MDM AI Matching Telemetry and Monitoring
It is possible to download the AI Matching metadata that can be used by Ataccama for further analysis of the AI Matching performance.
The metadata is a list of AI Matching events, for example:
-
UserIdentity
: Contains anonymized user identifier, anonymized user name, and a list of user roles. Used for correlating user actions to roles. -
PairLabeled
: Contains information about user decision - AI Matching model identifier (matching_id
), timestamp, request correlation id, a pair of internal record identifiers, user decision, labeling origin, and a record distance vector (column-wise affine gap distance). -
ProposalsGenerationResults
: Statistics for a finished Proposals Generation action. Contains initial job parameters, merge and split proposal counts, and a confidence histogram. -
JobScheduled
,JobAssigned
,JobStarted
,JobRunningPhaseChanged
,JobFinished
: Stages of the job performed.
The full schema of collected metadata looks as follows:
Schema of exported metadata
{
"title": "AI Matching events schema",
"definitions": {
"MatchingId": {
"title": "MatchingId",
"description": "Matching identifier.",
"type": "object",
"properties": {
"entity_name": {
"title": "Entity Name",
"type": "string"
},
"layer_name": {
"title": "Layer Name",
"type": "string"
}
},
"required": [
"entity_name",
"layer_name"
]
},
"UserIdentity": {
"title": "UserIdentity",
"description": "Part of the identity corresponding to the user (direct or impersonated one) calling the request.",
"type": "object",
"properties": {
"id": {
"title": "Id",
"type": "string"
},
"username": {
"title": "Username",
"type": "string"
},
"roles": {
"title": "Roles",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"id",
"username",
"roles"
]
},
"ServiceIdentity": {
"title": "ServiceIdentity",
"description": "Part of the identity corresponding to the service calling the request.",
"type": "object",
"properties": {
"id": {
"title": "Id",
"type": "string"
},
"module": {
"title": "Module",
"type": "string"
},
"roles": {
"title": "Roles",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"id",
"module",
"roles"
]
},
"Identity": {
"title": "Identity",
"description": "Identity parsed during authentication when processing incoming request.",
"type": "object",
"properties": {
"user_identity": {
"$ref": "#/definitions/UserIdentity"
},
"service_identity": {
"$ref": "#/definitions/ServiceIdentity"
}
}
},
"MatchingCreated": {
"title": "MatchingCreated",
"description": "Event emitted when a new Matching is created.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"created_by": {
"$ref": "#/definitions/Identity"
},
"correlation_id": {
"title": "Correlation Id",
"type": "string"
}
},
"required": [
"matching_id",
"created_at",
"created_by",
"correlation_id"
]
},
"JobParameters": {
"title": "JobParameters",
"description": "Base class for AI Matching job parameters.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
}
},
"required": [
"matching_id"
]
},
"JobScheduled": {
"title": "JobScheduled",
"description": "Event emitted when a job is scheduled.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"created_by": {
"$ref": "#/definitions/Identity"
},
"correlation_id": {
"title": "Correlation Id",
"type": "string"
},
"job_id": {
"title": "Job Id",
"type": "string",
"format": "uuid"
},
"job_type": {
"title": "Job Type",
"type": "string"
},
"parameters": {
"$ref": "#/definitions/JobParameters"
}
},
"required": [
"matching_id",
"created_at",
"created_by",
"correlation_id",
"job_id",
"job_type",
"parameters"
]
},
"JobCanceled": {
"title": "JobCanceled",
