US20230297609A1 - Systems and methods for naming objects based on object content - Google Patents
Systems and methods for naming objects based on object content Download PDFInfo
- Publication number
- US20230297609A1 US20230297609A1 US18/201,549 US202318201549A US2023297609A1 US 20230297609 A1 US20230297609 A1 US 20230297609A1 US 202318201549 A US202318201549 A US 202318201549A US 2023297609 A1 US2023297609 A1 US 2023297609A1
- Authority
- US
- United States
- Prior art keywords
- classification label
- objects
- name
- user
- slide
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000011156 evaluation Methods 0.000 claims 5
- 238000001914 filtration Methods 0.000 claims 2
- 238000010801 machine learning Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 38
- 230000005055 memory storage Effects 0.000 description 7
- 230000003993 interaction Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000009877 rendering Methods 0.000 description 4
- 241001133760 Acoelorraphe Species 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000002420 orchard Substances 0.000 description 2
- 101100127285 Drosophila melanogaster unc-104 gene Proteins 0.000 description 1
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/45—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/438—Presentation of query results
- G06F16/4387—Presentation of query results by the use of playlists
- G06F16/4393—Multimedia presentations, e.g. slide shows, multimedia albums
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/483—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90324—Query formulation using system suggestions
- G06F16/90328—Query formulation using system suggestions using search space presentation or visualization, e.g. category or range presentation and selection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
Definitions
- the present disclosure relates generally to graphical user interfaces (GUIs) and, more particularly, to determining descriptive object names for display on the GUI.
- GUIs graphical user interfaces
- GUI graphical user interface
- the GUI may enable a user to communicate with the electronic device by allowing the user to interact with graphical icons and visual indicators on the display. For example, a user may interact with a presentation application file using the presentation application icon. The user, in particular, may interact with multiple objects within the application to generate the application file. However, in instances when a relatively large number of objects are included in the application file, such as when objects are layered over one another, the user may have difficulty identifying and interacting with the appropriate objects to design the application file as intended.
- the present disclosure generally relates to determining descriptive object names for display on a graphical user interface (GUI) by using machine learning to identify contents of the object(s) and generating the descriptive name(s) based on the contents.
- Application files such as a presentation document, may include a variety of objects that are inserted and placed by the user. For example, a slide may include text object(s) and/or image object(s).
- the application file may include an object list that lists the inserted objects using associated default names, which may be generic. As an example, image objects may be listed under the default name “image”. When a relatively large number of objects are included in the application file, the user may have difficulty identifying objects via the default names displayed in the object list.
- a machine learning content classifier may detect the contents of the object and may determine an appropriate classification label for the object based on the contents.
- the electronic device may update metadata (e.g., object name) of the object to reflect the classification label. That is, the classification label may be used as the descriptive name.
- the object metadata may not be modified and the object name may remain the default name.
- the content classifier may output the user-defined name as the appropriate classification label (e.g., descriptive name) for objects with similar characteristics as the object whose classification label was replaced by the user-defined name.
- the appropriate classification label e.g., descriptive name
- FIG. 1 is a block diagram of an electronic device that includes a graphical user interface, in accordance with an embodiment
- FIG. 2 is a front view of a hand-held device representing an example of the electronic device of FIG. 1 , in accordance with an embodiment
- FIG. 3 is a front view of another hand-held device representing another example of the electronic device of FIG. 1 , in accordance with an embodiment
- FIG. 4 is a perspective view of a notebook computer representing another example of the electronic device of FIG. 1 , in accordance with an embodiment
- FIG. 5 is a front view of a wearable electronic device representing another example of the electronic device of FIG. 1 , in accordance with an embodiment
- FIG. 6 is a schematic of an application file having an object list that displays default names for each object in the application file, in accordance with an embodiment
- FIG. 7 is a schematic of the application file having an object list that displays descriptive names for each object in the application file, in accordance with an embodiment
- FIG. 8 is a process for determining the descriptive names for each object in the application file of FIG. 7 based on object content, in accordance with an embodiment
- FIG. 9 is a schematic of an application file having an object list that displays user-defined names for certain objects in the application file, in accordance with an embodiment
- FIG. 10 is a process for modifying the descriptive name of the certain objects in the application file of FIG. 9 based on the user-defined name, in accordance with an embodiment
- FIG. 11 is a process for automatically updating the descriptive name of the certain objects in the application file of FIG. 9 using the user-defined name for the certain objects, in accordance with an embodiment
- FIG. 12 is a schematic of an application file that includes indications of objects with object names related to a keyword search performed on the object list, in accordance with an embodiment.
- FIG. 13 is a process for generating the indication of the objects with object names related to the keyword search performed on the object list of FIG. 12 , in accordance with an embodiment.
- the present disclosure generally relates to graphical user interfaces (GUIs) used to visually facilitate communication between a user and an electronic device.
- GUIs graphical user interfaces
- the user may interact with components of an application file using the GUI.
- an application file such as Keynote and Pages
- the user may insert and place text objects, image objects, and/or shape objects within the application file to generate and design the application file.
- the application file may include an object list that displays a list of the objects included in at least a portion of the application file.
- the object list may include a list of objects present in a slide of a presentation file and may be searched by the user for a particular object.
- the objects may be listed in the object list using associated default name that are intended to be as descriptive as possible so that the user may easily find particular objects.
- an image object may have a default name of its object type (e.g., “image”) and a text object may have a default name of its object type (e.g., “text”).
- the object list may no longer assist the user in easily and quickly identifying a specific object.
- the default name may no longer be descriptive enough to efficiently identify the specific object within the application file.
- a search of the object list may result in multiple objects with a similar default name. For example, a user that may search “image” in the object list may receive a result of all image objects included within the application file or the portion of the application file.
- visually-impaired users may use a voiceover application to identify objects within the application file.
- the voiceover application may voice the metadata (e.g., name) of the object that the user hovers over or selects within the application file and/or the object list.
- the default name may no longer be descriptive enough to efficiently describe the object to the visually-impaired user.
- the present disclosure provides systems and techniques to determine descriptive object names for efficient identification of objects within an application file.
- the default name of each object may be made descriptive by updating the default name to a name based a description of the object contents (e.g., descriptive name).
- an electronic device implementing the application may detect an input to insert an object into the application file.
- the input may include copying and pasting, collaborations between application users, importing of an object without a name into the application file, and the like.
- a machine learning content classifier may detect the contents of the object and determine an appropriate classification label for the object based on the contents.
- the content classifier may determine whether the classification label describes the contents of the object with high enough accuracy and whether to filter out the classification label from use, for example, because the label is derogatory or otherwise undesirable.
- the electronic device may update metadata (e.g., name metadata) of the object to reflect the classification label.
- the updated metadata may be stored in the application file for use later and the classification label may be displayed as the descriptive object name, replacing the default name.
- the electronic device may refrain from modifying the object metadata, resulting in the object name remaining the default name.
- the content classifier may use the user-defined name when generating descriptive names for objects with similar characteristics as that of the certain object. Further, if the user removes the user-defined name from use in the object list, the object name may be restored to the classification label and/or to the default name. Additional details with regard to providing descriptive object names for efficient identification of objects within the application file using the embodiments described herein are detailed below with reference to FIGS. 1 - 13 .
- FIG. 1 an embodiment of an electronic device 10 that includes a graphical user interface (GUI) is shown in FIG. 1 .
- the electronic device 10 may be any suitable electronic device, such as a computer, a mobile phone, a portable media device, a tablet, a television, a virtual-reality headset, a vehicle dashboard, and the like.
- FIG. 1 is merely one example of a particular implementation and is intended to illustrate the types of components that may be present in the electronic device 10 .
- the electronic device 10 includes a radio frequency system 12 , one or more input devices 14 , local memory 16 , a processor core complex 18 , one or more main memory storage devices 20 , a power source 22 , one or more input/output ports 24 , and an electronic display 26 .
- the various components described in FIG. 1 may include hardware elements (e.g., circuitry), software elements (e.g., a tangible, non-transitory computer-readable medium storing instructions), or a combination of both hardware and software elements. It should be noted that the various depicted components may be combined into fewer components or separated into additional components. For example, the local memory 16 and a main memory storage device 20 may be included in a single component.
- the processor core complex 18 is operably coupled with the local memory 16 and the main memory storage device 20 .
- the processor core complex 18 may execute instruction stored in the local memory 16 and/or the main memory storage device 20 to perform operations, such as instructing the electronic display 26 to display application icons that the user may interact with.
- the processor core complex 18 may include one or more general purpose microprocessors, one or more application specific processors (ASICs), one or more field programmable logic arrays (FPGAs), or any combination thereof.
- the local memory 16 and/or the main memory storage device 20 may store data to be processed by the processor core complex 18 .
- the local memory and/or the main memory storage device 20 may include one or more tangible, non-transitory, computer-readable mediums.
- the local memory 16 may include random access memory (RAM) and the main memory storage device 20 may include read only memory (ROM), rewritable non-volatile memory such as flash memory, hard drives, optical discs, and the like.
- the processor core complex 18 may be operably coupled with the radio frequency system 12 .
- the radio frequency system 12 may facilitate wireless communication of data with another electronic device and/or a network.
- the radio frequency system 12 may enable the electronic device 10 to communicatively couple to a personal area network (PAN), such as a Bluetooth network, a local area network (LAN), such as an 802.11x Wi-Fi network, and/or a wide area network (WAN), such as a fourth-generation wireless technology (4G), 5G, or LTE cellular network.
- PAN personal area network
- LAN local area network
- WAN wide area network
- 4G fourth-generation wireless technology
- 5G Fifth Generation
- LTE Long Term Evolution
- the radio frequency system 12 may enable wireless communication of data using various communication protocols and/or at various output powers (e.g., strength of transmitted analog electrical signals).
- the processor core complex 18 is also operably coupled with the I/O ports 24 .
- the I/O ports 24 may enable the electronic device 10 to interface with other electronic devices.
- a portable storage device may be connected to an I/O port 24 , thereby enabling the processor core complex 18 to communicate data with a portable storage device.
- the processor core complex 18 is operably coupled to the power source 22 .
- the power source 22 may provide power to one or more components in the electronic device 10 , such as the processor core complex 18 and/or the radio frequency system 12 .
- the power source 22 may include any suitable energy source, such as a rechargeable lithium polymer (Li-poly) battery and/or an alternating current (AC) power converter.
- the processor core complex 18 is operably coupled with the input devices 14 .
- the input device 14 may facilitate user interaction with the electronic device 10 , for example, by receiving user inputs.
- the input devices 14 may include a button, a keyboard, a mouse, a trackpad, and/or the like.
- the input devices 14 may include touch-sensing components in the electronic display 26 . In such embodiments, the touch-sensing components may receive user inputs by detecting occurrence and/or position of an object touching the surface of the electronic display 26 .
- the electronic display 26 may display image frames, such as a graphical user interface (GUI) for an operating system, an application interface, a still image, or video content. As depicted, the electronic display 26 is operably coupled to the processor core complex 18 . In this manner, the electronic display 26 may display image frames based at least in part on image data received from the processor core complex 18 .
- GUI graphical user interface
- a user may interact with applications displayed on the GUI.
- the applications may include an object list that displays names of the objects inserted and placed by the user within an application file.
- a voiceover application may voice the names of the objects inserted and placed by the user within the application file.
- a machine learning content classifier may detect the contents of the object and determine an appropriate classification label for the object based on the contents. The default name of each object may be made more descriptive by updating the default names to a descriptive name based on the classification label.
- the electronic device 10 may be any suitable electronic device.
- a suitable electronic device 10 specifically a handheld electronic device 10 A, is shown in FIG. 2 .
- the handheld electronic device 10 A may be a portable phone, a media player, a personal data organizer, a handheld game platform, and/or the like.
- the handheld electronic device 10 A may be a smart phone, such as any iPhone® model available from Apple Inc.
- the handheld electronic device 10 A includes an enclosure 34 (e.g., housing).
- the enclosure 34 may protect interior components from physical damage and/or shield them from electromagnetic interference.
- a radio frequency system 12 (not shown) may also be enclosed within the enclosure 34 and internal to the handheld electronic device 10 A.
- the enclosure 34 may operate as part of the one or more antennas of the radio frequency system 12 .
- the enclosure 34 may surround the electronic display 26 .
- the electronic display 26 is displaying a graphical user interface (GUI) 36 having an array of icons 38 .
- GUI graphical user interface
- an application program may launch, such as a presentation application.
- input devices 14 open through the enclosure 34 .
- the input devices 14 may enable a user to interact with the handheld electronic device 10 A.
- the input devices 14 may enable the user to activate or deactivate the handheld electronic device 10 A, navigate a user interface to a home screen, navigate a user interface to a user-configurable application screen, activate a voice-recognition feature, provide volume control, and/or toggle between vibrate and ring modes.
- the I/O ports 24 also open through the enclosure 34 .
- the I/O ports 24 may include, for example, a multi-function connector port (e.g., Lightning port) to connect to external devices.
- a multi-function connector port e.g., Lightning port
- FIG. 3 another example of a suitable electronic device 10 , specifically a tablet electronic device 10 B is shown in FIG. 3 .
- the tablet electronic device 10 B may be any iPad® model available from Apple Inc.
- FIG. 4 A further example of a suitable electronic device 10 , specifically a computer 10 C, is shown in FIG. 4 .
- the computer 10 C may be any Macbook® or iMac® model available from Apple Inc.
- FIG. 5 Another example of a suitable electronic device 10 , specifically a watch 10 D, is shown in FIG. 5 .
- the watch 10 D may be any Apple Watch® model available from Apple Inc.
- the tablet electronic device 10 B, the computer 10 C, and the watch 10 D each also include an electronic display 26 , input devices 14 , I/O ports 24 , and an enclosure 34 .
- the enclosure 34 may enclose a radio frequency system 12 in the tablet electronic device 10 B, the computer 10 C, and/or the watch 10 D to facilitate wireless communication of data with other electronic devices and/or a network.
- FIG. 6 depicts a GUI 600 rendering an application file having an object list that displays default names for each object in the application file, in accordance with an embodiment.
- the application file may be a presentation file that, for example, includes three presentation slides 602 , 604 , 606 .
- the user may choose a slide 606 for modification, as shown by the bolded indication.
- the user may insert an image object 608 , a shape object 610 , and/or a text object 612 into the slide 606 .
- the application file is depicted as a presentation file, it should be appreciated that the application file may be any type of file, such as a word processing file or a spreadsheet file.
- the slide 606 may also include an object list 614 that displays a list of objects (e.g., 608 , 610 , 612 ) within the slide 606 .
- the object list 614 may display default names for the objects (e.g., 608 , 610 , 612 ) within the slide 606 , such that the default names are as descriptive as possible for easy and quick identification by the user.
- the image objects e.g., 608
- the shape objects e.g., 610
- the text objects e.g., 612
- the object list 614 may include sequential objects names, such as image 1 , image 2 , and the like. Further, when an object, such as the image object 608 , is selected by the user, the associated object name 628 may be highlighted in the object list 614 to improve user interaction with the application content.
