Software product development defect and issue prediction and diagnosis

• US 10,311,404 B1
• Filed: 01/05/2018
• Issued: 06/04/2019
• Est. Priority Date: 01/05/2018
• Status: Active Grant

• Current Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Original Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Inventors: Lecue, Freddy, Bouhini, Chahrazed, Golla, Benedikt M.
• Primary Examiner(s): Vo, Ted T.
• Application Number:
  US15/863,743
• Time in Patent Office: 515 Days
• Field of Search: 717101-102, 717124-131
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/063112 Skill-based matching of a person or a group to a task
• CPC Class Codes: G06Q 10/063114 Status monitoring or status determination for a person or group
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services

Abstract

According to an example, with respect to software product development defect and issue prediction and diagnosis, worker profile information and worker state information for a plurality of workers involved in development of a product may be ascertained. A general worker signature that includes a plurality of clusters for all of the plurality of workers may be generated. For each of the plurality of workers, an individual worker signature vector that represents at least one cluster of the plurality of clusters that an individual worker is aligned to may be generated. A product signature vector may be generated based on product state information. Further, an output that includes an explanation for a defect associated with the development of the product may be generated based on a neural network model based analysis of the individual worker signature vectors and the product signature vector over a temporal dimension.

Claims

1. A software product development defect and issue prediction and diagnosis system comprising:

a worker profile analyzer, executed by at least one hardware processor, to ascertain worker profile information that includes roles of a plurality of workers involved in development of a product;

a plurality of hardware sensors to sense worker state information of physiology of the plurality of workers;

a worker state analyzer, executed by the at least one hardware processor, to ascertain, from the plurality of hardware sensors, the worker state information of physiology of the plurality of workers with respect to the development of the product;

a worker signature vector generator, executed by the at least one hardware processor, to generate, based on the worker profile information and the worker state information, a general worker signature that includes a plurality of clusters for all of the plurality of workers, and for each of the plurality of workers, generate, based on worker profile information for an individual worker, worker state information for the individual worker, and the general worker signature, an individual worker signature vector that represents at least one cluster of the plurality of clusters that the individual worker is aligned to;

a product state analyzer, executed by the at least one hardware processor, to ascertain product state information on a status of temporal development for the product;

a product signature vector generator, executed by the at least one hardware processor, to generate, based on the product state information, a product signature vector that represents changes in the product; and

a product development defect analyzer, executed by the at least one hardware processor, to

generate, based on analysis of the individual worker signature vectors and the product signature vector over a temporal dimension, an output that includes an explanation for a defect associated with the development of the product.

2. The system according to claim 1, wherein the product includes a software application.

3. The system according to claim 2, wherein the worker profile information includes

static information that includes the roles of the plurality of workers in association with the development of the software application, skill levels of the plurality of workers with respect to languages usable for the development of the software application, and strength levels of the plurality of workers in association with the development of the software application, and

dynamic information that includes prior software applications utilized by the plurality of workers.

4. The system according to claim 1, wherein the plurality of sensors include at least two of

an anxiety sensor to measure an anxiety level of each of the plurality of workers during the development of the product,

a tracking sensor to measure a focus level of each of the plurality of workers during the development of the product, or

a presence sensor to measure a working level of each of the plurality of workers during the development of the product.

5. The system according to claim 1, wherein the product state analyzer is to ascertain product state information on the status of temporal development for the product by:

analyzing success and failure activities associated with the temporal development for the product by the plurality of workers.

6. The system according to claim 1, wherein the worker signature vector generator is to generate, based on the worker profile information and the worker state information, the general worker signature that includes the plurality of clusters for all of the plurality of workers by:

analyzing, based on the worker profile information and the worker state information, characteristics of each of the plurality of workers;

determining similarities between the analyzed characteristics; and

clustering workers of the plurality of workers based on the determined similarities between the analyzed characteristics to generate the plurality of clusters.

7. The system according to claim 1, wherein, for each of the plurality of workers, the worker signature vector generator is to generate, based on the worker profile information for the individual worker, the worker state information for the individual worker, and the general worker signature, the individual worker signature vector that represents the at least one cluster of the plurality of clusters that the individual worker is aligned to by:

filtering the worker profile information for the individual worker and the worker state information for the individual worker, using the general worker signature, to identify the at least one cluster of the plurality of clusters that the individual worker is aligned to.

8. The system according to claim 2, wherein the product signature vector generator is to generate, based on the product state information, the product signature vector that represents changes in the software application by:

analyzing, based on a number of character changes in code of the software application and a measure of uniqueness of a change in the code of the software application, the changes in the code of the software application; and

utilizing a neural network model to generate the product signature vector that represents the changes in the software application.

9. The system according to claim 1, wherein the product development defect analyzer is to generate, based on the analysis of the individual worker signature vectors and the product signature vector over the temporal dimension, the output that includes the explanation for the defect associated with the development of the product by:

generating, based on a neural network model based analysis of the individual worker signature vectors and the product signature vector over the temporal dimension, the output that includes the explanation for the defect associated with the development of the product.

