# US 2017/0287348 A1 · Analytics platform

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0287348 A1
- Document ID: US20170287348A1
- Status: Published application
- Kind: A1
- Application number: 15/365,395
- Filed: 2016-11-30
- Published: 2017-10-05
- Earliest claimed: 2008-06-18
- Assignees: Accenture Global Solutions Limited
- Applicants: Accenture Global Solutions Limited
- Inventors: Patrick MOSHER; Keith Thomas McInerney; Richard J. Bakosh; Tanushree Guha; Samuel R. Tepper
- Web page: https://patentgrep.com/patent/US20170287348A1

## CPC

- G09B 7/10: wherein a set of answers is common to a plurality of questions
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06Q 10/06393: {Score-carding, benchmarking or key performance indicator [KPI] analysis}
- G06Q 10/10: Office automation; Time management
- G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

An analytics platform may generate one or more user interfaces based on the set of testing parameters. The analytics platform may provide the one or more user interfaces. The analytics platform may receive first test information corresponding to first respondents. The analytics platform may identify, based on the first test information and based on information identifying particular respondents of the first respondents, characteristic attributes of the particular respondents. The analytics platform may train, based on the values of the characteristic attributes and performance information associated with the first respondents, a predictive model. The analytics platform may obtain the second test information corresponding to the one or more second respondents. The analytics platform may determine the predicted performance information associated with the one or more second respondents using the predictive model. The analytics platform may perform an action based on the predicted performance information.

## Claims

### Claim 1

An analytics platform, comprising:
one or more processors to:
receive a plurality of testing parameters;
generate one or more user interfaces based on the plurality of testing parameters,
the user interfaces including elements based on which to determine values associated with attributes of respondents;
provide, for display by a plurality of user devices, the one or more user interfaces;
receive, from the plurality of user devices and based on interactions with the one or more user interfaces, first test information corresponding to first respondents,
the first test information identifying first values of the attributes associated with the first respondents;
identify, based on the first test information and based on information identifying particular respondents of the first respondents, characteristic attributes of the particular respondents,
the analytics platform identifying the characteristic attributes based on the characteristic attributes being associated with the particular respondents;
train, based on the values of the characteristic attributes and performance information associated with the first respondents, a predictive model,
the predictive model to receive, as input, second test information associated with one or more second respondents, and
the predictive model to output predicted performance information associated with the one or more second respondents;
obtain the second test information corresponding to the one or more second respondents;
determine the predicted performance information associated with the one or more second respondents using the predictive model; and
perform an action based on the predicted performance information.

### Claim 2 (depends on 1)

The analytics platform of claim 1, where the one or more user interfaces include one or more first user interfaces; and
where the one or more processors, when obtaining the second test information, are to:
provide a second user interface that includes information relevant to determining the values of the characteristic attributes with regard to the one or more second respondents.

### Claim 3 (depends on 1)

The analytics platform of claim 1, where the one or more processors, when identifying the characteristic attributes, are to:
identify the characteristic attributes based on performing at least one of:
a discriminant analysis test,
a logarithmic regression analysis, or
a T test,
the characteristic attributes being identified based on respective values of the characteristic attributes being correlated with the particular respondents.

### Claim 4 (depends on 1)

The analytics platform of claim 1, where the one or more processors are further to:
receive observed performance information,
the observed performance information relating to the one or more second respondents; and
update the predictive model based on a machine learning algorithm, the observed performance information, and the predicted performance information.

### Claim 5 (depends on 1)

The analytics platform of claim 1, where the one or more processors are further to:
identify respective values of the characteristic attributes, corresponding to the one or more second respondents, based on the second test information; and
where the one or more processors, when determining the predicted performance information, are to:
input the respective values to the predictive model,
the predictive model to output the predicted performance information based on the respective values.

### Claim 6 (depends on 5)

The analytics platform of claim 5, where the respective values of the characteristic attributes are second values of the characteristic attributes; and
where the one or more processors, when performing the action, are to:
generate a report identifying differences between first values of the characteristic attributes and the second values,
the first values being associated with the particular respondents.

### Claim 7 (depends on 1)

The analytics platform of claim 1, where the one or more processors, when determining the predicted performance information, are to:
determine information identifying a prediction of whether the one or more second respondents will be categorized as particular respondents.

