Jira Service Management 中的人工智能

Whether your goal is to enhance automated support, streamline onboarding, or provide knowledge at your customers' fingertips, Jira Service Management’s AI-powered support workflows are designed to ensure employees receive the assistance they need while simultaneously increasing the productivity of front-line agents.

In this section, we'll walk through how you can use AI in Jira Service Management to:

• Deliver great self-service support experiences
• Accelerate agent & admin productivity

虚拟服务支持人员意图流

虚拟服务支持人员的意图代表了虚拟服务支持人员可以帮助客户解决的具体问题、疑问或请求。每个意图都包括一组训练短语，以帮助虚拟服务支持人员识别求助者的请求，还包括一个对话流，以根据求助者对虚拟服务支持人员的回复，帮助指导求助者解决问题。意图非常适合以下问题：

• 需要引导式工作/故障排除
• 需要信息集合并进行分类
• 需要通过 Web 请求自动执行操作

示例：软件访问请求、报告事件、新硬件、采购请求、入职培训工作流

使用现成可用的模板和低代码/无代码编辑器可以轻松配置意图。虚拟服务支持人员还使用生成式人工智能，根据团队的历史请求单数据建议相关意图，并实际填充一些基本设置，如描述和训练短语。

虚拟服务支持人员中的人工智能回答

人工智能回答使用 Atlassian Intelligence 中的生成式人工智能在关联的知识库空间中进行搜索，并回答客户的问题。由于只需很少的设置，因此若要快速开始使用虚拟服务支持人员，此功能就非常合适，尤其是在转移以下帮助请求方面：

• 可以通过提供信息或说明来解决
• 包含在（或可以轻松添加到）您现有的知识库文章中
• 通常不需要上报给人工支持人员

设置 AI 回答

要设置人工智能回答，您首先需要配置虚拟服务支持人员承接通道。您可以在我们的虚拟服务支持人员产品指南中了解有关如何执行此操作的更多信息。

连接您的自助服务知识库

您的承接通道准备就绪后，您需要确保您的知识库已通过 Confluence 或 Jira Service Management 的原生知识库链接到您的项目。您可以直接从 Jira Service Management 构建知识库，也可以整合 Confluence 中已有的现有常见问题解答和文档。

激活人工智能回答

知识库准备就绪后，就该在虚拟服务支持人员设置中激活人工智能回答了：

在左侧导航栏中，选择项目设置，然后选择虚拟服务支持人员。选择设置，然后选择基本设置（如果尚未选择）。打开 Atlassian Intelligence 回答旁边的开关，然后选择激活。

事务编辑器中的生成式 AI

生成式 AI 为撰写知识库文章助力

除了为事务编辑提供生成式 AI 功能之外，Atlassian Intelligence 还允许支持人员直接基于 Jira Service Management 事务创作知识库文章。只需完成几个简单的步骤，即可轻松地就新文章内容开展头脑风暴、确保您的拼写和语法正确无误，以及让您的文章保持专业、善解人意的口吻。

如何使用生成式 AI 创作知识库文章

在 Jira Service Management 事务视图中：

1. 从项目侧边栏的导航中，选择知识库。
2. 选择创建文章。
3. 选择要在其中创作文章的知识库空间，然后选择下一步。
4. 通过工具栏或在编辑器中输入 /ai 来启动 Atlassian Intelligence。
5. 写出所需提示。
6. Atlassian Intelligence 将提供一份草稿，您可以此为起点进行创作。

请求类型建议

根据您对团队管理的工作类型的描述，请求类型建议功能可智能地提出请求类型建议，从而帮助消除创建服务台时的主观臆测。Atlassian Intelligence 可以针对各种用例（从 IT 和人力资源到狗狗美容和餐饮）提供请求类型建议，然后您只需点击几下即可将其添加到自己的服务台。

使用 Atlassian Intelligence 创建请求类型后，您可以添加其他表单和字段，以收集客户的所有相关详情，并在必要时调整工作流。

How to view suggested AI drafts:

如何使用请求类型建议：

1. 导航到项目设置 > 请求类型。
2. 选择建议。
3. 描述您的团队管理的工作类型。
4. 从 AI 建议列表中选择请求类型，然后选择创建。
5. 确定请求类型的名称、描述、图标和事务类型。
6. 选择下一步，并将请求类型添加到门户群组。
7. 选择“创建”。

Ticket triage and prioritization

Jira Service Management offers several AI powered capabilities to help you organize your queue and prioritize the tickets that matter:

1. AI triage

Quickly clean up queues by taking bulk action to intelligently assign work items to the correct request type. By using AI to streamline the triage process, support teams can significantly reduce the time spent on manual sorting, enabling them to resolve high-priority issues more efficiently.

AI triage analyzes tickets in your queue and makes recommendations for appropriate request types and associated fields. This feature can be particularly useful when you receive requests by email and end up with a lot of work items with the “Emailed request” request type.

To use AI to triage work items:

1. Select work items in your queue.
2. Select Triage.
3. Review the suggestions and update request types if necessary.
4. Select the work items you want to update.
5. Select Apply.

