最近搜索
没有最近搜索

Magda Pereira
已加入2024年1月23日
·
最后活动2025年2月10日
关注
0
关注者
2
活动总数
18
投票
0
订阅
8
活动概览
标记
文章
帖子
社区评论
文章评论
活动概览
的最新活动 Magda Pereira
Magda Pereira 创建了一篇文章,
宣布日期 | 推行日期 |
2025 年 2 月 12 日 | 2025 年 2 月 12 日 |
我们很高兴宣布推出取消激活意向功能,以便管理员更好地进行意向管理。
此公告包括以下主题:
有什么变化?
现在,您可以直接在列表中取消激活意向,防止工单上出现不需要的意向。
Zendesk 为何作出这项更改?
我们致力于简化智能分类,并面向所有客户扩展其功能。
我们在今年早些时候推出了添加自定义意向 (EAP) 功能,现在又支持用户根据需要取消激活意向。这样您就可以根据业务需求定制意向,提高自行程序准确性,增强对人工智能决策的信心。
我需要做些什么?
如果您目前在使用智能分类,您的帐户将自动启用取消激活意向功能。要取消激活意向,请参阅查看和管理智能分类预测和通过创建自定义意向定制智能分类 (EAP)。
如果您有兴趣使用 Zendesk 高级人工智能附加功能,请参阅购买高级人工智能附加功能或联系您的 Zendesk 客户代表。
如果您有此公告相关产品反馈或功能请求,请访问我们的社区论坛,我们将在这里收集和管理客户对产品的反馈。如需获取关于 Zendesk 产品的常规帮助,请联系 Zendesk 客户支持。
已于 2025年2月20日 编辑 · Magda Pereira
0
关注者
1
投票
0
评论
Magda Pereira 创建了一个帖子,
We’re excited to announce an early access program (EAP) for custom intents, which marks a significant evolution in how Zendesk supports intent prediction in intelligent triage.
This announcement contains the following topics:
What’s changing?
Intelligent triage leverages AI to automatically classify incoming tickets by intent, language and sentiment. The Zendesk Intent Model includes pre-trained intents across several industries, providing relevant intents and use cases tailored to each account's ticket data.
Previously, all you could do to customize these intents was to request a new intent, a process that required human evaluation for an intent to be added to your account.
With the release of custom intents, we're eliminating the wait time entirely. Custom intents can now be created instantly, added immediately to your intent list, and made available right away to start predicting the intent of incoming tickets. Leveraging custom intents will help you optimize and extract valuable insights about your customer service operations.
Note: The request new intent feature will be retired for accounts enrolled in the custom intents EAP, reflecting our commitment to delivering faster, more flexible solutions for tailored business needs.
Why is Zendesk making this change?
Custom intents empower admins with greater control over managing intents. This enables you to tailor intents to your unique business needs, improve automation accuracy, and build confidence in AI-powered decisions.
What do I need to do?
If you'd like to create custom intents, first sign up for the EAP. Then, to learn how to create a custom intent, see Personalizing intelligent triage by creating custom intents.
If you have feedback or questions related to this announcement, visit our community forum where we collect and manage customer product feedback. For general assistance with your Zendesk products, contact Zendesk Customer Support.
已于 2025年1月23日 发布 · Magda Pereira
0
关注者
0
投票
0
评论
Magda Pereira 创建了一篇文章,
宣布日期 | 推行日期 |
2025 年 1 月 23 日 | 2025 年 1 月 23 日 |
我们很高兴宣布推出自定义意向的早期试用计划 (EAP),这标志着 Zendesk 支持智能分类中的意向预测方式发生了重大变化。
此公告包含以下主题:
有什么变化?
智能分类会利用人工智能,根据意向、语言和情绪自动对新到的工单进行分类。Zendesk 意向模型包含多个行业预先训练的意向,针对每个帐户的工单数据提供相应意向和用例。
以前,只有请求新意向才能自定义这些意向,并需要进行人工评估才能将意向添加到帐户中。
随着自定义意向推出,我们将完全消除等待时间。现在,您可以立即创建自定义意向或将其添加到意向列表中或用于预测新到工单的意向。利用自定义意向可帮助您优化并提取关于客户服务运营的宝贵见解。
Zendesk 为何作出这项更改?
通过自定义意向,管理员可以更好地控制意向管理。这样您可以根据独特的业务需求定制意向,提高自行程序的准确性,并建立对人工智能驱动决策的信心。
我需要做些什么?
