Proactive resource allocation plan generator for improving product releases

Patent metadata

Field	Value
Publication number	US-10304014-B2
Application number	US-201715644315-A
Country	US
Kind code	B2
Filing date	Jul 7, 2017
Priority date	Jul 7, 2017
Publication date	May 28, 2019
Grant date	May 28, 2019

Abstract

Systems, methods, and computer program products to perform an operation comprising identifying a plurality of data sources, receiving input specifying one or more of the plurality of data sources and a set of parameters, wherein the set of parameters comprise at least a product and a due date for the product, generating, based on a machine learning (ML) model and data received from each of the specified one or more data sources, a resource allocation plan for a product specified in the input, wherein the resource allocation plan specifies at to allocate at least one resource to the product, wherein the at least one resource comprises one or more of hardware resources and software resources, and responsive to receiving input accepting the generated resource allocation plan, allocating the at least one resource in the resource allocation plan to develop the product.

First claim

What is claimed is:

1. A method, comprising:
identifying, by a resource management component executing by operation of one or more computer processors, a plurality of data sources;
receiving, by the resource management component, from a user, at a first point in time, input specifying one or more of the plurality of data sources and a set of parameters;
retrieving, by the resource management component, a code repository for an ongoing project, based on the input specifying one or more of the plurality of data sources;
retrieving, by the resource management component, a calendar of future availability of one or more hardware resources, based on the input specifying one or more of the plurality of data sources;
retrieving, by the resource management component, employee information, wherein the employee information includes an efficiency of each employee and a set of skills possessed by each employee, based on the input specifying one or more of the plurality of data sources;
determining, by the resource management component, based on the input specifying the set of parameters, an ongoing project, a current due date for the ongoing project, a required level of quality for the ongoing project, a budget for the ongoing project, an indication that additional employees can be added to the project, and an indication that the current due date can be extended;
identifying, by the resource management component, a current resource allocation for the ongoing project, wherein the current resource allocation specifies hardware and software resources currently assigned to the ongoing project, and employees currently working on the ongoing project;
generating, by the resource management component, one or more features to be used as input to a machine learning (ML) model, based on the specified data sources and set of parameters;
providing, by the resource management component, the generated features as input for a machine learning (ML) model to generate a modified resource allocation plan for the ongoing project, wherein the modified resource allocation plan specifies allocation of at least one allocate additional resources to the ongoing project, wherein the additional resources comprise (i) one or more of-additional hardware resources specified in the calendar of future availability of the one or more hardware resources, (ii) one or more additional software resources, and (iii) one or more additional employees for the ongoing project;
determining, by the resource management component, a set of repercussions for the modified resource allocation, based at least in part on processing the modified resource allocation plan for the ongoing project using the ML model, wherein the set of repercussions comprise an indication that (i) the current due date will not be met, (ii) a cost of the ongoing project will remain below the budget, and (iii) a quality of the ongoing project will meet the required level of quality;
providing, by the resource management component, the modified resource allocation and the determined set of repercussions to the user;
responsive to receiving input accepting the modified resource allocation plan:
allocating, by the resource management component, the one or more hardware resources and the one or more additional software resources to the ongoing project;
modifying, by the resource management component, the current due date of the ongoing project; and
notifying, by the resource management component, the one or more additional employees that they have been added to the ongoing project;

determining, by the resource management component, at a second point in time subsequent to the first point in time, a final completion status of the project, wherein the final completion status indicates (i) a date when the ongoing project was completed, and (ii) an amount that the ongoing project cost to be completed;
generating, by the resource management component, a set of refinement features based on the completion status; and
refining, by the resource management component, the ML model based on the generated refinement features, wherein refining the ML model comprises adjusting one or more weights included in the ML model.

2. The method of claim 1 , wherein the at least one resource further comprises a human resource, wherein the set of parameters further comprise: (i) a modified due date for the project, (ii) a set of available hardware resources, (iii) a set of available software resources, (iv) a desired skill level of human resources added to develop the project, (iv) a source code repository, and (v) a desired number of recommended resource allocations for the resource allocation plan, wherein the generated resource allocation plan specifies the desired number of recommended resource allocations.

3. The method of claim 2 , wherein the resource allocation plan further comprises at least one repercussion for at least one of the recommended resource allocation plans, wherein the hardware resources comprise: (i) one or more processors, (ii) a memory, (iii) a network bandwidth, and (iv) a storage, wherein the software resources comprise: (i) virtualized systems, and (ii) software test applications.

4. The method of claim 1 , further comprising prior to generating the resource allocation plan:
receiving data from the specified data sources, wherein the received data comprises: (i) audio data of recorded speech, and (ii) a plurality of electronic documents, wherein the plurality of documents are formatted according to a plurality of different formats;
converting, by a transcription service, the audio data of the recorded speech to text; and
converting, by a document conversion service, each of the plurality of documents to a standard format.

5. The method of claim 4 , further comprising:
aggregating: (i) the received data from the specified data sources, (ii) the audio data converted to text, and (iii) the converted plurality of documents to create an aggregated data set; and
processing the aggregated data set based at least in part on a tradeoff service to identify: (i) the at least one resource to allocate to the project, and (ii) a plurality of recommendations for the resource allocation plan.

6. The method of claim 5 , further comprising:
identifying, for each of the plurality of recommendations based on the ML model, a corresponding repercussion of implementing the plurality of recommendations.

7. The method of claim 6 , further comprising:
ranking each of the plurality of recommendations and corresponding repercussion; and
generating the resource allocation plan based on the ranked plurality of recommendations and corresponding repercussions; and
storing the generated resource allocation plan.

8. A system, comprising:
one or more processors; and
a memory containing a program which when executed by the processors performs an operation comprising:
identifying, by a resource management component executing by operation of one or more computer processors, a plurality of data sources;
receiving, by the resource management component, from a user, at a first point in time, input specifying one or more of the plurality of data sources and a set of parameters;
retrieving, by the resource management component, a code repository for an ongoing project, based on the input specifying one or more of the plurality of data sources;
retrieving, by the resource management component, a calendar of future availability of one or more hardware resources, based on the input specifying one or more of the plurality of data sources;
retrieving, by the resource management component, employee information, wherein the employee information includes an efficiency of each employee and a set of skills possessed by each employee, based on the input specifying o

Assignees

• IBM

Inventors

• Garza Alberto
• Kowalski Emile L
• Lopez Rodolfo
• Maldonado Julio A

Classifications

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G06F9/50

  Allocation of resources, e.g. of the central processing unit [CPU] · CPC title

• G06F40/103

  Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191) · CPC title

• G06Q10/06 Primary

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title

• G06Q10/06313

  Resource planning in a project environment · CPC title