US-20260127219-A1 - TECHNIQUES FOR GENERATING NARRATIVE CONTENT BASED ON MULTIMODAL INPUT WITH CONTENT FILTERS

US20260127219A1US 20260127219 A1US20260127219 A1US 20260127219A1US-20260127219-A1

Abstract

Techniques for generating filtered narrative content by a portable content-generating device are provided. A computer-implemented method can include receiving multimodal data. In some instances, the multimodal data is received based on one or more interactions with a portable content-generating device. The method can also include accessing a content-filter data associated with the portable content-generating device. The content-filter data can identify protocols for excluding content associated with one or more narrative-content categories. The method can also include applying a machine-learning model to the multimodal data and the content-filter data to generate filtered model-generated narrative content. In some instances, generating the filtered model-generated narrative content includes using the machine-learning model to remove or modify one or more portions of model-generated narrative content based on the content-filter data. The method can also include presenting the filtered model-generated narrative content on the portable content-generating device.

Inventors

Robert Locascio

Assignees

Kid Company

Dates

Publication Date: 20260507
Application Date: 20251105

Claims (20)

1 . A computer-implemented method comprising: receiving multimodal data, wherein the multimodal data includes visual data and audio data, and wherein the multimodal data is received based on one or more interactions with a portable content-generating device; accessing a content-filter data associated with the portable content-generating device, wherein the content-filter data identifies protocols for excluding content associated with one or more narrative-content categories; applying a machine-learning model to the multimodal data and the content-filter data to generate filtered model-generated narrative content that describes a sequence of events associated with one or more objects depicted in the multimodal data, wherein generating the filtered model-generated narrative content includes using the machine-learning model to remove or modify one or more portions of model-generated narrative content based on the content-filter data; and presenting the filtered model-generated narrative content on the portable content-generating device.
2 . The computer-implemented method of claim 1 , further comprising: receiving a request to transmit the filtered model-generated narrative content to a recipient device; accessing access-permission policy associated with the portable content-generating device; and denying transmission of the filtered model-generated narrative content to the recipient device.
3 . The computer-implemented method of claim 1 , further comprising: receiving a request to transmit the filtered model-generated narrative content to a recipient device; and establishing a communication session with recipient device before authorizing transmission of the filtered model-generated narrative content.
4 . The computer-implemented method of claim 1 , wherein the filtered model-generated narrative content is generated additionally based on a device configuration associated with the portable content-generating device.
5 . The computer-implemented method of claim 1 , wherein applying the machine-learning model includes preprocessing the visual data to extract visual features associated with the multimodal data, and wherein the visual features include the one or more portions.
6 . The computer-implemented method of claim 1 , wherein the filtered model-generated narrative content includes a multimedia content that visually describe the sequence of events.
7 . The computer-implemented method of claim 1 , wherein the filtered model-generated narrative content includes a video game associated with the sequence of events.
8 . The computer-implemented method of claim 1 , wherein the machine-learning model is locally stored within the portable content-generating device, and wherein the machine-learning model is applied within the portable content-generating device.
9 . A system comprising: one or more processors; and memory storing thereon instructions that, as a result of being executed by the one or more processors, cause the system to perform operations comprising: receiving multimodal data, wherein the multimodal data includes visual data and audio data, and wherein the multimodal data is received based on one or more interactions with a portable content-generating device; accessing a content-filter data associated with the portable content-generating device, wherein the content-filter data identifies protocols for excluding content associated with one or more narrative-content categories; applying a machine-learning model to the multimodal data and the content-filter data to generate filtered model-generated narrative content that describes a sequence of events associated with one or more objects depicted in the multimodal data, wherein generating the filtered model-generated narrative content includes using the machine-learning model to remove or modify one or more portions of model-generated narrative content based on the content-filter data; and presenting the filtered model-generated narrative content on the portable content-generating device.
10 . The system of claim 9 , wherein the instructions further cause the system to perform operations comprising: receiving a request to transmit the filtered model-generated narrative content to a recipient device; accessing access-permission policy associated with the portable content-generating device; and denying transmission of the filtered model-generated narrative content to the recipient device.
11 . The system of claim 9 , wherein the instructions further cause the system to perform operations comprising: receiving a request to transmit the filtered model-generated narrative content to a recipient device; and establishing a communication session with recipient device before authorizing transmission of the filtered model-generated narrative content.
12 . The system of claim 9 , wherein the filtered model-generated narrative content is generated additionally based on a device configuration associated with the portable content-generating device.
13 . The system of claim 9 , wherein applying the machine-learning model includes preprocessing the visual data to extract visual features associated with the multimodal data, and wherein the visual features include the one or more portions.
14 . The system of claim 9 , wherein the filtered model-generated narrative content includes a multimedia content that visually describe the sequence of events.
15 . The system of claim 9 , wherein the filtered model-generated narrative content includes a video game associated with the sequence of events.
16 . The system of claim 9 , wherein the machine-learning model is locally stored within the portable content-generating device, and wherein the machine-learning model is applied within the portable content-generating device.
17 . A non-transitory, computer-readable storage medium storing thereon executable instructions that, as a result of being executed by one or more processors of a computer system, cause the computer system to perform operations comprising: receiving multimodal data, wherein the multimodal data includes visual data and audio data, and wherein the multimodal data is received based on one or more interactions with a portable content-generating device; accessing a content-filter data associated with the portable content-generating device, wherein the content-filter data identifies protocols for excluding content associated with one or more narrative-content categories; applying a machine-learning model to the multimodal data and the content-filter data to generate filtered model-generated narrative content that describes a sequence of events associated with one or more objects depicted in the multimodal data, wherein generating the filtered model-generated narrative content includes using the machine-learning model to remove or modify one or more portions of model-generated narrative content based on the content-filter data; and presenting the filtered model-generated narrative content on the portable content-generating device.
18 . The non-transitory, computer-readable storage medium of claim 17 , wherein the instructions further cause the computer system to perform operations comprising: receiving a request to transmit the filtered model-generated narrative content to a recipient device; accessing access-permission policy associated with the portable content-generating device; and denying transmission of the filtered model-generated narrative content to the recipient device.
19 . The non-transitory, computer-readable storage medium of claim 17 , wherein the instructions further cause the computer system to perform operations comprising: receiving a request to transmit the filtered model-generated narrative content to a recipient device; and establishing a communication session with recipient device before authorizing transmission of the filtered model-generated narrative content.
20 . The non-transitory, computer-readable storage medium of claim 17 , wherein the filtered model-generated narrative content is generated additionally based on a device configuration associated with the portable content-generating device.