- the object list 614 may also improve the ability of the user to easily and quickly identify and interact with the application content by enabling the user to perform a search within the object list 614 for a particular object. For example, the user may search for the keyword “image”, which may generate a result that includes objects named “image”. However, when multiple objects of the same object type or other similar characteristics are included within the slide 606 , the search result may fail to provide accurate and narrowed search results. As an example, when the user searches for “image”, the object list may display all image objects 608 , 622 , 624 on the slide 606 and their associated object names 616 , 626 , 628 .
- the voiceover application may only be able to describe the object using the default object name. Since the default name may not be descriptive enough when multiple objects with similar characteristics are included within the slide 606 , the voiceover application may not provide an accurate and identifying description of the chosen object.
- FIG. 7 depicts a GUI 700 rendering an application file having an object list 702 that displays descriptive names for the objects based on the respective object contents, in accordance with an embodiment.
- the application may detect one or more inputs to insert an object into the application file. For example, the user may copy and paste or import the object 608 into the application file.
- a content classifier may be applied to the object 608 to determine the contents of the object 608 .
- the content classifier may be built into the operating system of the electronic device 10 . Further, the content classifier may be trained using a set of object contents considered to be representative of classification labels a designer may want to display on the GUI. For example, the content classifier may be fed images of trees that adequately represent the classification label “tree.” In addition, a subset of classification labels or terms in the classification labels that are deemed appropriate may be preselected and used to train the content classifier to recognize object content conforming to such approved classification labels. As such, the output of the content classifier may be accurate and may only include appropriate/desired classification labels.
- the content classifier may applied to the object 608 as soon as the object 608 is inserted into the application file or once a group of other objects (e.g., 622 , 624 ) that also have been inserted into the application file.
- the content classifier may determine an appropriate classification label for the object 608 based on the contents within the object 608 . For example, the content classifier may determine that the object 608 includes a palm tree and thus, may output classification labels of tree and/or palm tree. Before outputting the classification label to the application file, the content classifier may determine whether the classification label(s) describes the contents of the object 608 with high enough accuracy (e.g., confidence). For example, the content classifier may determine an 80% confidence level for the classification label “tree” and a 30% confidence level for the classification label “palm tree”.
- the content classifier may select, as the output, the classification label that has the highest confidence level when multiple classification labels have been determined and/or may select the classification label whose confidence level is greater than or equal to a predetermined confidence threshold. As such, the content classifier may provide classification labels of greater accuracy and/or specificity.
- the content classifier may use keywords from the text and/or associations with other objects to determine classification label(s) that best describes the subject of the text. For example, the content classifier may evaluate proper nouns and verbs within the text. As another example, the content classifier may evaluate metadata (e.g., name, caption) of objects associated with the text object 612 to determine the classification label(s) that best describes the subject of the text.
- keywords from the text and/or associations with other objects to determine classification label(s) that best describes the subject of the text.
- the content classifier may evaluate proper nouns and verbs within the text.
- the content classifier may evaluate metadata (e.g., name, caption) of objects associated with the text object 612 to determine the classification label(s) that best describes the subject of the text.
- the content classifier may perform an image classification on one or more frames of the video to determine a classification label that appropriately describes the contents of the video.
- a classification label may be “landscape.”
- the content classifier may determine a confidence for each generated classification label and may output the appropriate classification label for the object.
- the electronic device 10 may update metadata (e.g., name metadata) of the object 608 to reflect the classification label.
- the classification label may be stored in the application file and the classification label may be displayed as the descriptive object name.
- the content classifier may output the classification label “tree” as the most appropriate classification label for the object 608 and the object name may be updated to “tree”.
- the updated object name for the object 608 may be included in the object list 702 .
- the content classifier may output classification labels for the other objects 610 , 612 , such as “Txt Rectangle_ 3 ” 706 and “Text: Palm Tree” 708 , respectively.
- the content classifier may output these classification labels by identifying words (e.g., proper nouns) that tend to suggest a particular classification for the word.
- the content classifier may use metadata (e.g., name) of objects, such as image objects, associated with the object (e.g., 610 , 612 ) to determine the appropriate classification labels.
- the name of the object may be updated to provide an indication of the subject matter of the object (e.g., 610 , 612 ).
- the updated metadata may follow the object (e.g., 608 ) and be used to populate corresponding fields when, for example, the object (e.g., 608 ) is exported to another application file.
- the voiceover applications may voice the more descriptive, updated object name to better describe objects to, for example, a visually-impaired user.
- FIG. 8 summarizes a process 800 for determining the descriptive names for each object in the application file based on the object content, in accordance with an embodiment. While process 800 is described according to a certain sequence, it should be understood that the present disclosure contemplates that the described steps may be performed in different sequences than the sequence illustrated, and certain described steps may be skipped or not performed altogether.
- the process 800 may be implemented at least in part by executing instructions stored in a tangible, non-transitory, computer-readable medium, such as the memory 20 , using processing circuitry, such as the processor core complex 18 . Additionally or alternatively, the process 800 may be implemented at least in part by circuit connections and/or control logic implemented in an electronic device 10 .
- the process 800 may be initiated when the processor core complex 18 of the electronic device 10 detects an input to insert the object (e.g., 608 ) in a portion of an application file (e.g., the slide 606 ) (process block 802 ).
- the input may include the user copying and pasting the object 608 into the application file and/or importing the object 608 into the application file.
- the processor core complex 18 may subsequently classify contents of the object 608 by instructing the application to apply the content classifier to the object 608 as soon as the object 608 is inserted into the application file or with a group of objects included in the application file (process block 804 ).
- the content classifier may determine one or more classification labels that describe the contents of the object 608 along with a confidence level for each classification label.
- the processor core complex 18 may also instruct the content classifier to filter the one or more classification labels according to one or more predetermined filters stored in the application or content classifier or according to one or more user-defined filters (process block 806 ). For example, the filters may remove classification labels related to politics or that are derogatory.
- the processor core complex 18 may subsequently instruct the content classifier to determine whether a classification label determined by the content classifier has passed the confidence level and filter criteria (decision block 808 ).
- the content classifier may be reapplied to the object (e.g., 608 ) to determine another set of classification labels.
- the default name may be used to populate the object list 702 rather than a descriptive name based on the classification label.
- the processor core complex 18 may update the metadata of the object based on the classification label by instructing the application file to store the classification label as the object name (process block 810 ). Once the object name has been updated, the classification label may be displayed as the descriptive name in the object list 702 (process block 812 ).
- FIG. 9 depicts a GUI 900 rendering an application file that has an object list 902 which displays user-defined names, in accordance with an embodiment.
- the user may prefer using a user-defined name for certain objects or object types as compared to the default name or the descriptive name generated by the content classifier.
- the content classifier may learn the user's preference and automatically output the user-defined metadata for similar objects instead of the content-based classification label.
- the user may prefer to use the description “rectangle” to describe the shape objects (e.g., 610 ) used within the slide 606 .
- the content classifier may use the description “rectangle” to describe the newly inserted shape object 904 .
- the object list 902 may include the object name “Rectangle 4 ” to describe the shape object 904 .
- the user-defined name may be used even when the object (e.g., 904 ) is exported from the application file and/or when the content classifier version is updated, such as with an update of the application supporting the application file.
- the classification labels for each object may be restored, if available.
- the default names for each object may be restored.
- FIG. 10 depicts a process 1000 for determining the descriptive name of the objects based on the user-defined name for the object (e.g., 610 , 904 ), in accordance with an embodiment. While the process 1000 is described according to a certain sequence, it should be understood that the present disclosure contemplates that the described steps may be performed in different sequences than the sequence illustrated, and certain described steps may be skipped or not performed altogether. In some embodiments, the process 1000 may be implemented at least in part by executing instructions stored in a tangible, non-transitory, computer-readable medium, such as the memory 20 , using processing circuitry, such as the processor core complex 18 . Additionally or alternatively, the process 1000 may be implemented at least in part by circuit connections and/or control logic implemented in an electronic device 10 .
- a tangible, non-transitory, computer-readable medium such as the memory 20
- processing circuitry such as the processor core complex 18
- the process 1000 may be implemented at least in part by circuit connections and/or control logic implemented in an electronic device 10 .
- the process 1000 may begin when the application file receives a user input to change metadata (e.g., name metadata) of an object to the user-defined name, as described above (process block 1002 ).
- a user input to change metadata e.g., name metadata
- the user may elect to rename the shape objects 610 , 904 with the name “rectangle”.
- the processor core complex 18 may instruct the application to modify the object name to the user-defined name (process block 1004 ).
- FIG. 11 depicts a process 1100 for automatically updating the name of the object (e.g., 904 ) using the user-defined name for objects (e.g., 610 , 904 ) of a similar type, in accordance with an embodiment. While process 1100 is described according to a certain sequence, it should be understood that the present disclosure contemplates that the described steps may be performed in different sequences than the sequence illustrated, and certain described steps may be skipped or not performed altogether. In some embodiments, the process 1100 may be implemented at least in part by executing instructions stored in a tangible, non-transitory, computer-readable medium, such as the memory 20 , using processing circuitry, such as the processor core complex 18 . Additionally or alternatively, the process 1100 may be implemented at least in part by circuit connections and/or control logic implemented in an electronic device 10 .
- a tangible, non-transitory, computer-readable medium such as the memory 20
- processing circuitry such as the processor core complex 18
- the process 1100 may be implemented at least in part by circuit
- the process 1100 may be initiated when the application receives an input to add a new object that has similar characteristics as an object whose metadata, and thus descriptive name, has been modified to a user-defined name (process block 1102 ).
- the user may indicate that he/she wants to insert the shape object 904 , which has similar characteristics (e.g., object content, shape, color) to other shape objects (e.g., 610 ) in the application file.
- the processor core complex 18 may then instruct the content classifier to determine the user-defined name to replace the name of the new object (e.g., 904 ) (process block 1104 ).
- the content classifier may determine the objects (e.g., 610 ) that are to the new object (e.g., 904 ) and use the user-defined name associated with these object (e.g., 610 ) to determine the appropriate user-defined name (e.g., “rectangle”) for the new object (e.g., 904 ).
- the processor core complex 18 may then instruct the application to insert the new object (e.g., 904 ) into the application file with metadata that is updated with the user-defined name (process block 1106 ).
- FIG. 12 depicts a GUI 1200 rendering an application file that includes indications of objects that have object names related to a keyword searched in the object list 1202 , in accordance with an embodiment.
- the user may perform a search in the object list 1202 , such as for the keyword “tree”.
- the application and/or the content classifier may analyze the names of each object included within the application file or a portion of the application file and may determine the object names that are related to the keyword. For example, the application and/or the content classifier may determine that object names “orchards” and “tree” are related to the keyword “tree”.
- the application file may then be updated to reflect the search results.
- the object list 1202 may be updated with the object names “orchards” and “tree”.
- indications e.g., bold highlighting
- slides e.g., slide 604
- slides that do not show objects with the object names related to the keyword may be filtered from the preview bar 1204 to make it easier and faster for the user to find the location of the objects with the related object names.
- FIG. 13 illustrates a process 1300 for generating the indication of the objects with object names that are related to the keyword search performed on the object list 1202 , in accordance with an embodiment. While process 1300 is described according to a certain sequence, it should be understood that the present disclosure contemplates that the described steps may be performed in different sequences than the sequence illustrated, and certain described steps may be skipped or not performed altogether. In some embodiments, the process 1300 may be implemented at least in part by executing instructions stored in a tangible, non-transitory, computer-readable medium, such as the memory 20 , using processing circuitry, such as the processor core complex 18 . Additionally or alternatively, the process 1300 may be implemented at least in part by circuit connections and/or control logic implemented in an electronic device 10 .
- the process 1300 may begin when the application receives a search request from the user that includes a content keyword to search for in the application file (process block 1302 ). For example, and as described above, the user may search for the content keyword “tree” in the application file.
- the processor core complex 18 may then instruct the application and/or the content classifier to perform a keyword search on one or more object names included in the application file (process block 1304 ).
- the processor core complex 18 may then determine whether there are any objects with object names related to the keyword included in the application file (decision block 1306 ). When no objects with object names are related to the keyword included in the application file, no indication (e.g., empty search result in the object list, no bold highlighting) may be provided to the user (process block 1308 ). When objects with object names are related to the keyword included in the application file, an indication of portions of the application file that include these objects may be provided to the user, as described above (process block 1310 ).
- no indication e.g., empty search result in the object list
- the present technique may automatically provide more accurate and narrow results of searches performed on objects within the object list, may automatically provide better descriptions of the objects included in the application, and may improve accessibility and navigation of the application file for, for example, visually-impaired users.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
Systems, methods, and devices are provided for determining descriptive object names for display on a graphical user interface (GUI). The method may include detecting an input to insert an object into a portion of an application file. The object includes content and has a first metadata name. The method may also include generating a classification label for the object using a content classifier machine learning model, such that the classification label describes the object contents. The method may also further involve updating the first metadata name of the object to a second metadata name that comprises the classification label. Further, the method may also include displaying the second metadata name of the object in an object list of the application file. The object list may enumerate one or more objects of the portion of the application file.
Description
- This application is a continuation of U.S. application Ser. No. 16/426,736, filed May 30, 2019, entitled, “SYSTEMS AND METHODS FOR NAMING OBJECTS BASED ON OBJECT CONTENT,” which claims the benefit of U.S. Provisional Application No. 62/820,078, entitled “SYSTEMS AND METHODS FOR NAMING OBJECTS BASED ON OBJECT CONTENT,” filed on Mar. 18, 2019, which is incorporated herein by reference in its entirety for all purposes.
- The present disclosure relates generally to graphical user interfaces (GUIs) and, more particularly, to determining descriptive object names for display on the GUI.
- This section is intended to introduce the reader to various aspects of art that may be related to various aspects of the present disclosure, which are described and/or claimed below. This discussion is believed to be helpful in providing the reader with background information to facilitate a better understanding of the various aspects of the present disclosure. Accordingly, it should be understood that these statements are to be read in this light, and not as admissions of prior art.
- Electronic devices, such as smartphones and laptops, often include a display that supports a graphical user interface (GUI). The GUI may enable a user to communicate with the electronic device by allowing the user to interact with graphical icons and visual indicators on the display. For example, a user may interact with a presentation application file using the presentation application icon. The user, in particular, may interact with multiple objects within the application to generate the application file. However, in instances when a relatively large number of objects are included in the application file, such as when objects are layered over one another, the user may have difficulty identifying and interacting with the appropriate objects to design the application file as intended.
- A summary of certain embodiments disclosed herein is set forth below. It should be understood that these aspects are presented merely to provide the reader with a brief summary of these certain embodiments and that these aspects are not intended to limit the scope of this disclosure. Indeed, this disclosure may encompass a variety of aspects that may not be set forth below.