如果您想创建自定义意向,请先注册 EAP。要了解如何创建自定义意向,请参阅通过创建自定义意向定制智能分类。
如果您对此公告有任何反馈或疑问,请访问我们的社区论坛,我们将在这里收集和管理客户对产品的反馈。如需获取关于 Zendesk 产品的常规帮助,请联系 Zendesk 客户支持。
已于 2025年1月28日 编辑 · Magda Pereira
0
关注者
1
投票
0
评论
Magda Pereira 创建了一个帖子,
Intents offer automated and consistent classification of incoming tickets and conversations. This will provide valuable insights into your ticket patterns, helping you identify the most relevant intents for your business. Additionally, it will streamline the triage process and, ultimately, reduce the volume of incoming tickets by enabling smarter automation.
With the option of adding custom intents, customers will now tailor intents to their unique business needs, enabling more precise automation and driving greater confidence in decision-making.
Requirements
- You must be an Advanced AI customer, with an Intent model assigned.
- Sign-up with the Custom Intents EAP form, where you accepted the EAP agreements.
- You must have intents turned on to create a custom intent.
To create a custom intent
- In Admin Center, click Objects and rules in the sidebar, then select Business rules > Intelligent triage.
- Click Intent.
- Select the Intent list tab.
- Click the Actions drop-down and select Create custom intent.
- The Create custom intent page opens.
- Fill in the following required fields. Forms submitted without all the fields will be declined.
- Name. A short, descriptive name for the intent. To see the intents currently available to you for comparison, see Viewing all intent, language, and sentiment values.
- Description. An explanation of the meaning behind the intent. Remember that an intent is a prediction of what the ticket is about.
- Category. The category and subcategory that the new intent applies to. After the custom intent is created, it will be placed under this category and subcategory.
-
Tickets with this intent. Example tickets that the new intent applies to. You must list up to ten examples, and each ticket must:
- Have the full URL (for example, https://.zendesk.com/agent/tickets/1)
- Come from the Email channel
- Be in English
- Have a subject and description
- Be unique (in other words, tickets can't be repeated) but must represent the same intent
- Click Create intent.
How does custom intent work?
The custom intent is being automatically added to the customer's account list of intents, and from that moment on, the intent model will take into consideration this new custom intent to predict the newly created tickets.
Our Zendesk Intent Model leverages Generative AI to understand the end-user message and link with the correct intent, be it a Zendesk intent or a custom intent.
All the custom intents added are account based and will not be available for other customers.
Guidelines
- The intent should explain what the ticket is about, the main reason the end-user is reaching out. It should cover a single reason.
- Intents are organized hierarchically in three levels: Category, Sub-category, and Intent. This structure helps in systematically grouping and managing incoming requests
- Category: The top-level grouping that includes broad reason of incoming requests.
- Sub-category: Within each Category, Sub-categories provide a more detailed breakdown of the reason.
- Provide a good intent name and description:
- Be clear and descriptive.
- When writing the description, clearly define what the intent should include and exclude.
- Make a description as if to be read by a first day agent that understands the meaning of the sentences but has little inside knowledge about the business.
- Feel free to provide examples and common words users might use.
- Before adding a custom intent, check if you already have that intent or a similar one in the list of intents provided by Zendesk.
- Having similar or overlapping intents might lead to low confidence intent predictions, or wrong predictions.
- A custom intent should not be added to identify details of the ticket, such as product or service names, branch locations, or subscription type etc. (See entity detection for automatically identifying business critical information from your incoming requests)
- The intent name will be visible for your agent, make sure it is clear and concise, so they quickly understand it.
Here are some examples:
- Intent name: Product not working as expected
- Category: Order
- Sub-category: Product issue
- Description: The requester wants to report a product that is not functioning correctly, has developed a fault, or is not meeting quality expectations.
- Intent name: Cancel direct debit
- Category: Billing
- Sub-category: Change payment method
- Description: The customer wants to stop or cancel an existing direct debit or automatic payment arrangement. They may cite reasons such as financial constraints, changes in circumstances, or dissatisfaction with the service.
- Intent name: Change booking arrival location
- Category: Travel
- Sub-category: Booking update
- Description: The end-user wants to modify the arrival location of their booking. This could include changing flight destinations, correcting errors in the booked location, or updating hotel addresses.
Known limitations for EAP
- Create up to 50 custom intents
- There's a limitation that blocks the Admin from creating more than 50 custom intents.
- Only English language supported
- Custom intents created in English by the Admin are supported by Zendesk. Custom intents created in other languages, for now, are not supported.
- Tickets with its content in English, will get a prediction, and are supported by Zendesk.
Tickets with its content in other languages, will get a prediction, for now, are not supported.
- Unable to check conflicts between intents
- Newly added custom intents prediction quality highly depends on the quality of the intent name, description, and ticket examples provided by the customer.
- Newly custom intents aren't compared against Zendesk intents or even between other custom intents to understand if it might be duplicated or ambiguous.