"description": "Event emitted when a job is canceled.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"created_by": {
"$ref": "#/definitions/Identity"
},
"correlation_id": {
"title": "Correlation Id",
"type": "string"
},
"job_type": {
"title": "Job Type",
"type": "string"
}
},
"required": [
"matching_id",
"created_at",
"created_by",
"correlation_id",
"job_type"
]
},
"MatchingDecision": {
"title": "MatchingDecision",
"description": "Type of training pair - needs to be kept in sync with gRPC enum.",
"enum": [
[
0,
0,
null,
null
],
[
1,
1,
1,
"match"
],
[
2,
2,
0,
"distinct"
]
]
},
"LabeledIdsPair": {
"title": "LabeledIdsPair",
"description": "Ordered pair of record IDs with a label (matching decision).",
"type": "object",
"properties": {
"id1": {
"title": "Id1",
"type": "string",
"format": "uuid"
},
"id2": {
"title": "Id2",
"type": "string",
"format": "uuid"
},
"label": {
"$ref": "#/definitions/MatchingDecision"
}
},
"required": [
"id1",
"id2",
"label"
]
},
"PairLabeled": {
"title": "PairLabeled",
"description": "Event emitted when a training pair is labeled.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"created_by": {
"$ref": "#/definitions/Identity"
},
"correlation_id": {
"title": "Correlation Id",
"type": "string"
},
"labeled_ids_pair": {
"$ref": "#/definitions/LabeledIdsPair"
},
"labeling_origin": {
"title": "Labeling Origin",
"type": "string"
},
"pair_distance": {
"title": "Pair Distance",
"type": "array",
"items": {
"type": "number"
}
}
},
"required": [
"matching_id",
"created_at",
"created_by",
"correlation_id",
"labeled_ids_pair",
"labeling_origin"
]
},
"LabeledPairsDeleted": {
"title": "LabeledPairsDeleted",
"description": "Event emitted when all labeled pairs for a Matching are deleted.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"created_by": {
"$ref": "#/definitions/Identity"
},
"correlation_id": {
"title": "Correlation Id",
"type": "string"
},
"deleted_pair_count": {
"title": "Deleted Pair Count",
"type": "integer"
}
},
"required": [
"matching_id",
"created_at",
"created_by",
"correlation_id",
"deleted_pair_count"
]
},
"MatchingDeleted": {
"title": "MatchingDeleted",
"description": "Event emitted when a Matching is deleted.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"created_by": {
"$ref": "#/definitions/Identity"
},
"correlation_id": {
"title": "Correlation Id",
"type": "string"
}
},
"required": [
"matching_id",
"created_at",
"created_by",
"correlation_id"
]
},
"ProposalsDiscarded": {
"title": "ProposalsDiscarded",
"description": "Event emitted when generated proposals are discarded.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"created_by": {
"$ref": "#/definitions/Identity"
},
"correlation_id": {
"title": "Correlation Id",
"type": "string"
},
"proposals_generation_id": {
"title": "Proposals Generation Id",
"type": "string",
"format": "uuid"
}
},
"required": [
"matching_id",
"created_at",
"created_by",
"correlation_id",
"proposals_generation_id"
]
},
"ProposalsLoaded": {
"title": "ProposalsLoaded",
"description": "Event emitted when generated proposals are loaded into client.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"created_by": {
"$ref": "#/definitions/Identity"
},
"correlation_id": {
"title": "Correlation Id",
"type": "string"
},
"proposals_generation_id": {
"title": "Proposals Generation Id",
"type": "string",
"format": "uuid"
},
"loaded_count": {
"title": "Loaded Count",
"type": "integer"
}
},
"required": [
"matching_id",
"created_at",
"created_by",
"correlation_id",
"proposals_generation_id",
"loaded_count"
]
},
"ProposalResolved": {
"title": "ProposalResolved",
"description": "Event emitted when proposal was resolved in the client.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"created_by": {