- The present disclosure generally relates to determining descriptive object names for display on a graphical user interface (GUI) by using machine learning to identify contents of the object(s) and generating the descriptive name(s) based on the contents. Application files, such as a presentation document, may include a variety of objects that are inserted and placed by the user. For example, a slide may include text object(s) and/or image object(s). To facilitate user interaction with the content of the application file, the application file may include an object list that lists the inserted objects using associated default names, which may be generic. As an example, image objects may be listed under the default name “image”. When a relatively large number of objects are included in the application file, the user may have difficulty identifying objects via the default names displayed in the object list.
- To improve user identification and interaction with objects included within the application file, in some embodiments, once an inserted object in the application file is detected, a machine learning content classifier may detect the contents of the object and may determine an appropriate classification label for the object based on the contents. When the classification label meets confidence and filter criteria, the electronic device may update metadata (e.g., object name) of the object to reflect the classification label. That is, the classification label may be used as the descriptive name. In some embodiments, when the confidence level and the filter criteria are not met, the object metadata may not be modified and the object name may remain the default name. Further, in some embodiments, when the user overrides a classification label generated by the content classifier with a user-defined name, the content classifier may output the user-defined name as the appropriate classification label (e.g., descriptive name) for objects with similar characteristics as the object whose classification label was replaced by the user-defined name.
- Various aspects of this disclosure may be better understood upon reading the following detailed description and upon reference to the drawings in which:
-
FIG. 1 is a block diagram of an electronic device that includes a graphical user interface, in accordance with an embodiment; -
FIG. 2 is a front view of a hand-held device representing an example of the electronic device ofFIG. 1 , in accordance with an embodiment; -
FIG. 3 is a front view of another hand-held device representing another example of the electronic device ofFIG. 1 , in accordance with an embodiment; -
FIG. 4 is a perspective view of a notebook computer representing another example of the electronic device ofFIG. 1 , in accordance with an embodiment; -
FIG. 5 is a front view of a wearable electronic device representing another example of the electronic device ofFIG. 1 , in accordance with an embodiment; -
FIG. 6 is a schematic of an application file having an object list that displays default names for each object in the application file, in accordance with an embodiment; -
FIG. 7 is a schematic of the application file having an object list that displays descriptive names for each object in the application file, in accordance with an embodiment; -
FIG. 8 is a process for determining the descriptive names for each object in the application file ofFIG. 7 based on object content, in accordance with an embodiment; -
FIG. 9 is a schematic of an application file having an object list that displays user-defined names for certain objects in the application file, in accordance with an embodiment; -
FIG. 10 is a process for modifying the descriptive name of the certain objects in the application file ofFIG. 9 based on the user-defined name, in accordance with an embodiment; -
FIG. 11 is a process for automatically updating the descriptive name of the certain objects in the application file ofFIG. 9 using the user-defined name for the certain objects, in accordance with an embodiment; -
FIG. 12 is a schematic of an application file that includes indications of objects with object names related to a keyword search performed on the object list, in accordance with an embodiment; and -
FIG. 13 is a process for generating the indication of the objects with object names related to the keyword search performed on the object list ofFIG. 12 , in accordance with an embodiment. - One or more specific embodiments will be described below. In an effort to provide a concise description of these embodiments, not all features of an actual implementation are described in the specification. It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another. Moreover, it should be appreciated that such a development effort might be complex and time consuming, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure.
- When introducing elements of various embodiments of the present disclosure, the articles “a,” “an,” and “the” are intended to mean that there are one or more of the elements. The terms “comprising,” “including,” and “having” are intended to be inclusive and mean that there may be additional elements other than the listed elements. Additionally, it should be understood that references to “one embodiment” or “an embodiment” of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features.
- The present disclosure generally relates to graphical user interfaces (GUIs) used to visually facilitate communication between a user and an electronic device. In particular, the user may interact with components of an application file using the GUI. For example, in an iWork® application, such as Keynote and Pages, the user may insert and place text objects, image objects, and/or shape objects within the application file to generate and design the application file.
- To facilitate user interaction with the contents of the application file, the application file may include an object list that displays a list of the objects included in at least a portion of the application file. As an example, the object list may include a list of objects present in a slide of a presentation file and may be searched by the user for a particular object. Further, the objects may be listed in the object list using associated default name that are intended to be as descriptive as possible so that the user may easily find particular objects. For example, an image object may have a default name of its object type (e.g., “image”) and a text object may have a default name of its object type (e.g., “text”).
- However, when the application file or the portion of the application file includes a relatively large number of objects, the object list may no longer assist the user in easily and quickly identifying a specific object. In particular, when default names are used to describe the objects in the object list, the default name may no longer be descriptive enough to efficiently identify the specific object within the application file. In other words, a search of the object list may result in multiple objects with a similar default name. For example, a user that may search “image” in the object list may receive a result of all image objects included within the application file or the portion of the application file.
- Moreover, visually-impaired users may use a voiceover application to identify objects within the application file. The voiceover application may voice the metadata (e.g., name) of the object that the user hovers over or selects within the application file and/or the object list. However, when the application file includes multiple objects that have similar default names, as described above, the default name may no longer be descriptive enough to efficiently describe the object to the visually-impaired user.
- Accordingly, the present disclosure provides systems and techniques to determine descriptive object names for efficient identification of objects within an application file. In some embodiments, the default name of each object may be made descriptive by updating the default name to a name based a description of the object contents (e.g., descriptive name). In particular, an electronic device implementing the application may detect an input to insert an object into the application file. The input may include copying and pasting, collaborations between application users, importing of an object without a name into the application file, and the like. Once the input is received, a machine learning content classifier may detect the contents of the object and determine an appropriate classification label for the object based on the contents.
- In some embodiments, the content classifier may determine whether the classification label describes the contents of the object with high enough accuracy and whether to filter out the classification label from use, for example, because the label is derogatory or otherwise undesirable. When the accuracy (e.g., confidence level) and the filter criteria are met, the electronic device may update metadata (e.g., name metadata) of the object to reflect the classification label. The updated metadata may be stored in the application file for use later and the classification label may be displayed as the descriptive object name, replacing the default name.
- In some embodiments, when the confidence level and/or the filter criteria are not met, the electronic device may refrain from modifying the object metadata, resulting in the object name remaining the default name. Additionally or alternatively, when the user overrides the descriptive name for a certain object with a user-defined name, the content classifier may use the user-defined name when generating descriptive names for objects with similar characteristics as that of the certain object. Further, if the user removes the user-defined name from use in the object list, the object name may be restored to the classification label and/or to the default name. Additional details with regard to providing descriptive object names for efficient identification of objects within the application file using the embodiments described herein are detailed below with reference to
FIGS. 1-13 . - With this in mind, an embodiment of an
electronic device 10 that includes a graphical user interface (GUI) is shown inFIG. 1 . As will be described in more detail below, theelectronic device 10 may be any suitable electronic device, such as a computer, a mobile phone, a portable media device, a tablet, a television, a virtual-reality headset, a vehicle dashboard, and the like. Thus, it should be noted thatFIG. 1 is merely one example of a particular implementation and is intended to illustrate the types of components that may be present in theelectronic device 10. - In the depicted embodiment, the
electronic device 10 includes aradio frequency system 12, one ormore input devices 14,local memory 16, aprocessor core complex 18, one or more mainmemory storage devices 20, apower source 22, one or more input/output ports 24, and anelectronic display 26. The various components described inFIG. 1 may include hardware elements (e.g., circuitry), software elements (e.g., a tangible, non-transitory computer-readable medium storing instructions), or a combination of both hardware and software elements. It should be noted that the various depicted components may be combined into fewer components or separated into additional components. For example, thelocal memory 16 and a mainmemory storage device 20 may be included in a single component. - As depicted, the
processor core complex 18 is operably coupled with thelocal memory 16 and the mainmemory storage device 20. Thus, theprocessor core complex 18 may execute instruction stored in thelocal memory 16 and/or the mainmemory storage device 20 to perform operations, such as instructing theelectronic display 26 to display application icons that the user may interact with. As such, theprocessor core complex 18 may include one or more general purpose microprocessors, one or more application specific processors (ASICs), one or more field programmable logic arrays (FPGAs), or any combination thereof. - In addition to the instructions, the
local memory 16 and/or the mainmemory storage device 20 may store data to be processed by theprocessor core complex 18. Thus, in some embodiments, the local memory and/or the mainmemory storage device 20 may include one or more tangible, non-transitory, computer-readable mediums. For example, thelocal memory 16 may include random access memory (RAM) and the mainmemory storage device 20 may include read only memory (ROM), rewritable non-volatile memory such as flash memory, hard drives, optical discs, and the like. - As depicted, the
processor core complex 18 may be operably coupled with theradio frequency system 12. Theradio frequency system 12 may facilitate wireless communication of data with another electronic device and/or a network. For example, theradio frequency system 12 may enable theelectronic device 10 to communicatively couple to a personal area network (PAN), such as a Bluetooth network, a local area network (LAN), such as an 802.11x Wi-Fi network, and/or a wide area network (WAN), such as a fourth-generation wireless technology (4G), 5G, or LTE cellular network. In other words, theradio frequency system 12 may enable wireless communication of data using various communication protocols and/or at various output powers (e.g., strength of transmitted analog electrical signals). - Additionally, as depicted, the
processor core complex 18 is also operably coupled with the I/O ports 24. In some embodiments, the I/O ports 24 may enable theelectronic device 10 to interface with other electronic devices. For example, a portable storage device may be connected to an I/O port 24, thereby enabling theprocessor core complex 18 to communicate data with a portable storage device. - Further, as depicted, the
processor core complex 18 is operably coupled to thepower source 22. In some embodiments, thepower source 22 may provide power to one or more components in theelectronic device 10, such as theprocessor core complex 18 and/or theradio frequency system 12. Thus, thepower source 22 may include any suitable energy source, such as a rechargeable lithium polymer (Li-poly) battery and/or an alternating current (AC) power converter. - Furthermore, as depicted, the
processor core complex 18 is operably coupled with theinput devices 14. In some embodiments, theinput device 14 may facilitate user interaction with theelectronic device 10, for example, by receiving user inputs. Thus, theinput devices 14 may include a button, a keyboard, a mouse, a trackpad, and/or the like. Additionally, in some embodiments, theinput devices 14 may include touch-sensing components in theelectronic display 26. In such embodiments, the touch-sensing components may receive user inputs by detecting occurrence and/or position of an object touching the surface of theelectronic display 26. - In addition to enabling user inputs, the
electronic display 26 may display image frames, such as a graphical user interface (GUI) for an operating system, an application interface, a still image, or video content. As depicted, theelectronic display 26 is operably coupled to theprocessor core complex 18. In this manner, theelectronic display 26 may display image frames based at least in part on image data received from theprocessor core complex 18. - As mentioned previously, a user may interact with applications displayed on the GUI. In particular, the applications may include an object list that displays names of the objects inserted and placed by the user within an application file. Further, a voiceover application may voice the names of the objects inserted and placed by the user within the application file. Once the object is inserted in the application file, a machine learning content classifier may detect the contents of the object and determine an appropriate classification label for the object based on the contents. The default name of each object may be made more descriptive by updating the default names to a descriptive name based on the classification label.
- As described above, the
electronic device 10 may be any suitable electronic device. To help illustrate, one example of a suitableelectronic device 10, specifically a handheldelectronic device 10A, is shown inFIG. 2 . In some embodiments, the handheldelectronic device 10A may be a portable phone, a media player, a personal data organizer, a handheld game platform, and/or the like. For example, the handheldelectronic device 10A may be a smart phone, such as any iPhone® model available from Apple Inc. - As depicted, the handheld
electronic device 10A includes an enclosure 34 (e.g., housing). In some embodiments, theenclosure 34 may protect interior components from physical damage and/or shield them from electromagnetic interference. Thus, a radio frequency system 12 (not shown) may also be enclosed within theenclosure 34 and internal to the handheldelectronic device 10A. In some examples, theenclosure 34 may operate as part of the one or more antennas of theradio frequency system 12. - Additionally, as depicted, the
enclosure 34 may surround theelectronic display 26. In the depicted embodiment, theelectronic display 26 is displaying a graphical user interface (GUI) 36 having an array oficons 38. By way of example, when anicon 38 is selected either by aninput device 14 or a touch sensing component of theelectronic display 26, an application program may launch, such as a presentation application. - Furthermore, as depicted,
input devices 14 open through theenclosure 34. As described above, theinput devices 14 may enable a user to interact with the handheldelectronic device 10A. For example, theinput devices 14 may enable the user to activate or deactivate the handheldelectronic device 10A, navigate a user interface to a home screen, navigate a user interface to a user-configurable application screen, activate a voice-recognition feature, provide volume control, and/or toggle between vibrate and ring modes. As depicted, the I/O ports 24 also open through theenclosure 34. In some embodiments, the I/O ports 24 may include, for example, a multi-function connector port (e.g., Lightning port) to connect to external devices. - To further illustrate, another example of a suitable
electronic device 10, specifically a tabletelectronic device 10B is shown inFIG. 3 . For example, the tabletelectronic device 10B may be any iPad® model available from Apple Inc. A further example of a suitableelectronic device 10, specifically a computer 10C, is shown inFIG. 4 . For example, the computer 10C may be any Macbook® or iMac® model available from Apple Inc. Another example of a suitableelectronic device 10, specifically a watch 10D, is shown inFIG. 5 . For example, the watch 10D may be any Apple Watch® model available from Apple Inc. - As depicted, the tablet
electronic device 10B, the computer 10C, and the watch 10D each also include anelectronic display 26,input devices 14, I/O ports 24, and anenclosure 34. Thus, in some embodiments, theenclosure 34 may enclose aradio frequency system 12 in the tabletelectronic device 10B, the computer 10C, and/or the watch 10D to facilitate wireless communication of data with other electronic devices and/or a network. - To help illustrate determining descriptive object names for display on the GUI,
FIG. 6 depicts aGUI 600 rendering an application file having an object list that displays default names for each object in the application file, in accordance with an embodiment. In particular, the application file may be a presentation file that, for example, includes three presentation slides 602, 604, 606. The user may choose aslide 606 for modification, as shown by the bolded indication. For example, the user may insert animage object 608, ashape object 610, and/or atext object 612 into theslide 606. Although the application file is depicted as a presentation file, it should be appreciated that the application file may be any type of file, such as a word processing file or a spreadsheet file. - The
slide 606 may also include anobject list 614 that displays a list of objects (e.g., 608, 610, 612) within theslide 606. As shown, theobject list 614 may display default names for the objects (e.g., 608, 610, 612) within theslide 606, such that the default names are as descriptive as possible for easy and quick identification by the user. For example, the image objects (e.g., 608) may be listed under the name “image” 616, the shape objects (e.g., 610) under the name of their shape (e.g., “txt rectangle” 706), and the text objects (e.g., 612) under the name of “text” 620. Additionally or alternatively, when similar object types are included within theslide 606, theobject list 614 may include sequential objects names, such as image1, image2, and the like. Further, when an object, such as theimage object 608, is selected by the user, the associatedobject name 628 may be highlighted in theobject list 614 to improve user interaction with the application content. - The
object list 614 may also improve the ability of the user to easily and quickly identify and interact with the application content by enabling the user to perform a search within theobject list 614 for a particular object. For example, the user may search for the keyword “image”, which may generate a result that includes objects named “image”. However, when multiple objects of the same object type or other similar characteristics are included within theslide 606, the search result may fail to provide accurate and narrowed search results. As an example, when the user searches for “image”, the object list may display all image objects 608, 622, 624 on theslide 606 and their associatedobject names slide 606, the voiceover application may not provide an accurate and identifying description of the chosen object. - The default object names may be updated to a more descriptive name that facilitates the user's interaction with the application contents.
