Patents by Inventor Hamed Ahmadi
Hamed Ahmadi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11704386Abstract: Herein are feature extraction mechanisms that receive parsed log messages as inputs and transform them into numerical feature vectors for machine learning models (MLMs). In an embodiment, a computer extracts fields from a log message. Each field specifies a name, a text value, and a type. For each field, a field transformer for the field is dynamically selected based the field's name and/or the field's type. The field transformer converts the field's text value into a value of the field's type. A feature encoder for the value of the field's type is dynamically selected based on the field's type and/or a range of the field's values that occur in a training corpus of an MLM. From the feature encoder, an encoding of the value of the field's typed is stored into a feature vector. Based on the MLM and the feature vector, the log message is detected as anomalous.Type: GrantFiled: March 12, 2021Date of Patent: July 18, 2023Assignee: Oracle International CorporationInventors: Amin Suzani, Saeid Allahdadian, Milos Vasic, Matteo Casserini, Hamed Ahmadi, Felix Schmidt, Andrew Brownsword, Nipun Agarwal
-
Publication number: 20220405781Abstract: A system for managing customer feedback regarding a product or service is disclosed, particularly, at a point-of-sale location. The system includes a backend system and a frontend system wherein feedback from a customer regarding the product or service is collected using the frontend system. The feedback is transmitted to the backend system where one or more sales or business hypothesis are generated to present to the customer to acquire further feedback from the customer. One or more action items, such as product offering optimization, marketing campaign customization, and inventory management can be suggested based on the customer response to the generated hypothesis.Type: ApplicationFiled: February 16, 2022Publication date: December 22, 2022Inventors: Hamed Ahmadi, Parinaz Vahabzadeh
-
Patent number: 11514697Abstract: Herein is a probabilistic indexing technique for searching semi-structured text documents in columnar storage formats such as Parquet, using columnar input/output (I/O) avoidance, and needing minimal storage overhead. In an embodiment, a computer associates columns with text strings that occur in semi-structured documents. Text words that occur in the text strings are detected. Respectively for each text word, a bitmap, of a plurality of bitmaps, that contains a respective bit for each column is generated. Based on at least one of the bitmaps, some of the columns or some of the semi-structured documents are accessed.Type: GrantFiled: July 15, 2020Date of Patent: November 29, 2022Assignee: Oracle International CorporationInventors: Jian Wen, Hamed Ahmadi, Sanjay Jinturkar, Nipun Agarwal, Lijian Wan, Shrikumar Hariharasubrahmanian
-
Patent number: 11451670Abstract: Herein are machine learning (ML) techniques for unsupervised training with a corpus of signaling system 7 (SS7) messages having a diversity of called and calling parties, operation codes (opcodes) and transaction types, numbering plans and nature of address indicators, and mobile country codes and network codes. In an embodiment, a computer stores SS7 messages that are not labeled as anomalous or non-anomalous. Each SS7 message contains an opcode and other fields. For each SS7 message, the opcode of the SS7 message is stored into a respective feature vector (FV) of many FVs that are based on respective unlabeled SS7 messages. The FVs contain many distinct opcodes. Based on the FVs that contain many distinct opcodes and that are based on respective unlabeled SS7 messages, an ML model such as a reconstructive model such as an autoencoder is unsupervised trained to detect an anomalous SS7 message.Type: GrantFiled: December 16, 2020Date of Patent: September 20, 2022Assignee: Oracle International CorporationInventors: Hamed Ahmadi, Ali Moharrer, Venkatanathan Varadarajan, Vaseem Akram, Nishesh Rai, Reema Hingorani, Sanjay Jinturkar, Nipun Agarwal
-
Publication number: 20220292304Abstract: Herein are feature extraction mechanisms that receive parsed log messages as inputs and transform them into numerical feature vectors for machine learning models (MLMs). In an embodiment, a computer extracts fields from a log message. Each field specifies a name, a text value, and a type. For each field, a field transformer for the field is dynamically selected based the field's name and/or the field's type. The field transformer converts the field's text value into a value of the field's type. A feature encoder for the value of the field's type is dynamically selected based on the field's type and/or a range of the field's values that occur in a training corpus of an MLM. From the feature encoder, an encoding of the value of the field's typed is stored into a feature vector. Based on the MLM and the feature vector, the log message is detected as anomalous or not.Type: ApplicationFiled: March 12, 2021Publication date: September 15, 2022Inventors: AMIN SUZANI, SAEID ALLAHDADIAN, MILOS VASIC, MATTEO CASSERINI, HAMED AHMADI, FELIX SCHMIDT, ANDREW BROWNSWORD, NIPUN AGARWAL
