Data Discovery is currently in Private Preview and is not available for General Availability (GA). It should not be used in production environments, as features and functionality may change before the final GA release.
Sample Response with Detail
Sample Response with Detail.
{
"transform": {
"text": "[PERSON] lives at [LOCATION] [LOCATION], [LOCATION] [LOCATION], [LOCATION]."
},
"providers": [
{
"name": "Pattern Classification Provider",
"version": "1.1.0",
"status": 200,
"elapsed_time": 0.011328935623168945,
"config_provider": {
"name": "Pattern",
"address": "http://pattern_provider_service:8051",
"supported_content_types": []
}
},
{
"name": "Context Classification Provider",
"version": "1.1.0",
"status": 200,
"elapsed_time": 0.03895401954650879,
"config_provider": {
"name": "Context",
"address": "http://context_provider_service:8052",
"supported_content_types": []
}
}
],
"classifications": {
"LOCATION": [
{
"score": 0.85,
"location": {
"start_index": 17,
"end_index": 24
},
"classifiers": [
{
"provider_index": 0,
"name": "SpacyRecognizer",
"score": 0.85,
"original_entity": "LOCATION",
"details": {}
}
]
},
{
"score": 0.9240000128746033,
"location": {
"start_index": 26,
"end_index": 32
},
"classifiers": [
{
"provider_index": 0,
"name": "SpacyRecognizer",
"score": 0.85,
"original_entity": "LOCATION",
"details": {}
},
{
"provider_index": 1,
"name": "context",
"score": 0.9980000257492065,
"original_entity": "CITY",
"details": {}
}
]
},
{
"score": 0.9244499981403351,
"location": {
"start_index": 40,
"end_index": 51
},
"classifiers": [
{
"provider_index": 0,
"name": "SpacyRecognizer",
"score": 0.85,
"original_entity": "LOCATION",
"details": {}
},
{
"provider_index": 1,
"name": "context",
"score": 0.9988999962806702,
"original_entity": "STATE",
"details": {}
}
]
},
{
"score": 0.9958999752998352,
"location": {
"start_index": 14,
"end_index": 16
},
"classifiers": [
{
"provider_index": 1,
"name": "context",
"score": 0.9958999752998352,
"original_entity": "BUILDING",
"details": {}
}
]
},
{
"score": 0.9983999729156494,
"location": {
"start_index": 33,
"end_index": 38
},
"classifiers": [
{
"provider_index": 1,
"name": "context",
"score": 0.9983999729156494,
"original_entity": "ZIPCODE",
"details": {}
}
]
}
],
"PERSON": [
{
"score": 0.8819000124931335,
"location": {
"start_index": 0,
"end_index": 4
},
"classifiers": [
{
"provider_index": 1,
"name": "context",
"score": 0.8819000124931335,
"original_entity": "NAME",
"details": {}
}
]
}
]
}
}The fields for the transform section are described as follows:
| Name | Example Response | Description |
|---|---|---|
| transform.text | [PERSON] lives at [LOCATION].. | The labed input text with classified entities listed by name in place of the original sensitive data |
The fields for the providers section are described as follows:
| Name | Example Response | Description |
|---|---|---|
| providers | Array | Array of provider objects that participated in the request, including their respective success or failure codes. |
| providers[n].name | Pattern Classification Provider | Product name of the provider. |
| providers[n].version | 1.0.0 | Version of the provider. |
| providers[n].status | 200 | HTTP response code returned by the provider. |
| providers[n].elapsed_time | 0.028 | Time, in seconds, taken by the provider to process the request. |
| providers[n].config_provider | Object | Object containing configuration details for each provider. |
| providers[n].config_provider.name | Pattern | Internal name of the provider. |
| providers[n].config_provider.address | http://pattern_provider_service:8051 | Network address or endpoint of the provider. |
| providers[n].config_provider.supported_content_types | [] | Array of supported content types. An empty array indicates support for all content types. |
The fields for the classificartion section are described as follows:
| Name | Example Response | Description |
|---|---|---|
| classifications | Dictionary | A dictionary mapping entity types (e.g., “PERSON”, “PHONE_NUMBER”) to arrays of occurrence objects. Each key is an entity type, and its value is a list of detected occurrences, each containing location and classifier details. |
| classifications[’entity’][n].score | 0.9238 | The confidence score for the detected entity, aggregated from all contributing classifiers. |
| classifications[’entity’][n].location | Object | An object specifying the location of the entity within the input text. |
| classifications[’entity’][n].location.start_index | 14 | The starting index of the entity in the input text. |
| classifications[’entity’][n].location.end_index | 25 | The ending index of the entity in the input text. |
| classifications[’entity’][n].classifiers | Array | An array of classifier objects that contributed to the entity detection. |
| classifications[’entity’][n].classifiers[m].provider_index | 0 | The index of the provider in the top-level providers array. |
| classifications[’entity’][n].classifiers[m].name | SpacyRecognizer | The name of the classifier. A provider may have multiple classifiers. |
| classifications[’entity’][n].classifiers[m].score | 0.85 | The score assigned by the classifier for the entity detection. |
| classifications[’entity’][n].classifiers[m].original_entity | PERSON | The original entity type detected by the classifier. See Harmonization for details. |
| classifications[’entity’][n].classifiers[m].details | Object | Optional. Additional key-value details provided by the classifier. |