FIG. 7 depicts aGUI 700 rendering an application file having anobject list 702 that displays descriptive names for the objects based on the respective object contents, in accordance with an embodiment. In particular, the application may detect one or more inputs to insert an object into the application file. For example, the user may copy and paste or import theobject 608 into the application file. - Once the application file receives the input, a content classifier may be applied to the
object 608 to determine the contents of theobject 608. The content classifier may be built into the operating system of theelectronic device 10. Further, the content classifier may be trained using a set of object contents considered to be representative of classification labels a designer may want to display on the GUI. For example, the content classifier may be fed images of trees that adequately represent the classification label “tree.” In addition, a subset of classification labels or terms in the classification labels that are deemed appropriate may be preselected and used to train the content classifier to recognize object content conforming to such approved classification labels. As such, the output of the content classifier may be accurate and may only include appropriate/desired classification labels. In some embodiments, the content classifier may applied to theobject 608 as soon as theobject 608 is inserted into the application file or once a group of other objects (e.g., 622, 624) that also have been inserted into the application file. - The content classifier may determine an appropriate classification label for the
object 608 based on the contents within theobject 608. For example, the content classifier may determine that theobject 608 includes a palm tree and thus, may output classification labels of tree and/or palm tree. Before outputting the classification label to the application file, the content classifier may determine whether the classification label(s) describes the contents of theobject 608 with high enough accuracy (e.g., confidence). For example, the content classifier may determine an 80% confidence level for the classification label “tree” and a 30% confidence level for the classification label “palm tree”. The content classifier may select, as the output, the classification label that has the highest confidence level when multiple classification labels have been determined and/or may select the classification label whose confidence level is greater than or equal to a predetermined confidence threshold. As such, the content classifier may provide classification labels of greater accuracy and/or specificity. - For text objects 612, the content classifier may use keywords from the text and/or associations with other objects to determine classification label(s) that best describes the subject of the text. For example, the content classifier may evaluate proper nouns and verbs within the text. As another example, the content classifier may evaluate metadata (e.g., name, caption) of objects associated with the
text object 612 to determine the classification label(s) that best describes the subject of the text. - For other objects, such as videos, the content classifier may perform an image classification on one or more frames of the video to determine a classification label that appropriately describes the contents of the video. As an example, when a first frame of the video includes a waterfall and a second frame of the video includes a cliff, the content classifier may output a classification label of “landscape.” Regardless of the object type, the content classifier may determine a confidence for each generated classification label and may output the appropriate classification label for the object.
- Once the classification label is generated, the
electronic device 10 may update metadata (e.g., name metadata) of theobject 608 to reflect the classification label. In particular, the classification label may be stored in the application file and the classification label may be displayed as the descriptive object name. For example, the content classifier may output the classification label “tree” as the most appropriate classification label for theobject 608 and the object name may be updated to “tree”. As shown, the updated object name for theobject 608 may be included in theobject list 702. - In addition, the content classifier may output classification labels for the
other objects -
FIG. 8 summarizes aprocess 800 for determining the descriptive names for each object in the application file based on the object content, in accordance with an embodiment. Whileprocess 800 is described according to a certain sequence, it should be understood that the present disclosure contemplates that the described steps may be performed in different sequences than the sequence illustrated, and certain described steps may be skipped or not performed altogether. In some embodiments, theprocess 800 may be implemented at least in part by executing instructions stored in a tangible, non-transitory, computer-readable medium, such as thememory 20, using processing circuitry, such as theprocessor core complex 18. Additionally or alternatively, theprocess 800 may be implemented at least in part by circuit connections and/or control logic implemented in anelectronic device 10. - The
process 800 may be initiated when theprocessor core complex 18 of theelectronic device 10 detects an input to insert the object (e.g., 608) in a portion of an application file (e.g., the slide 606) (process block 802). As previously discussed, the input may include the user copying and pasting theobject 608 into the application file and/or importing theobject 608 into the application file. Theprocessor core complex 18 may subsequently classify contents of theobject 608 by instructing the application to apply the content classifier to theobject 608 as soon as theobject 608 is inserted into the application file or with a group of objects included in the application file (process block 804). The content classifier may determine one or more classification labels that describe the contents of theobject 608 along with a confidence level for each classification label. - The
processor core complex 18 may also instruct the content classifier to filter the one or more classification labels according to one or more predetermined filters stored in the application or content classifier or according to one or more user-defined filters (process block 806). For example, the filters may remove classification labels related to politics or that are derogatory. Theprocessor core complex 18 may subsequently instruct the content classifier to determine whether a classification label determined by the content classifier has passed the confidence level and filter criteria (decision block 808). - When no classification labels have passed the criteria, the content classifier may be reapplied to the object (e.g., 608) to determine another set of classification labels. In some embodiments, when no classification labels have passed the criteria, the default name may be used to populate the
object list 702 rather than a descriptive name based on the classification label. When a classification label has passed the criteria, theprocessor core complex 18 may update the metadata of the object based on the classification label by instructing the application file to store the classification label as the object name (process block 810). Once the object name has been updated, the classification label may be displayed as the descriptive name in the object list 702 (process block 812). - The user may choose to override one or more classification labels based on personal preference and instead use a user-defined name for objects associated with the one or more classification labels.
FIG. 9 depicts aGUI 900 rendering an application file that has anobject list 902 which displays user-defined names, in accordance with an embodiment. In particular, the user may prefer using a user-defined name for certain objects or object types as compared to the default name or the descriptive name generated by the content classifier. When the user chooses to override the descriptive name using the user-defined name, the content classifier may learn the user's preference and automatically output the user-defined metadata for similar objects instead of the content-based classification label. - As an example, the user may prefer to use the description “rectangle” to describe the shape objects (e.g., 610) used within the
slide 606. When the user inserts anothershape object 904 into the application file, the content classifier may use the description “rectangle” to describe the newly insertedshape object 904. As shown, theobject list 902 may include the object name “Rectangle 4” to describe theshape object 904. - In some embodiments, the user-defined name may be used even when the object (e.g., 904) is exported from the application file and/or when the content classifier version is updated, such as with an update of the application supporting the application file. Further, if the user elects to remove the user-defined names from use in the
object list 902 and/or use in the voiceover application, the classification labels for each object may be restored, if available. In addition, if the user elects to remove the classification labels from use in theobject list 902 and/or use in the voiceover application, the default names for each object may be restored. -
FIG. 10 depicts aprocess 1000 for determining the descriptive name of the objects based on the user-defined name for the object (e.g., 610, 904), in accordance with an embodiment. While theprocess 1000 is described according to a certain sequence, it should be understood that the present disclosure contemplates that the described steps may be performed in different sequences than the sequence illustrated, and certain described steps may be skipped or not performed altogether. In some embodiments, theprocess 1000 may be implemented at least in part by executing instructions stored in a tangible, non-transitory, computer-readable medium, such as thememory 20, using processing circuitry, such as theprocessor core complex 18. Additionally or alternatively, theprocess 1000 may be implemented at least in part by circuit connections and/or control logic implemented in anelectronic device 10. - The
process 1000 may begin when the application file receives a user input to change metadata (e.g., name metadata) of an object to the user-defined name, as described above (process block 1002). For example, the user may elect to rename the shape objects 610, 904 with the name “rectangle”. Upon receiving the user input to change the object name metadata, theprocessor core complex 18 may instruct the application to modify the object name to the user-defined name (process block 1004). - In addition,
FIG. 11 depicts aprocess 1100 for automatically updating the name of the object (e.g., 904) using the user-defined name for objects (e.g., 610, 904) of a similar type, in accordance with an embodiment. Whileprocess 1100 is described according to a certain sequence, it should be understood that the present disclosure contemplates that the described steps may be performed in different sequences than the sequence illustrated, and certain described steps may be skipped or not performed altogether. In some embodiments, theprocess 1100 may be implemented at least in part by executing instructions stored in a tangible, non-transitory, computer-readable medium, such as thememory 20, using processing circuitry, such as theprocessor core complex 18. Additionally or alternatively, theprocess 1100 may be implemented at least in part by circuit connections and/or control logic implemented in anelectronic device 10. - Generally, the
process 1100 may be initiated when the application receives an input to add a new object that has similar characteristics as an object whose metadata, and thus descriptive name, has been modified to a user-defined name (process block 1102). For example, the user may indicate that he/she wants to insert theshape object 904, which has similar characteristics (e.g., object content, shape, color) to other shape objects (e.g., 610) in the application file. Theprocessor core complex 18 may then instruct the content classifier to determine the user-defined name to replace the name of the new object (e.g., 904) (process block 1104). In particular, the content classifier may determine the objects (e.g., 610) that are to the new object (e.g., 904) and use the user-defined name associated with these object (e.g., 610) to determine the appropriate user-defined name (e.g., “rectangle”) for the new object (e.g., 904). Theprocessor core complex 18 may then instruct the application to insert the new object (e.g., 904) into the application file with metadata that is updated with the user-defined name (process block 1106). - To further facilitate quick and simple identification of objects in the application file by the user, the object list may be searchable and the objects that fit the results may be indicated in the application file.
FIG. 12 depicts aGUI 1200 rendering an application file that includes indications of objects that have object names related to a keyword searched in theobject list 1202, in accordance with an embodiment. As shown, the user may perform a search in theobject list 1202, such as for the keyword “tree”. The application and/or the content classifier may analyze the names of each object included within the application file or a portion of the application file and may determine the object names that are related to the keyword. For example, the application and/or the content classifier may determine that object names “orchards” and “tree” are related to the keyword “tree”. The application file may then be updated to reflect the search results. For example, theobject list 1202 may be updated with the object names “orchards” and “tree”. Further, indications (e.g., bold highlighting) may be generated around the slide and/or the objects that are associated with the related object names. Additionally or alternatively, in some embodiments, slides (e.g., slide 604) that do not show objects with the object names related to the keyword may be filtered from thepreview bar 1204 to make it easier and faster for the user to find the location of the objects with the related object names. -
FIG. 13 illustrates aprocess 1300 for generating the indication of the objects with object names that are related to the keyword search performed on theobject list 1202, in accordance with an embodiment. Whileprocess 1300 is described according to a certain sequence, it should be understood that the present disclosure contemplates that the described steps may be performed in different sequences than the sequence illustrated, and certain described steps may be skipped or not performed altogether. In some embodiments, theprocess 1300 may be implemented at least in part by executing instructions stored in a tangible, non-transitory, computer-readable medium, such as thememory 20, using processing circuitry, such as theprocessor core complex 18. Additionally or alternatively, theprocess 1300 may be implemented at least in part by circuit connections and/or control logic implemented in anelectronic device 10. - The
process 1300 may begin when the application receives a search request from the user that includes a content keyword to search for in the application file (process block 1302). For example, and as described above, the user may search for the content keyword “tree” in the application file. Theprocessor core complex 18 may then instruct the application and/or the content classifier to perform a keyword search on one or more object names included in the application file (process block 1304). Theprocessor core complex 18 may then determine whether there are any objects with object names related to the keyword included in the application file (decision block 1306). When no objects with object names are related to the keyword included in the application file, no indication (e.g., empty search result in the object list, no bold highlighting) may be provided to the user (process block 1308). When objects with object names are related to the keyword included in the application file, an indication of portions of the application file that include these objects may be provided to the user, as described above (process block 1310). - As such, the present technique may automatically provide more accurate and narrow results of searches performed on objects within the object list, may automatically provide better descriptions of the objects included in the application, and may improve accessibility and navigation of the application file for, for example, visually-impaired users.
- The specific embodiments described above have been shown by way of example, and it should be understood that these embodiments may be susceptible to various modifications and alternative forms. It should be further understood that the claims are not intended to be limited to the particular forms disclosed, but rather to cover all modifications, equivalents, and alternatives falling within the spirit and scope of this disclosure.
Claims (20)
1. A tangible, non-transitory computer-readable medium configured to store a program for determining object names based on object content, the program comprising instructions to:
detect an input to insert an object into a slide of a presentation file via graphical user interface (GUI) of an application, wherein the object includes content;
in response to detecting the input into the slide, insert the object into the slide, the object having a metadata name comprising an indication of a type of the object, and provide the object to a content classifier;
receive a classification label for the object from the content classifier, wherein:
when the object comprises a text, the classification label comprises a description of subject matter of the text based upon an evaluation of a meaning of one or more words of the text, and
update in the application, the metadata name of the object to an updated metadata name, based upon the classification label; and
display, in lieu of the metadata name, the updated metadata name of the object in an object list of the presentation file, wherein the object list enumerates a plurality of objects present within the slide.
2. The tangible, non-transitory computer-medium of claim 1 , comprising instructions to receive the classification label for the object from the content classifier, wherein when the object comprises a video, the classification label is based on an evaluation of one or more frames of the video.
3. The tangible, non-transitory computer-medium of claim 1 , comprising instructions to receive the classification label for the object from the content classifier, wherein when the object comprises an image, the classification label is based on subject matter contained in the image.
4. The tangible, non-transitory computer-readable medium of claim 1 , comprising instructions to receive a confidence level of the classification label from the content classifier.
5. The tangible, non-transitory computer-readable medium of claim 4 , wherein the metadata name of the object is updated only after determining the confidence level of the classification label is greater than or equal to an accuracy threshold.
6. The tangible, non-transitory computer-readable medium of claim 1 , comprising instructions to:
receive an additional input to modify the metadata name to a user-defined name; and
update the metadata name to the user-defined name.
7. The tangible, non-transitory computer-readable medium of claim 1 , comprising instructions to filter the classification label according to one or more predefined filters, one or more user-defined filters, or any combination thereof.
8. The tangible, non-transitory computer-readable medium of claim 1 , wherein the classification label is based at least in part on a presentation file association between the object and one or more additional objects in the slide, the presentation file association indicating that the one or more additional objects provide context to the object.
