DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment/Argument
Applicant's amendments filed on February 20, 2026 have been fully considered.
Claims 9-10, 12-14, and 20 are cancelled.
Claims 21-26 are new.
Applicant's arguments filed on February 20, 2026 have been fully considered but they are not persuasive.
Applicant argues Zavesky and Nonaka does not teach generation of prompt that identify keyframes corresponding to at least one of the panels and includes instruction regarding how the segmented element of the at least one panel change between different keyframes.
In response: Zavesky teaches: generate one or more prompts that identify kevframes corresponding to at least one of the panels (Zavesky: ¶48, . . . For instance, if multiple consecutive frames of the comic strip series depict a superhero trading punches with a villain, these frames could be inferred to be part of a narrative element involving a battle between the superhero and the villain. Similarly, if multiple consecutive frames of the comic strip series depict a superhero growing weak after being exposed to an object, these frames could be inferred to be part of a narrative element involving the superhero losing his super powers. If multiple consecutive frames of a comic strip series show a character daydreaming about different types of food, then these frames could be inferred to be part of a narrative element involving the character looking for a snack. If a set of consecutive frames shows men in masks running out of a bank, jumping into a car, and being chased by police in that order, then these frames could be inferred to be part of a narrative element involving a bank robbery. Thus, simply by observing the actions of the characters and individuals appearing in the two-dimensional media over a window of time, a narrative element can be inferred. . .”; ¶51, “. . . data models may be used to help to identify narrative elements that may be part of the same narrative arc, as well as an order in which the narrative elements may occur. For instance, a character in a comic strip stating, “I am hungry” may be related to a loose narrative about eating lunch, going hunting, cooking a meal, or the like. A villain stating that he will get revenge on a superhero may be related to a later narrative involving a battle between the villain and the superhero . . .”; NOTE: The generated prompts are the narrative of hierarchy as discussed above, based on the identified narrative elements from the multiple frames. The keyframes are the set of consecutive multiple frames from a comic strips that depict a scene and are identified by the narrative elements.),
and include instructions regarding how the segmented elements of the at least one panel change between different keyframes (Zavesky: ¶56, “. . . rendering the immersive experience may involve extrapolating between a set of narrative elements in order to bridge any “gaps” that may exist in the original two-dimensional media content. For instance, where the plurality of two-dimensional images comprise frames of a comic strip series, two narrative elements may have been identified in the plurality of two-dimensional images. However, due to the nature of comic strips, the original two-dimensional content may not explicitly show how to get from one narrative element (e.g., a super hero transforming from his alter ego) to another narrative element (e.g., the super hero fighting a villain). Thus, rendering the immersive experience may include rendering events to fill in any gaps between narrative elements of the overarching hierarchy of the narrative. Machine learning techniques such as convolution neural networks (CNNs) or generative adversarial networks (GANs) could be used to infer the most natural ways to fill the gaps. . .”; NOTE: The instructions included is the extrapolation between two keyframes, such as a super hero transformation, changing to a keyframe where the superhero is fighting a villain in order to generate events to in between that is not explicitly shown in the 2D content. )
Claim Objections
Claim 23 is objected to because of the following informalities:
The phrase “the at least on panel” should read “the at least one panel”.
Appropriate correction is required.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 6, 11, 15-16, 18, 19, 21, 25-26 are rejected under 35 U.S.C. 103 as being unpatentable over Zavesky et al. (US 20220165024 A1, hereinafter “Zavesky”) in view of Nonaka (US 20130282376 A1, hereinafter “Nonaka”).
Regarding apparatus claim 19,
Zavesky teaches:
A computing apparatus for generating moving pictures from digital graphic narrative files, the apparatus comprising: a processor; and a memory storing instructions (Zavesky: ¶65, “FIG. 3 depicts a high-level block diagram of a computing device or processing system specifically programmed to perform the functions described herein. As depicted in FIG. 3, the processing system 300 comprises one or more hardware processor elements 302 (e.g., a central processing unit (CPU), a microprocessor, or a multi-core processor), a memory 304 (e.g., random access memory (RAM) and/or read only memory (ROM)), a module 305 for transforming static two-dimensional images into immersive computer generated content)
that, when executed by the processor, configure the apparatus to:
partition one or more pages of a graphic narrative file into panels (“Zavesky: ¶27, "The DB 106 may store a plurality of images extracted from static, two-dimensional media content such as frames of comic strips (note: graphic narrative), pages of illustrated books, frames or pages of graphic novels (note: graphic narrative), paintings, drawings, or the like"; Zavesky: ¶36, "The method 200 begins in step 202 and proceeds to step 204. In step 204, the processing system may extract a plurality of physical features of a media asset from a plurality of two-dimensional images of the media asset. In one example, the media asset may comprise a character or an object, and the plurality of two-dimensional images may comprise images from different instances of a two-dimensional visual media. For instance, the two-dimensional visual media may comprise a comic strip series, where the plurality of two-dimensional images comprises frames from different comic strips within the comic strip series. In other examples, the two-dimensional visual media may comprise an illustrated book or series of books, a graphic novel or series of graphic novels, a two-dimensional animated work comprising a plurality of cells, or other types of two-dimensional visual media".");
NOTE 19A: Zavesky's system extracts information from, for example, frames of comic strips as referenced in Zavesky: ¶27, therefore, Zavesky's system identifies individual frames (panels) within a static, two-dimensional media content (pages of a graphic novel) to extract images. Therefore, Zavesky's system inherently teaches partitioning (identifying individual frames of comic strips) one or more pages of a graphic narrative (graphic novel, comic strips) into panels (frames). The graphic narrative file is the comic file, where the media content are extracted .
