這筆付款。 客戶要求協助付款，在整個通話過程中表現出正面情緒。

AutoSummary Data in CXone

The interaction summaries that AutoSummary generates are passed to 客服專員應用程式. To save the data, you must configure AutoSummary to pass it to your CRM 管理聯絡人、銷售資訊、支援詳情和案例歷史的第三方系統。. This makes summaries from previous conversations with the contact available in the CRM. Other agents who handle interactions with the contact can quickly understand the contact's history with your organization. Without a CRM integration, the generated summaries aren't visible to other agents.

AutoSummary data is also available In Interaction Analytics. If you use that application, you can filter interactions based on the intents, actions, and outcomes captured in generated summaries.

Agent Experience with AutoSummary

Agents don't need to do anything to make AutoSummary work. After it's set up, AutoSummary automatically generates summaries and sends them to 客服專員應用程式. The summaries appear within a few seconds after an interaction ends. Agents can modify the summaries if they want to change the text or add details. The agent must save the summary to complete the interaction.

AutoSummary works with CXone Agent, CXone Agent Integrated, CXone Agent Embedded, and CXone Agent for Microsoft Teams.

Key Facts about AutoSummary

Enlighten AutoSummary:

• Works with voice channels 聯絡人與客服專員或機器人互動的方式。 通道可以是語音、電郵、聊天、社交媒體等等。 and digital 任何與Digital Experience相關的通道、聯絡或技能。 messaging channels. Summaries for CXone email are only supported using the 產生式 AI mode.
• Currently is only available in English and Portuguese. Summaries in Portuguese are only available via the 產生式 AI mode. You do not have the option to include sentiment 透過分析字詞、短語和轉錄內容確定的整體情緒或互動結果。 details or resolution status in these summaries like you can for summaries in English.
• Works with CXone Agent, CXone Agent Integrated, CXone Agent Embedded, CXone Agent for Microsoft Teams.
• Summaries can be passed to the data feeds of any supported CRM 管理聯絡人、銷售資訊、支援詳情和案例歷史的第三方系統。. This requires mapping a field from 客服專員應用程式 to the CRM.
• Summaries appear in 客服專員應用程式 within a few seconds after the interaction ends.
• Summaries include the contact's primary intent 聯絡人所說/所輸入內容背後的含義或目的；聯絡要傳達或實現什麼 and the main actions 互動過程中發生的事件或動作，例如退回或完成支付。 and outcomes 客服專員或系統在語音（處置方式）或數位（狀態）互動結束時指派的結果。 of the interaction.
• Summaries can include sentiment 透過分析字詞、短語和轉錄內容確定的整體情緒或互動結果。 details and resolution status.

• Allows you to configure summary length to be between 40 and 250 words.

• Summaries can be modified by agents in 客服專員應用程式.