9. A method, comprising:
detecting an input to insert an object into a slide of a presentation file via graphical user interface (GUI) of an application, wherein the object includes content;
in response to detecting the input into the slide,
inserting the object into the slide, the object having a metadata name comprising an indication of a type of the object, and
providing the object to a content classifier;
receiving a classification label for the object from the content classifier, wherein:
when the object comprises a text, the classification label comprises a description of subject matter of the text based upon an evaluation of a meaning of one or more words of the text, and
updating in the application, the metadata name of the object to an updated metadata name, based upon the classification label; and
displaying, in lieu of the metadata name, the updated metadata name of the object in an object list of the presentation file, wherein the object list enumerates a plurality of objects present within the slide.
10. The method of claim 9 , comprising:
receiving a search request from a user, wherein the search request comprises a content keyword to search for in the presentation file; and
performing a keyword search of the updated metadata name of each of the plurality of objects in the presentation file to identify a set of the plurality of objects associated with the content keyword; and
determining whether the set of the plurality of objects matches the content keyword.
11. The method of claim 10 , comprising providing an additional indication in response to determining the set of the plurality of objects matches the content keyword, wherein the additional indication comprises outlining the set of the plurality of objects.
12. The method of claim 9 , comprising filtering the classification label according to one or more predefined filters, one or more user-defined filters, or a combination thereof.
13. The method of claim 12 , wherein the one or more predefined filters, the one or more user-defined filters, or a combination thereof comprises filtering out derogatory language, metadata names previously overridden, or any combination thereof.
14. The method of claim 9 , wherein the classification label is based at least in part on an association between the object and one or more additional objects in the slide, the one or more additional objects comprising a second object with a different object type than the object.
15. An electronic device, comprising:
a graphical user interface (GUI) configured to display a slide of a presentation file;
a processor configured to execute instructions to:
detect an input to insert an object into the slide via the GUI of an application, wherein the object includes content;
in response to detecting the input, insert the object into the slide, the object having a metadata name comprising an indication of a type of the object, and provide the object to a content classifier;
receive a classification label for the object from the content classifier, wherein:
when the object comprises a text, the classification label comprises a description of subject matter of the text based upon an evaluation of a meaning of one or more words of the text, and
update in the application, the metadata name of the object to an updated metadata name, based upon the classification label; and
display, in lieu of the metadata name, the updated metadata name of the object in an object list of the presentation file, wherein the object list enumerates a plurality of objects present within the slide.
16. The electronic device of claim 15 , wherein the classification label is based at least in part on an association between the object and one or more additional objects in the slide, independent of a user input classifying the one or more additional objects.
17. The electronic device of claim 16 , wherein when the one or more additional objects comprise an image, the classification label is based on subject matter contained in the image.
18. The electronic device of claim 16 , wherein the object comprises an image object, a video object, a shape object, or any combination thereof.
19. The electronic device of claim 15 , wherein the classification label is based upon the metadata name of the object, a caption associated with the object, or both.
20. The electronic device of claim 15 , wherein the evaluation of the meaning of the one or more words of the text comprises an identification and analysis of nouns, verbs, or both, of the one or more words.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/201,549 US20230297609A1 (en) | 2019-03-18 | 2023-05-24 | Systems and methods for naming objects based on object content |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201962820078P | 2019-03-18 | 2019-03-18 | |
US16/426,736 US11720621B2 (en) | 2019-03-18 | 2019-05-30 | Systems and methods for naming objects based on object content |
US18/201,549 US20230297609A1 (en) | 2019-03-18 | 2023-05-24 | Systems and methods for naming objects based on object content |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/426,736 Continuation US11720621B2 (en) | 2019-03-18 | 2019-05-30 | Systems and methods for naming objects based on object content |
Publications (1)
Publication Number | Publication Date |
---|---|
US20230297609A1 true US20230297609A1 (en) | 2023-09-21 |
Family
ID=72515982
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/426,736 Active US11720621B2 (en) | 2019-03-18 | 2019-05-30 | Systems and methods for naming objects based on object content |
US18/201,549 Pending US20230297609A1 (en) | 2019-03-18 | 2023-05-24 | Systems and methods for naming objects based on object content |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/426,736 Active US11720621B2 (en) | 2019-03-18 | 2019-05-30 | Systems and methods for naming objects based on object content |
Country Status (1)
Country | Link |
---|---|
US (2) | US11720621B2 (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11720621B2 (en) * | 2019-03-18 | 2023-08-08 | Apple Inc. | Systems and methods for naming objects based on object content |
EP4078603A1 (en) * | 2019-12-18 | 2022-10-26 | Koninklijke Philips N.V. | A co-training framework to mutually improve concept extraction from clinical notes and medical image classification |
US11762934B2 (en) * | 2021-05-11 | 2023-09-19 | Oracle International Corporation | Target web and social media messaging based on event signals |
USD1009075S1 (en) | 2021-12-21 | 2023-12-26 | Igt | Display screen or a portion thereof with a graphical user interface |
Citations (169)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030167402A1 (en) * | 2001-08-16 | 2003-09-04 | Stolfo Salvatore J. | System and methods for detecting malicious email transmission |
US20050027664A1 (en) * | 2003-07-31 | 2005-02-03 | Johnson David E. | Interactive machine learning system for automated annotation of information in text |
US20060041564A1 (en) * | 2004-08-20 | 2006-02-23 | Innovative Decision Technologies, Inc. | Graphical Annotations and Domain Objects to Create Feature Level Metadata of Images |
US20070094600A1 (en) * | 2005-10-24 | 2007-04-26 | International Business Machines Corporation | Automatic 3d object generation and deformation for representation of data files based on taxonomy classification |
US20070143284A1 (en) * | 2005-12-09 | 2007-06-21 | Lee Chang K | Apparatus and method for constructing learning data |
US20070185876A1 (en) * | 2005-02-07 | 2007-08-09 | Mendis Venura C | Data handling system |
US20070217701A1 (en) * | 2005-08-12 | 2007-09-20 | Che-Bin Liu | Systems and Methods to Convert Images into High-Quality Compressed Documents |
US20080270462A1 (en) * | 2007-04-24 | 2008-10-30 | Interse A/S | System and Method of Uniformly Classifying Information Objects with Metadata Across Heterogeneous Data Stores |
US20090006285A1 (en) * | 2007-06-29 | 2009-01-01 | Microsoft Corporation | Content-based tagging of rss feeds and e-mail |
US20090055242A1 (en) * | 2007-08-24 | 2009-02-26 | Gaurav Rewari | Content identification and classification apparatus, systems, and methods |
US7849141B1 (en) * | 2001-06-14 | 2010-12-07 | Apple Inc. | Training a computer storage system for automatic filing of data using graphical representations of storage locations |
US20110145327A1 (en) * | 2009-06-19 | 2011-06-16 | Moment Usa, Inc. | Systems and methods of contextualizing and linking media items |
US20110270834A1 (en) * | 2010-04-28 | 2011-11-03 | Microsoft Corporation | Data Classifier |
US8132099B2 (en) * | 2007-10-11 | 2012-03-06 | International Business Machines Corporation | Method for obtaining accessibility information, computer program and accessibility information device |
US20120093354A1 (en) * | 2010-10-19 | 2012-04-19 | Palo Alto Research Center Incorporated | Finding similar content in a mixed collection of presentation and rich document content using two-dimensional visual fingerprints |
US20120233110A1 (en) * | 2009-10-31 | 2012-09-13 | Helen Balinsky | Determining Probability Than An Object Belongs To A Topic Using Sample Items Selected From Object And Probability Distribution Profile Of The Topic |
US20120254191A1 (en) * | 2011-04-01 | 2012-10-04 | Yahoo! Inc. | Method and system for concept sumarization |
US20120278705A1 (en) * | 2010-01-18 | 2012-11-01 | Yang sheng-wen | System and Method for Automatically Extracting Metadata from Unstructured Electronic Documents |
US20120314941A1 (en) * | 2011-06-13 | 2012-12-13 | Microsoft Corporation | Accurate text classification through selective use of image data |
US8473981B1 (en) * | 2011-06-30 | 2013-06-25 | Google Inc. | Augmenting metadata of digital media objects using per object classifiers |
US8478052B1 (en) * | 2009-07-17 | 2013-07-02 | Google Inc. | Image classification |
US20130272575A1 (en) * | 2011-11-01 | 2013-10-17 | Intel Corporation | Object detection using extended surf features |
US20140092990A1 (en) * | 2012-10-01 | 2014-04-03 | Google Inc. | System and method for optimizing videos |
US20140096092A1 (en) * | 2011-03-20 | 2014-04-03 | William J. Johnson | System and Method for Indirect Manipulation of User Interface Object(s) |
US20140146053A1 (en) * | 2012-11-29 | 2014-05-29 | International Business Machines Corporation | Generating Alternative Descriptions for Images |
US20140149376A1 (en) * | 2011-06-23 | 2014-05-29 | Cyber Ai Entertainment Inc. | System for collecting interest graph by relevance search incorporating image recognition system |
US20140201113A1 (en) * | 2013-01-15 | 2014-07-17 | International Business Machines Corporation | Automatic Genre Determination of Web Content |
US8843424B2 (en) * | 2009-04-01 | 2014-09-23 | Sony Corporation | Device and method for multiclass object detection |
US9025811B1 (en) * | 2013-01-02 | 2015-05-05 | Google Inc. | Performing image similarity operations using semantic classification |
US20150178383A1 (en) * | 2013-12-20 | 2015-06-25 | Google Inc. | Classifying Data Objects |
US9111579B2 (en) * | 2011-11-14 | 2015-08-18 | Apple Inc. | Media editing with multi-camera media clips |
US20150242525A1 (en) * | 2014-02-26 | 2015-08-27 | Pixured, Inc. | System for referring to and/or embedding posts within other post and posts within any part of another post |
US9141883B1 (en) * | 2015-05-11 | 2015-09-22 | StradVision, Inc. | Method, hard negative proposer, and classifier for supporting to collect hard negative images using a similarity map |
US20150309987A1 (en) * | 2014-04-29 | 2015-10-29 | Google Inc. | Classification of Offensive Words |
US20160034425A1 (en) * | 2014-07-31 | 2016-02-04 | Linkedln Corporation | Providing recommendations for electronic presentations based on contextual and behavioral data |
US20160065605A1 (en) * | 2014-08-29 | 2016-03-03 | Linkedin Corporation | Spam detection for online slide deck presentations |
US20160092730A1 (en) * | 2014-09-30 | 2016-03-31 | Abbyy Development Llc | Content-based document image classification |
US20160098645A1 (en) * | 2014-10-02 | 2016-04-07 | Microsoft Corporation | High-precision limited supervision relationship extractor |
US20160147434A1 (en) * | 2014-11-25 | 2016-05-26 | Samsung Electronics Co., Ltd. | Device and method of providing handwritten content in the same |
US20160232456A1 (en) * | 2015-02-06 | 2016-08-11 | Box, Inc. | Method and system for implementing machine learning analysis of documents |
US20160269334A1 (en) * | 2015-03-11 | 2016-09-15 | Microsoft Technology Licensing, Llc | Tags in communication environments |
US9449080B1 (en) * | 2010-05-18 | 2016-09-20 | Guangsheng Zhang | System, methods, and user interface for information searching, tagging, organization, and display |
US9495614B1 (en) * | 2015-02-27 | 2016-11-15 | Google Inc. | Verifying labels for images using image recognition |
US20160342895A1 (en) * | 2015-05-21 | 2016-11-24 | Baidu Usa Llc | Multilingual image question answering |
US20160364419A1 (en) * | 2015-06-10 | 2016-12-15 | Blackbird Technologies, Inc. | Image and text data hierarchical classifiers |
US20170017696A1 (en) * | 2015-07-14 | 2017-01-19 | Microsoft Technology Licensing, Llc | Semantic object tagging through name annotation |
US20170052946A1 (en) * | 2014-06-06 | 2017-02-23 | Siyu Gu | Semantic understanding based emoji input method and device |
US20170091153A1 (en) * | 2015-09-29 | 2017-03-30 | Apple Inc. | Device, Method, and Graphical User Interface for Providing Handwriting Support in Document Editing |
US9613296B1 (en) * | 2015-10-07 | 2017-04-04 | GumGum, Inc. | Selecting a set of exemplar images for use in an automated image object recognition system |
US20170124067A1 (en) * | 2015-11-04 | 2017-05-04 | Kabushiki Kaisha Toshiba | Document processing apparatus, method, and program |
US20170132526A1 (en) * | 2015-11-11 | 2017-05-11 | Adobe Systems Incorporated | Structured Knowledge Modeling and Extraction from Images |
US20170132498A1 (en) * | 2015-11-11 | 2017-05-11 | Adobe Systems Incorporated | Structured Knowledge Modeling, Extraction and Localization from Images |
US20170140297A1 (en) * | 2015-11-17 | 2017-05-18 | International Business Machines Corporation | Generating efficient sampling strategy processing for business data relevance classification |
US20170140250A1 (en) * | 2015-11-13 | 2017-05-18 | Microsoft Technology Licensing, Llc | Content file image analysis |
US20170140051A1 (en) * | 2015-11-16 | 2017-05-18 | Facebook, Inc. | Ranking and Filtering Comments Based on Labelling |
US20170177584A1 (en) * | 2015-12-17 | 2017-06-22 | The Nielsen Company (Us), Llc | Media names matching and normalization |
US20170193324A1 (en) * | 2015-12-31 | 2017-07-06 | Nokia Technologies Oy | Method and apparatus for identifying salient subimages within a panoramic image |