segment one or more of the panels into segmented elements including one or more image segments and one or more text segments (Zavesky: ¶24, "In further examples, the AS 104 may extract narrative elements from the plurality of static, two-dimensional images. For instance, a narrative element such as dialogue, recurring bits or jokes, exposition, or the like could be extracted from text on the page of an illustrated book, a thought or speech bubble associated with a character in a comic strip (note: text segments), or the like, where natural language processing techniques could be used to extract meaning from the text"; Zavesky: ¶38, "In one example, the physical features may be extracted using one or more image analysis techniques. For instance, facial features and expressions of a human (or human-like) character may be extracted using one or more facial recognition and analysis techniques that are capable of locating a facial region in an image and/or locating different elements of the facial regions (NOTE: image segments) (e.g., eyes, nose, mouth, hair, ears, etc.). Physical features of objects of other non-human assets could be extracted using one or more object recognition techniques. The recognition techniques may be provided with one or more sample images of the media asset to facilitate location of the media asset in the plurality of two-dimensional images");
(NOTE: Zavesky's system extracts text from a thought or speech bubble (segmenting the text region), therefore, Zavesky's system effectively locates and identifies the segment where to extract the texts. Zavesky's system also extracts physical features by locating a facial region (segmenting the facial region).
identify labels for the segmented elements (Zavesky: ¶24, "In further examples, the AS 104 may extract narrative elements from the plurality of static, two-dimensional images. For instance, a narrative element such as dialogue, recurring bits or jokes, exposition (note: labels of the segmented text elements), or the like could be extracted from text on the page of an illustrated book, a thought or speech bubble associated with a character in a comic strip, or the like, where natural language processing techniques could be used to extract meaning from the text; A narrative element could also be inferred from images (e.g., an image of a character shivering may imply that it is cold out, an image of a Christmas tree or a jack-o-lantern may imply that a narrative takes place during a holiday season, etc.), where different image analysis techniques may be used to recognize objects and other elements in the plurality of two-dimensional images. Zavesky: ¶38, "In one example, the physical features may be extracted using one or more image analysis techniques. For instance, facial features and expressions of a human (or human-like) character may be extracted using one or more facial recognition and analysis techniques that are capable of locating a facial region in an image and/or locating different elements of the facial regions (e.g., eyes, nose, mouth, hair, ears, etc. (note: labels of segmented image elements");
NOTE 19C: The words "dialogue", "recurring bits or jokes", or "exposition" are labels that classify the narrative elements (segmented elements) extracted from text. The words "eyes", "nose", "mouth", "hair" are labels that classify the segmented elements of a facial region. Zavesky's system also indicate roles (labels) of particular characters in the set of media such as "hero", "villain", "comic relief" as described in Zavesky ¶13; facial expressions such as "happy", "scared", "angry", sad"; characters such as "protagonist", "antagonist", "sidekick", "animal"; objects such as "vehicle", "building", "accessory", "weapon" as disclosed in Zavesky: ¶37. Also, Zavesky discloses machine learning methods including natural language processing techniques, facial recognition and analysis techniques, and object recognition techniques.
generate one or more prompts that identify kevframes corresponding to at least one of the panels (Zavesky: ¶48, . . . For instance, if multiple consecutive frames of the comic strip series depict a superhero trading punches with a villain, these frames could be inferred to be part of a narrative element involving a battle between the superhero and the villain. Similarly, if multiple consecutive frames of the comic strip series depict a superhero growing weak after being exposed to an object, these frames could be inferred to be part of a narrative element involving the superhero losing his super powers. If multiple consecutive frames of a comic strip series show a character daydreaming about different types of food, then these frames could be inferred to be part of a narrative element involving the character looking for a snack. If a set of consecutive frames shows men in masks running out of a bank, jumping into a car, and being chased by police in that order, then these frames could be inferred to be part of a narrative element involving a bank robbery. Thus, simply by observing the actions of the characters and individuals appearing in the two-dimensional media over a window of time, a narrative element can be inferred. . .”; ¶51, “. . . data models may be used to help to identify narrative elements that may be part of the same narrative arc, as well as an order in which the narrative elements may occur. For instance, a character in a comic strip stating, “I am hungry” may be related to a loose narrative about eating lunch, going hunting, cooking a meal, or the like. A villain stating that he will get revenge on a superhero may be related to a later narrative involving a battle between the villain and the superhero . . .”; NOTE: The generated prompts are the narrative of hierarchy as discussed above, based on the identified narrative elements from the multiple frames. The keyframes are the set of consecutive multiple frames from a comic strips that depict a scene and are identified by the narrative elements.),
and include instructions regarding how the segmented elements of the at least one panel change between different keyframes (Zavesky: ¶56, “. . . rendering the immersive experience may involve extrapolating between a set of narrative elements in order to bridge any “gaps” that may exist in the original two-dimensional media content. For instance, where the plurality of two-dimensional images comprise frames of a comic strip series, two narrative elements may have been identified in the plurality of two-dimensional images. However, due to the nature of comic strips, the original two-dimensional content may not explicitly show how to get from one narrative element (e.g., a super hero transforming from his alter ego) to another narrative element (e.g., the super hero fighting a villain). Thus, rendering the immersive experience may include rendering events to fill in any gaps between narrative elements of the overarching hierarchy of the narrative. Machine learning techniques such as convolution neural networks (CNNs) or generative adversarial networks (GANs) could be used to infer the most natural ways to fill the gaps. . .”; NOTE: The instructions included is the extrapolation between two keyframes, such as a super hero transformation, changing to a keyframe where the superhero is fighting a villain in order to generate events to in between that is not explicitly shown in the 2D content. )