"$ref": "#/definitions/Identity"
},
"correlation_id": {
"title": "Correlation Id",
"type": "string"
},
"proposals_generation_id": {
"title": "Proposals Generation Id",
"type": "string",
"format": "uuid"
},
"proposal_ids_pair": {
"title": "Proposal Ids Pair",
"type": "array",
"minItems": 2,
"maxItems": 2,
"items": [
{
"type": "integer"
},
{
"type": "integer"
}
]
},
"decision": {
"title": "Decision",
"type": "string"
},
"resolution": {
"title": "Resolution",
"type": "string"
},
"confidence": {
"title": "Confidence",
"type": "integer"
},
"intended_for_learning": {
"title": "Intended For Learning",
"type": "boolean"
}
},
"required": [
"matching_id",
"created_at",
"created_by",
"correlation_id",
"proposals_generation_id",
"proposal_ids_pair",
"decision",
"resolution",
"confidence",
"intended_for_learning"
]
},
"JobAssigned": {
"title": "JobAssigned",
"description": "Event emitted when a job is assigned to a worker.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"job_id": {
"title": "Job Id",
"type": "string",
"format": "uuid"
},
"job_type": {
"title": "Job Type",
"type": "string"
},
"worker_id": {
"title": "Worker Id",
"type": "string"
}
},
"required": [
"matching_id",
"created_at",
"job_id",
"job_type",
"worker_id"
]
},
"JobAssignmentReleased": {
"title": "JobAssignmentReleased",
"description": "Event emitted when a job is no longer assigned to a worker.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"job_id": {
"title": "Job Id",
"type": "string",
"format": "uuid"
},
"job_type": {
"title": "Job Type",
"type": "string"
}
},
"required": [
"matching_id",
"created_at",
"job_id",
"job_type"
]
},
"JobStarted": {
"title": "JobStarted",
"description": "Event emitted when a job is executed.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"job_id": {
"title": "Job Id",
"type": "string",
"format": "uuid"
},
"job_type": {
"title": "Job Type",
"type": "string"
},
"worker_id": {
"title": "Worker Id",
"type": "string"
}
},
"required": [
"matching_id",
"created_at",
"job_id",
"job_type",
"worker_id"
]
},
"JobRunningPhaseChanged": {
"title": "JobRunningPhaseChanged",
"description": "Event emitted when a job running phase is updated.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"job_id": {
"title": "Job Id",
"type": "string",
"format": "uuid"
},
"job_type": {
"title": "Job Type",
"type": "string"
},
"running_phase": {
"title": "Running Phase",
"type": "string"
}
},
"required": [
"matching_id",
"created_at",
"job_id",
"job_type",
"running_phase"
]
},
"JobResults": {
"title": "JobResults",
"description": "Base class for AI Matching job results.",
"type": "object",
"properties": {
"parameters": {
"$ref": "#/definitions/JobParameters"
}
},
"required": [
"parameters"
]
},
"JobFinished": {
"title": "JobFinished",
"description": "Event emitted when a job execution is successfully finished.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"job_id": {
"title": "Job Id",
"type": "string",
"format": "uuid"
},
"job_type": {
"title": "Job Type",
"type": "string"
},
"worker_id": {
"title": "Worker Id",
"type": "string"
},
"results": {
"$ref": "#/definitions/JobResults"
}
},
"required": [
"matching_id",
"created_at",
"job_id",
"job_type",
"worker_id",
"results"
]
},
"JobError": {
"title": "JobError",
"description": "Event emitted when an error is encountered during a job execution.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"created_at": {
"title": "Created At",
"type": "string",
"format": "date-time"
},
"job_id": {
"title": "Job Id",
"type": "string",
"format": "uuid"
},
"job_type": {
"title": "Job Type",
"type": "string"
},
"classname": {
"title": "Classname",