US20170192958A1 (en) * | 2015-12-31 | 2017-07-06 | Accenture Global Solutions Limited | Input entity identification from natural language text information |
US20170206435A1 (en) * | 2016-01-15 | 2017-07-20 | Adobe Systems Incorporated | Embedding Space for Images with Multiple Text Labels |
US20170220605A1 (en) * | 2016-01-29 | 2017-08-03 | M-Files Oy | Centralized content management system with an intelligent metadata layer, and a method thereof |
US20170243077A1 (en) * | 2016-02-18 | 2017-08-24 | Fuji Xerox Co., Ltd. | Image processing apparatus and non-transitory computer readable medium |
US20170278015A1 (en) * | 2016-03-24 | 2017-09-28 | Accenture Global Solutions Limited | Self-learning log classification system |
US20170295118A1 (en) * | 2016-04-11 | 2017-10-12 | Yahoo!, Inc. | Content subject suggestions |
US20170351934A1 (en) * | 2015-03-05 | 2017-12-07 | Omron Corporation | Object recognition device, object recognition method, and program |
US20170364575A9 (en) * | 2014-09-28 | 2017-12-21 | Microsoft Technology Licensing, Llc | Graph-driven authoring in productivity tools |
US9852377B1 (en) * | 2016-11-10 | 2017-12-26 | Dropbox, Inc. | Providing intelligent storage location suggestions |
US20170372408A1 (en) * | 2016-06-28 | 2017-12-28 | Facebook, Inc. | Product Page Classification |
US20180012236A1 (en) * | 2016-07-06 | 2018-01-11 | Facebook, Inc. | Systems and methods for analyzing interaction-bait content based on classifier models |
US20180018309A1 (en) * | 2016-07-18 | 2018-01-18 | International Business Machines Corporation | Automatically annotating literary text |
US20180075323A1 (en) * | 2016-09-13 | 2018-03-15 | Sophistio, Inc. | Automatic wearable item classification systems and methods based upon normalized depictions |
US20180121533A1 (en) * | 2016-10-31 | 2018-05-03 | Wal-Mart Stores, Inc. | Systems, method, and non-transitory computer-readable storage media for multi-modal product classification |
US20180121825A1 (en) * | 2016-10-27 | 2018-05-03 | Dropbox, Inc. | Providing intelligent file name suggestions |
US20180137560A1 (en) * | 2016-11-16 | 2018-05-17 | Microsoft Technology Licensing, Llc | User trainable user interface page classification system |
US20180137119A1 (en) * | 2016-11-16 | 2018-05-17 | Samsung Electronics Co., Ltd. | Image management method and apparatus thereof |
US20180144270A1 (en) * | 2016-11-23 | 2018-05-24 | Primal Fusion Inc. | System and method for modifying a knowledge representation based on a machine learning classifier |
US20180181832A1 (en) * | 2016-12-27 | 2018-06-28 | Facebook, Inc. | Systems and methods for image description generation |
US20180189597A1 (en) * | 2016-12-30 | 2018-07-05 | Facebook, Inc. | Training an Image Classifier |
US10019654B1 (en) * | 2017-06-28 | 2018-07-10 | Accenture Global Solutions Limited | Image object recognition |
US20180196697A1 (en) * | 2017-01-06 | 2018-07-12 | Microsoft Technology Licensing, Llc | Dynamic context of tasks |
US10055479B2 (en) * | 2015-01-12 | 2018-08-21 | Xerox Corporation | Joint approach to feature and document labeling |
US20180246846A1 (en) * | 2017-02-27 | 2018-08-30 | Canon Kabushiki Kaisha | Information processing apparatus, information processing method, and storage medium |
US20180253219A1 (en) * | 2017-03-06 | 2018-09-06 | Microsoft Technology Licensing, Llc | Personalized presentation of content on a computing device |
US20180267994A1 (en) * | 2017-03-20 | 2018-09-20 | Google Inc. | Contextually disambiguating queries |
US20180276561A1 (en) * | 2017-03-24 | 2018-09-27 | Facebook, Inc. | Automatically tagging topics in posts during composition thereof |
US20180285321A1 (en) * | 2017-03-31 | 2018-10-04 | Dropbox, Inc. | Generating digital document content from a digital image |
US20180285773A1 (en) * | 2017-03-31 | 2018-10-04 | Intuit Inc. | Composite machine-learning system for label prediction and training data collection |
US20180322339A1 (en) * | 2017-05-08 | 2018-11-08 | Adobe Systems Incorporated | Page segmentation of vector graphics documents |
US20180330206A1 (en) * | 2017-05-10 | 2018-11-15 | The Travelers Indemnity Company | Machine-based learning systems, methods, and apparatus for interactively mapping raw data objects to recognized data objects |
US20180336574A1 (en) * | 2017-05-16 | 2018-11-22 | Facebook, Inc. | Classifying Post Types on Online Social Networks |
US10140553B1 (en) * | 2018-03-08 | 2018-11-27 | Capital One Services, Llc | Machine learning artificial intelligence system for identifying vehicles |
US20180348989A1 (en) * | 2017-06-01 | 2018-12-06 | Microsoft Technology Licensing, Llc | Managing electronic documents |
US20180349449A1 (en) * | 2017-06-01 | 2018-12-06 | Microsoft Technology Licensing, Llc | Managing electronic slide decks |
US20180349450A1 (en) * | 2017-06-01 | 2018-12-06 | Microsoft Technology Licensing, Llc | Managing electronic slide decks |
US20180359107A1 (en) * | 2017-06-07 | 2018-12-13 | Tg-17, Llc | System and method for real-time decoding and monitoring for encrypted instant messaging and other information exchange applications |
US20180373980A1 (en) * | 2017-06-27 | 2018-12-27 | drive.ai Inc. | Method for training and refining an artificial intelligence |
US10176198B1 (en) * | 2016-05-09 | 2019-01-08 | A9.Com, Inc. | Techniques for identifying visually similar content |
US20190019052A1 (en) * | 2017-07-14 | 2019-01-17 | Adobe Systems Incorporated | Text Region Detection in Digital Images using Image Tag Filtering |
US20190018983A1 (en) * | 2017-07-17 | 2019-01-17 | Microsoft Technology Licensing, Llc | Removing Sensitive Content from Documents while Preserving their Usefulness for Subsequent Processing |
US10191990B2 (en) * | 2016-11-21 | 2019-01-29 | Comcast Cable Communications, Llc | Content recommendation system with weighted metadata annotations |
US20190034751A1 (en) * | 2017-07-26 | 2019-01-31 | Vmware, Inc. | Managing camera actions |
US20190042880A1 (en) * | 2017-08-04 | 2019-02-07 | Medallia, Inc. | System and method for cascading image clustering using distribution over auto-generated labels |
US20190068551A1 (en) * | 2017-08-28 | 2019-02-28 | Go Daddy Operating Company, LLC | Suggesting a domain name from digital image metadata |
US10222942B1 (en) * | 2015-01-22 | 2019-03-05 | Clarifai, Inc. | User interface for context labeling of multimedia items |
US20190095466A1 (en) * | 2017-09-22 | 2019-03-28 | Pinterest, Inc. | Mixed type image based search results |
US20190095465A1 (en) * | 2017-09-22 | 2019-03-28 | Pinterest, Inc. | Object based image search |
US20190108274A1 (en) * | 2017-10-06 | 2019-04-11 | Optum, Inc | Automated concepts for interrogating a document storage database |
US20190114047A1 (en) * | 2017-10-17 | 2019-04-18 | Microsoft Technology Licensing, Llc | Drag and drop of objects to create new composites |
US20190138610A1 (en) * | 2017-11-06 | 2019-05-09 | Microsoft Technology Licensing, Llc | Electronic document content classification and document type determination |
US20190163768A1 (en) * | 2017-11-28 | 2019-05-30 | Adobe Systems Incorporated | Automatically curated image searching |
US20190250891A1 (en) * | 2018-02-12 | 2019-08-15 | Oracle International Corporation | Automated code generation |
US20190258895A1 (en) * | 2018-02-20 | 2019-08-22 | Microsoft Technology Licensing, Llc | Object detection from image content |
US10395108B1 (en) * | 2018-10-17 | 2019-08-27 | Decision Engines, Inc. | Automatically identifying and interacting with hierarchically arranged elements |
US10402061B2 (en) * | 2014-09-28 | 2019-09-03 | Microsoft Technology Licensing, Llc | Productivity tools for content authoring |
US10402641B1 (en) * | 2019-03-19 | 2019-09-03 | Capital One Services, Llc | Platform for document classification |
US20190272419A1 (en) * | 2018-03-05 | 2019-09-05 | Shutterfly, Inc. | Automated communication design construction system |
US10423826B2 (en) * | 2008-01-18 | 2019-09-24 | Mitek Systems, Inc. | Systems and methods for classifying payment documents during mobile image processing |
US20190294665A1 (en) * | 2018-03-23 | 2019-09-26 | Abbyy Production Llc | Training information extraction classifiers |
US10445772B1 (en) * | 2011-09-09 | 2019-10-15 | Google Llc | Label placement based on objects in photographic images |
US20190317986A1 (en) * | 2018-04-13 | 2019-10-17 | Preferred Networks, Inc. | Annotated text data expanding method, annotated text data expanding computer-readable storage medium, annotated text data expanding device, and text classification model training method |
US20190325626A1 (en) * | 2018-04-18 | 2019-10-24 | Sawa Labs, Inc. | Graphic design system for dynamic content generation |
US20190325259A1 (en) * | 2018-04-12 | 2019-10-24 | Discovery Communications, Llc | Feature extraction and machine learning for automated metadata analysis |
US10496884B1 (en) * | 2017-09-19 | 2019-12-03 | Deepradiology Inc. | Transformation of textbook information |
US20190373322A1 (en) * | 2018-05-29 | 2019-12-05 | Sony Interactive Entertainment LLC | Interactive Video Content Delivery |
US20190370749A1 (en) * | 2018-05-31 | 2019-12-05 | Microsoft Technology Licensing, Llc | Document status management system |
US10515125B1 (en) * | 2016-07-26 | 2019-12-24 | The Thought & Expression Company LLC | Structured text segment indexing techniques |
US20190392035A1 (en) * | 2018-06-20 | 2019-12-26 | Abbyy Production Llc | Information object extraction using combination of classifiers analyzing local and non-local features |
US20200004815A1 (en) * | 2018-06-29 | 2020-01-02 | Microsoft Technology Licensing, Llc | Text entity detection and recognition from images |
US20200005065A1 (en) * | 2018-06-28 | 2020-01-02 | Google Llc | Object classification for image recognition processing |
US20200004561A1 (en) * | 2018-06-28 | 2020-01-02 | Radiology Partners, Inc. | User interface for determining real-time changes to content entered into the user interface to provide to a classifier program and rules engine to generate results for the content |
US20200012943A1 (en) * | 2017-03-17 | 2020-01-09 | Neurala, Inc. | Online, incremental real-time learning for tagging and labeling data streams for deep neural networks and neural network applications |
US20200012894A1 (en) * | 2018-07-05 | 2020-01-09 | Mitsubishi Electric Research Laboratories, Inc. | Visually Aided Active Learning for Training Object Detector |
US20200026966A1 (en) * | 2018-07-23 | 2020-01-23 | Accenture Global Solutions Limited | Information transition management platform |
US20200042575A1 (en) * | 2018-08-01 | 2020-02-06 | Microsoft Technology Licensing, Llc | Cross-application ingestion and restructuring of slide presentation content |
US20200076746A1 (en) * | 2018-08-28 | 2020-03-05 | International Business Machines Corporation | Managing content in a collaboration environment |
US20200104353A1 (en) * | 2018-09-28 | 2020-04-02 | Microsoft Technology Licensing, Llc | Personalization of content suggestions for document creation |
US20200110839A1 (en) * | 2018-10-05 | 2020-04-09 | International Business Machines Corporation | Determining tags to recommend for a document from multiple database sources |
US20200117903A1 (en) * | 2018-10-10 | 2020-04-16 | Autodesk, Inc. | Architecture, engineering and construction (aec) construction safety risk analysis system and method for interactive visualization and capture |
US20200125928A1 (en) * | 2018-10-22 | 2020-04-23 | Ca, Inc. | Real-time supervised machine learning by models configured to classify offensiveness of computer-generated natural-language text |
US20200126533A1 (en) * | 2018-10-22 | 2020-04-23 | Ca, Inc. | Machine learning model for identifying offensive, computer-generated natural-language text or speech |
US20200160098A1 (en) * | 2018-08-30 | 2020-05-21 | The Government Of The United States Of America, As Represented By The Secretary Of The Navy | Human-Assisted Machine Learning Through Geometric Manipulation and Refinement |
US20200162561A1 (en) * | 2018-11-16 | 2020-05-21 | Microsoft Technology Licensing, Llc | System and method for managing notifications of document modifications |
US20200167566A1 (en) * | 2018-11-25 | 2020-05-28 | International Business Machines Corporation | Automatic generation of secondary class annotations |
US20200175095A1 (en) * | 2018-11-29 | 2020-06-04 | Adobe Inc. | Object recognition and tagging based on fusion deep learning models |
US20200184307A1 (en) * | 2018-12-11 | 2020-06-11 | Adobe Inc. | Utilizing recurrent neural networks to recognize and extract open intent from text inputs |
US20200196011A1 (en) * | 2018-12-15 | 2020-06-18 | Activision Publishing, Inc. | Systems and Methods for Receiving Digital Media and Classifying, Labeling and Searching Offensive Content Within Digital Media |
US20200226128A1 (en) * | 2013-03-15 | 2020-07-16 | Palantir Technologies Inc. | System and method for generating event visualizations |
US10719301B1 (en) * | 2018-10-26 | 2020-07-21 | Amazon Technologies, Inc. | Development environment for machine learning media models |
US20200250537A1 (en) * | 2019-02-01 | 2020-08-06 | Google Llc | Training image and text embedding models |
US20200265153A1 (en) * | 2019-02-15 | 2020-08-20 | Microsoft Technology Licensing, Llc | Image classification modeling while maintaining data privacy compliance |
US20200265218A1 (en) * | 2019-02-20 | 2020-08-20 | Peng Dai | Semi-supervised hybrid clustering/classification system |
US20200272850A1 (en) * | 2019-02-22 | 2020-08-27 | Kabushiki Kaisha Toshiba | Information display method, information display system, and storage medium |
US20200302021A1 (en) * | 2019-03-18 | 2020-09-24 | Apple Inc. | Shape library suggestions based on document content |
US20200311871A1 (en) * | 2017-12-20 | 2020-10-01 | Huawei Technologies Co., Ltd. | Image reconstruction method and device |
US20200372066A1 (en) * | 2019-05-22 | 2020-11-26 | SalesTing, Inc. | Content summarization leveraging systems and processes for key moment identification and extraction |
US20200372047A1 (en) * | 2019-05-21 | 2020-11-26 | Microsoft Technology Licensing, Llc | Generating and Applying an Object-Level Relational Index for Images |
US20200380067A1 (en) * | 2019-05-30 | 2020-12-03 | Microsoft Technology Licensing, Llc | Classifying content of an electronic file |
US10909401B2 (en) * | 2018-05-29 | 2021-02-02 | Sri International | Attention-based explanations for artificial intelligence behavior |
US20210065859A1 (en) * | 2018-02-16 | 2021-03-04 | Google Llc | Automated extraction of structured labels from medical text using deep convolutional networks and use thereof to train a computer vision model |
US20210110587A1 (en) * | 2019-10-14 | 2021-04-15 | Adobe Inc. | Automatic Positioning of Textual Content within Digital Images |