wherein the prompts are generated based on one or more of the labels, the labels, the image segments, and the text segments, the prompts representing script information, storyboard information, or scene information corresponding to the at least one panel (Zavesky: ¶25, "In further examples, the AS 104 may build a hierarchy of a narrative (note: prompts), or a narrative arc, from the extracted narrative elements (note: the image segments, and the text segments). For instance, machine learning techniques may be used to identify relationships between narrative elements (e.g., a character stating, “I am hungry,” may be related to a later scene in which the character is depicted eating a slice of pizza) (note: script information, storyboard information, or scene information corresponding to the one or more panels). The AS 104 may also learn recurring narrative elements (e.g., such as recurring jokes, character interactions, and the like) (NOTE: script information, storyboard information, or scene information corresponding to the one or more panels, the text segment “I am hungry”.) and may use these recurring narrative elements to construct an entirely new narrative arc");
generate the moving picture that renders motion of the segmented elements between the different keyframes in accordance with the instructions provided by the prompts, wherein generating the moving picture includes inputting the prompts into a second ML model (Zavesky: ¶53, "In step 212, the processing system may create an immersive experience (NOTE: moving picture) based on the three-dimensional model constructed in step 206 and the hierarchy of the narrative (NOTE: prompts) built in step 210. For instance, the immersive experience may comprise a media that can be presented to a user via an immersive display (note: moving pictures, also see NOTE 1A) (e.g., a head mounted display, a stereoscopic display, or any other types of display that, along or in combination with other devices, are capable of presenting an immersive experience to a user). In one example, the immersive experience may allow the user to interact with the three-dimensional model, e.g., such that an interaction with the media asset is simulated. In another example, the interaction of the user with the three-dimensional model may occur within the hierarchy of the narrative that is built. For instance, the immersive experience may allow the user to assist a superhero with a mission to locate a villain, to drive a famous fictional vehicle, or to participate in some other sort of narrative involving a character or object"; Zavesky: ¶56, "In optional step 218 (illustrated in phantom), the processing system may render the immersive experience on one or more user endpoint devices of a user. For instance, the processing system may send data and signals to an immersive display that cause the immersive display to present the immersive experience to the user. In one example, rendering the immersive experience may involve extrapolating between a set of narrative elements in order to bridge any “gaps” that may exist in the original two-dimensional media content. For instance, where the plurality of two-dimensional images comprise frames of a comic strip series, two narrative elements may have been identified in the plurality of two-dimensional images. However, due to the nature of comic strips, the original two-dimensional content may not explicitly show how to get from one narrative element (e.g., a super hero transforming from his alter ego) to another narrative element (e.g., the super hero fighting a villain). Thus, rendering the immersive experience may include rendering events to fill in any gaps between narrative elements of the overarching hierarchy of the narrative. Machine learning techniques such as convolution neural networks (CNNs) or generative adversarial networks (GANs) could be used (NOTE: second ML model) to infer the most natural ways to fill the gaps"; NOTE: Zavesky discloses generating a moving picture, which is the immersive experience displayed to the user such as a driving experience. The system uses GAN as the second ML, that takes input prompts, which is the hierarchy of narratives.).
NOTE 19D: As disclosed in Zavesky ¶53, for a user to "assist a superhero with a mission" and/or "drive a famous fictional vehicle" in an immersive environment for an immersive experience, the "vehicle" and the "superhero" must be moving (moving picture) to allow interaction. Thus, Zavesky teaches a method of generating a moving picture (immersive computer generated content) from a graphic narrative (static two-dimensional images such as comics and graphic novels).
Although Zavesky teaches image analysis techniques and object recognition techniques for label identification, it is not clear if Zavesky uses a machine learning model to implement the label identification, and therefore, Zavesky does not teach the image analysis method to determine labels for the segmented elements by applying the segemented elements to a first machine learning (ML) model.
Nonaka teaches the image analysis method can be a machine learning method (Nonaka: ¶90, “. . . known image analysis technique or text analysis technique is used to analyze and acquire the page information by the page information analysis section 10. For example, the position, size, and type of a content element such as a face, an animal, a building, an automobile, and other objects may be automatically detected based on a feature amount regarding image information thereof. The content element may be automatically detected based on machine learning. For example, the accuracy of detecting an outer edge of a panel or a speech balloon, and a determination threshold value for the validity of a region other than a rectangular region as a panel or a speech balloon is empirically set based on a sample comic for learning”).
Therefore, it would have been obvious to a person with ordinary skill in the art to have modified Zavesky to include: the image analysis method to determine labels of the segmented elements is a machine learning method.
The reason of doing so is because machine learning is a better, more accurate method of doing things such as image analysis. Additionally, so that “the content element may be automatically detected” (Nonaka: ¶90).
Regarding CRM claim 21,
CRM claim 21 is drawn to the CRM corresponding to the configuration of using same as claimed in the apparatus of claim 19. Therefore, CRM claim 21 corresponds to the configuration of the apparatus of claim 19, and is rejected for the same reasons of obviousness as used above.
Regarding method claim 1,
Method claim 1, is drawn to the methods corresponding to the configuration of using same as claimed in the apparatus of claim 19. Therefore, method claim 1 corresponds to the configuration of the apparatus of claim 19, and are rejected for the same reasons of anticipation as used above.
Regarding claim 2, depending on 1,
The combination of Zavesky and Nonaka teaches:
The method of claim 1,
Zavesky further teaches:
further comprising: generating a user interface for a user device in which the moving picture is selectable during display of the digital graphic narrative file (Zavesky: ¶20, "In one particular example, at least one of the user endpoint devices 108, 110, 112, and 114 may comprise an immersive display. The immersive display may comprise a display with a wide; Zavesky: ¶56, "the processing system may render the immersive experience on one or more user endpoint devices of a user. For instance, the processing system may send data and signals to an immersive display that cause the immersive display to present the immersive experience to the user"; ¶26, “. . . the immersive experience may allow a user to interact with the three-dimensional models of the media assets within some simulated narrative arc as part of the experience. . .”; NOTE: The user interface generated is the immersive environment where the user interacts with the generated immersive experience. Since the users can interact with the media assets of the moving picture, therefore, the moving picture is selectable during display of the digital graphic narrative file.)
