-
公开(公告)号:US12131127B2
公开(公告)日:2024-10-29
申请号:US18088588
申请日:2022-12-25
Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
Inventor: William Tunstall-Pedoe , Finlay Curran , Harry Roscoe , Robert Heywood
IPC: G06N5/02 , G06F16/242 , G06F16/31 , G06F16/332 , G06F16/951 , G06F40/123 , G06F40/126 , G06F40/20 , G06F40/205 , G06F40/211 , G06F40/226 , G06F40/242 , G06F40/279 , G06F40/30 , G06F40/35 , G06F40/45 , G06F40/47 , G06F40/58 , G06N3/0442 , G06N3/0455 , G06N3/0499 , G06N3/08 , G06Q10/1053 , G06Q30/0251 , G06Q30/0601 , G10L15/16 , G10L15/18 , G10L15/22 , G10L15/26 , G10L25/63 , G16H10/60 , H04L51/02 , G06N3/091 , G10L15/08
CPC classification number: G06F40/35 , G06F16/243 , G06F16/322 , G06F16/3329 , G06F16/951 , G06F40/123 , G06F40/126 , G06F40/20 , G06F40/205 , G06F40/211 , G06F40/226 , G06F40/242 , G06F40/279 , G06F40/30 , G06F40/45 , G06F40/47 , G06F40/58 , G06N3/0442 , G06N3/0455 , G06N3/0499 , G06N3/08 , G06N5/02 , G06Q10/1053 , G06Q30/0255 , G06Q30/0257 , G06Q30/0631 , G10L15/16 , G10L15/1815 , G10L15/22 , G10L15/26 , G10L25/63 , G16H10/60 , H04L51/02 , G06N3/091 , G10L2015/088
Abstract: A computer implemented method for automated analysis or use of data, comprising: (a) storing in a non-transitory computer-readable medium a structured, machine-readable representation of data that conforms to a machine-readable language, wherein the data relates to social media postings; (b) automatically processing structured, machine-readable representation of data to determine if the social media postings are compliant with requirements preventing abusive or illegal social media postings.
-
公开(公告)号:US20240347201A1
公开(公告)日:2024-10-17
申请号:US18747433
申请日:2024-06-18
Applicant: FUJIFILM Corporation
Inventor: Kenichi HARADA
IPC: G16H50/20 , G06F40/242 , G06T7/00 , G10L15/22
CPC classification number: G16H50/20 , G06F40/242 , G06T7/0012 , G10L15/22 , G06T2207/10068 , G06T2207/30096 , G10L2015/223
Abstract: Provided are an information processing device, a tablet terminal, an operating method for an information processing device, an information processing program, and a recording medium with which record information related to endoscopy can be acquired in a stress-free manner using natural utterances during endoscopy. The tablet terminal includes a processor (110) and a first dictionary (122) in which record information to be recorded in relation to endoscopy is registered. The first dictionary (122) is configured such that identifying characters that differ from the record information and the record information are associated with each other. The processor (110) recognizes speech which is uttered by a user during endoscopy and which expresses the identifying characters, and acquires the record information corresponding to the identifying characters from the first dictionary (122) on the basis of the recognized identifying characters.
-
公开(公告)号:US12111919B2
公开(公告)日:2024-10-08
申请号:US17464413
申请日:2021-09-01
Applicant: Fortinet, Inc.
Inventor: Sameer T. Khanna
IPC: G06F21/55 , G06F18/24 , G06F21/31 , G06F21/62 , G06F40/242 , G06F40/279 , G06F40/284 , G06V10/56 , G06V10/764 , G06V10/776 , G06V40/20 , H04L9/40 , H04L43/045 , G06F40/205
CPC classification number: G06F21/552 , G06F18/24 , G06F21/316 , G06F21/6218 , G06F40/242 , G06F40/279 , G06F40/284 , G06V10/56 , G06V10/764 , G06V10/776 , G06V40/20 , H04L43/045 , H04L63/1416 , H04L63/1425 , G06F40/205
Abstract: Systems, devices, and methods are discussed for identifying possible improper file accesses by an endpoint device. In some cases an agent is placed on each system to be surveilled that records the absolute paths for each file accessed for each user. This information may be accumulated and sent to a central server or computer for analysis of all such file accesses on a user basis. In some cases, a file access tree is created, and in some implementations be pruned of branches and leaves if deemed to be duplicates or very similar to other branched and leaves via a Levenshtein distance threshold. The resulting tree's edges may be scaled in particular implementations based on the deviation of a user's file accesses from their sphere of permissions. A variance metric may be computed from the final tree's form to capture the user's access patterns.