US20210150263A1 (en) * | 2019-11-19 | 2021-05-20 | Salesforce.Com, Inc. | Machine learning systems and methods for translating captured input images into an interactive demonstration presentation for an envisioned software product |
US11057652B1 (en) * | 2019-04-30 | 2021-07-06 | Amazon Technologies, Inc. | Adjacent content classification and targeting |
US20210216765A1 (en) * | 2019-05-09 | 2021-07-15 | Hangzhou Glority Software Limited | Receipt identification method, apparatus, device and storage medium |
US20210264203A1 (en) * | 2018-11-16 | 2021-08-26 | Google Llc | Multimodal Image Classifier using Textual and Visual Embeddings |
US11106715B1 (en) * | 2018-04-24 | 2021-08-31 | Facebook, Inc. | Systems and methods for using heterogeneous graphs to derive object embeddings |
US20220012268A1 (en) * | 2018-10-18 | 2022-01-13 | Oracle International Corporation | System and method for smart categorization of content in a content management system |
US20220050867A1 (en) * | 2018-09-10 | 2022-02-17 | Rewyndr, Llc | Image management with region-based metadata indexing |
US20220091706A1 (en) * | 2017-12-22 | 2022-03-24 | Google Llc | Image selection suggestions |
US11436446B2 (en) * | 2018-01-22 | 2022-09-06 | International Business Machines Corporation | Image analysis enhanced related item decision |
US11720621B2 (en) * | 2019-03-18 | 2023-08-08 | Apple Inc. | Systems and methods for naming objects based on object content |
-
2019
- 2019-05-30 US US16/426,736 patent/US11720621B2/en active Active
-
2023
- 2023-05-24 US US18/201,549 patent/US20230297609A1/en active Pending
Patent Citations (177)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7849141B1 (en) * | 2001-06-14 | 2010-12-07 | Apple Inc. | Training a computer storage system for automatic filing of data using graphical representations of storage locations |
US20030167402A1 (en) * | 2001-08-16 | 2003-09-04 | Stolfo Salvatore J. | System and methods for detecting malicious email transmission |
US20050027664A1 (en) * | 2003-07-31 | 2005-02-03 | Johnson David E. | Interactive machine learning system for automated annotation of information in text |
US20060041564A1 (en) * | 2004-08-20 | 2006-02-23 | Innovative Decision Technologies, Inc. | Graphical Annotations and Domain Objects to Create Feature Level Metadata of Images |
US20070185876A1 (en) * | 2005-02-07 | 2007-08-09 | Mendis Venura C | Data handling system |
US20070217701A1 (en) * | 2005-08-12 | 2007-09-20 | Che-Bin Liu | Systems and Methods to Convert Images into High-Quality Compressed Documents |
US20070094600A1 (en) * | 2005-10-24 | 2007-04-26 | International Business Machines Corporation | Automatic 3d object generation and deformation for representation of data files based on taxonomy classification |
US20070143284A1 (en) * | 2005-12-09 | 2007-06-21 | Lee Chang K | Apparatus and method for constructing learning data |
US20080270462A1 (en) * | 2007-04-24 | 2008-10-30 | Interse A/S | System and Method of Uniformly Classifying Information Objects with Metadata Across Heterogeneous Data Stores |
US20090006285A1 (en) * | 2007-06-29 | 2009-01-01 | Microsoft Corporation | Content-based tagging of rss feeds and e-mail |
US8239460B2 (en) * | 2007-06-29 | 2012-08-07 | Microsoft Corporation | Content-based tagging of RSS feeds and E-mail |
US20090055242A1 (en) * | 2007-08-24 | 2009-02-26 | Gaurav Rewari | Content identification and classification apparatus, systems, and methods |
US8132099B2 (en) * | 2007-10-11 | 2012-03-06 | International Business Machines Corporation | Method for obtaining accessibility information, computer program and accessibility information device |
US10423826B2 (en) * | 2008-01-18 | 2019-09-24 | Mitek Systems, Inc. | Systems and methods for classifying payment documents during mobile image processing |
US8843424B2 (en) * | 2009-04-01 | 2014-09-23 | Sony Corporation | Device and method for multiclass object detection |
US20110145327A1 (en) * | 2009-06-19 | 2011-06-16 | Moment Usa, Inc. | Systems and methods of contextualizing and linking media items |
US20150161170A1 (en) * | 2009-07-17 | 2015-06-11 | Google Inc. | Image classification |
US8478052B1 (en) * | 2009-07-17 | 2013-07-02 | Google Inc. | Image classification |
US20120233110A1 (en) * | 2009-10-31 | 2012-09-13 | Helen Balinsky | Determining Probability Than An Object Belongs To A Topic Using Sample Items Selected From Object And Probability Distribution Profile Of The Topic |
US20120278705A1 (en) * | 2010-01-18 | 2012-11-01 | Yang sheng-wen | System and Method for Automatically Extracting Metadata from Unstructured Electronic Documents |
US20110270834A1 (en) * | 2010-04-28 | 2011-11-03 | Microsoft Corporation | Data Classifier |
US9449080B1 (en) * | 2010-05-18 | 2016-09-20 | Guangsheng Zhang | System, methods, and user interface for information searching, tagging, organization, and display |
US20120093354A1 (en) * | 2010-10-19 | 2012-04-19 | Palo Alto Research Center Incorporated | Finding similar content in a mixed collection of presentation and rich document content using two-dimensional visual fingerprints |
US20140096092A1 (en) * | 2011-03-20 | 2014-04-03 | William J. Johnson | System and Method for Indirect Manipulation of User Interface Object(s) |
US20120254191A1 (en) * | 2011-04-01 | 2012-10-04 | Yahoo! Inc. | Method and system for concept sumarization |
US20140270497A1 (en) * | 2011-06-13 | 2014-09-18 | Microsoft Corporation | Accurate text classification through selective use of image data |
US8768050B2 (en) * | 2011-06-13 | 2014-07-01 | Microsoft Corporation | Accurate text classification through selective use of image data |
US20120314941A1 (en) * | 2011-06-13 | 2012-12-13 | Microsoft Corporation | Accurate text classification through selective use of image data |
US20140149376A1 (en) * | 2011-06-23 | 2014-05-29 | Cyber Ai Entertainment Inc. | System for collecting interest graph by relevance search incorporating image recognition system |
US8473981B1 (en) * | 2011-06-30 | 2013-06-25 | Google Inc. | Augmenting metadata of digital media objects using per object classifiers |
US10445772B1 (en) * | 2011-09-09 | 2019-10-15 | Google Llc | Label placement based on objects in photographic images |
US20130272575A1 (en) * | 2011-11-01 | 2013-10-17 | Intel Corporation | Object detection using extended surf features |
US9111579B2 (en) * | 2011-11-14 | 2015-08-18 | Apple Inc. | Media editing with multi-camera media clips |
US20140092990A1 (en) * | 2012-10-01 | 2014-04-03 | Google Inc. | System and method for optimizing videos |
US20140146053A1 (en) * | 2012-11-29 | 2014-05-29 | International Business Machines Corporation | Generating Alternative Descriptions for Images |
US9025811B1 (en) * | 2013-01-02 | 2015-05-05 | Google Inc. | Performing image similarity operations using semantic classification |
US20140201113A1 (en) * | 2013-01-15 | 2014-07-17 | International Business Machines Corporation | Automatic Genre Determination of Web Content |
US20200226128A1 (en) * | 2013-03-15 | 2020-07-16 | Palantir Technologies Inc. | System and method for generating event visualizations |
US20150178383A1 (en) * | 2013-12-20 | 2015-06-25 | Google Inc. | Classifying Data Objects |
US20150242525A1 (en) * | 2014-02-26 | 2015-08-27 | Pixured, Inc. | System for referring to and/or embedding posts within other post and posts within any part of another post |
US20150309987A1 (en) * | 2014-04-29 | 2015-10-29 | Google Inc. | Classification of Offensive Words |
US20170052946A1 (en) * | 2014-06-06 | 2017-02-23 | Siyu Gu | Semantic understanding based emoji input method and device |
US20160034425A1 (en) * | 2014-07-31 | 2016-02-04 | Linkedln Corporation | Providing recommendations for electronic presentations based on contextual and behavioral data |
US20160065605A1 (en) * | 2014-08-29 | 2016-03-03 | Linkedin Corporation | Spam detection for online slide deck presentations |
US10528597B2 (en) * | 2014-09-28 | 2020-01-07 | Microsoft Technology Licensing, Llc | Graph-driven authoring in productivity tools |
US20170364575A9 (en) * | 2014-09-28 | 2017-12-21 | Microsoft Technology Licensing, Llc | Graph-driven authoring in productivity tools |
US10402061B2 (en) * | 2014-09-28 | 2019-09-03 | Microsoft Technology Licensing, Llc | Productivity tools for content authoring |
US20160092730A1 (en) * | 2014-09-30 | 2016-03-31 | Abbyy Development Llc | Content-based document image classification |
US20160098645A1 (en) * | 2014-10-02 | 2016-04-07 | Microsoft Corporation | High-precision limited supervision relationship extractor |
US20160147434A1 (en) * | 2014-11-25 | 2016-05-26 | Samsung Electronics Co., Ltd. | Device and method of providing handwritten content in the same |
US10055479B2 (en) * | 2015-01-12 | 2018-08-21 | Xerox Corporation | Joint approach to feature and document labeling |
US10222942B1 (en) * | 2015-01-22 | 2019-03-05 | Clarifai, Inc. | User interface for context labeling of multimedia items |
US20160232456A1 (en) * | 2015-02-06 | 2016-08-11 | Box, Inc. | Method and system for implementing machine learning analysis of documents |
US9495614B1 (en) * | 2015-02-27 | 2016-11-15 | Google Inc. | Verifying labels for images using image recognition |
US20170351934A1 (en) * | 2015-03-05 | 2017-12-07 | Omron Corporation | Object recognition device, object recognition method, and program |
US20160269334A1 (en) * | 2015-03-11 | 2016-09-15 | Microsoft Technology Licensing, Llc | Tags in communication environments |
US9141883B1 (en) * | 2015-05-11 | 2015-09-22 | StradVision, Inc. | Method, hard negative proposer, and classifier for supporting to collect hard negative images using a similarity map |
US20160342895A1 (en) * | 2015-05-21 | 2016-11-24 | Baidu Usa Llc | Multilingual image question answering |
US20160364419A1 (en) * | 2015-06-10 | 2016-12-15 | Blackbird Technologies, Inc. | Image and text data hierarchical classifiers |
US20170017696A1 (en) * | 2015-07-14 | 2017-01-19 | Microsoft Technology Licensing, Llc | Semantic object tagging through name annotation |
US20170091153A1 (en) * | 2015-09-29 | 2017-03-30 | Apple Inc. | Device, Method, and Graphical User Interface for Providing Handwriting Support in Document Editing |
US9613296B1 (en) * | 2015-10-07 | 2017-04-04 | GumGum, Inc. | Selecting a set of exemplar images for use in an automated image object recognition system |
US20170124067A1 (en) * | 2015-11-04 | 2017-05-04 | Kabushiki Kaisha Toshiba | Document processing apparatus, method, and program |
US10460033B2 (en) * | 2015-11-11 | 2019-10-29 | Adobe Inc. | Structured knowledge modeling, extraction and localization from images |
US20170132526A1 (en) * | 2015-11-11 | 2017-05-11 | Adobe Systems Incorporated | Structured Knowledge Modeling and Extraction from Images |
US20170132498A1 (en) * | 2015-11-11 | 2017-05-11 | Adobe Systems Incorporated | Structured Knowledge Modeling, Extraction and Localization from Images |
US20170140250A1 (en) * | 2015-11-13 | 2017-05-18 | Microsoft Technology Licensing, Llc | Content file image analysis |
US20170140051A1 (en) * | 2015-11-16 | 2017-05-18 | Facebook, Inc. | Ranking and Filtering Comments Based on Labelling |
US20170140297A1 (en) * | 2015-11-17 | 2017-05-18 | International Business Machines Corporation | Generating efficient sampling strategy processing for business data relevance classification |
US20170177584A1 (en) * | 2015-12-17 | 2017-06-22 | The Nielsen Company (Us), Llc | Media names matching and normalization |
US20170192958A1 (en) * | 2015-12-31 | 2017-07-06 | Accenture Global Solutions Limited | Input entity identification from natural language text information |
US20170193324A1 (en) * | 2015-12-31 | 2017-07-06 | Nokia Technologies Oy | Method and apparatus for identifying salient subimages within a panoramic image |
US20170206435A1 (en) * | 2016-01-15 | 2017-07-20 | Adobe Systems Incorporated | Embedding Space for Images with Multiple Text Labels |
US20170220605A1 (en) * | 2016-01-29 | 2017-08-03 | M-Files Oy | Centralized content management system with an intelligent metadata layer, and a method thereof |
US20170243077A1 (en) * | 2016-02-18 | 2017-08-24 | Fuji Xerox Co., Ltd. | Image processing apparatus and non-transitory computer readable medium |
US20170278015A1 (en) * | 2016-03-24 | 2017-09-28 | Accenture Global Solutions Limited | Self-learning log classification system |
US20170295118A1 (en) * | 2016-04-11 | 2017-10-12 | Yahoo!, Inc. | Content subject suggestions |
US10303720B2 (en) * | 2016-04-11 | 2019-05-28 | Oath Inc. | Content subject suggestions |
US10176198B1 (en) * | 2016-05-09 | 2019-01-08 | A9.Com, Inc. | Techniques for identifying visually similar content |
US20170372408A1 (en) * | 2016-06-28 | 2017-12-28 | Facebook, Inc. | Product Page Classification |
US20180012236A1 (en) * | 2016-07-06 | 2018-01-11 | Facebook, Inc. | Systems and methods for analyzing interaction-bait content based on classifier models |
US20180018309A1 (en) * | 2016-07-18 | 2018-01-18 | International Business Machines Corporation | Automatically annotating literary text |
US10515125B1 (en) * | 2016-07-26 | 2019-12-24 | The Thought & Expression Company LLC | Structured text segment indexing techniques |
US20180075323A1 (en) * | 2016-09-13 | 2018-03-15 | Sophistio, Inc. | Automatic wearable item classification systems and methods based upon normalized depictions |
US20180121825A1 (en) * | 2016-10-27 | 2018-05-03 | Dropbox, Inc. | Providing intelligent file name suggestions |
US20180121533A1 (en) * | 2016-10-31 | 2018-05-03 | Wal-Mart Stores, Inc. | Systems, method, and non-transitory computer-readable storage media for multi-modal product classification |
US9852377B1 (en) * | 2016-11-10 | 2017-12-26 | Dropbox, Inc. | Providing intelligent storage location suggestions |
US20180137119A1 (en) * | 2016-11-16 | 2018-05-17 | Samsung Electronics Co., Ltd. | Image management method and apparatus thereof |
US20180137560A1 (en) * | 2016-11-16 | 2018-05-17 | Microsoft Technology Licensing, Llc | User trainable user interface page classification system |
US10191990B2 (en) * | 2016-11-21 | 2019-01-29 | Comcast Cable Communications, Llc | Content recommendation system with weighted metadata annotations |
US20180144270A1 (en) * | 2016-11-23 | 2018-05-24 | Primal Fusion Inc. | System and method for modifying a knowledge representation based on a machine learning classifier |
US20180181832A1 (en) * | 2016-12-27 | 2018-06-28 | Facebook, Inc. | Systems and methods for image description generation |
US20180189597A1 (en) * | 2016-12-30 | 2018-07-05 | Facebook, Inc. | Training an Image Classifier |
US20180196697A1 (en) * | 2017-01-06 | 2018-07-12 | Microsoft Technology Licensing, Llc | Dynamic context of tasks |