### Claim 8

A method, comprising:
receiving, by a device, a plurality of testing parameters;
generating, by the device, one or more user interfaces based on the plurality of testing parameters,
the user interfaces including elements based on which to determine values associated with attributes of respondents;
providing, by the device and for display by a plurality of user devices, the one or more user interfaces;
receiving, from the plurality of user devices and based on interactions with the one or more user interfaces, first test information corresponding to first respondents,
the first test information identifying first values of the attributes associated with the first respondents;
identifying, by the device, based on the first test information and based on information identifying particular respondents of the first respondents, characteristic attributes of the first respondents,
the characteristic attributes being identified based on respective values of the characteristic attributes being associated with the particular respondents;
training, based on the values of the characteristic attributes and performance information associated with the first respondents, a predictive model,
the predictive model to receive, as input, second test information associated with one or more second respondents, and
the predictive model to output predicted performance information associated with the one or more second respondents;
obtaining, by the device, the second test information corresponding to the one or more second respondents;
determining, by the device, the predicted performance information associated with the one or more second respondents using the predictive model; and
performing, by the device, an action based on the predicted performance information.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
determining the information identifying the particular respondents based on particular performance information, of the performance information, associated with the particular respondents,
the information identifying the particular respondents being determined based on the particular performance information satisfying a threshold.

### Claim 10 (depends on 8)

The method of claim 8, where training the predictive model comprises:
training the predictive model based on one or more of:
a machine learning algorithm, or
a neural network.

### Claim 11 (depends on 8)

The method of claim 8, further comprising:
determining, based on the first test information, first values of the characteristic attributes associated with the particular respondents;
determining, based on the second test information, second values of the characteristic attributes associated with the one or more second respondents; and
where performing the action based on the predicted performance information comprises:
providing information identifying a difference between the first values and the second values.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
providing information identifying a recommendation for training to improve the second values.

### Claim 13 (depends on 11)

The method of claim 11, where determining the first values comprises:
determining the first values based on natural language processing; and
where determining the second values comprises:
determining the second values based on natural language processing.

### Claim 14 (depends on 8)

The method of claim 8, where the characteristic attributes relate to one or more of:
personality attributes of the particular respondents,
behavior attributes of the particular respondents, or
competency attributes of the particular respondents.

### Claim 15

A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
receive a plurality of testing parameters;
generate one or more user interfaces based on the plurality of testing parameters,
the user interfaces to receive information identifying values associated with attributes of a plurality of respondents;
provide, for display by a plurality of user devices, the one or more user interfaces;
receive, from the plurality of user devices and based on interactions with the one or more user interfaces, first test information corresponding to first respondents of the plurality of respondents,
the first test information identifying first values of the attributes associated with the first respondents;
identify, based on the first test information and based on information identifying particular respondents of the first respondents, characteristic attributes of the particular respondents,
the characteristic attributes being identified based on values of the characteristic attributes that are correlated with the particular respondents;
train, based on the values of the characteristic attributes and performance information associated with the first respondents, a predictive model,
the predictive model to receive, as input, second test information associated with one or more second respondents of the plurality of respondents, and
the predictive model to output predicted performance information associated with the one or more second respondents;
obtain the second test information corresponding to the one or more second respondents;
determine the predicted performance information associated with the one or more second respondents using the predictive model; and
perform an action based on the predicted performance information.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
receive observed performance information associated with the second respondents; and
update the predictive model based on the observed performance information and the predicted performance information,
the predictive model being updated based on one or more of:
a machine learning algorithm, or
a neural network process.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, where the one or more instructions, that cause the one or more processors to perform the action, further cause the one or more processors to:
generate a report based on second values of the characteristic attributes associated with a particular second respondent of the one or more second respondents,
the report to compare the second values and first values of the characteristic attributes associated with the particular respondents.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, where the testing parameters identify questions to be provided to the plurality of respondents; and
where the one or more instructions, that cause the one or more processors to generate the one or more user interfaces, cause the one or more processors to:
generate a questionnaire, including the questions, to be provided to the plurality of respondents.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, where the one or more user interfaces are one or more first user interfaces; and
where the one or more instructions, that cause the one or more processors to obtain the second test information, cause the one or more processors to:
generate a second user interface,
the second user interface to receive responses to questions regarding the characteristic attributes,
respective values of the characteristic attributes associated with the one or more second respondents to be determined based on the responses.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, where the one or more instructions, that cause the one or more processors to obtain the second test information, cause the one or more processors to:
obtain particular test information, of the second test information, associated with a particular second respondent of the one or more second respondents,
the particular test information being provided by an entity associated with the particular second respondent; and
where the one or more instructions, when executed by the one or more processors, cause the one or more processors to:
assign a weight to the particular test information based on information identifying a relationship between the particular second respondent and the entity associated with the particular second respondent,
the predicted performance information being determined based on the weight and the particular test information.
