108 results about "AN codes" patented technology

The invention provides a code dynamic completion method for a large language model. The method comprises the following steps: constructing a mixed training data set; the method comprises the following steps of: initializing a Transform model architecture fused with probability space topological transformation; based on the mixed training data set, executing model training of collaborative optimization of the main target and the auxiliary target; in each step of decoding, the model calculates the probability distribution of the next token according to the current context; the generated probability distribution is restrained in an effective probability subspace through spherical probability mapping, and grammar error candidates are filtered in real time and the probability distribution is adjusted in combination with a tabu table mechanism; and dynamically selecting a sampling strategy according to the current decoding depth, sampling from the adjusted probability distribution to obtain a next code snippet, and finally generating a code completion suggestion conforming to abstract syntax tree rules and semantic constraints. According to the method, the probability distribution constraint and the taboo table mechanism are combined, the model can dynamically adjust the generated probability distribution, the more appropriate candidate token can obtain the higher probability, and therefore the accuracy of code completion is improved.

An example CXL (Compute eXpress Link)-based memory module includes a memory device and a controller. The memory device includes a plurality of volatile memory cells and stores data or reads the stored data. The controller communicates with a host device through a CXL interface and controls the memory device. The controller includes an error correction code (ECC) circuit that generates a first codeword by adding a parity vector generated based on Reed-Solomon encoding to data received from the host device, an error injecting circuit that generates an error symbol and generates a second codeword by injecting the error symbol into at least a portion of the first codeword, and a memory device interface that controls the memory device such that the second codeword where the error symbol is injected is stored in the memory device. The controller determines a number of error symbols to be injected into the second codeword.

The invention provides a method and device for determining a code patch, equipment and a storage medium, and the method comprises the steps: generating a test case for a set fragment in a to-be-tested file by executing a first large language model; running the test case for the to-be-tested file; if the error description of the test failure is obtained, inputting the error description and the problem code block into a second large language model to obtain at least one code patch for the problem code block; wherein the at least one code patch is obtained by the second large language model according to at least one code repair strategy through a cluster search mode; the at least one code patch is in one-to-one correspondence with the at least one code repair strategy; a final patch is determined from the at least one code patch and the set segment is replaced. According to the method, the test case is automatically generated through the first large language model, the patch is automatically generated for the problem code block through the second large language model, and the automation degree and efficiency of the test are improved.

A computerized method generates a structure configuration from a codebase and generates application code using the structure configuration. Code examples of the codebase are obtained, and a structure configuration is generated using the obtained code examples and a standard configuration dataset. The structure configuration includes code components specific to the codebase. Labels that are indicative of component attributes are assigned to the code components of the structure configuration. A code generation request is received, and the request is converted into a plurality of feature prompts. At least one code component is mapped to each feature prompt based on semantic similarity of the feature prompt to a label of the mapped code component. Application code is generated using the mapped code components. The generated application code is deployed for execution. This method enables the automatic generation of code that conforms to common patterns and accurately exhibits the features requested.

This application provides an information transmission method and an apparatus. In the method, a sending device sends a first bit sequence to a receiving device. Optionally, the first bit sequence is an information bit sequence, or the first bit sequence is an information bit sequence obtained through first encoding. The sending device receives a second bit sequence from the receiving device. The sending device sends a first code block to the receiving device, where the first code block is obtained based on a first error pattern and a first check matrix. The first error pattern is determined based on the second bit sequence and the first bit sequence.

This application discloses a code block identification method and related apparatus. The method includes: obtaining a code block stream, where the code block stream includes a first code block; determining a to-be-identified bit pattern and comparing the to-be-identified bit pattern with a template bit pattern to obtain a quantity of inconsistent bits; and identifying the first code block as a first boundary code block when the quantity of inconsistent bits is less than or equal to a first threshold. The to-be-identified bit pattern includes a first bit pattern and corresponds to the first code block. The template bit pattern includes a first template bit pattern and corresponds to the first boundary code block.

The invention provides a data processing method and related equipment. The method comprises the steps of obtaining an original code file; determining a coding format corresponding to each code block in the original code file according to the compiling instruction; and compiling the at least one code block into a target execution file according to the coding format corresponding to each code block. The target execution file comprises at least one segment, and each segment comprises a segment identifier and at least one sub-module. The segment identifier is used for indicating the type of the code block corresponding to the segment. The sub-module includes a sub-module option and a sub-module code. The sub-module options are used for indicating coding formats corresponding to the sub-module codes. The sub-module code comprises at least one data sequence or identification information corresponding to the at least one data sequence, and each data sequence is determined according to a coding format indicated by the sub-module option and a corresponding code block. According to the method, the code blocks are coded in a standardized mode to generate the target execution file, so that cross-platform operation of the target execution file is realized, and the operation efficiency is improved.

