Page Comparison

Ever wanted to add a field that does not exist in our out-of-the-box models and you thought, “We don’t need a smart model to do this. I just need to look at these certain words.” ? For this use-case we provide a predictor you can control through the predictor settings.

First add a tag field to your format. We choose the name In the example below we describe the implementation for the field email_coming_from with the tag options no_reply and info. Then, add your , so they will match no-reply@contract.fit and info@contract.fit respectively.

The field and tags need to be added in a specified rule as a regex in the predictor settings. On the swagger page of your environment you can find the endpoint /predictor_settings/{scope}. The scope is the inbox/project for which you would want this predictor to run. Inside key_value_pairs::rule_config you can specify per tag_field which regexes you want to match for a given field_name. Note that the field_name and tag options have to match exactly (case sensitive). Otherwise the prediction will be empty. We created these rules to match no-reply@contract.fit and info@contract.fit respectively:

{
  "key_value_pairs": {
    "rule_config": {
      "email_coming_from": {
        "no_reply": {
          "rules": [
            {
              "confidence": 97,
              "+rule": ["L:no-reply@contract.fit"]
            }
          ]
        },
        "info": {
          "rules": [
            {
              "confidence": 97,
              "+rule": ["L:info@contract.fit", "L:"]                
            }
          ]
        }
      }
    }
  }
}

Per tag field (level of no_reply and info) you can specify a list of rules with a confidence per rule. The rule that matched with the highest confidence will be presented in the prediction. If we see no-reply@contract.fit somewhere in the uploaded document, a prediction with confidence 97 for the tag_option no_reply will be returned.

...

The rule we have specified now will look in apply to the whole document, this is way too broad. We only want to search inside the email field which specifies the from. For this we can use the where_to_search option specified on the same level of the +rule. To specify where and how to search there are 4 options. All of these are optional:

1. preprocess_text: This is a bool specifying if the text needs to be cleaned (noise removed).

2. search_in: This field specifies which part of the text we look in. There are 5 options which can be combined. When left empty we will look in all these options:

   1. email_from

   2. email_to

   3. email_subject

   4. email_body

   5. attachment

3. limits: This field specifies which limits we apply to our search_space (add link to further here).

4. granularity: This field specifies what the granularity for a match should be (add link to further here).

...