317 results about "Quality Score" patented technology

The technology disclosed assigns quality scores to bases called by a neural network-based base caller by (i) quantizing classification scores of predicted base calls produced by the neural network-based base caller in response to processing training data during training, (ii) selecting a set of quantized classification scores, (iii) for each quantized classification score in the set, determining a base calling error rate by comparing its predicted base calls to corresponding ground truth base calls, (iv) determining a fit between the quantized classification scores and their base calling error rates, and (v) correlating the quality scores to the quantized classification scores based on the fit.

The invention discloses an intention classification method and device based on vector retrieval and context awareness and a medium, and relates to the technical field of artificial intelligence. The method comprises the steps of extracting business metadata and associating the business metadata with typical problem examples to generate a standardized service description document; encoding the standardized service description document into a high-dimensional semantic vector through a pre-training language model, and constructing a neighbor search index to store the high-dimensional semantic vector; splicing the user identity information and the current question text into an enhanced query statement, and encoding the enhanced query statement into a context-aware dynamic query vector through a semantic model; performing similarity retrieval based on the dynamic query vector to obtain candidate intelligent services, performing business domain filtering, context weighted sorting and dynamic priority rearrangement, and outputting target recommendation services; by collecting interactive behavior data of a target recommendation service, quality scoring is performed on service descriptions and problem examples based on a preset evaluation rule, and the service descriptions and the problem examples of which the quality scores are lower than a quality threshold value are updated.

Methods and systems for assessing a software bill of materials (SBOM) include building a knowledge graph from repositories, using function fingerprints of software packages in the repositories. Dependencies of an application are identified using function fingerprints of the application and comparing to function fingerprints of the software packages. A quality score for an SBOM of the application is generated based on a comparison of the identified dependencies to claimed dependencies of the SBOM. An action is performed responsive to the quality score.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating and updating project plans for software development projects. In one aspect, a method includes obtaining data indicative of initial project plan parameters associated with a software development project; identifying multiple program modules associated with the software development project; obtaining, for a first set of modules of the multiple modules, corresponding source code segments; executing a quality assessment process to compute, for each corresponding source code segment, a corresponding quality score; identifying, based on the quality scores, that at least a subset of the corresponding source code segments are integrable into a corresponding first subset of the first set of modules; and generating a revised project plan by generating updates to the initial project plan parameters by accounting for the corresponding source code segments being integrated in to corresponding ones of the first set of modules.

The invention relates to the technical field of artificial intelligence, and discloses a model fine tuning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a knowledge document of a target domain; extracting question and answer pairs in the knowledge document to obtain a question and answer pair set in the knowledge document; determining a quality score of each question and answer pair according to the text information of each question and answer pair in the question and answer pair set; according to the quality score of each question and answer pair, screening a target question and answer pair from the question and answer pair set, and taking the target question and answer pair as a fine tuning training sample of the to-be-fine-tuned model; and based on the fine tuning training sample, performing fine tuning optimization on the to-be-fine-tuned model to obtain a target model. According to the method provided by the scheme, the domain classification is performed on the knowledge document, and the target question and answer pair which can be used as the fine tuning training sample is screened according to the quality score of the question and answer pair, so that the quality of the fine tuning training sample is improved, deviation of the model in the fine tuning process is avoided, and the fine tuning precision of the model is improved.

A computerized-method for comprehensive text-summarization quality-assessment with rank-based normalization and weighted-hierarchical-ranking strategy. The computerized-method includes: (i) receiving an original-text and a summary-text that has been generated by a (GPT)-based LLM that has been provided the original-text and a text-prompt; (ii) operating a text-processing NLP module on the original-text and the summary-text to yield a processed-text of both; (iii) measuring the summary-text to assess text-summarization-quality thereof by operating a plurality of metrics to yield a metric-score; (iv) operating ranked-based normalization on each metric-score to yield a normalized-score; and (v) operating an aggregation based on weighted-hierarchical-ranking strategy of the normalized scores to yield an interpreted final-quality score. The interpreted final-quality score indicates a comprehensive text summarization quality assessment of the summary-text, and the plurality of metrics includes: (i) grammatically; (ii) Flesch-Kincaid (FK) readability; (iii) topic coverage; (iv) compression ratio; (v) cosine similarity; (vi) NER accuracy; (vii) BLEU; and (viii) ROUGE.