The invention relates to a hybrid automatic repeat request (HARQ) with joint context and application optimization. For example, an apparatus is disclosed that is configured to process a data unit comprising one or more representations based on a signal received from a base station, each of the representations comprising one or more data blocks, where each data block comprises a weight, and wherein each of the data blocks is assigned to a code block group (CBG) of a plurality of code block groups (CBG) based on the weight of the corresponding data block; determining the total weight of the successfully decoded data block; and comparing the total weight to a total weight threshold for the data unit.

The invention discloses a code merging method and device, equipment and a medium. The method comprises the following steps: acquiring a trunk code, and acquiring a to-be-merged code; detecting the to-be-merged codes to obtain at least one piece of code fault information; generating at least one piece of fault prompt information according to each piece of code fault information and the trunk code, and sending the fault prompt information to a code detection large model to obtain code repair information; and repairing the to-be-merged code according to the code repairing information, and merging the repaired to-be-merged code into the trunk code. According to the embodiment of the invention, the code merging accuracy can be improved.

The invention discloses a code generation method and device, electronic equipment and a storage medium, and belongs to the technical field of software development, in the method, operation granularity information of MMA and tensor information of input tensor and output tensor are determined in response to an instruction for performing MMA intermediate representation on tensor, the input tensor comprises a left tensor and a right tensor, and the right tensor comprises a left tensor and a right tensor; partitioning the output tensor according to the tensor information and the operation granularity information of each tensor, and generating a code segment based on a corresponding left data block in the left tensor and a corresponding right data block in the right tensor of each region in the output tensor so as to write a matrix multiplication result of the left data block and the right data block into the region, and fusing the code segments corresponding to the regions to obtain an MMA intermediate representation. Therefore, no matter how many dimensions of each tensor are, the MMA intermediate representation can be automatically generated according to the target information, and developers do not need to develop loop codes and understand the memory layout of the tensors, so that the development difficulty is relatively low.

The invention belongs to the technical field of software engineering, and discloses a token-level semantic matching-based code annotation generation method and system, and the method comprises the following steps: obtaining a target code and a data set, carrying out the preprocessing and dividing, and obtaining a training set as a corpus; performing word segmentation on the codes in the corpus by using a word segmentation device of a pre-trained large language model, and extracting and storing a context semantic embedding vector of each token in the codes to form a code semantic warehouse; calculating the lexical similarity between the target code and the code in the corpus, and taking the top k high examples as candidate examples; according to the method, a target code and a candidate sample are subjected to token-level semantic matching, the most similar token in another code segment is matched, the accuracy rate and the recall rate are combined to obtain an F1 score, and the sample with the highest score is reused, the context semantic feature of fine granularity is considered in the aspect of retrieval, the code annotation generation precision is improved, extra training is not needed, and the retrieval efficiency is improved. And the method has good applicability to different scenes.

The embodiment of the invention provides a code detection method, system and device, electronic equipment, a storage medium and a program product. According to the scheme provided by the embodiment of the invention, the received change code data comprises at least one change code line, and the change code line is a code line of which the content is changed relative to the previous version source code in the current version source code. Based on the current version source code and the change code data, extracting at least one code program segment from the current version source code; one code program segment comprises one change code line or a plurality of change code lines with continuous line numbers or a plurality of change code lines with discontinuous line numbers. Furthermore, the change classification corresponding to the code program segment can be determined. And based on the code program segment and a risk rule associated with the change classification corresponding to the code program segment, determining a risk detection result of the change code line in the code program segment.

The invention relates to a code processing method and device, electronic equipment, a storage medium and a computer program product. The code processing method comprises the following steps: performing word segmentation processing on a to-be-processed code to obtain a code sequence comprising at least one code unit; on the basis of the characteristic parameters of any code unit in the code sequence, the correlation degree between any code unit and other code units except any code unit in the code sequence is determined; wherein the correlation degree is used for representing the degree of dependence between any code unit and other code units; based on the correlation degree corresponding to each code unit, respectively determining a highlight parameter of each code unit; wherein the highlight parameter is used for performing highlight display on the code unit. According to the embodiment of the invention, code highlighting can be realized by using the same word segmentation rule in different programming languages, so that the universality of realizing code highlighting is improved.

The invention provides a request processing method and device, and the method comprises the steps: responding to a received current code merging request associated with a target branch, and obtaining the states of a plurality of code merging entrance guards associated with the current code merging request; on the basis of the weight and the state corresponding to each code merging entrance guard, determining a merging readiness score of the current code merging request; in response to the fact that the merging readiness score is smaller than a set score threshold value, determining a target access control with the maximum weight from at least one unpassed code merging access control; according to the access control failure log associated with the target access control and the first incremental code difference between the source branch and the target branch associated with the current code merging request, merging blocking information is generated and visually displayed, and therefore the automation and intelligence level of the code merging process is improved, and the code merging efficiency is improved. And the problem repairing period is shortened, so that the stability and delivery efficiency of the target branch are improved.