Regarding claim 6, depending on 1,
The combination of Zavesky and Nonaka teaches:
The method of claim 1,
Zavesky teaches:
The method of claim 1, wherein the text labels indicate one or more of the text segments that include onomatopoeia, narration, or dialogue (Zavesky: ¶24, "In further examples, the AS 104 may extract narrative elements from the plurality of static, two-dimensional images. For instance, a narrative element such as dialogue, recurring bits or jokes, exposition (note: an exposition is part of a narration), or the like could be extracted from text on the page of an illustrated book, a thought or speech bubble associated with a character in a comic strip, or the like, where natural language processing techniques could be used to extract meaning from the text"),
respective dialogue segments of the text segments, a source of a dialogue segment, a tone of the dialogue segment (Zavesky: ¶24, "In further examples, the AS 104 may extract narrative elements from the plurality of static, two-dimensional images. For instance, a narrative element such as dialogue, recurring bits or jokes, exposition, or the like could be extracted from text on the page of an illustrated book, a thought or speech bubble associated with a character in a comic strip, or the like (note: source of the dialogue), where natural language processing techniques could be used to extract meaning from the text"; Zavesky: ¶43, "It should further be noted that the three-dimensional model may not comprise a single representation of the media asset. For instance, where the media asset is a human character, the three-dimensional model may model or simulate a plurality of different facial expressions and/or mannerisms for the character. As an example, the three-dimensional model may include different facial expressions of the character, such as happy, sad, angry, scared, and the like and may emulate a different gait when walking versus running. In one example, observed facial expressions of the human character may be mapped to stored facial expressions in a database, in order to determine which of the human character's facial expressions demonstrate happiness, sadness, anger, and the like. The emotion corresponding to a facial expression could also be detected from textual clues. For instance, if a character in a frame of a comic strip series says, “I'm scared,” then the facial expression of the character in that frame may be assumed to demonstrate fear (note: fear or an emotion of being scared is the emotional tone of the dialogue).);
one or more characters of the image segments, a name of a character represented in a character image segment (Zavesky: ¶12, "Examples of the present disclosure facilitate the conversion of a static, two-dimensional media asset into an artistically faithful, immersive (e.g., three-dimensional) computer-generated asset by automatically (or semi-automatically) detecting repeated appearances of the media asset within a set of media. For instance, the media asset may be a recurring character in a printed comic strip series, and the set of media may include several different instances of the comic strip series in which the character appeared. Based on analysis of the repeated appearances, a three-dimensional model may be constructed to simulate the media asset's appearance and/or behavior. For instance, referring again to the recurring character in the comic strip series, the model may simulate various facial expressions (e.g., happy, sad, scared, etc.), costumes (does the character always wear the same outfit or accessories?), mannerisms (e.g., catchphrases, character-specific ways of moving or emoting, such as a character who speaks with his hands a lot, etc.), responses within some context-specific scenario (e.g., whether the character is quick to anger or rarely gets angry), and other character-specific characteristics (e.g., whether the character always appears with another character and how the character interacts with the other character, etc.); Zavesky: 37, "The media asset may comprise a regular or recurring character within the comic strip series (e.g., a protagonist, an antagonist, a sidekick or comic relief character, an animal, etc.)")
NOTE 6A: Zavesky's system tracks recurring characters across the images of the comic strip series. This means that it distinguishes a certain character, for example, character A to a from character B. This inherently requires labeling different characters with unique identifiers. The unique identifiers (label roles) such as "a protagonist", or "an antagonist" function as a names for respective characters of the image segment of a character represented in a character image segment.
Regarding claim 11, depending on 1,
The combination of Zavesky and Nonaka teaches:
The method of claim 1,
further comprising: integrating, the moving picture and the with at least one additional moving picture to generate a film of the digital graphic narrative file.
Nonaka further teaches generating a film of the graphic narrative (Nonaka: ¶77, "The display control information also includes screen scrolling and/or screen switching. The screen scrolling information may include a scrolling speed, a scrolling direction, a scrolling order, and a method for starting, ending, suspending, and repeating scrolling as detailed information. The screen switching information may include a unit of switching (panel, etc.), a method for determining a switching timing (manual, automatic, semiautomatic), and a display effect (wiping, fading in/fading out, dissolving) accompanying switching as detailed information").
NOTE 11A: As established in claim 1, and 10, Zavesky teaches generating moving pictures based from narrative elements extracted from the frames or panels of a comic/graphic novel by using a machine learning method such as GAN. Nonaka teaches an automatic switching of panels (also moving pictures) with display effects equivalent to a film. The additional moving picture that is integrated are the display effects.
It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to modify Zavesky and combine the teachings of Nonaka including: integrating, the moving picture and the with at least one additional moving picture to generate a film of the digital graphic narrative file.
The reason for doing so is to enable the panel image of each panel within the image of the entire page to be viewed on the monitor of the viewer device in a panel view (Nonaka: ¶18) and to add a display effect accompanying switching as detailed information (Nonaka: ¶77)
Regarding claim 15, depending on 1,
The combination of Zavesky and Nonaka teaches:
The method of claim 1
However, Zavesky fails to teach: generating a title sequence for the digital graphic narrative file wherein the title sequence is a moving picture, that includes text content from a title page of the digital graphic narrative file.
Nonaka teaches:
generating a title sequence for the digital graphic narrative file wherein the title sequence is a moving picture, that includes text content from a title page of the digital graphic narrative file (Nonaka: ¶34, “. . . The file format includes tag information including a comic title, which episode, which volume, an author, and a publisher. . .”; ¶63, "The content image and its accompanying information may be saved in any format, and are saved in an XML file or the like. The accompanying information may be recorded on the original content image. The accompanying information may include a content author, a title, the total number of pages, a volume number, an episode number, the holder of the right of publication (a publisher), or the like"; Nonaka: ¶77, "The display control information also includes screen scrolling and/or screen switching. The screen scrolling information may include a scrolling speed, a scrolling direction, a scrolling order, and a method for starting, ending, suspending, and repeating scrolling as detailed information. The screen switching information may include a unit of switching (panel, etc.), a method for determining a switching timing (manual, automatic, semiautomatic), and a display effect (wiping, fading in/fading out, dissolving) accompanying switching as detailed information)”; NOTE: The title information is generated as part of the content image in automatic switching (moving picture) including displaying of the title. The frame(s) with the title is the title sequence for the digital graphic narrative file. The title is from the title page where it the comic title tag information is extracted.
It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to combine Zavesky and Nonaka and include: generating a title sequence for the digital graphic narrative file wherein the title sequence is a moving picture, that includes text content from a title page of the digital graphic narrative file.
The reason for doing so is to provide a dynamic introduction mimicking movies showing animated title sequence at the start of the movie.
