Abstract: Disclosed are a method and a system for bug localization based on a code knowledge graph, including the steps of: extracting source codes from a Git version control system, parsing in the source codes to generate an abstract syntax tree (AST), constructing a code knowledge graph, preprocessing the summary and description of a bug report crawled from a Bugzilla bug tracking system, and performing the named entity recognition to identify bug-related entity sequence, converting the code knowledge graph and the bug-related entity sequence into vector representation through an embedding algorithm, calculating cosine similarities of vector representations between the code knowledge graph and the bug entity sequence, ranking the similarities from high to low to generate a list of suspicious methods, filtering redundant information in the source codes, identifying bug-related entity elements in the bug report, and reserving the bug-related information.

Abstract: A foldable windproof unit, a large-span windproof net structure thereof, and a windproof method are disclosed. The foldable windproof unit comprises a flexible windproof net, towers arranged at intervals, and a load-bearing rope erected on the two towers. The tower on one side is provided with a horizontal pulley assembly, and the tower on the other side is provided with two vertical pulleys. The top edge of the flexible windproof net is slidably connected to the load-bearing rope by means of a plurality of hanging structures. The foldable windproof unit further comprises a traction rope, the traction rope is arranged on the horizontal pulley assembly in a sleeving manner, and the two free ends of the traction rope extend to respectively bypass the two vertical pulleys and are connected to winding mechanism. The hanging structure close to the tower on one side is fixedly connected to the traction rope.

Abstract: A system for predicting and summarizing medical events from electronic health records includes a computer memory storing aggregated electronic health records from a multitude of patients of diverse age, health conditions, and demographics including medications, laboratory values, diagnoses, vital signs, and medical notes. The aggregated electronic health records are converted into a single standardized data structure format and ordered arrangement per patient, e.g., into a chronological order. A computer (or computer system) executes one or more deep learning models trained on the aggregated health records to predict one or more future clinical events and summarize pertinent past medical events related to the predicted events on an input electronic health record of a patient having the standardized data structure format and ordered into a chronological order.

Abstract: The present disclosure generally relates to multi-stage digital converters, including multi-stage digital down-converters (DDCs) and multi-stage digital up-converters (DUCs). In at least one example, the multi-stage digital down converter (DDC) comprises a plurality of stages, each stage comprising a frequency mixer and a decimation filter, and at least one controller coupled to one or more of the plurality of stages and operable to control one of the frequency mixer and decimation filter. In another example, the multi-stage digital up converter (DUC) comprises a plurality of stages, each stage comprising a frequency mixer and interpolation filter; at least one controller coupled to one or more of the plurality of stages and operable to control one of the frequency mixer and the interpolation filter.

Abstract: Provided is a method for generating web codes for a user interface (UI) based on a generative adversarial network (GAN) and a convolutional neural network (CNN). The method includes steps described below. A mapping relationship between display effects of a HyperText Markup Language (HTML) element and source codes of the HTML element is constructed. A location of an HTML element in an image I is recognized. Complete HTML codes of the image I are generated. The similarity between manually-written HTML codes and the generated complete HTML codes and the similarity between the image I and an image I1 generated by the generated complete HTML codes are obtained. After training, an image-to-HTML-code generation model M is obtained. A to-be-processed UI image is input into the model M so as to obtain corresponding HTML codes. According to the method of the present disclosure, an image-to-HTML-code generation model M can be obtained.

Abstract: Provided is an automatic event graph construction method for multi-source vulnerability information. The method includes the following steps. A vulnerability report is crawled from a vulnerability database, a cause of vulnerability is taken as an event trigger word, and a vulnerability type is determined through the cause of vulnerability. An attacker, consequence, location and other information in a description are identified by named-entity recognition, and information completion is performed. An explicit relation between events is extracted by using text information, an implicit relation between events is extracted by using text similarity, and vulnerability-related code representation is performed. Obtained vulnerability event information is visualized into an event graph through a visualization tool.

Abstract: Disclosed is a template-based automatic question and answer method for software bug. An entity relationship triple is extracted from a bug corpus and a natural language pattern is acquired; an entity relationship in the triple is determined; a query template corresponding to the natural language pattern is acquired; an entity in a question q proposed by a user is replaced with an entity type to acquire a question q?; then, the entity type in q? and an entity type in the natural language pattern are compared and searched for and a similarity is calculated; then, a SPARQL query pattern of the question q is acquired according to the similarity and the entity in the question q; and finally, the SPARQL query pattern of the question q is executed so as to acquire an answer to the question q.