If the suggestions don't match what you need, you can always manually select a request type from the list and continue the bulk update with your own selected request types.

2. Customer sentiment analysis

Get to know your customers better with AI sentiment analysis, which analyzes and interprets the emotional tone of customer comments to help you understand how customers are feeling. Using ticket context like the title, description, and comments, AI assesses the customer sentiment – whether it's positive, neutral, or negative – and displays it directly on the work item view, updating in real-time as new comments come in. By spotting frustrations early, you can provide top-notch service, keeping customer happiness as a top priority.

3. Rovo Agent: Service Triage Assistant

If you want to really supercharge your triaging process, try the Service Triage Assistant, one of our out-of-the-box Rovo Agents. It helps you triage incoming requests by analyzing their content, sentiment, and other details to determine the request type, urgency, and priority. The agent is designed to be used within an automation rule so it can instantly rewrite ticket titles and descriptions, update the priority, or assign request types as work items appear in your queue. It can also determine whether a request should be escalated based on SLAs, customer interactions, urgency, etc.

There are a two different ways you can engage with Service Triage Assistant.

Once you’ve sorted your queue and know which tickets to tackle first, use AI to pull critical context into your workflows, helping you respond promptly and take the right steps to get to resolution.

Get up to speed with AI summaries

Rather than reading through numerous comments on a Jira Service Management work item, AI can quickly summarize ticket activity so you can get up to speed, easily loop in new stakeholders or transition tickets to a new agent, and take action.

To use AI summaries:

1. From your Jira Service Management project, navigate to your desired work item.
2. Scroll down to the Activity section.

3. Select Comments, and then Summarize.

   1. The AI-generated summary will only be visible to you, and will disappear when you navigate away from the ticket. You can summarize an issue’s details as many times as you like.

Use AI to craft the perfect help-seeker response

AI can help agents quickly draft and edit their response to help-seekers, ensuring clear and thoughtful communication. There are a couple different ways to do this:

1. Draft Replies

This feature uses AI to draft a recommend response to your customers. It allows agents to respond to tickets smartly and efficiently with the appropriate troubleshooting tips or follow-up questions based on comments added by agents while resolving similar requests.

2. AI editing

Use the AI slash command or the drop down AI menu in the editor to fine tune your customer response, including shortening it, adjusting the tone, and more.

AI suggestions

The suggestions panel, located on the right side of any work item view, uses AI to efficiently summarize requests and recommend assignees, pertinent requester details, escalation paths, troubleshooting steps, and more. It also enables you to directly take action from the panel, like updating the priority level.

Similar Requests

Make finding similar requests a breeze by using AI similar requests to find and identify recent requests with similar titles to the one you’re currently viewing in a service project. This feature uses Natural Language Processing (NLP) to provide a list of recent requests with similar titles to the one you’re currently viewing. This AI-automated process of finding related requests reduces the manual effort required to search for similar issues.

How to use AI Similar Requests:

1. First make sure you, Enable similar requests panel, start from your service project, select Project settings, then Features.
2. Under the Issue view, turn on the Similar requests panel toggle.
3. Next, to view similar service requests, problems, changes, and post-incident reviews. Go to the issue you want to find related requests for.
4. Select Similar requests or Similar incidents.
5. Select Open or Resolved to filter similar requests by status. 

3. Rovo agent: Service Request Helper

Another out-of-the-box Rovo Agent, Service Request Helper, provides your team with the insights needed to streamline request management and accelerate resolution times. Designed to use both Atlassian apps and connected third-party apps as knowledge sources, Service Request Helper can gather relevant information and offer guidance on how to resolve requests with speed and precision. Human agents can use Service Request Helper to identify SMEs, compose responses using insights from previous requests, summarize ticket activity, and even recommend next steps.

Like other Rovo Agents, Service Request Helper can be accessed through the Rovo Chat window in the top right corner of your navigation, near your profile icon or avatar. Navigate to any request in your queue, then open Rovo Chat, select Agents, and search for Service Request Helper.

From there you can chat with the Agent, asking it things like:

• What steps should I take next?
• Help me draft a reply to send to the customer.
• Find people who worked on similar requests before.

AI automations

Use AI to generate automation rules by simply describing the rule you want to create in natural language. This feature can be found in the automation rule builder in your project’s settings. Make sure whatever you input includes a trigger and an action.

Request type and field suggestions

Request type suggestions can help take the guesswork out of creating your service desk by intelligently suggesting request types based on how you describe the kind of work your team manages. AI can suggest request types across a range of use cases, from IT and HR to dog grooming and catering, and then add them to your service desk with just a few clicks.

How to use request type suggestions:

1. Navigate to Project settings > Request types.
2. Select Suggest.
3. Describe the type of work your team manages.
4. Select a request type from the list of AI suggestions and then select Create.
5. Confirm the request type’s name, description, icon, and issue type.
6. Select Next and add the request type to a portal group.
7. Select Create.

Once a request type has been created using AI, it can suggest relevant existing and custom fields you can add.