Abstract: Aspects of the present disclosure provide techniques for improved automated parsing and display of electronic documents. Embodiments include identifying a set of topics in a first electronic document based on one or more rules related to one or more keywords in the first electronic document. Embodiments include providing one or more inputs to a machine learning model based on the set of topics and a second electronic document related to the first electronic document. Embodiments include receiving, from the machine learning model in response to the one or more inputs, one or more outputs related to formatting the second electronic document for display. Embodiments include generating a formatted version of the first electronic document based on the set of topics and generating a formatted version of the second electronic document based on the one or more outputs.

Abstract: A visual-based classification model influenced by text features as a result of the outputs of a text-based classification model is disclosed. A system receives one or more documents to be classified based on one or more visual features and provides the one or more documents to a student classification model, which is a visual-based classification model. The system also classifies, by the student classification model, the one or more documents into one or more document types based on one or more visual features. The one or more visual features are generated by the student classification model that is trained based on important text identified by a teacher classification model for the one or more document types, with the teacher classification model being a text-based classification model. Generating training data and training the student classification model based on the training data are also described.

Abstract: Aspects of the present disclosure provide techniques for improved automated parsing and display of electronic documents. Embodiments include identifying a set of topics in a first electronic document based on one or more rules related to one or more keywords in the first electronic document. Embodiments include providing one or more inputs to a machine learning model based on the set of topics and a second electronic document related to the first electronic document. Embodiments include receiving, from the machine learning model in response to the one or more inputs, one or more outputs related to formatting the second electronic document for display. Embodiments include generating a formatted version of the first electronic document based on the set of topics and generating a formatted version of the second electronic document based on the one or more outputs.

Abstract: The present disclosure provides a portable terahertz security inspection apparatus, including: a carrying body; a terahertz emitting device arranged on the carrying body, wherein the terahertz emitting device includes a terahertz signal source and an emitting unit connected to the terahertz signal source and configured to emit a terahertz wave; a terahertz detector arranged on the carrying body and configured to receive the terahertz wave reflected from an inspected object; a data acquisition and processing system arranged on the carrying body and connected to the terahertz detector, wherein the data acquisition and processing system is configured to receive a scan data for the inspected object from the terahertz detector and generate a terahertz image; and a display device connected to the data acquisition and processing system and configured to receive and display the terahertz image from the data acquisition and processing system.

Abstract: A visual-based classification model influenced by text features as a result of the outputs of a text-based classification model is disclosed. A system receives one or more documents to be classified based on one or more visual features and provides the one or more documents to a student classification model, which is a visual-based classification model. The system also classifies, by the student classification model, the one or more documents into one or more document types based on one or more visual features. The one or more visual features are generated by the student classification model that is trained based on important text identified by a teacher classification model for the one or more document types, with the teacher classification model being a text-based classification model. Generating training data and training the student classification model based on the training data are also described.

Abstract: Aspects of the present disclosure provide techniques for improved text classification. Embodiments include providing, based on a text string, one or more first inputs to a summary model. Embodiments include determining, based on one or more first outputs from the summary model in response to the one or more first inputs, a summarized version of the text string. In some embodiments the summarized version of the text string comprises a number of tokens that is less than or equal to a maximum number of input tokens for a machine learning model. Embodiments include providing, based on the summarized version of the text string, one or more second inputs to the machine learning model. Embodiments include determining one or more attributes of the text string based on one or more second outputs received from the machine learning model in response to the one or more second inputs.

Abstract: Provided are a method and a device of binding security inspection information, an electronic apparatus and a storage medium, which may be applied to the field of security inspection technology. In the method of binding security inspection information of the present disclosure, the pedestrian detection frame is acquired by detecting the video stream, and each pedestrian detection frame has the coordinate information and the tracking information. According to the coordinate information and the tracking information of the pedestrian detection frame, the baggage security inspection information, the pedestrian security inspection information, and the identity information are bound to acquire all security inspection information of a detected person, so that a security inspection efficiency is improved.

Abstract: Certain aspects of the present disclosure provide techniques for detecting sentences that are utterances by an agent indicating an intent to poach a customer. According to certain embodiments, a language model is trained using query sentences that are confirmed to be sentences used in poaching a customer, to identify semantically similar sentences in a corpus. These semantically similar sentences are then used as base sentences for comparison to sentences in a transcript. Sentences of the transcript that are found to be semantically similar to one or more base sentences are provided to a user device for review and confirmation that the similar sentence was generated by an agent in an attempt to poach a customer.

Abstract: Provided are a circuit board, an apparatus and a method for forming a via hole structure. A via hole structure formed on a main body (10) of a circuit board includes a hole (12) enclosed by a conductive layer in the main body (10), the conductive layer constitutes a wall (11) of the hole (12), and a dielectric filling layer (13), which has a dielectric constant smaller than that of the main body (10), is disposed between at least a portion of the wall (11) of the hole (12) and the main body (10), so that the parasitic capacitance of a via hole is decreased, and the impedance of the via hole is increased to become closer to the impedance of a transmission line, thereby effectively improving impedance continuity of a system link.

Abstract: A terahertz detector and a method of manufacturing a terahertz detector, wherein the terahertz detector including a substrate (2) and at least one detection unit. Each detection unit includes: a channel material (1) arranged on the substrate, two electrodes (3, 4) respectively in ohmic contact with both ends of the channel material (1) in a longitudinal direction, and a three-dimensional grapheme (5) in direct or indirect thermal contact with the channel material (1).