-
Publication number: 20220188410Abstract: Approaches herein relate to reconstructive models such as an autoencoder for anomaly detection. Herein are machine learning techniques that detect and suppress any feature that causes model decay by concept drift. In an embodiment in a production environment, a computer initializes an unsuppressed subset of features with a plurality of features that an already-trained reconstructive model can process. A respective reconstruction error of each feature of the unsuppressed subset of features is calculated. The computer detects that a respective moving average based on the reconstruction error of a particular feature of the unsuppressed subset of features exceeds a respective feature suppression threshold of the particular feature, which causes removal of the particular feature from the unsuppressed subset of features.Type: ApplicationFiled: December 15, 2020Publication date: June 16, 2022Inventors: SAEID ALLAHDADIAN, ANDREW BROWNSWORD, MILOS VASIC, MATTEO CASSERINI, AMIN SUZANI, HAMED AHMADI, FELIX SCHMIDT, NIPUN AGARWAL
-
Publication number: 20220188694Abstract: Approaches herein relate to model decay of an anomaly detector due to concept drift. Herein are machine learning techniques for dynamically self-tuning an anomaly score threshold. In an embodiment in a production environment, a computer receives an item in a stream of items. A machine learning (ML) model hosted by the computer infers by calculation an anomaly score for the item. Whether the item is anomalous or not is decided based on the anomaly score and an adaptive anomaly threshold that dynamically fluctuates. A moving standard deviation of anomaly scores is adjusted based on a moving average of anomaly scores. The moving average of anomaly scores is then adjusted based on the anomaly score. The adaptive anomaly threshold is then adjusted based on the moving average of anomaly scores and the moving standard deviation of anomaly scores.Type: ApplicationFiled: December 15, 2020Publication date: June 16, 2022Inventors: Amin Suzani, Matteo Casserini, Milos Vasic, Saeid Allahdadian, Andrew Brownsword, Hamed Ahmadi, Felix Schmidt, Nipun Agarwal
-
Publication number: 20220191332Abstract: Herein are machine learning (ML) techniques for unsupervised training with a corpus of signaling system 7 (SS7) messages having a diversity of called and calling parties, operation codes (opcodes) and transaction types, numbering plans and nature of address indicators, and mobile country codes and network codes. In an embodiment, a computer stores SS7 messages that are not labeled as anomalous or non-anomalous. Each SS7 message contains an opcode and other fields. For each SS7 message, the opcode of the SS7 message is stored into a respective feature vector (FV) of many FVs that are based on respective unlabeled SS7 messages. The FVs contain many distinct opcodes. Based on the FVs that contain many distinct opcodes and that are based on respective unlabeled SS7 messages, an ML model such as a reconstructive model such as an autoencoder is unsupervised trained to detect an anomalous SS7 message.Type: ApplicationFiled: December 16, 2020Publication date: June 16, 2022Inventors: Hamed Ahmadi, Ali Moharrer, Venkatanathan Varadarajan, Vaseem Akram, Nishesh Rai, Reema Hingorani, Sanjay Jinturkar, Nipun Agarwal
-
Publication number: 20220108181Abstract: A multilayer perceptron herein contains an already-trained combined sequence of residual blocks that contains a semantic sequence of residual blocks and a contextual sequence of residual blocks. The semantic sequence of residual blocks contains a semantic sequence of layers of an autoencoder. The contextual sequence of residual blocks contains a contextual sequence of layers of a recurrent neural network. Each residual block of the combined sequence of residual blocks is used based on a respective survival probability. By the autoencoder and based on the using each residual block of the semantic sequence, a previous entry of a log is semantically encoded. By the recurrent neural network and based on the using each residual block of the contextual sequence, a next entry of the log is predicted. In an embodiment during training, survival probabilities are hyperparameters that are learned and used to probabilistically skip residual blocks such that the multilayer perceptron has stochastic depth.Type: ApplicationFiled: October 7, 2020Publication date: April 7, 2022Inventors: HAMED AHMADI, SAEID ALLAHDADIAN, MATTEO CASSERINI, MILOS VASIC, AMIN SUZANI, FELIX SCHMIDT, ANDREW BROWNSWORD, NIPUN AGARWAL
-