Regarding claim 16, depending on 1,
The combination of Zavesky, and Nonaka teaches:
The method of claim 1,
Zavesky teaches:
wherein segmenting the segmented elements is based on one or more of a Fully Convolutional Network (FCN) model, a U-Net model, a SegNet model, a Pyramid Scene Parsing Network (PSPNet) model, a DeepLab model, a Mask R-CNN, an Object Detection and Segmentation model, a fast R-CNN model, a faster R-CNN model, a You Only Look Once (YOLO) model, a fast R-CNN model, a PASCAL VOC model, a COCO model, a ILSVRC model, a Single Shot Detection (SSD) model, a Single Shot MultiBox Detector model, and a Vision Transformer, ViT) model (Zavesky: ¶38, "In one example, the physical features may be extracted using one or more image analysis techniques. For instance, facial features and expressions of a human (or human-like) character may be extracted using one or more facial recognition and analysis techniques that are capable of locating a facial region (note: segmentation model) in an image and/or locating different elements of the facial regions (e.g., eyes, nose, mouth, hair, ears, etc.). Physical features of objects of other non-human assets could be extracted using one or more object recognition techniques (note: object detection model). The recognition techniques may be provided with one or more sample images of the media asset to facilitate location of the media asset in the plurality of two-dimensional images").
Regarding claim 18, depending on 1,
The combination of Zavesky, and Nonaka teaches:
The method of claim 1,
Zavesky further teaches:
wherein the second ML model includes one or more of a generative adversarial network (GAN) model; a Stable Diffusion model; a DALL-E Model; a Craiyon model; a Deep Al model; a Runaway Al model; a Colossyan Al model; a DeepBrain Al model; a Synthesia.io model; a Flexiclip model; a Pictory model; a InVideo.io model; a Lumen5 model; and a Designs.ai Videomaker model (Zavesky: ¶56, "In optional step 218 (illustrated in phantom), the processing system may render the immersive experience (moving picture representing the one or more panels) on one or more user endpoint devices of a user. For instance, the processing system may send data and signals to an immersive display that cause the immersive display to present the immersive experience to the user. In one example, rendering the immersive experience may involve extrapolating between a set of narrative elements in order to bridge any “gaps” that may exist in the original two-dimensional media content. For instance, where the plurality of two-dimensional images comprise frames of a comic strip series, two narrative elements may have been identified in the plurality of two-dimensional images. However, due to the nature of comic strips, the original two-dimensional content may not explicitly show how to get from one narrative element (e.g., a super hero transforming from his alter ego) to another narrative element (e.g., the super hero fighting a villain). Thus, rendering the immersive experience (note: moving picture representing the one or more panels) may include rendering events to fill in any gaps between narrative elements of the overarching hierarchy of the narrative. Machine learning techniques such as convolution neural networks (CNNs) or generative adversarial networks (GANs) could be used to infer the most natural ways to fill the gaps").
Regarding claim 25, depending on 1,
The combination of Zavesky, and Nonaka teaches:
The method of claim 1,
However, Zavesky fails to teach: further comprising creating a dynamic path of action for the moving picture, the path of action include visual transition elements corresponding to zoom or pan.
The analogous art Nonaka teaches:
creating a dynamic path of action for the moving picture, the path of action include visual transition elements corresponding to zoom or pan (Nonaka: ¶8, “. . . panel features are converted into scores, and effects such as zooming and panning are applied. . . ¶77, “. . . The display control information also includes screen scrolling and/or screen switching. The screen scrolling information may include a scrolling speed, a scrolling direction, a scrolling order, and a method for starting, ending, suspending, and repeating scrolling as detailed information. The screen switching information may include a unit of switching (panel, etc.), a method for determining a switching timing (manual, automatic, semiautomatic), and a display effect (wiping, fading in/fading out, dissolving) accompanying switching as detailed information. . .”; NOTE: Nonaka generates moving pictures by automatically switching between panels. Effects such as panning and zooming are applied based on panel features scores. Different scores correspond to automatically zooming or panning of a panel when switching to a different panel creating a dynamic path of action for the moving picture.).
It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to combine Zavesky, and Nonaka and include: further comprising creating a dynamic path of action for the moving picture, the path of action include visual transition elements corresponding to zoom or pan.
The reason for doing so is to provide display effects to notify users visually when a panel is going through a transition to a new panel.
Regarding claim 26, depending on 1,
The combination of Zavesky, and Nonaka teaches:
The method of claim 1,
Zavesky further teaches:
further comprising receiving information regarding one or more of the segmented elements over a communication network from one or more online sources, wherein generating the prompts is further based on the information received from the online sources (Zavesky ¶31, “. . . one or more servers 128 and databases (DBs) 126 may be accessible to the AS 104 via Internet 124 in general. The servers 128 may include Web servers that support physical data interchange with other devices connected to the World Wide Web. For instance, the Web servers may support Web sites for Internet content providers, such as social media providers, ecommerce providers, service providers, news organizations, and the like. At least some of these Web sites may include sites where two-dimensional static images of media assets, or additional information related to the media assets which may help to guide construction of three-dimensional models, may be obtained”; ¶42, “machine learning techniques may be used to guide the process of constructing the three-dimensional model using the extracted physical features “; NOTE: Accessing web servers to obtain additional information related to the media assets, which are the segmented elements corresponding to extracted physical features, inherently interchanging data over a communication network. The system then uses the additional information from online sources regarding the segmented elements to generate prompts used by the machine learning model to construct the 3d model.).
Claims 3, and 22-24 is rejected under 35 U.S.C. 103 as being unpatentable over Zavesky et al. (US 20220165024 A1, hereinafter “Zavesky”) in view of Nonaka (US 20130282376 A1, hereinafter “Nonaka”) and further in view of Goodsitt et al. (US 20210390247 A1,hereinafter “Goodsitt”).
Regarding claim 3, depending on 1,
The combination of Zavesky and Nonaka teaches:
The method of claim 1:
However, the combination fails to teach: wherein the instructions provided by the prompts include an instruction to render the moving picture as either a live-action moving picture or as an animated moving picture of a specified animation style, and wherein the moving picture is generated as either the live- action moving picture or as the animated moving picture in accordance with the prompts.
The analogous art Goodsitt teaches:
wherein the instructions provided by the prompts include an instruction to render the moving picture as either a live-action moving picture or as an animated moving picture of a specified animation style, and wherein the moving picture is generated as either the live- action moving picture or as the animated moving picture in accordance with the prompts (Goodsitt: Fig. 3, ¶2, "For example, children may prefer anime or cartoon (note: specified animation style) advertisements. On the other hand, adults might prefer a live-action advertisement (note: live-action moving picture)"; Goodsitt: ¶33, "The content generator 40 may comprise one or more algorithms which are configured to apply a selected style transfer to a base image and convert it into a desired style. . .”; ¶34, “the content generator 40 can be implemented using machine learning. For example, the content generator 40 can comprise one or more generative adversarial networks (GANs)”; NOTE: The content generates a selected style of the moving picture such as a specified animation style (cartoon/anime) or live-action style. The GAN takes input prompts in order to generate the preferred content. In Fig. 3 step 303-305, the instruction provided by the prompt that is used as an input for the GAN is based on the user preference information on whichever style is preferred by the user.).