Abstract: Provided is a method for generating web codes for a user interface (UI) based on a generative adversarial network (GAN) and a convolutional neural network (CNN). The method includes steps described below. A mapping relationship between display effects of a HyperText Markup Language (HTML) element and source codes of the HTML element is constructed. A location of an HTML element in an image I is recognized. Complete HTML codes of the image I are generated. The similarity between manually-written HTML codes and the generated complete HTML codes and the similarity between the image I and an image I1 generated by the generated complete HTML codes are obtained. After training, an image-to-HTML-code generation model M is obtained. A to-be-processed UI image is input into the model M so as to obtain corresponding HTML codes. According to the method of the present disclosure, an image-to-HTML-code generation model M can be obtained.

Abstract: Provided is an automatic construction method of a software bug knowledge graph. The method includes extraction of a relationship triple of a bug and domain classification of the bug. Specifically, the method includes: collecting bug information in a bug library and processing bug description information, obtaining a verb phrase and a noun phrase in a description sentence by means of natural language processing, and then obtaining a relationship triple of the bug according to a dependency relationship between words related to the bug information, extracting a domain feature of the bug, performing learning and training with a semi-supervised classifier to enable the classifier automatically to classify unlabeled triples, storing all the classified relationship triples in a graph database, and thus constructing a software bug knowledge graph.

Abstract: Disclosed is a template-based automatic question and answer method for software bug. An entity relationship triple is extracted from a bug corpus and a natural language pattern is acquired; an entity relationship in the triple is determined; a query template corresponding to the natural language pattern is acquired; an entity in a question q proposed by a user is replaced with an entity type to acquire a question q?; then, the entity type in q? and an entity type in the natural language pattern are compared and searched for and a similarity is calculated; then, a SPARQL query pattern of the question q is acquired according to the similarity and the entity in the question q; and finally, the SPARQL query pattern of the question q is executed so as to acquire an answer to the question q.

Abstract: Provided is an entity and relationship joint extraction method oriented to software bug knowledge. The method includes collecting text data of an open-source bug library and preprocessing the text data to obtain a bug text data corpus; extracting, from the bug text data corpus, a statement S for describing a bug, and then processing S, and using the processed S as a subsequent input statement; constructing an entity and relationship joint extraction model; obtaining, in conjunction with the constructed entity and relationship joint extraction model based on a transition system, an entity set E and a relationship set R corresponding to the input statement; and outputting the entity set E and the relationship set R to complete joint extraction of entities and relationships.

Abstract: Provided is an entity and relationship joint extraction method oriented to software bug knowledge. The method includes collecting text data of an open-source bug library and preprocessing the text data to obtain a bug text data corpus; extracting, from the bug text data corpus, a statement S for describing a bug, and then processing S, and using the processed S as a subsequent input statement; constructing an entity and relationship joint extraction model; obtaining, in conjunction with the constructed entity and relationship joint extraction model based on a transition system, an entity set E and a relationship set R corresponding to the input statement; and outputting the entity set E and the relationship set R to complete joint extraction of entities and relationships.

Abstract: The present invention relates to a preparation method for a traditional Chinese medicine drop pill and a traditional Chinese medicine micro drop pill prepared by using the method, and in particular, the present invention relates to a micro drop pill preparation method with high drug-loading capacity, simple preparation process and high production rate and a micro drop pill prepared by using the method. Specially, The drop pill preparation method used comprises the following steps: (1) material melting step: heat melting a medicine and a drop pill matrix to obtain a molten medicine liquid; (2) dropping step: delivering the molten medicine liquid to a dripper, and acquiring medicine drops of the molten medicine liquid by means of vibration dropping; and, (3) condensation step: cooling the medicine drops with a cooling gas to obtain micro drop pills.

Abstract: An intelligent dripping pill machine for continuous liquid solidification comprises: a feeding device (1), a material combining device (2), a homogenizing device (3), a dripping device (4) and a de-oiling device (5) sequentially connected via a transmission channel. The intelligent dripping pill machine removes, via high-speed centrifugation, a cooling liquid attached to dripping pills, and each component device is connected compactly, thereby achieving a continuous manufacturing operation, and reducing an occupied space of the devices as a whole while ensuring the yield of the dripping pills.