"type": "string"
},
"message": {
"title": "Message",
"type": "string"
},
"traceback": {
"title": "Traceback",
"type": "string"
}
},
"required": [
"matching_id",
"created_at",
"job_id",
"job_type",
"classname",
"message",
"traceback"
]
},
"MdcColumnType": {
"title": "MdcColumnType",
"description": "Definition of a type of MDC columns - needs to be kept in sync with gRPC enum.",
"enum": [
[
0,
0,
"str"
],
[
1,
1,
"str"
],
[
2,
2,
"str"
],
[
3,
3,
"str"
],
[
4,
4,
"str"
],
[
5,
5,
"str"
],
[
6,
6,
"str"
],
[
-1,
4,
"int"
]
]
},
"MdcColumn": {
"title": "MdcColumn",
"description": "Container class holding name and type of an MDC column.",
"type": "object",
"properties": {
"name": {
"title": "Name",
"type": "string"
},
"type": {
"$ref": "#/definitions/MdcColumnType"
}
},
"required": [
"name",
"type"
]
},
"InitializationParameters": {
"title": "InitializationParameters",
"description": "Parameters for running an Initialization job.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"scheduled_by": {
"$ref": "#/definitions/Identity"
},
"matching_columns": {
"title": "Matching Columns",
"type": "array",
"items": {
"$ref": "#/definitions/MdcColumn"
}
},
"record_id_column": {
"$ref": "#/definitions/MdcColumn"
},
"file_path": {
"title": "File Path",
"type": "string"
}
},
"required": [
"matching_id",
"scheduled_by",
"matching_columns",
"record_id_column"
]
},
"TrainingPairComputationParameters": {
"title": "TrainingPairComputationParameters",
"description": "Parameters for running a Training Pair Computation job.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"matching_columns": {
"title": "Matching Columns",
"type": "array",
"items": {
"$ref": "#/definitions/MdcColumn"
}
},
"model_id": {
"title": "Model Id",
"type": "string",
"format": "uuid"
},
"model_history_version": {
"title": "Model History Version",
"type": "string",
"format": "date-time"
}
},
"required": [
"matching_id",
"matching_columns",
"model_id",
"model_history_version"
]
},
"ModelQualityEstimationParameters": {
"title": "ModelQualityEstimationParameters",
"description": "Parameters for running a Model Quality Estimation job.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"matching_columns": {
"title": "Matching Columns",
"type": "array",
"items": {
"$ref": "#/definitions/MdcColumn"
}
},
"model_id": {
"title": "Model Id",
"type": "string",
"format": "uuid"
},
"model_history_version": {
"title": "Model History Version",
"type": "string",
"format": "date-time"
}
},
"required": [
"matching_id",
"matching_columns",
"model_id",
"model_history_version"
]
},
"ProposalsGenerationParameters": {
"title": "ProposalsGenerationParameters",
"description": "Parameters for running a Proposals Generation job.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"scheduled_by": {
"$ref": "#/definitions/Identity"
},
"matching_columns": {
"title": "Matching Columns",
"type": "array",
"items": {
"$ref": "#/definitions/MdcColumn"
}
},
"master_id_column": {
"$ref": "#/definitions/MdcColumn"
},
"record_id_column": {
"$ref": "#/definitions/MdcColumn"
},
"file_path": {
"title": "File Path",
"type": "string"
},
"max_proposals_count": {
"title": "Max Proposals Count",
"type": "integer"
},
"min_confidence": {
"title": "Min Confidence",
"type": "number"
},
"model_id": {
"title": "Model Id",
"type": "string",
"format": "uuid"
},
"model_history_version": {
"title": "Model History Version",
"type": "string",
"format": "date-time"
}
},
"required": [
"matching_id",
"scheduled_by",
"matching_columns",
"master_id_column",
"record_id_column",
"max_proposals_count",
"min_confidence",
"model_id",
"model_history_version"
]
},
"RulesExtractionParameters": {