The invention discloses a privacy protection data sharing and cooperative training method and system based on federated learning. The method comprises the steps of receiving software development log data, adaptively judging the sensitivity degree according to a data type, dynamically adjusting noise disturbance intensity according to the sensitivity degree to perform data desensitization, and generating a sensitivity index; selecting a feature extraction strategy, extracting time sequence correlation features from the desensitization data, constructing a dynamic graph structure with a weight, and obtaining a time sequence feature vector through iterative fusion; calculating the time sequence correlation of the time sequence feature vector to obtain a data quality score, and setting a contribution weight based on the quality score to perform parameter aggregation; combining sensitivity indexes with data quality scores to construct a security sharing domain, decoupling global training parameters into knowledge fragments in the domain, formulating a recombination rule, and selectively acquiring the required knowledge fragments by all parties for local training. According to the method, deep collaboration is realized on the premise of protecting data privacy, and the collaboration training effect is improved.

Methods and systems for assessing a software bill of materials (SBOM) include extracting package names from code of an application to identify first dependencies of the application. Package names are extracted from accesses by the application to identify second dependencies of the application. A quality score is generated for an SBOM of the application based on a comparison of the contents of the SBOM to the first dependencies and the second dependencies. An action is performed responsive to the quality score.

The invention relates to the technical field of incremental training, and particularly discloses a method for large model incremental training, comprising the following steps: S1, obtaining a target data set based on an industry corpus data set, dividing the target data set into sub-data sets, obtaining quality indexes of the sub-data sets, and determining quality scores of the sub-data sets; s2, acquiring a first sequence, and determining a performance score of the universal model from the first sub-data set in the first sequence; calculating a performance score difference value, and determining whether the state is an abnormal state or not according to a performance score difference value threshold value; s3, coordinate points are generated and fitted to obtain a fitted curve, and abnormal sorting positions are obtained according to the fitted curve; and determining a target model according to the abnormal sorting position, and performing incremental training on the target model through the to-be-determined data set. According to the method, the negative influence of low-quality data on the model can be reduced, the adaptability of the model to new domain knowledge is improved, and the problem of performance degradation is avoided.

The invention provides a presentation file quality detection method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence, in particular to the field of document quality detection. According to the specific implementation scheme, a to-be-detected presentation file is obtained; wherein the to-be-detected presentation file comprises a plurality of pages of slides; converting each page of slide in the to-be-detected PowerPoint into structured data in a preset format; wherein the structured data represents elements contained in the slide and the distribution condition of the elements; determining a quality score of the to-be-detected PowerPoint according to the structured data corresponding to each page of slide; wherein the quality score represents the quality of the to-be-detected presentation file. And in combination with the element layout condition of each page of slides, the quality detection precision of the PowerPoint is improved.

The invention discloses a dialogue generation method and device, equipment, a storage medium and a computer program product, and relates to the technical field of artificial intelligence, and the method comprises the steps: determining multiple groups of official document question and answer pairs based on a corpus, and adding a quality score to an answer text in each group of official document question and answer pairs to obtain multiple groups of training question and answer pairs, the quality score is used for representing the quality of the content of the answer text; inputting the question text in each group of training question and answer pairs into a pre-trained big language model to obtain a model output text carrying a quality score, the pre-trained big language model being a big language model that has learned a natural language structure; the quality scores of the model output texts are input into a preset loss function to obtain loss values, model parameters of the large language model are updated based on the loss values to obtain an official document question and answer model, and the loss function is constructed based on a preference optimization model. According to the method, official document questions and answers can conform to values, intentions and preferences of human beings.