Patent number: 11238035Abstract: Techniques are described herein for indexing personal information in columnar data storage format based files. In an embodiment, row groups of rows that comprise a plurality of columns are stored in a set of files. Each column of a row group is stored in a chunk of column pages in the set of files. A regular expression index that indexes a particular column in the set of files is stored for each row group. The regular expression index identifies column pages in the chunk of the particular column that include a particular column value that satisfies a regular expression specified in a query. The regular expression specified in the query in evaluated against the particular column using the regular expression index.Type: GrantFiled: March 10, 2020Date of Patent: February 1, 2022Assignee: ORACLE INTERNATIONAL CORPORATIONInventors: Hamed Ahmadi, Jian Wen, Shrikumar Hariharasubrahmanian, Sanjay Jinturkar, Nipun Agarwal
-
Publication number: 20220019784Abstract: Herein is a probabilistic indexing technique for searching semi-structured text documents in columnar storage formats such as Parquet, using columnar input/output (I/O) avoidance, and needing minimal storage overhead. In an embodiment, a computer associates columns with text strings that occur in semi-structured documents. Text words that occur in the text strings are detected. Respectively for each text word, a bitmap, of a plurality of bitmaps, that contains a respective bit for each column is generated. Based on at least one of the bitmaps, some of the columns or some of the semi-structured documents are accessed.Type: ApplicationFiled: July 15, 2020Publication date: January 20, 2022Inventors: Jian Wen, Hamed Ahmadi, Sanjay Jinturkar, Nipun Agarwal, Lijian Wan, Shrikumar Hariharasubrahmanian
-
Publication number: 20210286806Abstract: Techniques are described herein for indexing personal information in columnar data storage format based files. In an embodiment, row groups of rows that comprise a plurality of columns are stored in a set of files. Each column of a row group is stored in a chunk of column pages in the set of files. A regular expression index that indexes a particular column in the set of files is stored for each row group. The regular expression index identifies column pages in the chunk of the particular column that include a particular column value that satisfies a regular expression specified in a query. The regular expression specified in the query in evaluated against the particular column using the regular expression index.Type: ApplicationFiled: March 10, 2020Publication date: September 16, 2021Inventors: Hamed Ahmadi, Jian Wen, Shrikumar Hariharasubrahmanian, Sanjay Jinturkar, Nipun Agarwal
-
Publication number: 20200410609Abstract: A system for managing and tracking plant management at a site is provided. The system includes a device management server and a plant management device communicatively connected to the device management server via a network. The plant management device is configured to: receive a plant management task order including task instructions for performing a plant management task and automatically perform the plant management task according to the task instructions; send a task receipt notification to the device management server, the task receipt notification including task beneficiary data; and transmit task performance data to the device management server, the task performance data logged during performance of the plant management task.Type: ApplicationFiled: September 14, 2020Publication date: December 31, 2020Inventors: Farhang Bidram, Hamed Ahmadi, Afshin Doustmohammadi
-
Patent number: 10810687Abstract: A system for managing and tracking plant management at a site is provided. The system includes a device management server and a plant management device communicatively connected to the device management server via a network. The plant management device is configured to: receive a plant management task order including task instructions for performing a plant management task and automatically perform the plant management task according to the task instructions; send a task receipt notification to the device management server, the task receipt notification including task beneficiary data; and transmit task performance data to the device management server, the task performance data logged during performance of the plant management task.Type: GrantFiled: July 9, 2019Date of Patent: October 20, 2020Assignee: Advanced Intelligent Systems Inc.Inventors: Farhang Bidram, Hamed Ahmadi, Afshin Doustmohammadi
-
Publication number: 20200118222Abstract: A system for managing and tracking plant management at a site is provided. The system includes a device management server and a plant management device communicatively connected to the device management server via a network. The plant management device is configured to: receive a plant management task order including task instructions for performing a plant management task and automatically perform the plant management task according to the task instructions; send a task receipt notification to the device management server, the task receipt notification including task beneficiary data; and transmit task performance data to the device management server, the task performance data logged during performance of the plant management task.Type: ApplicationFiled: July 9, 2019Publication date: April 16, 2020Inventors: Farhang Bidram, Hamed Ahmadi, Afshin Doustmohammadi