Real-time classification of evolving dictionaries

    公开(公告)号:US10691770B2

    公开(公告)日:2020-06-23

    申请号:US15817597

    申请日:2017-11-20

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: A method including identifying an emotion identifier from a message using an emotion identifier table is provided. The method includes separating emotion identifier from the message, splitting a portion into multiple tokens delimited by a space or a punctuation mark, and determining a score for the message based on an emotion score in the emotion identifier table, and on at least one of the multiple tokens. The method includes adding a token from the multiple tokens to the emotion identifier table based on a contribution from the token to the message score, associating a sentiment score for the token in the emotion identifier table based on the contribution of the token to the message score, and modifying an emotion score of the token when the token is already included in the emotion identifier table based on the contribution of the token to the message sentiment score.

    SYSTEM AND METHOD FOR PROCESSING COMPLEX DATASETS BY CLASSIFYING ABSTRACT REPRESENTATIONS THEREOF

    公开(公告)号:US20190156193A1

    公开(公告)日:2019-05-23

    申请号:US15817466

    申请日:2017-11-20

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: In the present disclosure, a system for analyzing complex datasets includes one or more servers, one or more machine learning algorithms, one or more client devices having one or more displays, and a network connecting the one or more servers and the one or more client devices. A complex dataset is stored on the one or more servers and is parsed into one or more chunks, which are abstracted as a plurality of abstract representations to form a plurality of graphical matrices. Still further, the one or more servers transmit, over the network to the one or more client devices, graphical matrices developed from the complex dataset for display to a human observer. The system includes the human observer comparing the first and second graphical matrices as well as classifying the graphical matrices, and said classification providing the one or more machine learning algorithms with information about the complex dataset.

    HEALTH TREND ANALYSIS AND INSPECTION
    13.
    发明申请

    公开(公告)号:US20190130066A1

    公开(公告)日:2019-05-02

    申请号:US15795544

    申请日:2017-10-27

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Methods for providing health trend analysis and inspection are provided. In one aspect, a method includes detecting a presence of a user. The method also includes determining that a threshold time period has elapsed. The method also includes retrieving, from a server, a health query customized for the user based on a patient data store associated with the user. The method also includes prompting the user to provide a response to the health query. The method also includes storing the response to the health query and an associated timestamp in a secure package. The method also includes uploading the secure package to the server via an available network connection to cause the server to store the contents of the secure package and perform an action based on one or more analysis algorithms applied on the patient data store associated with the user. Systems and machine-readable media are also provided.

    COMPUTATIONAL PHYLOGENETIC ANALYSIS
    14.
    发明申请

    公开(公告)号:US20190078156A1

    公开(公告)日:2019-03-14

    申请号:US15704157

    申请日:2017-09-14

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Systems and a method for computationally analyzing genetic base pairs are provided. In one or more aspects, a system includes a memory and a processor coupled to the memory. The processor is configured to receive a number of genetic sequences from a genetic sequencer device. The processor can generate, for each genetic sequence, a binary sequence. Each binary sequence is partitioned into a set of binary strings. Each binary string includes multiple binary base pairs. A set of entropy values are determined, each entropy value is associated with a binary string, and an entropy distribution function (EDF) is generated based on the set of entropy values.

    NON-LINGUISTIC CONTENT ANALYSIS SYSTEM
    15.
    发明申请

    公开(公告)号:US20190057146A1

    公开(公告)日:2019-02-21

    申请号:US15679714

    申请日:2017-08-17

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Methods for non-linguistic content analysis of a selected body of data are provided. In one aspect, a method includes identifying a delimiter token, parsing a reference base into reference units based on the delimiter token, calculating and storing a frequency of each occurrence of each reference unit of the reference base and a total number of occurrences of all reference units of the reference base, parsing the selected body of data into data units, calculating and storing a score for each data unit of the selected body of data, and providing a ranked list of concepts associate with the selected body of data. Systems and machine-readable media are also provided.

    Genetic generation of tools for convolutional neural network

    公开(公告)号:US11120338B2

    公开(公告)日:2021-09-14

    申请号:US15817539

    申请日:2017-11-20

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Methods for genetic generation of tools for use in a convolutional neural network are provided. Randomly generated starting points and sets of positive and negative tasks are distributed to multiple processors. Each processor iterates an instruction queue over its received tasks based on existing analysis tools, generating a test score for each iteration. A set of instructions is saved as a new tool if its generated test score determines a successful test. A convolutional neural network is executed over complex test cases based on a tool set that includes the new tools. Output results of the convolutional neural network are analyzed and a new tool set is created by removing tools that are not utilized in generating the output results. Systems and machine-readable media are also provided.

    Tracking the mental acuity of an electronic device user

    公开(公告)号:US10509691B2

    公开(公告)日:2019-12-17

    申请号:US15794660

    申请日:2017-10-26

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: A method including retrieving, from an operating system of a client device, a timestamp associated with a physical action on an input device coupled with the client device, is provided. The method includes tagging the timestamp with an action metadata of an application running in the client device, the physical action being associated with the application, and forming an aggregated dataset comprising the timestamp and the action metadata. The method also includes associating an acuity value to the timestamp based on the aggregated dataset, and modifying a display of an application output to indicate the acuity value within the application. A system and a non-transitory, computer readable medium storing instructions to perform the method are also provided.

    SYSTEM AND METHOD FOR ENCRYPTING INFORMATION WITH POLYNOMIAL DISTRIBUTED STRINGS

    公开(公告)号:US20190288838A1

    公开(公告)日:2019-09-19

    申请号:US15923897

    申请日:2018-03-16

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: An encryption system is provided. The system includes a plurality of communication devices, one or more processors, one or more memory components, one or more network connections, and a data repository. The data repository is stored by the plurality of communication devices on the one or more memory components thereof. A polynomial function is developed to point to message data within the data repository, wherein the polynomial function is transmitted between the plurality of communication devices to exchange the message data.

    METHOD AND DEVICE FOR PARTITION-BASED IMAGE TRACKING

    公开(公告)号:US20190244370A1

    公开(公告)日:2019-08-08

    申请号:US15888587

    申请日:2018-02-05

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    CPC classification number: G06T7/248 G06T7/74 G06T2207/10004 G06T2207/20021

    Abstract: Methods for partition-based image tracking are provided. In one aspect, a method includes determining a number of partitions for each image frame of image frames and dividing a first image frame of the image frames into first partitions and a second image frame of the image frames into second partitions based on the number of partitions. The method also includes detecting for a change between each of the first partitions of the first image frame and a corresponding second partition of the second partitions of the second image frame. The method also includes configuring priority settings for the second partitions based on the detection, and processing the second image frame and a third image frame based on the priority settings to detect for a change between each of the second partitions and a corresponding third partition of third partitions of a third image. Systems and machine-readable media are also provided.

    SYSTEM AND METHOD FOR NEAR REAL-TIME ANALYSIS OF INTERESTS AND SENTIMENT

    公开(公告)号:US20190156350A1

    公开(公告)日:2019-05-23

    申请号:US15817714

    申请日:2017-11-20

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: A system for analyzing user sentiment includes one or more processors, one or more memory components, one or more network connections, and first and second databases. Further according to this aspect, the first database includes a plurality of concepts partially developed by processing a plurality of data repositories, and the second database includes a user record partially developed by processing data related to post content. Still further, the one or more processors search the second database by one or more interests to determine one or more user interest levels, and the one or more interests are correlated with one or more of the plurality of concepts.

Patent Agency Ranking