-
公开(公告)号:US12106045B2
公开(公告)日:2024-10-01
申请号:US17500221
申请日:2021-10-13
Applicant: International Business Machines Corporation
Inventor: Anupama Ray , Christopher Fryett , Amitkumar Manoharrao Paradkar , Nicholas Tsang , Florian Wilhelm
IPC: G06F40/20 , G06F40/186 , G06F40/205 , G06F40/242 , G06F40/253 , G06F40/289 , G06N3/02
CPC classification number: G06F40/205 , G06F40/186 , G06F40/242 , G06F40/253 , G06F40/289 , G06N3/02 , G06F40/20
Abstract: A computer-implemented method, system and computer program product for generating rules to be utilized by a rule-based system. A parser analyzes a received string of words according to grammatical rules to generate a parse tree. The parse tree may then be reviewed by a user to determine if such a parse tree represents the appropriate syntactic structure of the string of words. If the user believes that the parse tree does not represent the appropriate syntactic structure of the string, then the user, who does not need to possess the expertise of natural language processing, may select the nodes and/or edges of the parse tree in a particular order that corresponds to the correct syntactic structure of the string of words. A grammatical rule is then created for parsing the string of words based on the user selection of nodes and/or edges of the parse tree in a particular order.
-
公开(公告)号:US20240320081A1
公开(公告)日:2024-09-26
申请号:US18670728
申请日:2024-05-21
Applicant: Microsoft Technology Licensing, LLC
Inventor: Allison Mae GIDDINGS , Mo ZHOU , Dong YUAN
IPC: G06F11/07 , G06F11/32 , G06F11/34 , G06F40/226 , G06F40/242 , G06N20/00
CPC classification number: G06F11/079 , G06F11/321 , G06F11/3409 , G06F40/226 , G06F40/242 , G06N20/00
Abstract: Examples provide a system and method for retraining a machine learning (ML) algorithm associated with a trained model using root cause pattern recognition. The system analyzes the results of parsing unstructured data and identifies a root cause pattern causing the trained model to underperform when parsing data including the identified pattern. Examples of data including the pattern are created for use in retraining the model to correctly detect and parse data following the identified pattern. Once retrained, the model is able to parse unstructured data, including data having the identified pattern, in accordance with expected performance metrics. The system automatically identifies parsing errors, identifies the root cause patterns for these errors and retrains the models to correctly handle those patterns for more accurate and efficient handing of unstructured data by trained models.
-
公开(公告)号:US12093662B2
公开(公告)日:2024-09-17
申请号:US17932909
申请日:2022-09-16
Applicant: Robert F. Deming, Jr.
Inventor: Robert F. Deming, Jr.
Abstract: A device includes a memory adapted to store a list in a file or database comprising a plurality of vocabulary words in a first language and, for each vocabulary word, a corresponding word in a second language, a display device, and a processor. The processor is adapted to receive a plurality of words in the first language, select one or more words among the plurality of words, based on one or more predetermined criteria, translate, match or equate the one or more selected words from the first language to words of the second language, and cause the display device to display the plurality of words, wherein one or more first words that are in the plurality of words and are not among the one or more selected words which are displayed in the first language and one or more second words that are in the plurality of words and are among the one or more selected words are displayed in the second language.
-
公开(公告)号:US12093654B2
公开(公告)日:2024-09-17
申请号:US17814516
申请日:2022-07-24
Applicant: FUJITSU LIMITED
Inventor: Mehdi Bahrami , Wei-Peng Chen
IPC: G06F40/30 , G06F8/30 , G06F8/36 , G06F8/41 , G06F8/65 , G06F8/73 , G06F11/36 , G06F16/951 , G06F18/20 , G06F18/22 , G06F18/23213 , G06F40/166 , G06F40/211 , G06F40/216 , G06F40/242 , G06F40/40 , G06F40/44 , G06N3/04 , G06N3/08
CPC classification number: G06F40/30 , G06F8/30 , G06F8/36 , G06F8/42 , G06F8/436 , G06F8/65 , G06F8/73 , G06F11/3624 , G06F16/951 , G06F18/22 , G06F18/23213 , G06F18/285 , G06F40/166 , G06F40/211 , G06F40/216 , G06F40/242 , G06F40/40 , G06F40/44 , G06N3/04 , G06N3/08
Abstract: According to an aspect of an embodiment, operations for code enrichment through metadata for code synthesis are provided. The operations include acquiring package data that include source code files and package metadata. The operations further include extracting additional metadata associated with software package and preparing metadata features based on the package metadata and the additional metadata. The operations further include identifying a set of target portions of a source code included in the source code files and updating one or more source code files using the metadata features. Such files are updated by performing at least one of a revision of existing code comments, and an addition of new code comments for the target portions. The operations further include generating a dataset of natural language (NL) text features and respective code features and training a language model on a sequence-to-sequence generation task.