US20180246846A1 (en) * | 2017-02-27 | 2018-08-30 | Canon Kabushiki Kaisha | Information processing apparatus, information processing method, and storage medium |
US20180253219A1 (en) * | 2017-03-06 | 2018-09-06 | Microsoft Technology Licensing, Llc | Personalized presentation of content on a computing device |
US20200012943A1 (en) * | 2017-03-17 | 2020-01-09 | Neurala, Inc. | Online, incremental real-time learning for tagging and labeling data streams for deep neural networks and neural network applications |
US20180267994A1 (en) * | 2017-03-20 | 2018-09-20 | Google Inc. | Contextually disambiguating queries |
US20180276561A1 (en) * | 2017-03-24 | 2018-09-27 | Facebook, Inc. | Automatically tagging topics in posts during composition thereof |
US20180285321A1 (en) * | 2017-03-31 | 2018-10-04 | Dropbox, Inc. | Generating digital document content from a digital image |
US20180285773A1 (en) * | 2017-03-31 | 2018-10-04 | Intuit Inc. | Composite machine-learning system for label prediction and training data collection |
US20180322339A1 (en) * | 2017-05-08 | 2018-11-08 | Adobe Systems Incorporated | Page segmentation of vector graphics documents |
US20180330206A1 (en) * | 2017-05-10 | 2018-11-15 | The Travelers Indemnity Company | Machine-based learning systems, methods, and apparatus for interactively mapping raw data objects to recognized data objects |
US20180336574A1 (en) * | 2017-05-16 | 2018-11-22 | Facebook, Inc. | Classifying Post Types on Online Social Networks |
US20180349450A1 (en) * | 2017-06-01 | 2018-12-06 | Microsoft Technology Licensing, Llc | Managing electronic slide decks |
US20180349449A1 (en) * | 2017-06-01 | 2018-12-06 | Microsoft Technology Licensing, Llc | Managing electronic slide decks |
US20180348989A1 (en) * | 2017-06-01 | 2018-12-06 | Microsoft Technology Licensing, Llc | Managing electronic documents |
US20180359107A1 (en) * | 2017-06-07 | 2018-12-13 | Tg-17, Llc | System and method for real-time decoding and monitoring for encrypted instant messaging and other information exchange applications |
US20180373980A1 (en) * | 2017-06-27 | 2018-12-27 | drive.ai Inc. | Method for training and refining an artificial intelligence |
US10019654B1 (en) * | 2017-06-28 | 2018-07-10 | Accenture Global Solutions Limited | Image object recognition |
US20190019052A1 (en) * | 2017-07-14 | 2019-01-17 | Adobe Systems Incorporated | Text Region Detection in Digital Images using Image Tag Filtering |
US20190018983A1 (en) * | 2017-07-17 | 2019-01-17 | Microsoft Technology Licensing, Llc | Removing Sensitive Content from Documents while Preserving their Usefulness for Subsequent Processing |
US20190034751A1 (en) * | 2017-07-26 | 2019-01-31 | Vmware, Inc. | Managing camera actions |
US20190042880A1 (en) * | 2017-08-04 | 2019-02-07 | Medallia, Inc. | System and method for cascading image clustering using distribution over auto-generated labels |
US20190068551A1 (en) * | 2017-08-28 | 2019-02-28 | Go Daddy Operating Company, LLC | Suggesting a domain name from digital image metadata |
US20200252372A1 (en) * | 2017-08-28 | 2020-08-06 | Go Daddy Operating Company, LLC | Computer-based system and computer based method for suggesting domain names based on entity profiles having neural networks of data structures |
US10496884B1 (en) * | 2017-09-19 | 2019-12-03 | Deepradiology Inc. | Transformation of textbook information |
US20190095466A1 (en) * | 2017-09-22 | 2019-03-28 | Pinterest, Inc. | Mixed type image based search results |
US20190095465A1 (en) * | 2017-09-22 | 2019-03-28 | Pinterest, Inc. | Object based image search |
US20190108274A1 (en) * | 2017-10-06 | 2019-04-11 | Optum, Inc | Automated concepts for interrogating a document storage database |
US20190114047A1 (en) * | 2017-10-17 | 2019-04-18 | Microsoft Technology Licensing, Llc | Drag and drop of objects to create new composites |
US20190138610A1 (en) * | 2017-11-06 | 2019-05-09 | Microsoft Technology Licensing, Llc | Electronic document content classification and document type determination |
US20190163768A1 (en) * | 2017-11-28 | 2019-05-30 | Adobe Systems Incorporated | Automatically curated image searching |
US20200311871A1 (en) * | 2017-12-20 | 2020-10-01 | Huawei Technologies Co., Ltd. | Image reconstruction method and device |
US20220091706A1 (en) * | 2017-12-22 | 2022-03-24 | Google Llc | Image selection suggestions |
US11436446B2 (en) * | 2018-01-22 | 2022-09-06 | International Business Machines Corporation | Image analysis enhanced related item decision |
US20190250891A1 (en) * | 2018-02-12 | 2019-08-15 | Oracle International Corporation | Automated code generation |
US20210065859A1 (en) * | 2018-02-16 | 2021-03-04 | Google Llc | Automated extraction of structured labels from medical text using deep convolutional networks and use thereof to train a computer vision model |
US20190258895A1 (en) * | 2018-02-20 | 2019-08-22 | Microsoft Technology Licensing, Llc | Object detection from image content |
US20190272419A1 (en) * | 2018-03-05 | 2019-09-05 | Shutterfly, Inc. | Automated communication design construction system |
US10140553B1 (en) * | 2018-03-08 | 2018-11-27 | Capital One Services, Llc | Machine learning artificial intelligence system for identifying vehicles |
US20190294665A1 (en) * | 2018-03-23 | 2019-09-26 | Abbyy Production Llc | Training information extraction classifiers |
US20190325259A1 (en) * | 2018-04-12 | 2019-10-24 | Discovery Communications, Llc | Feature extraction and machine learning for automated metadata analysis |
US20190317986A1 (en) * | 2018-04-13 | 2019-10-17 | Preferred Networks, Inc. | Annotated text data expanding method, annotated text data expanding computer-readable storage medium, annotated text data expanding device, and text classification model training method |
US20190325626A1 (en) * | 2018-04-18 | 2019-10-24 | Sawa Labs, Inc. | Graphic design system for dynamic content generation |
US11106715B1 (en) * | 2018-04-24 | 2021-08-31 | Facebook, Inc. | Systems and methods for using heterogeneous graphs to derive object embeddings |
US20190373322A1 (en) * | 2018-05-29 | 2019-12-05 | Sony Interactive Entertainment LLC | Interactive Video Content Delivery |
US10909401B2 (en) * | 2018-05-29 | 2021-02-02 | Sri International | Attention-based explanations for artificial intelligence behavior |
US20190370749A1 (en) * | 2018-05-31 | 2019-12-05 | Microsoft Technology Licensing, Llc | Document status management system |
US20190392035A1 (en) * | 2018-06-20 | 2019-12-26 | Abbyy Production Llc | Information object extraction using combination of classifiers analyzing local and non-local features |
US20200004561A1 (en) * | 2018-06-28 | 2020-01-02 | Radiology Partners, Inc. | User interface for determining real-time changes to content entered into the user interface to provide to a classifier program and rules engine to generate results for the content |
US20200005065A1 (en) * | 2018-06-28 | 2020-01-02 | Google Llc | Object classification for image recognition processing |
US20200004815A1 (en) * | 2018-06-29 | 2020-01-02 | Microsoft Technology Licensing, Llc | Text entity detection and recognition from images |
US20200012894A1 (en) * | 2018-07-05 | 2020-01-09 | Mitsubishi Electric Research Laboratories, Inc. | Visually Aided Active Learning for Training Object Detector |
US20200026966A1 (en) * | 2018-07-23 | 2020-01-23 | Accenture Global Solutions Limited | Information transition management platform |
US20200042575A1 (en) * | 2018-08-01 | 2020-02-06 | Microsoft Technology Licensing, Llc | Cross-application ingestion and restructuring of slide presentation content |
US20200076746A1 (en) * | 2018-08-28 | 2020-03-05 | International Business Machines Corporation | Managing content in a collaboration environment |
US20200160098A1 (en) * | 2018-08-30 | 2020-05-21 | The Government Of The United States Of America, As Represented By The Secretary Of The Navy | Human-Assisted Machine Learning Through Geometric Manipulation and Refinement |
US20220050867A1 (en) * | 2018-09-10 | 2022-02-17 | Rewyndr, Llc | Image management with region-based metadata indexing |
US20200104353A1 (en) * | 2018-09-28 | 2020-04-02 | Microsoft Technology Licensing, Llc | Personalization of content suggestions for document creation |
US20200110839A1 (en) * | 2018-10-05 | 2020-04-09 | International Business Machines Corporation | Determining tags to recommend for a document from multiple database sources |
US20200117903A1 (en) * | 2018-10-10 | 2020-04-16 | Autodesk, Inc. | Architecture, engineering and construction (aec) construction safety risk analysis system and method for interactive visualization and capture |
US10395108B1 (en) * | 2018-10-17 | 2019-08-27 | Decision Engines, Inc. | Automatically identifying and interacting with hierarchically arranged elements |
US20220012268A1 (en) * | 2018-10-18 | 2022-01-13 | Oracle International Corporation | System and method for smart categorization of content in a content management system |
US20200126533A1 (en) * | 2018-10-22 | 2020-04-23 | Ca, Inc. | Machine learning model for identifying offensive, computer-generated natural-language text or speech |
US20200125928A1 (en) * | 2018-10-22 | 2020-04-23 | Ca, Inc. | Real-time supervised machine learning by models configured to classify offensiveness of computer-generated natural-language text |
US10719301B1 (en) * | 2018-10-26 | 2020-07-21 | Amazon Technologies, Inc. | Development environment for machine learning media models |
US20210264203A1 (en) * | 2018-11-16 | 2021-08-26 | Google Llc | Multimodal Image Classifier using Textual and Visual Embeddings |
US20200162561A1 (en) * | 2018-11-16 | 2020-05-21 | Microsoft Technology Licensing, Llc | System and method for managing notifications of document modifications |
US20200167566A1 (en) * | 2018-11-25 | 2020-05-28 | International Business Machines Corporation | Automatic generation of secondary class annotations |
US20200175095A1 (en) * | 2018-11-29 | 2020-06-04 | Adobe Inc. | Object recognition and tagging based on fusion deep learning models |
US20200184307A1 (en) * | 2018-12-11 | 2020-06-11 | Adobe Inc. | Utilizing recurrent neural networks to recognize and extract open intent from text inputs |
US20200196011A1 (en) * | 2018-12-15 | 2020-06-18 | Activision Publishing, Inc. | Systems and Methods for Receiving Digital Media and Classifying, Labeling and Searching Offensive Content Within Digital Media |
US20200250537A1 (en) * | 2019-02-01 | 2020-08-06 | Google Llc | Training image and text embedding models |
US20200265153A1 (en) * | 2019-02-15 | 2020-08-20 | Microsoft Technology Licensing, Llc | Image classification modeling while maintaining data privacy compliance |
US20200265218A1 (en) * | 2019-02-20 | 2020-08-20 | Peng Dai | Semi-supervised hybrid clustering/classification system |
US20200272850A1 (en) * | 2019-02-22 | 2020-08-27 | Kabushiki Kaisha Toshiba | Information display method, information display system, and storage medium |
US11720621B2 (en) * | 2019-03-18 | 2023-08-08 | Apple Inc. | Systems and methods for naming objects based on object content |
US20200302021A1 (en) * | 2019-03-18 | 2020-09-24 | Apple Inc. | Shape library suggestions based on document content |
US10402641B1 (en) * | 2019-03-19 | 2019-09-03 | Capital One Services, Llc | Platform for document classification |
US11057652B1 (en) * | 2019-04-30 | 2021-07-06 | Amazon Technologies, Inc. | Adjacent content classification and targeting |
US20210216765A1 (en) * | 2019-05-09 | 2021-07-15 | Hangzhou Glority Software Limited | Receipt identification method, apparatus, device and storage medium |
US20200372047A1 (en) * | 2019-05-21 | 2020-11-26 | Microsoft Technology Licensing, Llc | Generating and Applying an Object-Level Relational Index for Images |
US20200372066A1 (en) * | 2019-05-22 | 2020-11-26 | SalesTing, Inc. | Content summarization leveraging systems and processes for key moment identification and extraction |
US20200380067A1 (en) * | 2019-05-30 | 2020-12-03 | Microsoft Technology Licensing, Llc | Classifying content of an electronic file |
US20210110587A1 (en) * | 2019-10-14 | 2021-04-15 | Adobe Inc. | Automatic Positioning of Textual Content within Digital Images |
US20210150263A1 (en) * | 2019-11-19 | 2021-05-20 | Salesforce.Com, Inc. | Machine learning systems and methods for translating captured input images into an interactive demonstration presentation for an envisioned software product |
Also Published As
Publication number | Publication date |
---|---|
US20200301960A1 (en) | 2020-09-24 |
US11720621B2 (en) | 2023-08-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230297609A1 (en) | Systems and methods for naming objects based on object content | |
CN110471858B (en) | Application program testing method, device and storage medium | |
US10698956B2 (en) | Active knowledge guidance based on deep document analysis | |
US20150339348A1 (en) | Search method and device | |
CN108228720B (en) | Identify method, system, device, terminal and the storage medium of target text content and original image correlation | |
EP2950239A1 (en) | Annotation display assistance device and method of assisting annotation display | |
US11295087B2 (en) | Shape library suggestions based on document content | |
US10162879B2 (en) | Label filters for large scale multi-label classification | |
CN106294549A (en) | A kind of image processing method and terminal | |
US20180018392A1 (en) | Topic identification based on functional summarization | |
CN111930964B (en) | Content processing method, device, equipment and storage medium | |
CN105378728A (en) | Apparatus and method for representing and manipulating metadata | |
US10185724B2 (en) | Method for sorting media content and electronic device implementing same | |
CN110196833A (en) | Searching method, device, terminal and the storage medium of application program | |
KR20090046137A (en) | Apparatus and method for searching media data | |
CN113626017A (en) | Heterogeneous program analysis method and device, computer equipment and storage medium | |
CN112181167A (en) | Input method candidate word processing method and electronic equipment | |
US20180157691A1 (en) | Information retrieval system | |
CN104216626B (en) | A kind of image acquiring method and electronic equipment | |
KR102181896B1 (en) | A method and system for presenting content on an electronic device | |
CN114415889A (en) | Icon management method, device, equipment and storage medium | |
US20160162752A1 (en) | Retrieval apparatus, retrieval method, and computer program product | |
CN111104026A (en) | Method and device for recommending service | |
CN113221572A (en) | Information processing method, device, equipment and medium | |
CN112818147A (en) | Picture processing method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |