归因令牌。归因令牌是由 Vertex AI Search 商务解决方案生成并随每次搜索请求返回的唯一 ID。请务必将该归因令牌作为 UserEvent.attributionToken 添加到因搜索而产生的任何用户事件中。这项设置用于确定搜索是由 Vertex AI Search for Commerce 提供的。
为了跟踪来自投放配置的点击,Vertex AI Search 商务解决方案会将 predict 和 search 响应的结果与提取的用户事件进行校准。如果一个点击项在一小时时段内出现在相同访问者 ID 的响应中,则该点击或购买将被视为 Vertex AI Search for Commerce 的结果。
[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-08-18。"],[],[],null,["# View analytics\n\nThis page describes metrics that can help you determine how Vertex AI Search for commerce is\naffecting your business. \n\nPrerequisites\n-------------\n\nThe analytics dashboards use ingested [user events](/retail/docs/user-events) as data sources for metrics. You must complete user events integration to be able to see user event analytics. Metrics are refreshed about every six hours, so it can take hours after you create your app to see metrics on the **Analytics** pages.\n\n### User events\n\nThe following user events are required to view some metrics:\n\n- **Search events.** Required for any type of metrics.\n- **Detail page view events.** Required for page view metrics.\n- **Add-to-cart events.** Required for add-to-cart rate, conversion rate.\n- **Purchase-complete events.** Required for total revenue, recommender-engaged revenue, average order value, purchase rate, revenue rate, average unit value, purchase order rate, conversion rate.\n\nThe following information is also used for analytics:\n\n- **Product details** . To ensure accurate computation of search-related metrics, include `UserInfo.productDetails` within your user events. This information allows Vertex AI Search for commerce to attribute searches with specific product interactions. If the `UserInfo.ProductDetail.quantity` field is omitted within user events, a default value of `1` will be assumed for calculations.\n- **Revenue** . The `UserInfo.PurchaseTransaction.revenue` field is crucial for generating accurate revenue metrics. Ensure this field is populated within your user events to enable meaningful revenue-related analysis.\n- **Attribution tokens** . Attribution tokens are unique IDs generated by Vertex AI Search for commerce and returned with each search request. Make sure to include that attribution token as `UserEvent.attributionToken` with any user events resulting from a search. This is needed to identify if a search is served by Vertex AI Search for commerce.\n- **User agent** . Include `UserInfo.userAgent` with user events resulting from a search so that you can filter on user event metrics by device type.\n\nView recommendations analytics\n------------------------------\n\nTo view recommendation analytics:\n\n1. In the Google Cloud console, go to the **Search for commerce** page.\n\n\n [Go to the Search for commerce console](https://console.cloud.google.com/ai/retail/)\n2. In the navigation menu, click **Analytics**.\n\n3. Click the **Recommendation** tab.\n\n4. Use filters to view your metrics:\n\n - If available, enter a custom date range or select a preset range.\n - You can select a device type on which the recommendation occurred.\n - To show metrics for a recommendation setting, use all of the following filters. Set none to display aggregated metrics over all recommendation settings.\n - Serving config ID\n - Recommendation ID\n - Context event type with a displayed recommendation\n\n| **Note:** Metrics displayed might be higher than actual values if only some recommendation setting filters are set while others are not.\n\nView search analytics\n---------------------\n\nIf there are no user events, default values are shown for all metrics.\n\nTo view search analytics:\n\n1. In the Google Cloud console, go to the **Search for commerce** page.\n\n\n [Go to the Search for commerce console](https://console.cloud.google.com/ai/retail/)\n2. In the navigation menu, click **Analytics**.\n\n3. Click the **Search** tab.\n\n4. Click a tab to view that metric group:\n\n - **Per Search**. Metrics are grouped by searches.\n - **Per Visit**. Metrics are grouped by search visits.\n5. To filter your metrics, use the following filters:\n\n - **Date range**. Select a preset date range or, if available, enter a custom date range.\n - **Device type**. Select a device type that queries occurred on.\n\nView browse analytics\n---------------------\n\nIf there are not yet any user events, default values are shown for all metrics.\n\nTo view browse analytics:\n\n1. In the Google Cloud console, go to the **Search for commerce** page.\n\n\n [Go to the Search for commerce console](https://console.cloud.google.com/ai/retail/)\n2. In the navigation menu, click **Analytics**.\n\n3. Click the **Browse** tab.\n\n4. Click a tab to view that metric group:\n\n - **Per Browse**. Metrics are grouped by browses.\n - **Per Visit**. Metrics are grouped by browse visits.\n5. To filter your metrics, use the following filters:\n\n - **Date range**. Select a preset date range or, if available, enter a custom date range.\n - **Device type**. Select a device type that browsing occurred on.\n\nView serving config analytics\n-----------------------------\n\n1. In the Google Cloud console, go to the **Search for commerce** page.\n\n\n [Go to the Search for commerce console](https://console.cloud.google.com/ai/retail/)\n2. In the navigation menu, click **Serving Configs**.\n\n3. Click the name of the serving config that you want to view analytics for.\n\n4. Click the **Analytics** tab.\n\n5. Select a metric type from the **Metric** drop-down list to see its graph for the last month.\n\nMetrics definitions\n-------------------\n\nThese sections provide definitions of the site-wide metrics displayed on the\n[**Analytics** page](https://console.cloud.google.com/ai/retail/catalogs/default_catalog/analytics/):\n\n- [Recommendations summary metrics](#summary-recai): Metrics representing user engagement with recommendation results.\n- search summary metrics:\n - [Text query search summary metrics](#summary-search): Metrics representing engagement with text-based query search results.\n - [Browse search summary metrics](#summary-browse): Metrics representing engagement with category browse search results.\n\n#### Recommendations summary metrics\n\nThe following metrics are displayed for recommendations on the\n**Recommendations** tab.\n\n#### Text search summary metrics\n\nThe following metrics for text searches are displayed on\nthe **Search** tab.\n\n#### Browse search summary metrics\n\nThe following metrics for browse searches are displayed\non the **Browse** tab.\n\n### Configuration-specific metrics\n\n| **Note:** Serving config metrics are only available for recommendations.\n\nYou can see metrics for a specific serving config on the\n[Serving Configs page](https://console.cloud.google.com/ai/retail/catalogs/default_catalog/configs/).\nFor metric graphs, click a serving config name to go to its details page,\nthen select the **Analytics** tab.\n\nThis table provides definitions for configuration-specific metrics.\n\nTo track clicks from a serving config, Vertex AI Search for commerce aligns the\nresults in `predict` and `search` responses with ingested user events. If a\nclicked item appears in the responses for the same visitor ID within a\none hour time window, the click or purchase is treated as a result of the\nVertex AI Search for commerce.\n\nThis process is fully automatic; you don't need to set anything up. However,\nwhen you configure your prediction and search requests for the first time, you\nshould confirm that:\n\n- Visitor IDs in the request are the same as the visitor IDs you used in event ingestions.\n- The timestamp in the response roughly match the timestamp for that event.\n\nWhen metrics are compared to the ideal expected result, or ground truth, the\nvalues might be lower, but the trends align.\n\nA more direct alternative to this method is to use\n[attribution tokens](/retail/docs/attribution-tokens). This requires significant instrumentation and\nis only recommended as an advanced tracking use case."]]