A new radio (NR) bit prioritization procedure that may be executed by a UE and a base station is disclosed, resulting in transmission and reception of modulation symbols having prioritized bits. For example, a transmitter may encode a code block using low-density parity-check code to generate a stream of encoded bits. The transmitter may arrange the encoded bits in one or more modulation symbols according to a relative priority of the encoded bits. The highest priority bits may be located in the most significant bits of the modulation symbol, and therefore be less likely to experience errors. A receiver may receive the modulation symbols and reorder the encoded bits according to the coding scheme based on the relative priority prior to decoding the encoded bits. The prioritization of the bits within the modulation symbols may provide improved block error rates over sequential mapping of encoded bits to symbols.

The invention discloses a project defect code determination method and device, equipment, a medium and a product, and the method comprises the steps: obtaining a current defect report and code change information of a current project, carrying out the word embedding coding processing of the current defect report and the code change information, and obtaining a defect report input vector and at least one code block input vector; performing language coding processing on the defect report input vector and each code block input vector by utilizing a pre-trained defect positioning model to obtain a defect report feature vector and at least one code block feature vector; and performing defect positioning classification processing on the defect report feature vector and each code block feature vector by using a pre-trained defect positioning model to obtain at least one association probability, and determining a defect code of the current defect report according to each association probability. According to the method, the current defect report can be automatically analyzed, and the defect code of the current defect report is accurately and efficiently determined according to the association probability of the current defect report and each code block.

A data transmission method includes generating a first code block, where the first code block includes a first load and a first redundancy code, the first load includes N second code blocks, the first redundancy code is used to perform error correction on the first load, an ith second code block includes a second load and a second redundancy code, the second redundancy code is used to perform error detection on the second load in the ith second code block, a value of i is an integer ranging from 1 to N, and Nis an integer greater than or equal to 1; and sending the first code block to a receive end.

The application discloses a defect code generation method and related device, and the method comprises the steps of: obtaining at least one code segment pair from a code library; analyzing the modification reason between the first code segment before modification and the second code segment after modification in each code segment pair through a first language model, and identifying the defect type of the first code segment in each code segment pair indicating defect repair; obtaining at least one code segment pair corresponding to each defect type as a target code segment pair, and calling a second language model to learn each target code segment pair with the generation of defect code as a learning target to obtain a learned second language model; and generating a defect code segment corresponding to the target code segment through the learned second language model. The method can realize the automatic generation of defect code, improve the generation efficiency of defect code, improve the generation quality of defect code, and enhance the comprehensiveness and authenticity of the generated defect code.

The present application relates to a code generation method, device and equipment based on a multi-agent language system. The method includes: obtaining a code generation task of a user. The code generation task includes: code task information and execution parameters of the code task information. The code task information is disassembled and judged by a planning engineer according to the complexity of the code generation task and the semantic understanding result to generate multiple sub-code tasks. After the sub-code task is converted into a Python code sequence by a code writing agent, the sub-code blocks of the Python code sequence are integrated into a standard running function by a code integration agent. Each Python code sequence is traversed and executed according to the standard running function to generate a standard code. After the standard code is corrected by a code testing agent, the corrected standard code is returned to the user. The use of this method can improve the efficiency of code generation under a large language model and reduce computing resource overhead.

A coding method for data communication is provided, and may be applied to a plurality of scenarios such as a metro network, a backbone network, and a data center interconnection. The method includes: forming a first codeword, where the first codeword includes n image bits and n to-be-transmitted bits, the n image bits are selected from to-be-transmitted bits in m source codewords, the source codeword is a codeword formed before the first codeword, both n and m are positive integers, and n>m; and sending the n to-be-transmitted bits in the first codeword. The bit in the first codeword is protected by a plurality of codewords generated at different moments, and a coding gain effect is better. In addition, the bit in the codeword is protected by different quantities of codewords.

A code presentation arrangement (10) consists of a carrier (20) and a card (30) attached to the carrier (20) or consists only of a card (30), wherein the card (30) or the carrier (20) respectively has a code presentation side (21b) on which a code (12) is applied. To enable more pleasant exposure of the code and more reliable detection of a code that has already been exposed, the code (12) on the code presentation side (21b) is covered by an opaque cover section (24) of the carrier (20) or an opaque cover section of the card (30), wherein the respective cover section is attached to the code presentation side (21b) by permanent adhesive strips (25) positioned along the edges of the code (12), and wherein the respective cover section in the area of the code (12) between the permanent adhesive strips (25) has a detachable tear-off tab (26) through which the code (12) can be exposed by pulling from the side facing away from the code (12).