Abstract: An intelligent continuous manufacturing method via liquid cooling of dripping pills comprises the following steps: (1) feeding: weighing and transferring multiple materials respectively; (2) material combining: performing staged heating on the materials transferred in step (1), and mixing the same to obtain a material mixture, wherein an RSD of an effective ingredient in the material mixture ?5%; (3) homogenizing: pressurizing the material mixture obtained in step (2), and increasing the temperature, so as to obtain a homogenized material having the RSD of the effective ingredient in the material mixture ?5%; (4) dripping: performing vibration dripping on the homogenized material obtained in step (3) to obtain dripping pills, delivering the dripping pills into a cooling liquid to be cooled and then transferred; and (5) de-oiling: removing the cooling liquid on surfaces of the dripping pills obtained in step (4) via tilting centrifugation.

Abstract: Provided is an automatic construction method of a software bug knowledge graph. The method includes extraction of a relationship triple of a bug and domain classification of the bug. Specifically, the method includes: collecting bug information in a bug library and processing bug description information, obtaining a verb phrase and a noun phrase in a description sentence by means of natural language processing, and then obtaining a relationship triple of the bug according to a dependency relationship between words related to the bug information, extracting a domain feature of the bug, performing learning and training with a semi-supervised classifier to enable the classifier automatically to classify unlabeled triples, storing all the classified relationship triples in a graph database, and thus constructing a software bug knowledge graph.

Abstract: The present invention relates to a preparation method for a traditional Chinese medicine drop pill and a traditional Chinese medicine micro drop pill prepared by using the method, and in particular, the present invention relates to a micro drop pill preparation method with high drug-loading capacity, simple preparation process and high production rate and a micro drop pill prepared by using the method. Specially, The drop pill preparation method used comprises the following steps: (1) material melting step: heat melting a medicine and a drop pill matrix to obtain a molten medicine liquid; (2) dropping step: delivering the molten medicine liquid to a dripper, and acquiring medicine drops of the molten medicine liquid by means of vibration dropping; and, (3) condensation step: cooling the medicine drops with a cooling gas to obtain micro drop pills.

Abstract: An air-cooling micro drop pill capsule production line comprises a drop pill system, an air-cooling circulation system and a control system. The drop pill system comprises a molten material tank and a dripper. A vibration apparatus is arranged between the molten material tank and the dripper, and drives the dripper to vibrate up and down. A vibration shear force cuts liquor flowing out from the dripper into drops, and drop pills are formed after the drops fall into the air-cooling circulation system and are cooled. An online monitoring apparatus is arranged on the dripper, and comprises a pulse signal emission mechanism with an emission frequency which is the same as a vibration frequency of the vibration apparatus. The control system controls and regulates a dropping parameter according to a monitoring result of the online monitoring apparatus.

Abstract: An intelligent dripping pill machine for continuous liquid solidification comprises: a feeding device (1), a material combining device (2), a homogenizing device (3), a dripping device (4) and a de-oiling device (5) sequentially connected via a transmission channel. The intelligent dripping pill machine removes, via high-speed centrifugation, a cooling liquid attached to dripping pills, and each component device is connected compactly, thereby achieving a continuous manufacturing operation, and reducing an occupied space of the devices as a whole while ensuring the yield of the dripping pills.

Abstract: An intelligent continuous manufacturing method via liquid cooling of dripping pills comprises the following steps:(1) feeding: weighing and transferring multiple materials respectively; (2) material combining: performing staged heating on the materials transferred in step (1), and mixing the same to obtain a material mixture, wherein an RSD of an effective ingredient in the material mixture ?5%; (3) homogenizing: pressurizing the material mixture obtained in step (2), and increasing the temperature, so as to obtain a homogenized material having the RSD of the effective ingredient in the material mixture ?5%; (4) dripping: performing vibration dripping on the homogenized material obtained in step (3) to obtain dripping pills, delivering the dripping pills into a cooling liquid to be cooled and then transferred; and (5) de-oiling: removing the cooling liquid on surfaces of the dripping pills obtained in step (4) via tilting centrifugation.