- Zendesk AI agents will not have custom intents predictions.
已于 2025年1月29日 编辑 · Magda Pereira
0
关注者
0
投票
0
评论
Magda Pereira 创建了一个帖子,
Why did we build it?
Intelligent triage leverages AI to automatically classify incoming tickets with its intent, language and sentiment. Currently, the Zendesk Intent Model supports pre-trained intents across several industries, providing relevant intents and use cases tailored to each account's ticket data.
To empower admins with greater control over managing intents, we now offer the ability to add custom intents. This enables admins to tailor intents to their unique business needs, improve automation accuracy and build confidence in decisions.
What is it?
The release of custom intents marks a significant evolution in how Zendesk supports intent prediction. Previously, customers could 'request new intents', a process that required human evaluation for an intent to be added to the customer account. With this release, we're eliminating the wait time entirely. Custom intents can now be created instantly, added immediately to the customer’s intent list, and made available right away to start predicting the intent of incoming tickets.
Adding customer intents will highly contribute to extract valuable insights about the customers’ service operations, and optimize it by leveraging intents in workflows.
As part of this update, the 'request new intent' feature will be retired for accounts enrolled in the custom intents closed EAP, reflecting our commitment to delivering faster, more flexible solutions for tailored business needs.
How do I start using it?
If you'd like access to these new and improved features, sign up for the Closed EAP.
After being enrolled in the custom intents closed EAP, under Intent Settings in Admin Center > Business and Rules > Intelligent Triage, you will have access to the custom intents feature, no additional configuration needed
Please review the product documentation to learn how to create a custom intent and the current limitations.
已于 2024年12月11日 编辑 · Magda Pereira
0
关注者
0
投票
0
评论
Magda Pereira 进行了评论,
Hello Izabella and Jess!
Thank you so much for your feedback. We believe it's super relevant to be able report all “Intelligent” fields in Explore. We have been working towards it, and in September we launched Intelligent Triage prebuilt dashboard in Explore, where you can already get reports from Intent, Sentiment, and Language. This is just one more step on the direction we want to go of providing good AI insights.
Really happy to connect with you, keep the feedback coming.
Thank you!
查看评论 · 已于 2024年11月15日 发布 · Magda Pereira
0
关注者
0
投票
0
评论
Magda Pereira 创建了一篇文章,
宣布日期 | 推行日期 |
2024 年 11 月 13 日 | 2024 年 11 月 8 日 |
我们很高兴宣布,总体智能分类管理员体验现已改进,不仅用户界面焕然一新,还可以查看已取消激活的意向。
此公告回答了以下问题:
有什么变化?
增强了智能分类的整体体验
根据收集的反馈,我们改进了管理中心中的智能分类设置页面。该功能的说明现在更为明确,让用户更易于理解其所处理的各种用例。此外,我们还添加了相关资源的链接,例如在 Explore 中快速访问智能分类预建面板。
已取消激活的意向
在意向列表中,现在可以轻松识别工单上不再预测的已取消激活意向。已弃用意向是已从 Zendesk 意向模型中移除的意向。
Zendesk 为何作出这项更改?
我们致力于简化智能分类,并面向所有客户扩展其功能。智能分类的扩展不仅在于扩展机器学习模型,还在于确保用户能够根据需求配置意向、情绪和语言。
我需要做些什么?
如果您目前在使用智能分类,这些改进已在您的帐户中可用。有关智能分类功能的更多信息,请参阅智能分类资源。
如果您处于我们提供意向支持的行业(零售、软件、金融服务、保险、员工体验、旅游、酒店和旅游、娱乐和游戏以及教育),但尚未使用智能分类,请参阅自动检测客户意向、语言或情绪。
如果您有兴趣使用 Zendesk 高级人工智能附加功能,请参阅购买高级人工智能附加功能或联系您的 Zendesk 客户代表。
如果您有此公告相关产品反馈或功能请求,请访问我们的社区论坛,我们将在这里收集和管理客户对产品的反馈。如需获取关于 Zendesk 产品的常规帮助,请联系 Zendesk 客户支持。
已于 2024年11月21日 编辑 · Magda Pereira
0
关注者
1
投票
0
评论
Magda Pereira 创建了一篇文章,
宣布日期 | 推行日期 |
2024 年 9 月 9 日 | 2024 年 9 月 9 日 |
我们很高兴地宣布现在支持教育行业的预先训练意向。这些意向可与智能分类和人工智能专员结合使用,为新到的工单和对话提供自动且一致的分类,用于业务规则、工作流程、路由等。
此公告回答了以下问题:
有什么变化?