The invention provides a multi-modal feature fusion reference-point-free cloud quality evaluation method, and belongs to the field of three-dimensional point cloud quality evaluation. The scheme comprises a data preprocessing step, a feature extraction step, a feature fusion step and a feature regression step. Firstly, point cloud is subjected to two kinds of preprocessing, one is that the point cloud is decomposed into sub-models, and the other is that a camera rotates around the point cloud to generate a dynamic video. And the obtained point cloud sub-model and the dynamic video are respectively sent to a feature extraction unit, and in the feature extraction stage, geometric distortion features are extracted from the point cloud sub-model, and spatial features and time features are extracted from the dynamic video. And then entering a feature fusion stage, fusing spatial features, time features and geometric distortion features by using a new cross-modal attention module to obtain final quality perception features, and finally, regressing the final quality features to a predicted quality score by using a dual full-connection layer.

Embodiments of the invention provide a data processing method and apparatus, a storage medium and a computer device. The method comprises the steps of obtaining data reported by each data source from at least two data sources; comparing the data corresponding to each data source with data in a preset database, and determining a matching rate, a false alarm rate and a missing report rate of each data source; determining a quality score of each data source based on the matching rate, the false alarm rate and the missing report rate of each data source; obtaining an index value of each piece of data, and classifying target data with the same index value reported by different data sources; acquiring a data confidence score of each piece of target data in the classified data; based on the data confidence score of each piece of target data and the quality score of the data source corresponding to each piece of target data, the classification score of the classified data is determined, the quality score of each data source is effectively determined, and the same data from different data sources are classified; a reliability assessment of the classified data is provided through the quality score of each data source.

The invention relates to the technical field of big data intelligent decision making, and provides a household appliance commodity dynamic pricing system and method based on multi-source data fusion, and the system comprises a data collection server, a feature extraction engine, a model training cluster, and a strategy execution terminal. The feature extraction engine comprises a time sequence feature constructor used for generating sliding window statistics; the semantic analysis unit is used for analyzing a commodity detail page text description to generate a brand premium coefficient; and the image recognition module is used for predicting the willingness to pay by the user through the commodity main image quality score. Through collaborative design of the feature extraction engine and the model training cluster, the dynamic response capability and the data application depth which are deficient in a traditional pricing mechanism are realized, traditional household appliance merchants are assisted to adapt to market changes, the customer satisfaction and the market share are improved, and the survival and development of the merchants are guaranteed.

A search system and method generates a quality score and / or a political lean score for a piece of content and returns the one or more scores to the user when returning search results from a query to the user. In one embodiment, the system and method may use artificial intelligence / machine learning to determine the one or more scores for each piece of content.

The invention discloses a knowledge graph-based search engine relation chain recommendation method, which comprises the following steps of: receiving a relation chain recommendation request submitted by a user through a search engine to obtain initial query information; performing semantic analysis and intention recognition on the initial query information, and determining a corresponding entity type and a relationship type; calling a dynamic knowledge selection and evaluation mechanism according to the entity type and the relationship type, and dynamically screening the original knowledge graph to obtain effective knowledge sub-graphs; performing diffusion type reasoning based on a knowledge graph diffusion model to generate a candidate relation chain path set; evaluating the quality score of each candidate path in real time; and performing dynamic screening according to the path quality score, and outputting a relation chain path recommendation result. According to the method, accurate mining and dynamic optimization of the knowledge graph relation chain path are realized, and the accuracy of a recommendation result and the flexibility of user interaction are improved.

The invention belongs to the technical field of front-end performance optimization. According to the webpage resource preloading method and system based on multi-factor dynamic evaluation, a network quality score is obtained according to an obtained bandwidth factor, a network delay factor and a resource stability factor of a current webpage; dynamically adjusting the behavior weight score of each webpage resource according to the user behavior; determining corresponding loading priority weight scores according to the types of different webpage resources; and taking the weighted sum of the network quality score, the behavior weight score and the loading priority weight score as a final loading score, and carrying out corresponding webpage resource loading according to the final loading score. According to the method, the network quality evaluation and the user behavior prediction are combined by monitoring the network quality score and the user interaction behavior in real time and dynamically adjusting the loading priority and the strategy of the key resource, the limitation of a traditional static resource loading strategy is broken through, and the page loading speed and the overall performance are remarkably improved.