10. The system according to claim 9, wherein the product development defect analyzer is to generate, based on the neural network model based analysis of the individual worker signature vectors and the product signature vector over the temporal dimension, the output that includes the explanation for the defect associated with the development of the product by:

performing, for the neural network model based analysis, a separate and a combination analysis of factors derived from the general worker signature to generate the output that includes the explanation for the defect associated with the development of the product.

11. The system according to claim 9, wherein the product development defect analyzer is to generate, based on the neural network model based analysis of the individual worker signature vectors and the product signature vector over the temporal dimension, the output that includes the explanation for the defect associated with the development of the product by:

determining, for the neural network model based analysis, a product state as a function of the product signature vector, the general worker signature, and a worker state, to generate the output that includes the explanation for the defect associated with the development of the product.

12. A computer implemented method for software product development defect and issue prediction and diagnosis, the method comprising:

ascertaining worker profile information that includes roles of a plurality of workers involved in development of a product;

implementing at least one sensor to monitor physiology of the plurality of workers;

ascertaining, from the at least one sensor, worker state information of the physiology of the plurality of workers with respect to the development of the product;

generating, based on the worker profile information and the worker state information, a general worker signature that includes a plurality of clusters for all of the plurality of workers;

for each of the plurality of workers, generating, based on worker profile information for an individual worker, worker state information for the individual worker, and the general worker signature, an individual worker signature vector that represents at least one cluster of the plurality of clusters that the individual worker is aligned to;

ascertaining product state information on a status of temporal development for the product;

generating, based on the product state information, a product signature vector that represents changes in the product; and

generating, based on a neural network model based analysis of the individual worker signature vectors and the product signature vector over a temporal dimension, an output that includes an explanation for a defect associated with the development of the product.

13. The method according to claim 12, wherein the product includes a software application.

14. The method according to claim 12, wherein the at least one sensor includes

an anxiety sensor to measure an anxiety level of each of the plurality of workers during the development of the product,

a tracking sensor to measure a focus level of each of the plurality of workers during the development of the product, or

a presence sensor to measure a working level of each of the plurality of workers during the development of the product.

15. The method according to claim 12, wherein ascertaining product state information on the status of temporal development for the product further comprises:

analyzing success and failure activities associated with the temporal development for the product by the plurality of workers.

16. A non-transitory computer readable medium having stored thereon machine readable instructions for software product development defect and issue prediction and diagnosis, the machine readable instructions, when executed, cause at least one hardware processor to:

ascertain worker profile information that includes roles of a plurality of workers involved in development of a product;

invoke at least one sensor to monitor physiology of the plurality of workers;

ascertain, from the at least one sensor that monitors physiology of the plurality of workers, worker state information of the physiology of the plurality of workers with respect to the development of the product;

generate, based on the worker profile information and the worker state information, a general worker signature that includes a plurality of clusters for all of the plurality of workers;

for each of the plurality of workers, generate, based on worker profile information for an individual worker, worker state information for the individual worker, and the general worker signature, an individual worker signature vector that represents at least one cluster of the plurality of clusters that the individual worker is aligned to;

ascertain product state information on a status of temporal development for the product;

generate, based on the product state information, a product signature vector that represents changes in the product; and

generate, based on a neural network model based analysis of the individual worker signature vectors and the product signature vector over a temporal dimension, an output that includes an explanation for a defect associated with the development of the product.

17. The non-transitory computer readable medium according to claim 16, wherein the machine readable instructions to generate, based on the worker profile information and the worker state information, the general worker signature that includes the plurality of clusters for all of the plurality of workers, when executed by the at least one hardware processor, further cause the at least one hardware processor to:

analyze, based on the worker profile information and the worker state information, characteristics of each of the plurality of workers;

determine similarities between the analyzed characteristics; and

cluster workers of the plurality of workers based on the determined similarities between the analyzed characteristics to generate the plurality of clusters.

18. The non-transitory computer readable medium according to claim 16, wherein, for each of the plurality of workers, the machine readable instructions to generate, based on the worker profile information for the individual worker, the worker state information for the individual worker, and the general worker signature, the individual worker signature vector that represents the at least one cluster of the plurality of clusters that the individual worker is aligned to, when executed by the at least one hardware processor, further cause the at least one hardware processor to:

filter the worker profile information for the individual worker and the worker state information for the individual worker, using the general worker signature, to identify the at least one cluster of the plurality of clusters that the individual worker is aligned to.

19. The non-transitory computer readable medium according to claim 17, wherein the machine readable instructions to generate, based on the product state information, the product signature vector that represents changes in the software application, when executed by the at least one hardware processor, further cause the at least one hardware processor to:

analyze, based on a number of character changes in code of the software application and a measure of uniqueness of a change in the code of the software application, the changes in the code of the software application; and

utilize a neural network model to generate the product signature vector that represents the changes in the software application.

20. The non-transitory computer readable medium according to claim 16, wherein the machine readable instructions to generate, based on the neural network model based analysis of the individual worker signature vectors and the product signature vector, the output that includes the explanation for the defect associated with the development of the product, when executed by the at least one hardware processor, further cause the at least one hardware processor to:

determine, for the neural network model based analysis, a product state as a function of the product signature vector, the general worker signature, and a worker state, to generate the output that includes the explanation for the defect associated with the development of the product.