-
公开(公告)号:US20240303418A1
公开(公告)日:2024-09-12
申请号:US18119123
申请日:2023-03-08
Applicant: CARLOTA DANIEL
Inventor: CARLOTA DANIEL
IPC: G06F40/174 , G06F40/242
CPC classification number: G06F40/174 , G06F40/242
Abstract: A method, apparatus, and storage media for implementing an intelligent form filling system are provided. The system generates an association between a first field name and a second field name based on entry of field values by users into a first form document at a first device within a plurality of devices connected to a network and stores the association in a field name dictionary data structure at a server device connected to the network to form a field name association. The system identifies a field name in a second form document that matches the first field name or the second field name in the field name association. In response to the second user entering a value into the identified field, the system causes to be presented to the second user a prompt to associate the first field name and the second field name in a data file.
-
公开(公告)号:US20240281618A1
公开(公告)日:2024-08-22
申请号:US18649304
申请日:2024-04-29
Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
Inventor: William TUNSTALL-PEDOE , Finlay CURRAN , Harry ROSCOE , Robert HEYWOOD
IPC: G06F40/35 , G06F16/242 , G06F16/31 , G06F16/332 , G06F16/951 , G06F40/123 , G06F40/126 , G06F40/20 , G06F40/205 , G06F40/211 , G06F40/226 , G06F40/242 , G06F40/279 , G06F40/30 , G06F40/45 , G06F40/47 , G06F40/58 , G06N3/0442 , G06N3/0455 , G06N3/0499 , G06N3/08 , G06N3/091 , G06N5/02 , G06Q10/1053 , G06Q30/0251 , G06Q30/0601 , G10L15/08 , G10L15/16 , G10L15/18 , G10L15/22 , G10L15/26 , G10L25/63 , G16H10/60 , H04L51/02
CPC classification number: G06F40/35 , G06F16/243 , G06F16/322 , G06F16/3329 , G06F16/951 , G06F40/123 , G06F40/126 , G06F40/20 , G06F40/205 , G06F40/211 , G06F40/226 , G06F40/242 , G06F40/279 , G06F40/30 , G06F40/45 , G06F40/47 , G06F40/58 , G06N3/0442 , G06N3/0455 , G06N3/0499 , G06N3/08 , G06N5/02 , G06Q10/1053 , G06Q30/0255 , G06Q30/0257 , G06Q30/0631 , G10L15/16 , G10L15/1815 , G10L15/22 , G10L15/26 , G10L25/63 , G16H10/60 , H04L51/02 , G06N3/091 , G10L2015/088
Abstract: A computer implemented method for the automated analysis or use of data is implemented by a voice assistant. The method comprises the steps of: (a) storing in a memory a structured, machine-readable representation of data that conforms to a machine-readable language (‘machine representation’); the machine representation including representations of user speech or text input to a human/machine interface; and (b) automatically processing the machine representations to analyse the user speech or text input.
-
公开(公告)号:US20240275805A1
公开(公告)日:2024-08-15
申请号:US18641610
申请日:2024-04-22
Applicant: Intellective Ai, Inc.
Inventor: Ming-Jung SEOW , Wesley Kenneth COBB , Gang XU , Tao YANG , Aaron POFFENBERGER , Lon W. RISINGER , Kishor Adinath SAITWAL , Michael S. YANTOSCA , David M. SOLUM , Alex David HEMSATH , Dennis G. URECH , Duy Trong NGUYEN , Charles Richard MORGAN
IPC: H04L9/40 , G06F40/226 , G06F40/242 , G06F40/247 , G06F40/253 , G06F40/284 , G06F40/289 , G06F40/30 , G06F40/40 , G06N20/00
CPC classification number: H04L63/1425 , G06F40/226 , G06F40/242 , G06F40/289 , G06F40/30 , G06N20/00 , H04L63/1408 , G06F40/247 , G06F40/253 , G06F40/284 , G06F40/40
Abstract: Embodiments presented herein describe techniques for generating a linguistic model of input data obtained from a data source (e.g., a video camera). According to one embodiment of the present disclosure, a sequence of symbols is generated based on an ordered stream of normalized vectors generated from the input data. A dictionary of words is generated from combinations of the ordered sequence of symbols based on a frequency at which combinations of symbols appear in the ordered sequence of symbols. A plurality of phrases is generated based an ordered sequence of words from the dictionary observed in the ordered sequence of symbols based on a frequency by which combinations of words in ordered sequence of words appear relative to one another.
-
-
-
-
-
-
-
-
-