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: The present disclosure provides a constant current drive circuit, a constant current control system, and a lamp. The constant current drive circuit includes a load module, a start-stop module for controlling the starting and stopping of the load module, an energy storage module, and a rectifier module for controlling the current angle and current magnitude of the load module circuit. The energy storage module can charge when the load module is input with a high voltage and discharge when the load module is input with a low voltage. The rectifier module includes a resistor R1, a first compensation circuit, a first reference circuit, a first comparator, and a field-effect transistor M1 connected, the drain electrode and the source electrode of the field-effect transistor M1 are connected to the energy storage module and the resistor R3.

Abstract: Provided in the present disclosure are a drive circuit, a drive controller, and a lamp. The drive circuit includes a load module, an energy storage module, a constant-current control module and a sampling signal module, where the load module includes a first load and a second load, which are connected to a power supply module; the energy storage module is connected to the first load, the power supply module charges the energy storage module, and the energy storage module can supply power to the load module; the constant-current control module includes a first control unit and a fourth control unit, which are connected to the second load in parallel, and a second control unit and a third control unit, which are connected to the second load in series; and the sampling signal module comprises a diode D1 and a sampling module.

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: Disclosure are a backdoor attack method and system for a classification task in a code model, the method includes: S1. collecting and preprocessing clean samples to obtain importance variable names; S2. classifying the variable names of the clean samples according to label categories to obtain a plurality of trigger sets; and selecting target labels from the clean samples; S3. performing score calculation on the variable names in the trigger sets corresponding to the target labels; replacing one importance variable name with the variable name having a maximum C score in the clean samples to obtain poisoned samples, and repeating the above process until the labels are changed into the target labels; and S4. randomly inserting the triggers in the poisoned samples into the clean samples to form negative samples; and performing an attack by using an attack model obtained based on the negative, poisoned and clean samples.

Abstract: Disclosed in the present disclosure are an explainable vulnerability detection method and system based on dual-view causal reasoning. The vulnerability detection method includes: S1, obtaining code samples, where the code samples include a training sample and a sample to be detected, sequentially performing data augmentation, static analysis, code property graph construction and feature extraction on the training sample, and obtaining a training data set; and sequentially performing static analysis, code property graph construction and feature extraction on the sample to be detected, and obtaining a data set to be detect; S2, processing the training data set through a hybrid contrastive learning method, and establishing a vulnerability detection model; and inputting the data set to be detected into the vulnerability detection model, and outputting a vulnerability code; and S3, performing causal reasoning on the vulnerability code, and outputting a vulnerability detection explanation.

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 in the present disclosure are an explainable vulnerability detection method and system based on dual-view causal reasoning. The vulnerability detection method includes: S1, obtaining code samples, where the code samples include a training sample and a sample to be detected, sequentially performing data augmentation, static analysis, code property graph construction and feature extraction on the training sample, and obtaining a training data set; and sequentially performing static analysis, code property graph construction and feature extraction on the sample to be detected, and obtaining a data set to be detect; S2, processing the training data set through a hybrid contrastive learning method, and establishing a vulnerability detection model; and inputting the data set to be detected into the vulnerability detection model, and outputting a vulnerability code; and S3, performing causal reasoning on the vulnerability code, and outputting a vulnerability detection explanation.

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: 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.