The invention discloses an intelligent question and answer method and terminal based on a retrieval-generation model. The method comprises the steps that a first target answer matched with a target question sent by a user is retrieved in a question and answer pair knowledge base; if the first target answer is not retrieved, generating a second target answer matched with the target question through a retrieval-generation model, and returning the second target answer to the user; obtaining feedback data of the user about the second target answer, and calling an evaluation index model according to the target question and the feedback data to analyze and process the second target answer to obtain a quality score; and if the quality score of the second target answer is greater than a preset target score, updating the target question and the second target answer to the question and answer pair knowledge base. According to the method, computing resources consumed by the RAG question-answering system can be reduced, the response speed is increased, and the reliability of generating answers by questions and answers is improved.

A search system and method generates a quality score and / or a political lean score for a piece of content and returns the one or more scores to the user when returning search results from a query to the user. In one embodiment, the system and method may use artificial intelligence / machine learning to determine the one or more scores for each piece of content.

The invention discloses an annotation task allocation method, a related device, equipment and a storage medium, and the method comprises the steps: obtaining the index data of a target task type executed by a candidate annotation customer based on the target task type of a to-be-allocated annotation task; wherein the index data comprises index values of a plurality of index dimensions; obtaining a weight factor of each index dimension under the target task type based on the configuration information about the relative emphasis of the plurality of index dimensions under the target task type; weighting based on the weight factor and the index value of the same index dimension under the target task type to obtain a marking quality score of the target task type executed by the candidate marking guest; and based on the annotation quality score of each candidate annotation customer, allocating a target annotation customer to each to-be-annotated file in the to-be-allocated annotation task. According to the scheme, the rationality of annotation task allocation can be improved.

The invention relates to the technical field of content analysis, and particularly discloses a delivery analysis method and system based on content characteristics and propagation effects, and the method comprises the steps: obtaining a plurality of delivery contents based on a target keyword; multi-dimensional putting effect analysis is carried out, and a putting effect comprehensive score is generated; performing content characteristic analysis on the plurality of delivery contents to generate a content quality score; acquiring propagation data of a plurality of delivery contents, constructing a propagation network based on the propagation data, inputting the propagation network into a pagerank model, and outputting a propagation effect score; and generating a delivery analysis report according to the delivery effect comprehensive score, the content quality score and the propagation effect score. Through analysis of multi-dimensional indexes such as the delivery amount, the category, the time interval distribution and the re-delivery proportion, a delivery effect comprehensive score is generated based on standardization and a weight distribution mechanism, the overall performance of a delivery strategy can be evaluated, delivery effect feedback can be provided, systematic decision support is provided, and the delivery efficiency and the return rate are improved.

In embodiments, a processing device detects a margin line in a model of a preparation from one or more images. The processing device determines, for each segment of a plurality of segments of the margin line, a quality score for the segment. The processing device determines that a segment of the margin line has a quality score that is below a quality threshold, wherein the segment of the margin line was generated based on a first set of images. Responsive to determining that the segment of the margin line has the quality score that is below the quality threshold, the processing devices updates the three-dimensional model of the preparation by replacing a portion of the three-dimensional model associated with the segment of the margin line with image data from at least one of a new image or a second set of images.

The invention discloses a setting process parameter recommendation method and device, computer equipment and a storage medium. The method comprises the steps of obtaining to-be-predicted production order data; preprocessing the production order data to be predicted; the preprocessing result is input into a prediction model for technological parameter prediction; outputting a prediction result; the prediction model is obtained by taking production order data as a sample set after the production order data is preprocessed and labeled and training a multi-weight main model by adopting an iterative training mode, and specifically, the quality score of each piece of preprocessed and labeled data is dynamically adjusted and is fused into a loss function for training; the multi-weight main model comprises a plurality of base models and meta-models, different weights are distributed according to the prediction performance of the base models, and results obtained through prediction of the weighted base models are integrated through the meta-models. By implementing the method disclosed by the invention, the effect of enhancing stacking by multiple models can be exerted, the dependence on artificial experience is reduced, the accuracy of process parameters and the one-time success rate of production are improved, and the product repair and production cost is reduced.