It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to combine Zavesky, Nonaka and Goodsitt and include wherein the instructions provided by the prompts include an instruction to render the moving picture as either a live-action moving picture or as an animated moving picture of a specified animation style, and wherein the moving picture is generated as either the live- action moving picture or as the animated moving picture in accordance with the prompts.
The reason for doing so is to dynamically generate image and video content based on specific user preferences (Goodsitt: ¶3).
Regarding claim 22, depending on 1,
The combination of Zavesky, and Nonaka teaches:
The method of claim 1,
However, Zavesky does not disclose if the GAN used for generating the immersive experience is trained, and fails to teach: further comprising training the second ML model to generate images in a style associated with the digital graphic narrative file, and generating additional image content using the trained ML model.
The analogous art Goodsitt teaches:
further comprising training the second ML model to generate images in a style associated with the digital graphic narrative file, and generating additional image content using the trained ML model (Goodsitt: Fig. 3, ¶2, "For example, children may prefer anime or cartoon (note: specified animation style) advertisements. On the other hand, adults might prefer a live-action advertisement (note: live-action moving picture)"; Goodsitt: ¶33, "The content generator 40 may comprise one or more algorithms which are configured to apply a selected style transfer to a base image and convert it into a desired style. . .”; ¶34-35, “the content generator 40 can be implemented using machine learning. For example, the content generator 40 can comprise one or more generative adversarial networks (GANs). . . each of the style transfers is trained with a distinct pre-built model. Specifically, each of the style transfers are trained with distinct generative adversarial networks.”; NOTE: The generated images are the frames of the output of the content generator that is trained based on a style associated such as cartoon, anime, or live-action styles).
It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to combine Zavesky, Nonaka, and Goodsitt and include: comprising training the second ML model to generate images in a style associated with the digital graphic narrative file, and generating additional image content using the trained ML model.
The reason for doing so is for “a meaningful mapping between the input and output images can be defined for unpaired datasets” (Goodsitt: ¶35).
Regarding claim 23, depending on 22,
The combination of Zavesky, Nonaka, and Goodsitt teaches:
The method of claim 22,
Zavesky further teaches:
wherein the additional image content is used to generate a view of the at least one panel that extends beyond an unmodified view of the at least on panel (Zavesky: ¶56, “. . . the processing system may render the immersive experience on one or more user endpoint devices of a user. For instance, the processing system may send data and signals to an immersive display that cause the immersive display to present the immersive experience to the user. In one example, rendering the immersive experience may involve extrapolating between a set of narrative elements in order to bridge any “gaps” that may exist in the original two-dimensional media content. For instance, where the plurality of two-dimensional images comprise frames of a comic strip series, two narrative elements may have been identified in the plurality of two-dimensional images. However, due to the nature of comic strips, the original two-dimensional content may not explicitly show how to get from one narrative element (e.g., a super hero transforming from his alter ego) to another narrative element (e.g., the super hero fighting a villain). Thus, rendering the immersive experience may include rendering events to fill in any gaps between narrative elements of the overarching hierarchy of the narrative. Machine learning techniques such as convolution neural networks (CNNs) or generative adversarial networks (GANs) could be used to infer the most natural ways to fill the gaps. . .”; NOTE: The generated view of the at least one panel is the immersive experience presented to the user. It extends beyond an unmodified view of the at least one panel (original 2D content) because the 2D content is transformed into an immersive experience with generated additional image content to fill the gaps.)
Regarding claim 24, depending on 23,
The combination of Zavesky, Nonaka, and Goodsitt teaches:
The method of claim 23,
Zavesky further teaches:
wherein the generated view has a different shape than the unmodified view (NOTE: As cited above referencing Zavesky paragraph 56, the generated immersive view is generated based on the unmodified original 2D content. The generated view will have a different shape due to its immersive 3D nature, transforming a 2D flat object to a 3D volumetric object.)
Claim 4-5 is rejected under 35 U.S.C. 103 as being unpatentable over Zavesky et al. in view of Nonaka further in view of Saban et al. (US 20140225978 A1, hereinafter “Saban”).
Regarding claim 4, depending on 1,
The combination of Zavesky and Nonaka teaches:
The method of claim 1,
Zavesky further teaches:
wherein the labels of the image segments include indicia regarding one or more of which of the image segments are foreground elements and background elements (Zavesky: ¶36, "The method 200 begins in step 202 and proceeds to step 204. In step 204, the processing system may extract a plurality of physical features of a media asset from a plurality of two-dimensional images of the media asset. In one example, the media asset may comprise a character or an object. . .; Zavesky: ¶37, ". . .Where the media asset is an object, physical features of the media asset may comprise a type of the object (e.g., vehicle, building, accessory, weapon, etc.), a shape of the object, a color of the object, a size of the object, unique physical characteristics of the object (e.g., a specific bumper sticker on a car or a dent (note: foreground element) in the car's hood (note: background element), an unusual edifice (note: foreground element) on a building (note: background element)), and other physical features (note: indicia of identified foreground elements). . .”),
indicia for how one or more of the image segments move (Zavesky: ¶37, "the character's mannerisms (e.g., repeated gestures)"; Zavesky: ¶41, "In further examples, mannerisms and/or physical behaviors of the media asset may be further mapped onto the three-dimensional model. For instance, if the media asset is a human character, the three-dimensional model may be adapted to emulate the character's gait, gestures (e.g., frequently playing with their hair, cracking their knuckles, playing with a piece of jewelry, etc.), and other physical behaviors”),
textures (Zavesky: ¶37, “. . .e.g., a specific bumper sticker on a car or a dent in the car's hood, an unusual edifice on a building. . .), and other physical features. . .”; NOTE: Textures are unique physical characteristics of the object such as a dent on a car’s hood)
and wherein the labels of the text segments include indicia regarding one or more of whether one or more of the text segments are dialogue, character thoughts, sounds, or narration (Zavesky: ¶24, " In further examples, the AS 104 may extract narrative elements from the plurality of static, two-dimensional images. For instance, a narrative element such as dialogue, recurring bits or jokes, exposition, or the like could be extracted from text on the page of an illustrated book, a thought or speech bubble associated with a character in a comic strip, or the like, where natural language processing techniques could be used to extract meaning from the text. . . "),
and a source/origin of the one or more of the text segments (Zavesky: ¶24, ". . .a thought or speech bubble associated with a character in a comic strip. . .);
However, the combination of Zavesky and Nonaka fails to teach an indicia regarding light reflection of one or more of the image segments.