Description

CROSS-REFERENCES TO RELATED APPLICATIONS The present application claims priority from and is a non-provisional of U.S. Provisional Application No. 63/716,405, entitled “TECHNIQUES FOR GENERATING NARRATIVE CONTENT BASED ON MULTIMODAL INPUT WITH CONTENT FILTERS” filed Nov. 5, 2024, the contents of which are herein incorporated by reference in its entirety for all purposes. FIELD The present disclosure relates generally to generally to generating narrative content using machine-learning techniques. In one example, the systems and methods described herein may be used to generate filtered model-generated narrative content by applying a machine-learning model to multimodal data and content-filter data. SUMMARY Disclosed embodiments may provide techniques for generating filtered narrative content by a portable content-generating device. A computer-implemented method can include receiving multimodal data. In some instances, the multimodal data is received based on one or more interactions with a portable content-generating device. The method can also include accessing a content-filter data associated with the portable content-generating device. The content-filter data can identify protocols for excluding content associated with one or more narrative-content categories. The method can also include applying a machine-learning model to the multimodal data and the content-filter data to generate filtered model-generated narrative content. In some instances, the machine-learning model is locally stored within the portable content-generating device, and the machine-learning model is applied within the portable content-generating device. The filtered model-generated narrative content can describe a sequence of events associated with one or more objects depicted in the multimodal data. In some instances, generating the filtered model-generated narrative content includes using the machine-learning model to remove or modify one or more portions of model-generated narrative content based on the content-filter data. In some instances, the visual data can be preprocessed to extract visual features associated with the multimodal data, in which the visual features include the one or more portions being removed or modified. In some instances, the filtered model-generated narrative content is generated additionally based on a device configuration associated with the portable content-generating device. The method can also include presenting the filtered model-generated narrative content on the portable content-generating device. In some instances, the filtered model-generated narrative content includes a multimedia content that visually describe the sequence of events. Alternatively or additionally, the filtered model-generated narrative content can include a video game associated with the sequence of events. In some implementations, the method can also include controlling transmission of the filtered model-generated narrative content. For example, the method can include: (i) receiving a request to transmit the filtered model-generated narrative content to a recipient device; (ii) accessing access-permission policy associated with the portable content-generating device; and (iii) denying transmission of the filtered model-generated narrative content to the recipient device. In some instances, a communication session with recipient device can be established before authorizing transmission of the filtered model-generated narrative content. In an embodiment, a system comprises one or more processors and memory including instructions that, as a result of being executed by the one or more processors, cause the system to perform the processes described herein. In another embodiment, a non-transitory computer-readable storage medium stores thereon executable instructions that, as a result of being executed by one or more processors of a computer system, cause the computer system to perform the processes described herein. Various embodiments of the disclosure are discussed in detail below. While specific implementations are discussed, it should be understood that this is done for illustration purposes only. A person skilled in the relevant art will recognize that other components and configurations can be used without parting from the spirit and scope of the disclosure. Thus, the following description and drawings are illustrative and are not to be construed as limiting. Numerous specific details are described to provide a thorough understanding of the disclosure. However, in certain instances, well-known or conventional details are not described in order to avoid obscuring the description. References to one or an embodiment in the present disclosure can be references to the same embodiment or any embodiment; and, such references mean at least one of the embodiments. Reference to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at lea