The present application discloses a method and device for evaluating the dissemination of social media information. A specific implementation of the method includes: obtaining users related to the current social media information and the relationships between each user; calculating the influence score of each user based on the relationships between each user; obtaining the interactive content of each user related to the current social media information based on the relationships between each user; calculating the quality score of each user's interactive content based on the interactive content of each user; and calculating the dissemination evaluation score of the current social media information based on the influence score of each user and the quality score of each user's interactive content. This implementation can effectively measure the dissemination effect of social media information.

Techniques are described for training and use of machine learning models to determine objective video quality scores. Video quality scores predict the quality of video content perceived by viewers. Quality scores have various uses, including the selection of encoding profiles and determination of encoding ladders. A core model and residual model may be used to determine quality scores.

Systems and methods are disclosed for generating an adaptive bitrate ladder for a content item based on the actual quality of the content item. A user uploaded content item is determined to have different quality scores in different time portions of the content item, where the quality score is based on an analysis of visual characteristics of frames of the content item. In response, an adaptive bitrate ladder (ABR) is generated for each time portion which contains a set of bitrates based on the quality score.

The invention discloses an RAG question and answer optimization method and system based on fusion retrieval, and relates to the technical field of large model knowledge question and answer. The method comprises the steps of obtaining user query, executing keyword retrieval and semantic vector retrieval in parallel, and obtaining a keyword retrieval result list and a semantic vector retrieval result list respectively; and calculating the quality score of each text unit in each retrieval result list based on multi-dimensional quality evaluation, and filtering out the text units with the quality scores lower than a preset quality threshold value. And sorting the text units in all the filtered retrieval result lists by adopting a quality weighted reciprocal sorting fusion algorithm. And based on the length of each text unit and the document format to which the text unit belongs, performing context content enhancement and combination on each text unit after sorting, and generating an enhanced context block list. And constructing structured prompt information based on the enhanced context block list and user query, inputting structured prompt words into the large language model, and generating and outputting a final answer.

The invention provides a session quality evaluation method, system and device and a medium, and relates to the technical field of data analysis, the method comprises the following steps: determining candidate keywords based on session information of a current session; determining the keyword weight of each candidate keyword based on the undirected graph, selecting a preset number of candidate keywords as keywords based on the values of the keyword weights, and determining the sentiment weight of each keyword according to the sentiment tendency and sentiment intensity corresponding to each keyword under each evaluation dimension; according to the dynamic change condition of the emotional tendency and / or emotional intensity corresponding to each keyword in the session information, dynamically adjusting the emotional weight of each keyword; and in combination with the occurrence frequency, the emotion weight and the keyword weight of each keyword, performing weighted summation on the score of each score dimension to obtain a session quality score of the current session. According to the method, the session quality can be accurately and quickly evaluated.

Methods, systems, and computer program products for implementing active learning in NLG tasks are provided herein. A computer-implemented method includes generating multiple natural language annotations associated with multiple items of unlabeled data by processing the unlabeled data using at least one artificial intelligence model; determining at least one quality score attributed to at least a portion of the multiple generated natural language annotations based at least in part on at least one quality metric; selecting at least one of the multiple natural language annotations and at least one corresponding item of the multiple items of unlabeled data based at least in part on the at least one determined quality score; and performing one or more automated actions based at least in part on the at least one selected natural language annotation.

The invention discloses a heat setting process parameter recommendation method and device, computer equipment and a storage medium. The method comprises the steps of obtaining to-be-predicted production order data; preprocessing the to-be-predicted production order data to obtain a preprocessing result; inputting the preprocessing result into a prediction model to perform process parameter prediction so as to obtain a prediction result; wherein the prediction model is obtained by preprocessing production order data, labeling the data as a sample set and training a multi-weight main model formed by stacking a plurality of base models with weights and meta-models, and the weights of the base models are determined by the prediction performance of the base models; a loss function in the training process is added into the quality score of each piece of preprocessed and labeled data; and outputting the prediction result. By implementing the method disclosed by the invention, the effect of enhancing stacking by multiple models can be exerted, the dependence on artificial experience is reduced, the accuracy of process parameters and the one-time success rate of production are improved, and the product repair and production cost is reduced.