The analogous art Saban teaches:
indicia regarding light reflection of one or more of the image segments (Saban: ¶99, “. . . obtain the additional important information, the mask can be applied on the original frame or video, and the RGB or gray scale texture, shade, or brightness scale on the object can be obtained. This information is much more accurate and convincing for color changes since it saves the original object's wrinkle texture, shading, light reflection, material signature, and the like. . .”; ¶108, “Material light reflection mask--representing light reflection of the object”).
It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to combine Zavesky, Nonaka, and Saban and include an indicia regarding light reflection of one or more of the image segments.
The reason for doing so is “to obtain additional information” in order “to create a convincing feeling of an object” (Saban: ¶99).
Regarding claim 5, depending on 4,
The combination of Zavesky, Nonaka, and Saban teaches:
The method of claim 4,
Zavesky further teaches:
wherein the instructions specify locations of the keyframes at intervals throughout the moving picture, a starting keyframe, and a concluding keyframe (Zavesky: ¶48, “. . . In a further example, non-text visual cues could be detected over a series of consecutive frames of a comic strip series (or other instances of two-dimensional media) and used to infer a narrative element. For instance, if multiple consecutive frames of the comic strip series depict a superhero trading punches with a villain, . . . if multiple consecutive frames of the comic strip series depict a superhero growing weak after being exposed to an object, . . . multiple consecutive frames of a comic strip series show a character daydreaming about different types of food. . . a set of consecutive frames shows men in masks running out of a bank, jumping into a car, and being chased by police in that order. . . Thus, simply by observing the actions of the characters and individuals appearing in the two-dimensional media over a window of time, a narrative element can be inferred. . .” ¶56, "In optional step 218 (illustrated in phantom), the processing system may render the immersive experience on one or more user endpoint devices of a user. For instance, the processing system may send data and signals to an immersive display that cause the immersive display to present the immersive experience to the user. In one example, rendering the immersive experience may involve extrapolating between a set of narrative elements in order to bridge any “gaps” that may exist in the original two-dimensional media content. For instance, where the plurality of two-dimensional images comprise frames of a comic strip series, two narrative elements may have been identified in the plurality of two-dimensional images. However, due to the nature of comic strips, the original two-dimensional content may not explicitly show how to get from one narrative element (e.g., a super hero transforming from his alter ego) (note: starting frame) to another narrative element (e.g., the super hero fighting a villain) (note: concluding frame). Thus, rendering the immersive experience may include rendering events to fill in any gaps between narrative elements of the overarching hierarchy of the narrative. Machine learning techniques such as convolution neural networks (CNNs) or generative adversarial networks (GANs) could be used to infer the most natural ways to fill the gaps");
NOTE 5A: Zavesky teaches rendering the immersive experience (moving picture) by extrapolating (generation of keyframes at intervals across the timeline between two frames) between a starting frame (e.g., a super hero transforming from his alter ego) and a concluding frame (e.g., the super hero fighting a villain). The interval is the is the set of multiple frames where a narrative element is inferred starting from a first frame event and a concluding frame event as described in the Zavesky paragraph 48.
Claims 7-8 are rejected under 35 U.S.C. 103 as being unpatentable over Zavesky in view of Nonaka further in view of Hartrell et al. (US 20170083196 A1, hereinafter “Hartrell”).
Regarding claim 7, depending on 1,
The combination of Zavesky, and Nonaka teaches:
The method of claim 1,
Zavesky further teaches:
generating information (note: extracting narrative elements locally from frames/panels of the graphic novel) regarding the digital graphic narrative file based on applying the panels to a third ML model (note: object detection techniques and analysis techniques including natural language processing and semantic analysis as taught by Zavesky: ¶38, 46),
wherein the information includes one or more plot information (Zavesky: ¶45, "In step 208, the processing system may extract a plurality of narrative elements associated with the media asset from the plurality of two-dimensional images of the media asset. In one example, a narrative element may comprise a recurring gag, a recurring character interaction, a catchphrase, or an ongoing narrative arc that involves the media asset. For instance, if the media asset is a human character, the character may have a particular line of dialogue that he repeats often, or a facial expression that he makes often. Alternatively, the character may interact with another character in a unique or specific way"),
genre information (Zavesky: ¶46, "Understanding the meaning of the dialogue and text may help the processing system to identify a type or context of the narrative element (e.g., a funny interaction versus a battle)"; note: Zavesky's system distinguishes between comedy and action genres, and a war setting),
and atmospheric information (Zavesky: ¶49, "Non-text visual cues from which narrative elements may be extracted may also include character facial expressions (e.g., if a character is depicted crying, this may indicate a sad event (note: lonely atmosphere)), movement lines (e.g., lines to indicate that a character is moving very quickly, leaning abruptly away from something, shivering, etc.), and other visual cues which may emphasize or guide an overall narrative arc. For instance, if movement lines show a comic strip character shivering from being cold, this may indicate that a villain who has the power to freeze things may be nearby (note: a mysterious atmosphere)").
However, Zavesky only extracts the plot, genre, and atmospheric information from individual panels and not from the graphic narrative file as a whole (global information), and fails to teach generating global information regarding the digital graphic narrative file.