我们通过支持教育行业的预先训练意向扩大了意向的覆盖范围,旨在满足管理和更新教育课程、考试、申请、奖助学金和学生生活等相关信息的特定需求。
现在,您可以使用为教育行业量身定制的意向改进工单。这样您就可以了解工单模式,识别与业务最相关的意向。此外,这还可以简化分类流程,并最终通过使用更智能的自行程序,减少新到工单量。
Zendesk 为何作出这项更改?
我们专注于为所有客户扩展人工智能的功能。我们的团队不断训练现有模型和新模型,以便将这些功能用于各种用例和工作流程。
我需要做些什么?
如果您想利用意向深入了解业务用例或创建工作流程,请参阅自动检测客户意向、语言和情绪。
如果您对此公告有任何反馈或疑问,请访问我们的社区论坛,我们将在这里收集和管理客户对产品的反馈。如需获取关于 Zendesk 产品的常规帮助,请联系 Zendesk 客户支持。
已于 2024年9月17日 编辑 · Magda Pereira
0
关注者
1
投票
0
评论
Magda Pereira 创建了一篇文章,
宣布日期 | 推行日期 |
2024 年 8 月 7 日 | 2024 年 8 月 7 日 |
我们很高兴宣布扩展新增原生和社交消息传送渠道的智能分类。
此公告回答了以下问题:
有什么变化?
来自原生和社交消息传送渠道(非智能机器人生成器)的工单现可通过意向、情绪和语言预测进行扩充。新增渠道包括:
- 电邮渠道
- Facebook 帖子
- X Corp
- 消息传送渠道
- 原生消息传送
- Apple Business Chat
- Google Business Messages
- KakaoTalk
- MessageBird 短信
- Sunshine Conversations API
Zendesk 为何作出这项更改?
我们专注于为所有客户扩展人工智能功能。我们的团队不断扩展支持的电邮和消息传送渠道,以便将这些功能用于各种用例和工作流程。
我需要做些什么?
如果您当前使用智能分类,新增的支持渠道将自动在您的帐户中可用。有关使用智能分类配置渠道的说明,请参阅打开和配置智能分类。
如果您对此公告有任何反馈或疑问,请访问我们的社区论坛,我们将在这里收集和管理客户对产品的反馈。如需获取关于 Zendesk 产品的常规帮助,请联系 Zendesk 客户支持。
已于 2024年8月15日 编辑 · Magda Pereira
0
关注者
1
投票
0
评论
Magda Pereira 创建了一篇文章,
宣布日期 | 推行日期 |
2024 年 7 月 11 日 | 2024 年 7 月 11 日 |
Zendesk 改进了 Zendesk 意向模型的覆盖范围,添加了客户通过自定义意向:请求新意向功能请求的新意向。这些意向可与智能分类和人工智能专员结合使用,为新到的工单和对话提供自动且一致的分类,用于业务规则、工作流程、路由等。
此公告回答了以下问题:
有什么变化?
通过自定义意向:请求新意向功能请求意向的客户现在可以查看新的可用意向。这些意向的添加提高了 Zendesk 意向模型中意向的覆盖范围,适用于零售、软件、保险、金融、员工体验、旅游以及娱乐和游戏行业。
Zendesk 为何作出这项更改?
Zendesk 意向模型是包含我们所有特定行业意向的整体模型。Zendesk 意向模型增强了我们的意向扩充能力,使我们能够:
- 仅分配与帐户相关的意向。
- 为来自不同行业的多个品牌或混合用例的帐户提供支持。
我们专注于为所有客户扩展人工智能的功能。我们的团队不断训练现有模型和新模型,以便将这些功能用于各种用例和工作流程。
我需要做些什么?
如果您当前使用智能分类,更新后的意向模型将自动在您的帐户中可用。今后,您可以在已设置的任意自行程序或报告中充分利用新的和更新后的意向。您可以在分类页面上查看所有意向。有关智能分类功能的更多信息,请参阅智能分类资源。
如果您处于我们意向受支持的行业(零售、软件、金融服务、保险、员工体验、旅行以及娱乐和游戏),但尚未使用智能分类,或者您虽已启用智能分类但未在工单上看到意向预测,请联系 Zendesk 客户支持,以获得如何与您的客户团队协调后续步骤的帮助。
如果您有兴趣使用 Zendesk 高级人工智能附加功能,请参阅购买高级人工智能附加功能或联系您的 Zendesk 客户代表。
如果您有此公告相关产品反馈或功能请求,请访问我们的社区论坛,我们将在这里收集和管理客户对产品的反馈。如需获取关于 Zendesk 产品的常规帮助,请联系 Zendesk 客户支持。
已于 2024年7月23日 编辑 · Magda Pereira
0
关注者
1
投票
0
评论