- Number
- 20240273260
- Published
- 2024-08-15
- Filed
- 2023-02-15
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Khalfan; Alif et al.
- CPC
- G06F30/27; G06Q30/0278; G06F30/10
- Verdict
- Set aside product design/business analytics
- Source
- Google Patents · FreePatentsOnline
Abstract
Systems and methods configured to train a product model to determine a configuration of a prospective product are disclosed. Exemplary implementations may: obtain a product model; obtain training information from electronic storage; train the product model using the training information for individual developed products by using object information, subject information, and subject content information for the individual developed products as training inputs and product performance information as training outputs for the individual developed products such that the product model is trained to predict product performance information based on object information, subject information, and subject content information; store the trained product model to the electronic storage; receive target information for a prospective product; transmit the target information to the trained product model; receive object information and/or subject information for the prospective product; generate and transmit instructions for a fabrication system to generate the prospective product according to the received information.
Background
FIELD OF THE DISCLOSURE
The present disclosure relates to systems and methods configured to train and utilize a product model to determine a configuration of a prospective product. BACKGROUND
Typically, developing a prospective product requires at least a team of artists to submit concepts, a research team to determine subjects to integrate into the prospective product, and a development team to determine how to configure or build the prospective product. This manual process may be time consuming and limited to the information known by the individuals in the teams as opposed to a comprehensive database of information. SUMMARY
One aspect of the present disclosure relates to reducing the manual research and input from users to more intelligently and swiftly determine specific products to develop based on known information about previously developed products. First, a product model is trained based on information about objects that are the previously developed products, subjects featured on the previously developed products, content related to these subjects, and performance of the previously developed products. Thus, a trained product model is trained to recognize the correlations between the performance and the information behind the previously developed products. Secondly, the trained product model is utilized to recommend a prospective product. Target information is input to the trained product model and the trained product model output details that char
Claims
1. A system configured to train a product model to determine a configuration of a prospective product, the system comprising: electronic storage that stores at least a product model and training information, wherein the training information includes, for individual developed products: (i) object information characterizing a developed product, (ii) product performance information representing performance of the developed product after release, (iii) subject information indicating individual subjects of the developed product, and (iv) subject content information related to content associated with the subject; and one or more processors configured by machine-readable instructions to: obtain the product model; obtain the training information; train the product model using the training information for the individual developed products by using the object information, the subject information, and the subject content information for the individual developed products as training inputs and the product performance information as training outputs for the individual developed products such that the product model is trained to predict product performance information for prospective products based on object information, subject information, and subject content information for the prospective products; and store the trained product model to the electronic storage. ||
7. A system configured to instruct a fabrication system to generate a product based on a product request, the system comprising: electronic storage that stores a trained product model trained to predict product performance information based on object information, subject information, and subject content information and recommend at least the object information and the subject information for a prospective product to achieve maximum performance; and one or more processors configured by machine-readable instructions to: receive target information for a prospective product, wherein the target information generally characterizes the prospective product as an object and a subject of the object; transmit the target information to the trained product model so that the trained product model identifies at least object information for the prospective product and/or subject information for the prospective product based on the target information; receive the object information and/or the subject information; and generate instructions for a fabrication system to generate the prospective product in accordance with the object information and/or the subject information. ||
11. A method to train a product model to determine a configuration of a prospective product, the method comprising: obtaining a product model, wherein the product model is obtained from electronic storage that stores at least the product model and training information, wherein the training information includes, for individual developed products: (i) object information characterizing a developed product, (ii) product performance information representing performance of the developed product after release, (iii) subject information indicating individual subjects of the developed product, and (iv) subject content information related to content associated with the subject; obtaining the training information from the electronic storage; training the product model using the training information for the individual developed products by using the object information, the subject information, and the subject content information for the individual developed products as training inputs and the product performance information as training outputs for the individual developed products such that the product model is trained to predict product performance information for prospective products based on object information, subject information, and subject content information for the prospective products; and storing the trained product model to the electronic storage. ||
17. A method to instruct a fabrication system to generate a product based on a product request, the method comprising: receiving target information for a prospective product, wherein the target information characterizes the prospective product as an object and a subject of the object; transmitting the target information to the trained product model, wherein electronic storage stores the trained product model trained to predict product performance information based on object information, subject information, and subject content information and recommend at least the object information and the subject information for a prospective product to achieve maximum performance, so that the trained product model identifies at least object information for the prospective product and/or subject information for the prospective product based on the target information; receiving the object information and/or the subject information; and generating instructions for a fabrication system to generate the prospective product in accordance with the object information and/or the subject information.