System and method for combining expert knowledge and deep learning to identify and classify regulatory maintenance compliances
A computer implemented method includes building a Positive Knowledge Base with directive words, designated verbs and designated objects. A Negative Knowledge Base with designated phrases and designated legal terms is built. Tasks and phrases from the Positive Knowledge Base and the Negative Knowledge Base are built. Regulations are received. Phrases from the regulations are weighted against the Positive Knowledge Base and the Negative Knowledge Base to isolate positive Maintenance Compliances. The positive Maintenance Compliances are matched to tasks to derive ranked Maintenance Compliances. The ranked Maintenance Compliances are supplied.
1. A computer implemented method, comprising:
building a Positive Knowledge Base with Directive Words, Designated Verbs and Designated Objects;
building a Negative Knowledge Base with Designated Phrases and Designated Legal Terms;
building tasks and phrases from the Positive Knowledge Base and the Negative Knowledge Base;
receiving regulations that are statutes and ordinances governing building maintenance;
weighing phrases from the regulations against the Positive Knowledge Base and the Negative Knowledge Base to isolate positive Maintenance Compliances specifying regulations to ensure metrics are enforced or met in connection with building maintenance;
matching the positive Maintenance Compliances to Tasks to derive ranked Maintenance Compliances;
confirming Task Matches to the positive Maintenance Compliances;
confirming the positive Maintenance Compliances;
training deep learning models for Maintenance Compliances and tasks;
refining tasks and phrases within the Positive Knowledge Base and Negative Knowledge Base; and
supplying the ranked Maintenance Compliances to a client device.
2. The method of claim 1 further comprising applying the ranked Maintenance Compliances to the Positive Knowledge Base and the Negative Knowledge Base to update weights within the Positive Knowledge Base and the Negative Knowledge Base.
3. The method of claim 1 wherein the building maintenance is for multi-family rental housing.
4. The method of claim 1 wherein the building maintenance is for commercial building maintenance.
5. The method of claim 1 wherein the building maintenance is for single-family rental housing.
6. The method of claim 1 wherein the building maintenance is for multi-family condominium housing.
7. The method of claim 1 wherein the Directive Words are weighed against fragments from the regulations to increase the likelihood of a Maintenance Compliance.
8. The method of claim 1 wherein the Designated Verbs are weighed against fragments from the regulations to increase the likelihood of a Maintenance Compliance.
9. The method of claim 1 wherein the Designated Objects are weighed against fragments from the regulations to increase the likelihood of a Maintenance Compliance.
10. The method of claim 1 wherein the Designated Phrases are weighed against fragments from the regulations to decrease the likelihood of a Maintenance Compliance.
11. The method of claim 1 wherein the Designated Legal Terms are weighed against fragments from the regulations to decrease the likelihood of a Maintenance Compliance.
12. The method of claim 1 wherein phrases from Headers are assigned a multiplied value.