Overview
Before a search query is used to retrieve documents, OpenSearch analyzes and processes the semantics of the search query. The term weight analysis feature evaluates the importance of each term in the search query and quantifies the evaluated importance as a weight. OpenSearch may not use low-importance terms to retrieve documents. This helps increase the number of documents that are retrieved. If the search query that you entered contain low-importance terms and these terms are involved in the document retrieval process, only a small number of documents may be retrieved based on the search query. Business scenarios vary with industries. To achieve the optimal search performance, you must use a term weight analysis model specific to your application.
OpenSearch Industry Algorithm Edition provides a wide range of domain-specific term weight analysis models. You can configure and train a custom term weight analysis model based on the corresponding industry-specific analyzer. When you train the term weight analysis model, the system automatically extracts the existing data of your application and analyzes the data based on the business logic of your application. No more data import is required.
You are charged for tailored retrieval models based on storage capacity, computing resources, and model training. For more information about billing rules, see Billing overview
Create and use a tailored retrieval model
To create and use a term weight analysis model, perform the following steps:
Create and train a term weight analysis model.
Configure a query analysis rule and reference the trained term weight analysis model.
Adjust the term weight analysis model as needed by using an intervention dictionary.
Create and train a model
1. Log on to the OpenSearch console. In the left-side navigation pane, choose Search Algorithm Center > Retrieval Configuration. On the Retrieval Configuration page, click Tailored Retrieval Models in the left-side pane. On the page that appears, select an application and click Create.
Configure the Model Name, Model Type, and Training Fields parameters, and click Submit.
Parameters:
Model Name: Enter a name based on the naming conventions. Example: ly_tets.
Model Type: Set this parameter to Term Weight Analysis Model. The parameters displayed vary based on the model type.
Training Fields: Selects fields from the application that you selected.
2. After the term weight analysis model is created, click Train.
Configure a query analysis rule
1. On the Retrieval Configuration page, click Query Analysis Rule Configuration in the left-side pane. On the page that appears, click Create. In the Create Rule panel, select Term Weight and set the Dictionaries parameter to System Built-in Model or Custom Term Weight Analysis Model.
2. If you select Custom Term Weight Analysis Model, specify the name and version of the custom term weight analysis model that you want to use.
Configure an intervention dictionary
On the Retrieval Configuration page, click Dictionary Management in the left-side pane. On the page that appears, find the intervention dictionary that you want to use and click Manage Entries in the Actions column. On the Manage Entries page, click Add Intervention Entry. In the Add Intervention Entries panel, configure the parameters such as Search Query, Analyzer, and Term Weight Analysis Model, and click Save.
Details pages
Tailored Retrieval Models page
Tailored Retrieval Models page
The Tailored Retrieval Models page displays the information about each model in columns such as Model Name, Model Type, Model Status, Last Training Started At, Latest Version Status, and Actions.
Note: You cannot delete the tailored retrieval models that are referenced by query analysis rules.
Details page of a term weight analysis model
The details page of a term weight analysis model consists of three sections: Basic Information, Configuration Information, and Training History.
1. After a term weight analysis model is trained, you can find the model and click Details in the Actions column. Then, in the Training History section, click View in the Reference Rule column to view the query analysis rules that reference the model.
2. Test the model.
3. Compare the performance of term weight analysis models in typical cases.
Note:
You can select a built-in model and different versions of the current model to compare the performance of term weight analysis models.
The Typical Case Comparison section displays a maximum of 200 term weight analysis results, including the text and the results of both term weight analysis models that you selected.
You can enter a search query in the Test Text field to obtain term weight analysis results.
Limits
This feature is available only for exclusive applications of Industry Algorithm Edition.
A maximum of five tailored retrieval models can be created for an application.
A tailored retrieval model is created for a specific application and cannot be configured across applications.