Embodiments herein describe a code obfuscation system. The code obfuscation system accesses computer code and identifies a subset of the code to obfuscate. The code obfuscation system analyzes the identified subset of code, the analysis comprising identifying code elements and identifying one or more files and directories. The code obfuscation system generates first obfuscation data for the identified code elements and generates second obfuscation data for the one or more files and directories. The code obfuscation system generates obfuscated computer code by applying the first obfuscation data and the second obfuscation data to the originally accessed computer code.

Example solutions performing software code vulnerability reduction. An input code portion is extracted from input software code. The input code passage may be syntactically incomplete and / or syntactically incorrect. A code vulnerability is detected in the input code portion. A correction of the code vulnerability is made, and an output code portion is generated including the correction. In some examples, a code vulnerability detection tool take, as input, the output from a code completion tool. The output is thus annotated or corrected in real-time, as a user is developing the code.

The present application discloses a code generation method, device, electronic device and storage medium, belonging to the field of software development technology. In this method, in response to an instruction to perform an intermediate representation of a tensor using MMA, the operation granularity information of the MMA, the tensor information of the input tensor and the output tensor are determined, the input tensor includes a left tensor and a right tensor, the output tensor is partitioned according to the tensor information and operation granularity information of each tensor, and a code segment is generated based on the left data block corresponding to each region in the output tensor in the left tensor and the right data block corresponding to each region in the right tensor, so that the matrix multiplication result of the left data block and the right data block is written into this region, and the code segments corresponding to each region are fused to obtain the intermediate representation of the MMA. In this way, regardless of the dimension of each tensor, the intermediate representation of the MMA can be automatically generated according to the target information, without the developer having to develop loop code or understand the memory layout of the tensor, so the development difficulty is relatively low.

The present invention discloses a method for encoding semantics and semantic sequences across symbol systems, which is composed of two types of codes and a set of encoding methods. The two types of codes are: absolute semantic code: the absolute semantic code is expressed in the form of A‑x, where x is an integer, such as A‑35; symbol system code: the symbol system code is expressed in the form of S‑x, where x is an integer, such as S‑35. The present invention can realize the encoding of semantics and semantic sequences across symbol systems, realize the correspondence between a single semantic and a sequence composed of semantics, and realize the correspondence between semantics and sequences composed of semantics determined by symbol systems, which is an enabling technology for building a strong artificial intelligence system; all absolute semantics and symbol systems encoded by the method of the present invention have connections that can be indexed to each other, that is, starting from any code, indexing to related codes, and this coordinate system reflecting the semantic structure makes it possible to calculate and generate new related semantics.

Methods, systems, and devices for wireless communications are described. A first wireless device, such as a wireless station (STA) or a wireless access point (AP), performs a low-density parity check (LDPC) coding operation on input bits of a set of code blocks. Performing the LDPC coding operation on the input bits produces a set of codewords including one or more codewords having a first codeword length and one or more codewords having a second, shorter codeword length. The first wireless device arranges the set of codewords into a set of symbols such that a last symbol in time of the set of symbols includes the one or more codewords each having the second codeword length and no codewords having the first codeword length. The first wireless device, transmits, to a second wireless device, the plurality of symbols.

The application discloses to the technical field of code completion, specifically a code completion method based on a multimodal two-stage fine-tuning, comprising the following specific steps: S1, constructing a code completion fine-tuning dataset D1: collecting source codes from public channels to construct an original code sample dataset D0; then generating three kinds of modal representation structures corresponding to each source code to construct a code completion fine-tuning dataset D1. The two-stage fine-tuning model proposed in the application combines prefix fine-tuning and adapter fine-tuning, not only reduces resource consumption, but also accurately adjusts the parameters of the model, and the type-code predictor is associated with the direct relationship between the specific code during prediction and the type label, so that it better adapts to the code completion task, and thus the accuracy and efficiency of code completion are improved.

An information processing device includes one or more processors. The one or more processors are configured to divide targets into a plurality of units for each predetermined identifier, define a set of a first predetermined number of said units as a sub-block from each of the units for the plurality of units; encode the sub-block by predetermined conversion, and obtain a code; and use the code as a key, and detect existence of another sub-block having identical content with the sub-block corresponding to the code when duplication of the key is detected.

The application discloses a code processing method and device, equipment and storage medium, and belongs to the computer technical field. The method comprises the following steps: acquiring source code in a code warehouse, wherein the source code comprises at least two functions; a code flow chart of the source code is displayed in a visual area, the code flow chart comprises a plurality of flow nodes, each flow node in the plurality of flow nodes corresponds to at least one code block in the source code, and each flow node is used for displaying at least one of a logic summary and a called function list of the code block corresponding to the flow node; wherein the node type of the flow node comprises at least one of the following: data declaration and initialization; guard statement and parameter check; function call and error handling; concurrency and synchronization; result construction and return; entry and exit nodes; and conditional loop nodes.