Abstract: Provided are a connector structure, and a skew calculation method and device. Specifically, the connector structure includes: a first Printed Circuit Board (PCB) (12), which includes a first board (122) and a second board (124), and is connected to a testing device; and a second PCB (14), which includes a third board (142) and a fourth board (144), and is connected to the testing device. The first board (122) is connected to the third board (142) through a connector (16).

Abstract: The present disclosure provides a portable terahertz security inspection apparatus, including: a carrying body; a terahertz emitting device arranged on the carrying body, wherein the terahertz emitting device includes a terahertz signal source and an emitting unit connected to the terahertz signal source and configured to emit a terahertz wave; a terahertz detector arranged on the carrying body and configured to receive the terahertz wave reflected from an inspected object; a data acquisition and processing system arranged on the carrying body and connected to the terahertz detector, wherein the data acquisition and processing system is configured to receive a scan data for the inspected object from the terahertz detector and generate a terahertz image; and a display device connected to the data acquisition and processing system and configured to receive and display the terahertz image from the data acquisition and processing system.

Abstract: Provided are a circuit board, an apparatus and a method for forming a via hole structure. A via hole structure formed on a main body (10) of a circuit board includes a hole (12) enclosed by a conductive layer in the main body (10), the conductive layer constitutes a wall (11) of the hole (12), and a dielectric filling layer (13), which has a dielectric constant smaller than that of the main body (10), is disposed between at least a portion of the wall (11) of the hole (12) and the main body (10), so that the parasitic capacitance of a via hole is decreased, and the impedance of the via hole is increased to become closer to the impedance of a transmission line, thereby effectively improving impedance continuity of a system link.

Abstract: Provided is a circuit board, a signal crosstalk suppression method, a storage medium and an electronic device. The circuit board includes: a circuit board body, provided with a signal via-hole structure, a ground via-hole structure and a slotted structure; the signal via-hole structure is configured to transmit a signal by changing a layer, and the ground via-hole structure is configured to return a signal transmitted from the signal via-hole structure; the slotted structure is provided between the signal via-hole structure and the ground via-hole structure, and configured to suppress a signal crosstalk of the signal via-hole structure.

Abstract: The present disclosure provides a terahertz detector. The terahertz detector includes a planar array structure that is constituted by a plurality of pixel units, the plurality of pixel units each include N sub pixels and each of the sub pixels includes no more than one signal trigger configured to transform a terahertz signal to an electrical current pulsing signal, and each of the plurality of pixel units detects a signal that is a sum of the electrical current pulsing signals of the N sub pixels, where N is an integer greater than 1.

Abstract: The present disclosure provides a terahertz detector. The terahertz detector includes a planar array structure that is constituted by a plurality of pixel units, the plurality of pixel units each include N sub pixels and each of the sub pixels includes no more than one signal trigger configured to transform a terahertz signal to an electrical current pulsing signal, and each of the plurality of pixel units detects a signal that is a sum of the electrical current pulsing signals of the N sub pixels, where N is an integer greater than 1.

Abstract: The present disclosure discloses a PCB processing method and a PCB. The method includes: respectively carrying out laminating processing on a plurality of PCB daughter boards constituting a PCB, and drilling and electroplating the top-most PCB daughter board to form a via hole; and laminating the plurality of PCB daughter boards together to form the PCB, and drilling and electroplating the formed PCB to form a through hole for mounting a connector, wherein a blind hole for mounting a connector is formed by the via hole, and a depth of the blind hole is greater than or equal to the length of a signal pin of the connector. By virtue of the technical scheme of the present disclosure, a space between wafers of the lower layer of PCBs may be doubled, and the space for layout between wafers may be doubled.

Abstract: The present disclosure discloses a PCB processing method and a PCB. The method includes: respectively carrying out laminating processing on a plurality of PCB daughter boards constituting a PCB, and drilling and electroplating the top-most PCB daughter board to form a via hole; and laminating the plurality of PCB daughter boards together to form the PCB, and drilling and electroplating the formed PCB to form a through hole for mounting a connector, wherein a blind hole for mounting a connector is formed by the via hole, and a depth of the blind hole is greater than or equal to the length of a signal pin of the connector. By virtue of the technical scheme of the present disclosure, a space between wafers of the lower layer of PCBs may be doubled, and the space for layout between wafers may be doubled.

Abstract: A method and an apparatus for detecting hidden hazardous substance including the steps of: performing terahertz imaging for a detected object; judging whether there is a suspicious area containing the hidden hazardous substance in a terahertz image of the detected object obtained by the terahertz imaging; performing a multi-wavelength spectroscopy measurement to the suspicious area, determining whether the hazardous substance is contained in the suspicious area according to results of multi-wavelength spectroscopy measurement; and outputting the image of the detected object and hazardous substance detecting result. Also disclosed is an apparatus for implementing the method for detecting the hidden hazardous substance according to the present invention. Determination of the hidden hazardous substance can be performed from the perspectives of shape features and substance composition, thus the accuracy of detection is greatly increased.

Abstract: A method and an apparatus for detecting hidden hazardous substance including the steps of: performing terahertz imaging for a detected object; judging whether there is a suspicious area containing the hidden hazardous substance in a terahertz image of the detected object obtained by the terahertz imaging; performing a multi-wavelength spectroscopy measurement to the suspicious area, determining whether the hazardous substance is contained in the suspicious area according to results of multi-wavelength spectroscopy measurement; and outputting the image of the detected object and hazardous substance detecting result. Also disclosed is an apparatus for implementing the method for detecting the hidden hazardous substance according to the present invention. Determination of the hidden hazardous substance can be performed from the perspectives of shape features and substance composition, thus the accuracy of detection is greatly increased.