IP Library Granted Patent US 12682222
Granted Patent B2
US 12682222 · App. 18/358,226 · Granted Jul 14, 2026

Automatic correlation of test logs with service ticket

Inventors: Zhengchu Liu (Neihu, TW); Zhenhua Sun (Shanghai, CN)
Assignee: DELL PRODUCTS L.P.
G06N3/048
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12682222
App. No.
18/358,226
Granted
Jul 14, 2026
Kind
B2
Abstract

Automatic correlation of test logs with service ticket (e.g., using a computerized tool), is enabled. For example, a system can comprise: a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising, based on test log data representative of test logs and using machine learning attention, generating a test log output vector, based on the test log output vector and a service ticket output vector, determining a probability of a relation between a test log represented in the test log output vector and a service ticket represented in the service ticket output vector, and in response to the probability being determined to satisfy a threshold relation probability, marking the test log and the service ticket as related.

Claims (37)

1 . A system, comprising:

at least one processor; and

at least one memory that stores executable instructions that, when executed by the at least one processor, facilitate performance of operations, comprising:

based on test log data representative of test logs and using machine learning attention, generating a test log output vector, wherein the generating of the test log output vector further comprises generating the test log output vector using a test log neural network applied to the test log data;

based on the test log output vector and a service ticket output vector, determining a probability of a relation between a test log represented in the test log output vector and a service ticket represented in the service ticket output vector; and

in response to the probability being determined to satisfy a threshold relation probability, marking the test log and the service ticket as related.

2 . The system of claim 1 , wherein the test log neural network comprises a rectified linear unit activation function.

3 . The system of claim 1 , wherein the service ticket output vector is generated using a service ticket neural network applied to service ticket data representative of service tickets.

4 . The system of claim 3 , wherein the service ticket data comprises a service ticket sparse matrix.

5 . The system of claim 3 , wherein the service ticket neural network comprises a rectified linear unit activation function.

6 . The system of claim 1 , wherein the test log data comprises a test log sparse matrix.

7 . The system of claim 1 , wherein the determining of the probability of the relation between the test log and the service ticket comprises:

concatenating the test log output vector and the service ticket output vector, resulting in a concatenated relation vector, and

inputting the concatenated relation vector to a relation neural network.

8 . The system of claim 7 , wherein the relation neural network comprises a softmax activation function.

9 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by at least one processor, facilitate performance of operations, comprising:

based on test log data representative of test logs and using machine learning attention, generating a test log output vector;

based on the test log output vector and a service ticket output vector, determining a probability of a relation between a test log represented in the test log output vector and a service ticket represented in the service ticket output vector, wherein the service ticket output vector is generated using a service ticket neural network applied to service ticket data representative of service tickets; and

in response to the probability being determined not to satisfy a threshold relation probability, determining that the test log comprises a previously unidentified problem.

10 . The non-transitory machine-readable medium of claim 9 , wherein the generating of the test log output vector comprises generating the test log output vector using a test log neural network applied to the test log data.

11 . The non-transitory machine-readable medium of claim 10 , wherein the test log neural network comprises a rectified linear unit activation function.

12 . The non-transitory machine-readable medium of claim 9 , wherein the service ticket data comprises a service ticket sparse matrix.

13 . The non-transitory machine-readable medium of claim 9 , wherein the service ticket neural network comprises a rectified linear unit activation function.

14 . The non-transitory machine-readable medium of claim 9 , wherein the determining of the probability of the relation between the test log and the service ticket comprises:

concatenating the test log output vector and the service ticket output vector, resulting in a concatenated relation vector, and

inputting the concatenated relation vector to a relation neural network.

15 . A method, comprising:

based on test log data representative of test logs and using machine learning attention, generating, by a system comprising at least one processor, a test log output vector; and

based on the test log output vector and a service ticket output vector, determining, by the system, a probability that a test log represented in the test log output vector is related to a service ticket represented in the service ticket output vector, wherein the determining of the probability that the test log is related to the service ticket comprises:

concatenating the test log output vector and the service ticket output vector, resulting in a concatenated relation vector, and

subjecting the concatenated relation vector to a relation neural network.

16 . The method of claim 15 , further comprising:

generating, by the system, an output representative of the probability.

17 . The method of claim 16 , wherein the relation neural network comprises a softmax activation function.

18 . The method of claim 15 , wherein the test log data comprises a test log sparse matrix.

19 . The method of claim 15 , wherein the generating of the test log output vector comprises generating the test log output vector using a test log neural network applied to the test log data.

20 . The method of claim 15 , wherein the service ticket output vector is generated using a service ticket neural network applied to service ticket data representative of service tickets.