Hartrell teaches:
generating global information regarding the graphic narrative file based on applying the panels to a third ML model, wherein the global information includes one or more of plot information, genre information, and atmospheric information (Hartrell: ¶23, "The graphic novel analysis system 120 applies machine-learning techniques to build and apply a model for identifying features (note: global information of the graphic narrative) within a digital graphic novel. In one embodiment, the features include the location of panels and speech bubbles as well as the intended reading order. In other embodiments, the features additionally or alternately include: depicted characters, depicted objects (e.g., doors, weapons, etc.), events (e.g., plots, inter-character relationships, etc.) . . . depicted weather, genre, right-to-left (RTL) reading, advertisements, and the like. In some instances, the identification of certain features of a digital graphic novel is used to assist in the identification of others. . . ").
It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to combine Zavesky, Nonaka, and Hartrell and include: generating global information regarding the graphic narrative file based on applying the panels to a third ML model, wherein the global information includes one or more of plot information, genre information, and atmospheric information to provide a packaged digital graphic novel to a reading device for presentation of the digital graphic novel content in accordance with the manner indicated in the presentation metadata (Hartrell: ¶6).
Regarding claim 8, depending on 7,
The combination of Zavesky, Nonaka, and Hartrell teaches:
The method of claim 7,
Zavesky further teaches:
wherein the plot information indicates one or more of a type of plot (Zavesky: ¶47, "In another example, non-text visual cues may also help to identify narrative elements. For instance, a superhero in a comic strip series may frequently be depicted fighting the same villain (note: overcoming-the-monster plot) or performing the same actions (e.g., transforming from an alter ego into a superhero inside a telephone booth or by spinning in place)"),
plot elements associated with respective portions of the panels (Zavesky: ¶47, "In another example, non-text visual cues may also help to identify narrative elements. For instance, a superhero in a comic strip series may frequently be depicted fighting the same villain (note: overcoming-the-monster plot) or performing the same actions (note: plot element associated with respective portions of the panels) (e.g., transforming from an alter ego into a superhero inside a telephone booth or by spinning in place)"; Zavesky: ¶13, “Further examples of the present disclosure detect narrative hierarchies within the set of media. Based on analysis of the narrative hierarchies, models of common narrative elements may be constructed to simulate events that may commonly occur in the set of media. For instance, recurring jokes or interactions (e.g., a character always makes an entrance in a certain way, a certain basic story structure is always followed, etc. (note: plot element associated with respective portions of the panels)) may be modeled as common narrative elements. The models of the common narrative elements may also indicate the roles of particular characters in the set of media (e.g., hero, villain, comic relief, etc.)”),
and pacing information associated with the respective portions of the panels (Zavesky: ¶41, "In further examples, mannerisms and/or physical behaviors of the media asset may be further mapped onto the three-dimensional model. For instance, if the media asset is a human character, the three-dimensional model may be adapted to emulate the character's gait, gestures (e.g., frequently playing with their hair, cracking their knuckles, playing with a piece of jewelry, etc.), and other physical behaviors. If the media asset is an object such as a car, the three-dimensional model could be adapted to emulate whether the car moves fast or slowly (note: pacing information associated with the respective portions of the panels), whether an unusual amount of physical exhaust is emitted from the tailpipe, and other physical behaviors");
and the atmospheric information indicates one or more settings associated with the respective portions of the panels (Zavesky: ¶47, "In another example, non-text visual cues may also help to identify narrative elements. For instance, a superhero in a comic strip series may frequently be depicted fighting the same villain or performing the same actions (note: plot element associated with respective portions of the panels) (e.g., transforming from an alter ego into a superhero inside a telephone booth or by spinning in place); (note: fantasy setting)"; Zavesky: ¶47, "In another example, non-text visual cues may also help to identify narrative elements. For instance, a superhero in a comic strip series may frequently be depicted fighting the same villain (note: a tense atmosphere) or performing the same actions (e.g., transforming from an alter ego into a superhero inside a telephone booth or by spinning in place)").
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Zavesky in view of Nonaka further in view of Bagga et al. (US 20250200962 A1, hereinafter “Bagga”).
Regarding claim 17, depending on 1,
The combination of Zavesky, and Nonaka teaches:
The method of claim 1,
Zavesky teaches:
wherein the first ML model includes; an image classifier and a language model and a language model (Zavesky: ¶38, “. . . one or more object recognition technique . . .”; (Zavesky: ¶46, ". . . analysis techniques including natural language processing and semantic analysis may be used to extract meaning from dialogue, text, and the like . . .”);
However, Zavesky fails to explicitly disclose the specific models for the image classifier model and the language model that the analogous art Bagga discloses.
Bagga teaches:
an image classifier based on one or more of a K-means model, an Iterative Self-Organizing Data Analysis Technique (ISODATA) model, a YOLO model. A ResNet model, a ViT model, a Contrastive Language-Image Pre-Training (CLIP) model, a convolutional neural network (CNN) model, a MobileNet model, and an EfficientNet model (Baga: ¶6, "In some instances, the selected AI service includes a third service for text extraction from image (note: classification), the input data includes a user request (note: prompt) and an image, and the third service is associated with a convolutional neural network (CNN) model and a transformer model");
and a language model based on one or more of a transformer model, a Generative pre-trained transformers (GPT), a Bidirectional Encoder Representations from Transformers (BERT) model, and a T5 model (Baga: ¶67, "At operation 612, the AI service module generates text content (for a current page) by applying a large language model (LLM) to the text description. The LLM model can be a suitable GenAI model known in the art, such as Chat Generative Pre-trained Transformer (ChatGPT), that can generate more text content based on a given text description").
It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention that choosing a specific model of an image classifier and language model is an obvious design choice from a finite list of available models and/or familiarity of the PHOSITA with a specific language model, as Zavesky already discloses that "one or more object recognition technique may be used, and analysis techniques including natural language and semantic analysis may be used.
It would also have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to combine Zavesky and Bagga to include: the image classifer as a CNN model and the language model as a GPT to process massive datasets and to automate complex tasks traditionally performed by humans, and thus can significantly improve efficiency and productivity in many ways (Bagga: ¶2).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PATRICK GALERA whose telephone number is (571)272-5070. The examiner can normally be reached Mon-Fri 0800-1700 ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, King Poon can be reached at 571-270-0728. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/PATRICK P GALERA/Examiner, Art Unit 2617 /KING Y POON/Supervisory Patent Examiner, Art Unit 2617
Prosecution Insights