Abstract: In some implementations, a system may capture audio from a call between a calling device and a called device. The system may filter the captured audio to generate a background audio layer. The system may generate an audio footprint that is a representation of sound in the background audio layer. The system may determine that the audio footprint includes a triggering sound footprint based on one or more audio characteristics of the audio footprint. The system may detect synthetic sound based on the audio footprint and after determining that the audio footprint includes the triggering sound footprint, wherein the synthetic sound is indicative of a sound recording. The system may transmit a notification to one or more devices associated with the call based on detecting the synthetic sound.

Abstract: Systems and methods for rearranging tags on a graphical user interface (GUI) based on known and unknown levels of web traffic are disclosed. To provide users with real estate listings that have popular home attributes with respect to a given region, the system uses known user interaction information to determine predicted user interaction information for real estate listing phrases (e.g., tags) that are associated with unknown user interaction information. The system then ranks the real estate listing phrases based on each real estate listing phrase's user interaction information. Based on the ranked real estate listing phrases, the system generates for display the highest ranked real estate listing phrase in association with a real estate listing being associated with the real estate listing phrase.

Abstract: Systems and methods of the present disclosure enable database search. The systems and/or methods may include receiving a search query that includes an input document having text. Word embeddings are generated within the input document, where the word embeddings include vector representations of words in the text of the input document. An average input document word embedding vector is determined for the word embeddings of the input document. A set of stored documents is accessed, where each stored document includes a stored text has a particular average stored document word embedding vector. A similarity model is used to determine a similarity metric measuring the similarity between the input document and each stored document based on the average input document word embedding vector and the particular average stored document word embedding vector of each stored document.

Abstract: A system may include processor(s), and memory in communication with the processor(s) and storing instructions configured to cause the system to correct ASR errors. The system may receive a transcription comprising transcribed word(s) and may determine whether the transcribed word(s) exceed associated predefined confidence level(s). Responsive to determining a transcribed word does not exceed a predefined confidence level, the system may generate a predicted word. The system may calculate a distance between numerical representations of the transcribed word and the predicted word and may determine whether the distance exceeds a predefined threshold. Responsive to determining the distance exceeds the predefined threshold, the system may determine whether at least one red flag word of a list of red flag words corresponds to a context of the transcription, and, responsive to making that determination, may classify the transcription as associated with a first category.

Abstract: An alignment method includes directing an illumination beam with a first polarization state to form a diffracted beam with a second polarization state from an alignment target, and passing the diffracted beam through a polarization analyzer. The alignment method further includes measuring a polarization state of the diffracted beam and determining a location of the alignment target from the measured polarization state relative to its initial polarization state. The alignment target includes a plurality of diffraction gratings with a single pitch and two or more duty cycles, wherein the pitch is smaller than a wavelength of the illumination beam, and the location of the alignment target corresponds to the duty cycle of the diffraction grating.

Abstract: A system and method for automatic remote mobile device data extraction is provided. The system and method can include transmitting a request to extract data from a server at a first location to a computer that is at a second location, where the mobile device is connected to the computer. A web link and an activation code can be provided that allows for downloading an agent application on the computer to assist with the request, and a list of exact data elements to be extracted can also be provided. The data can be extracted from the mobile device and sent to the server.

Abstract: Systems and methods for rearranging tags on a graphical user interface (GUI) based on known and unknown levels of web traffic are disclosed. To provide users with real estate listings that have popular home attributes with respect to a given region, the system uses known user interaction information to determine predicted user interaction information for real estate listing phrases (e.g., tags) that are associated with unknown user interaction information. The system then ranks the real estate listing phrases based on each real estate listing phrase's user interaction information. Based on the ranked real estate listing phrases, the system generates for display the highest ranked real estate listing phrase in association with a real estate listing being associated with the real estate listing phrase.

Abstract: A system may include processor(s), and memory in communication with the processor(s) and storing instructions configured to cause the system to correct ASR errors. The system may receive a transcription comprising transcribed word(s) and may determine whether the transcribed word(s) exceed associated predefined confidence level(s). Responsive to determining a transcribed word does not exceed a predefined confidence level, the system may generate a predicted word. The system may calculate a distance between numerical representations of the transcribed word and the predicted word and may determine whether the distance exceeds a predefined threshold. Responsive to determining the distance exceeds the predefined threshold, the system may determine whether at least one red flag word of a list of red flag words corresponds to a context of the transcription, and, responsive to making that determination, may classify the transcription as associated with a first category.

Abstract: Systems and methods of the present disclosure enable variable and dynamic feedback to electronic activities by receiving event data and utilizing a feedback machine learning model to predict an average feedback attribute and an average feedback variability attribute based on the event data. A feedback data entry is added to a user profile to store the average feedback attribute and the average feedback variability attribute. A new event and a new event attribute are received for the user profile, and a feedback probability distribution for the new event is generated based on the new event attribute, the average feedback attribute, and the average feedback variability attribute. A new event feedback is generated for the new event based on a random selection from the feedback probability distribution and is output to a computing device associated with the user profile.

Abstract: Systems and methods for providing visual indications of time sensitive real estate listing information on a Graphical User Interface (GUI) are disclosed. To provide users with visual indications of real estate listings that may sell soon with respect to a given region, the system uses days-sold information, real estate listing attributes, and user interaction data corresponding to a set of real estate listings associated with a given region to train a machine learning model to generate a selling soon prediction. The system then provides a days-on-market value, a set of home attributes, and user interaction data associated with a subject real estate listing as input to the machine learning model. The system then generates a selling soon prediction by applying the machine learning model and generates for display, on a GUI displaying information of the subject real estate listing, a visual indication of the selling soon prediction.

Abstract: Privacy cells can be configured to enable segmented control. A privacy cell can include a segmented array of electrodes that allow segments of liquid crystal to be independently controlled. By independently applying a voltage to each electrode, the liquid crystal within each segment can be independently oriented at a desired angle for a particular mode of operation.

Abstract: Privacy cells can be configured to enable segmented control. A privacy cell can include a segmented array of electrodes that allow segments of liquid crystal to be independently controlled. By independently applying a voltage to each electrode, the liquid crystal within each segment can be independently oriented at a desired angle for a particular mode of operation.