"title": "RulesExtractionParameters",
"description": "Parameters for running a Rules Extraction job.",
"type": "object",
"properties": {
"matching_id": {
"$ref": "#/definitions/MatchingId"
},
"scheduled_by": {
"$ref": "#/definitions/Identity"
},
"matching_columns": {
"title": "Matching Columns",
"type": "array",
"items": {
"$ref": "#/definitions/MdcColumn"
}
},
"record_id_column": {
"$ref": "#/definitions/MdcColumn"
},
"file_path": {
"title": "File Path",
"type": "string"
},
"min_match_confidence": {
"title": "Min Match Confidence",
"type": "number"
},
"min_distinct_confidence": {
"title": "Min Distinct Confidence",
"type": "number"
},
"model_id": {
"title": "Model Id",
"type": "string",
"format": "uuid"
},
"model_history_version": {
"title": "Model History Version",
"type": "string",
"format": "date-time"
}
},
"required": [
"matching_id",
"scheduled_by",
"matching_columns",
"record_id_column",
"min_match_confidence",
"min_distinct_confidence",
"model_id",
"model_history_version"
]
},
"InitializationResults": {
"title": "InitializationResults",
"description": "Results of an Initialization job.",
"type": "object",
"properties": {
"parameters": {
"$ref": "#/definitions/InitializationParameters"
},
"model_id": {
"title": "Model Id",
"type": "string",
"format": "uuid"
},
"candidate_records_count": {
"title": "Candidate Records Count",
"type": "integer"
},
"candidate_pairs_count": {
"title": "Candidate Pairs Count",
"type": "integer"
}
},
"required": [
"parameters",
"model_id",
"candidate_records_count",
"candidate_pairs_count"
]
},
"RecordIdsPair": {
"title": "RecordIdsPair",
"description": "Ordered pair of record IDs.",
"type": "object",
"properties": {
"id1": {
"title": "Id1",
"type": "string",
"format": "uuid"
},
"id2": {
"title": "Id2",
"type": "string",
"format": "uuid"
}
},
"required": [
"id1",
"id2"
]
},
"TrainingPairComputationResults": {
"title": "TrainingPairComputationResults",
"description": "Results of a Training Pair Computation job.",
"type": "object",
"properties": {
"parameters": {
"$ref": "#/definitions/TrainingPairComputationParameters"
},
"record_ids_pair": {
"$ref": "#/definitions/RecordIdsPair"
}
},
"required": [
"parameters",
"record_ids_pair"
]
},
"ModelQuality": {
"title": "ModelQuality",
"description": "AI Matching model quality.",
"enum": [
[
0,
-1
],
[
1,
0
],
[
2,
0.5
],
[
3,
0.8
]
]
},
"ConfusionMatrix": {
"title": "ConfusionMatrix",
"description": "Holds information useful for evaluating performance of a model on a classification task.\n\nSee: https://en.wikipedia.org/wiki/Confusion_matrix",
"type": "object",
"properties": {
"tp": {
"title": "Tp",
"type": "integer"
},
"fp": {
"title": "Fp",
"type": "integer"
},
"tn": {
"title": "Tn",
"type": "integer"
},
"fn": {
"title": "Fn",
"type": "integer"
}
},
"required": [
"tp",
"fp",
"tn",
"fn"
]
},
"ModelEvaluation": {
"title": "ModelEvaluation",
"description": "Holds model evaluation result statistics for one model.",
"type": "object",
"properties": {
"quality": {
"$ref": "#/definitions/ModelQuality"
},
"sensitivity": {
"title": "Sensitivity",
"type": "number"
},
"sequential_confusion_matrix": {
"$ref": "#/definitions/ConfusionMatrix"
},
"blocker_confusion_matrix": {
"$ref": "#/definitions/ConfusionMatrix"
},
"classifier_confusion_matrix": {
"$ref": "#/definitions/ConfusionMatrix"
}
},
"required": [
"quality",
"sensitivity",
"sequential_confusion_matrix",
"blocker_confusion_matrix",
"classifier_confusion_matrix"
]
},
"ModelQualityEstimationResults": {
"title": "ModelQualityEstimationResults",
"description": "Results of a Model Quality Estimation job.",
"type": "object",
"properties": {
"parameters": {
"$ref": "#/definitions/ModelQualityEstimationParameters"
},
"estimated_model_quality": {
"$ref": "#/definitions/ModelQuality"
},
"cv_evaluation": {
"$ref": "#/definitions/ModelEvaluation"
},
"all_data_evaluation": {
"$ref": "#/definitions/ModelEvaluation"
}
},
"required": [
"parameters"
]
},
"ProposalsGenerationResults": {
"title": "ProposalsGenerationResults",
"description": "Results of a Proposals Generation job.",
"type": "object",
"properties": {
"parameters": {
"$ref": "#/definitions/ProposalsGenerationParameters"
},
"merge_proposals_count": {
"title": "Merge Proposals Count",
"type": "integer"
},
"split_proposals_count": {
"title": "Split Proposals Count",
"type": "integer"
},
"cumulative_confidence_histogram": {
"title": "Cumulative Confidence Histogram",
"type": "object",
"additionalProperties": {
"type": "integer"
}
}
},
"required": [
"parameters",
"merge_proposals_count",
"split_proposals_count"
]
},
"RulesExtractionResults": {
"title": "RulesExtractionResults",
"description": "Results of a Rules Extraction job.",
"type": "object",
"properties": {
"parameters": {
"$ref": "#/definitions/RulesExtractionParameters"
},
"blocking_rules_count": {
"title": "Blocking Rules Count",
"type": "integer"
},
"matching_rules_count": {
"title": "Matching Rules Count",
"type": "integer"
},
"overall_coverage": {
"title": "Overall Coverage",
"type": "number"
}
},
"required": [
"parameters",
"blocking_rules_count",
"matching_rules_count",
"overall_coverage"
]
},
"BlockerStats": {
"title": "BlockerStats",
"description": "Container class for dedupe blocker statistics.",
"type": "object",
"properties": {
"block_sizes": {
"title": "Block Sizes",
"default": {},
"type": "object",
"additionalProperties": {
"type": "array",
"items": {
"type": "integer"
}
}
},
"blocking_predicates": {
"title": "Blocking Predicates",
"type": "array",
"items": {
"type": "string"
}
}
}
},
"ClassifierStats": {
"title": "ClassifierStats",
"description": "Container class for dedupe classifier (RRLR) statistics.",
"type": "object",
"properties": {
"alpha": {
"title": "Alpha",
"type": "number"
},
"bias": {
"title": "Bias",
"type": "number"
},
"weights": {
"title": "Weights",
"type": "array",
"items": {
"type": "number"
}
}
}
},
"ClusteringStats": {
"title": "ClusteringStats",
"description": "Container class for dedupe clustering statistics.",
"type": "object",
"properties": {
"sizes": {
"title": "Sizes",
"default": {},
"type": "object",
"additionalProperties": {
"type": "integer"
}
}
}
},
"CVStats": {
"title": "CVStats",
"description": "Container class for model cross-validation statistics.",
"type": "object",
"properties": {
"model_stats": {
"title": "Model Stats",
"default": [],
"type": "array",
"items": {
"type": "array",
"minItems": 2,
"maxItems": 2,
"items": [
{
"$ref": "#/definitions/BlockerStats"
},
{
"$ref": "#/definitions/ClassifierStats"
}
]
}
},
"model_evaluation": {
"$ref": "#/definitions/ModelEvaluation"
}
}
},
"ModelStats": {
"title": "ModelStats",
"description": "Container class for dedupe model statistics.",
"type": "object",
"properties": {
"blocker": {
"$ref": "#/definitions/BlockerStats"
},
"classifier": {
"$ref": "#/definitions/ClassifierStats"
},
"clustering": {
"$ref": "#/definitions/ClusteringStats"
},
"cv_stats": {
"$ref": "#/definitions/CVStats"
},
"all_data_stats": {
"$ref": "#/definitions/CVStats"
},
"matching_columns": {
"title": "Matching Columns",
"type": "array",
"items": {
"$ref": "#/definitions/MdcColumn"
}
}
}
}
}
}
An example of the expected output:
{"matching_id": {"entity_name": "party", "layer_name": "masters"}, "created_at": "2023-01-25T09:13:14.373405+00:00", "created_by": {"user_identity": {"id": "f7545e670d7ecddf84a23b1ec76fc12c", "username": "a7aa91520ceb9e3152cfece700d72514", "roles": ["MDM_admin", "DQIT_admin", "default-roles-ataccamaone", "admin", "MMM_user", "MDM_user", "DQIT_user", "ONE_ADMIN", "MMM_admin", "RDM_user", "default", "DPP_admin", "RDM_admin", "CS_admin", "offline_access", "MMM_export", "RDM", "uma_authorization", "AUDITOR", "DQIT_supervisor"]}, "service_identity": {"id": "mdm-server-svc:8051", "module": "mdm", "roles": ["IMPERSONATION"]}}, "correlation_id": "cbcdd7", "_event_class": "MatchingCreated"}
{"matching_id": {"entity_name": "party", "layer_name": "masters"}, "created_at": "2023-01-25T09:13:14.401771+00:00", "created_by": {"user_identity": {"id": "f7545e670d7ecddf84a23b1ec76fc12c", "username": "a7aa91520ceb9e3152cfece700d72514", "roles": ["MDM_admin", "DQIT_admin", "default-roles-ataccamaone", "admin", "MMM_user", "MDM_user", "DQIT_user", "ONE_ADMIN", "MMM_admin", "RDM_user", "default", "DPP_admin", "RDM_admin", "CS_admin", "offline_access", "MMM_export", "RDM", "uma_authorization", "AUDITOR", "DQIT_supervisor"]}, "service_identity": {"id": "mdm-server-svc:8051", "module": "mdm", "roles": ["IMPERSONATION"]}}, "correlation_id": "cbcdd7", "labeled_ids_pair": {"id1": "44053ff9-b59b-4d18-9fcc-3c66868af0c4", "id2": "807a3028-09ed-4f31-b114-313b0b8ca627", "label": 1}, "labeling_origin": "manual_match_decision", "pair_distance": [0.5, 0.0, 0.9750000238418579, 0.5, 0.5, 1.7826087474822998, 0.5, 0.0, 0.5, 0.0, 0.0, 0.5, 0.5, 0.0], "_event_class": "PairLabeled"}
{"matching_id": {"entity_name": "party", "layer_name": "masters"}, "created_at": "2023-01-25T09:13:14.773771+00:00", "job_id": "457d7093-589b-413f-a874-b5842927d1f6", "job_type": "initialization", "worker_id": "ai_matching:worker:14.2.0.main-230120-1201-77add35e:82ffc6c45b15479e8ce033777792df66", "_event_class": "JobAssigned"}
{"matching_id": {"entity_name": "party", "layer_name": "masters"}, "created_at": "2023-01-25T09:13:21.430008+00:00", "job_id": "457d7093-589b-413f-a874-b5842927d1f6", "job_type": "initialization", "worker_id": "ai_matching:worker:14.2.0.main-230120-1201-77add35e:82ffc6c45b15479e8ce033777792df66", "_event_class": "JobStarted"}
{"matching_id": {"entity_name": "party", "layer_name": "masters"}, "created_at": "2023-01-25T09:13:25.227946+00:00", "job_id": "457d7093-589b-413f-a874-b5842927d1f6", "job_type": "training_pair_computation", "worker_id": "ai_matching:worker:14.2.0.main-230120-1201-77add35e:82ffc6c45b15479e8ce033777792df66", "results": {"parameters": {"matching_id": {"entity_name": "party", "layer_name": "masters"}, "matching_columns": [{"name": "mat_party_type", "type": 0}, {"name": "mat_gender", "type": 0}, {"name": "mat_first_name", "type": 0}, {"name": "mat_middle_name", "type": 0}, {"name": "mat_last_name", "type": 0}, {"name": "mat_full_name", "type": 0}, {"name": "mat_initials", "type": 0}, {"name": "mat_person_id", "type": 0}, {"name": "mat_birth_date", "type": 2}, {"name": "mat_company_name", "type": 0}, {"name": "mat_company_id", "type": 0}, {"name": "mat_address_set", "type": 0}, {"name": "mat_contact_set", "type": 0}, {"name": "mat_id_doc_set", "type": 0}], "model_id": "5bb5c368-aee2-4494-95f0-076e19a5ef61", "model_history_version": "2023-01-25T09:13:23.620615+00:00"}, "record_ids_pair": {"id1": "d904a419-07df-4c4d-aba6-448c1694d116", "id2": "e8e305b6-9197-4e41-a65f-c700fb65aa77"}}, "_event_class": "JobFinished"}
The exported file does not contain any actual data, nor sensitive information. Sensitive data fields are anonymized by applying a one-way hash function. |
Entity and column names are exposed as part of exported metadata. |
Was this page useful?