16 results about "Attribute weight" patented technology

The invention discloses a big data measurement asset supply and demand matching and inventory optimization method, and relates to the technical field of big data processing and supply chain management. The method comprises the following steps: segmenting supply chain asset data through a hash function according to multi-dimensional attributes to generate a data fragment set, and constructing a global index tree according to the data fragment set; and monitoring the load state of the leaf nodes of the global index tree in real time, and migrating and verifying data during unbalance. And querying the global index tree, positioning fragment data associated with the query request from the uniformly distributed leaf nodes, generating a preliminary matching asset set, calculating the matching degree of each asset and the query request, and generating a resource allocation result. And updating the global index tree, and generating the latest data view representation. And adjusting the attribute weight coefficient of each dimension in the hash function, and generating optimized storage layout configuration. Irrelevant data are filtered through a neighbor algorithm, and a final matching result set is generated. Balanced storage, efficient query and accurate matching of asset data are realized, and the overall response speed and the resource utilization rate are improved.

The application provides a material similarity analysis method based on a semantic library and a knowledge graph, comprising the following steps: S1: judging whether the decisive attributes of two materials are similar, if any of the decisive attributes is not similar, then the two materials are non-redundant materials, otherwise, entering S2; S2: calculating the similarity of the field part according to the non-decisive attribute weight and the distance of each field; S3: combining all the knowledge graph paths and weight values to calculate the similarity of the graph part; S4: adding the similarity of the field part and the similarity of the graph part to obtain the final material similarity, and judging whether the two materials are high similarity through the final material similarity. The material similarity analysis method provided by the application optimizes the accuracy of the similarity algorithm.

The application discloses a kind of based on multiple confidence medical data missing value batch repair method, the method includes: using attribute weight updates sample confidence, missing sample set is introduced into model training;Using sample confidence optimization loss function, fill the missing value of data set;The sample confidence is calculated according to the attribute relationship between samples, according to the data attribute to be predicted and the number of missing values in sample, different confidence is given to sample;The influence degree of sample in model training process is adjusted by dynamic selection of confidence.Optimize model architecture, so that the network can fill the missing value of multidimensional data in batches at a time, can also eliminate the identity mapping problem of network transfer function, and enhance the intercorrelation between nodes.The application improves the utilization of data, improves the filling accuracy and filling efficiency of data.

A price analysis method and system based on a multi-attribute template, comprising: constructing a multi-attribute template, generating attribute weights and coding rules through association rule mining, and fusing commodity descriptions and business fields into attribute vectors; calculating similarity based on weighted Euclidean distance, normalizing attention weight through Softmax, and weighting and summing historical prices to obtain reference price; calculating deviation rate and comparing with threshold value to perform hierarchical disposal; constructing a knowledge graph to detect associated abnormalities and price avoidance paths; and implementing batch backtracking based on a version-identified feature cache table. The present application realizes fine-grained price analysis and hidden abnormality mining, and supports dynamic template updating, coding rule adaptive calibration and multi-level rollback mechanisms, significantly improving system robustness and cold start capability.

The invention discloses an intelligent automatic distribution method, system and device for college paper marking experts and a medium. The method comprises the steps of calculating a first attribute weight, a second attribute weight and a third attribute weight; inputting the historical data corresponding to each fourth attribute into a linear regression equation to obtain a fourth attribute weight of each fourth attribute; selecting a preset number of target experts; based on the multiple first attributes, the first attribute weights, the multiple second attributes, the second attribute weights, the multiple third attributes, the third attribute weights, the multiple fourth attributes and the fourth attribute weights, the test questions and the target experts are matched, and a matching success record set is obtained; and performing matching effect evaluation on the successful matching record set to obtain an evaluation result, and if the evaluation result is greater than or equal to a preset threshold value, taking the successful matching record set as a target matching result, and allocating paper marking experts according to the target matching result. The accuracy of matching between the expert and the test paper to be read is improved, and the matching efficiency is improved.

The application discloses an industry chain knowledge question and answer interaction method and system based on a large model, groups each process node contained in a target industry chain based on attribute weight values and continuity between process nodes and upstream and downstream relationships, so that the obtained node set contains process nodes that not only reflect the relationship between the upstream and downstream, but also can realize the solidification of the relationship between the process nodes based on the process sequence through the arrangement order between the node sets, and then realize the solidification of the knowledge structure of the target industry chain, reduce the phenomenon that the knowledge is too loose and it is difficult to find the logic and rules contained therein due to the weak knowledge structure, and provide conditions for the model to generate targeted and clear answers. The application is applicable to the application of electronic digital data processing technology in the field of question and answer interaction related technology.

The invention provides a normative checking method and tool for software requirement cases and a computer program product. The checking method comprises the following steps: extracting attributes from a software demand case, and converting the attributes into feature vectors by adopting one-hot coding according to a demand case related vocabulary set and a preset weight of each attribute; vector dimensions are equal to the size of the vocabulary set, vector positions are in one-to-one correspondence with words in the vocabulary set, and word frequencies are weighted and counted according to attribute weights and then are filled into the corresponding vector positions; on the basis of the feature vectors, classifying the software demand cases by utilizing a classification model; and matching the corresponding writing specification according to the category of the software demand case, and carrying out natural language structured analysis on the description of the software demand case by adopting an improved shift-protocol dependency analysis method to judge whether the description conforms to the writing specification or not. According to the method, the problem of low manual inspection efficiency is solved, the inspection efficiency is greatly improved through multi-dimensional technical optimization, and standardization and intelligentization of software demand review are promoted.

The invention relates to the technical field of fine adjustment of large mine models, in particular to a multi-field data weighted mixing method, device and equipment for fine adjustment of a large mine model and a computer storage medium. According to the method, the domain target weight and the sample multi-homing probability are accurately combined in the batch construction stage, controllable adjustment of the contribution proportion of each domain is achieved, and it is ensured that low-resource or key domains get full attention in training; in the loss calculation stage, multi-field loss is subjected to weighted fusion by using the attribution weight, so that the model learning process better fits the real multi-field distribution of the sample. Finally, according to the method, the performance balance and the overall generalization ability of the fine-tuned large mine model in each sub-field task are remarkably improved, and the adaptability to a complex multi-label scene is enhanced.

The invention discloses an alarm data aggregation method and device, equipment and a medium, and belongs to the technical field of computers. According to the method, the importance of condition attributes relative to each equivalence class corresponding to a preset decision attribute set is introduced, and according to the difference between the importance of each condition attribute in the preset condition attribute set relative to the equivalence class and the importance of the whole preset condition attribute set relative to the equivalence class, the equivalence class is determined. And determining an attribute weight of each condition attribute corresponding to the equivalence class, thereby identifying important attributes in respective associated condition attributes under different equivalence classes, and further judging whether the related alarm data is associated with the same attack classification according to the important attributes under each equivalence class. And the alarm data associated with the same attack classification is aggregated.

The invention relates to a fairness repairing method for constructing a table data classification model of multiple loss items, and belongs to the field of artificial intelligence and machine learning. The method comprises the following steps: firstly, counting the number proportion of various different sensitive attributes in a training set, adjusting the weight of a fair regular term of a loss function according to the proportion to retrain a model, and calculating a change ratio of a fairness index to an accuracy index by utilizing a test set; secondly, randomly replacing each attribute of the table with a reconstructed sample, and calculating the similarity between an original sample and the reconstructed sample as a model comparison loss item; and finally, adjusting the weight of a fair regular term and comparing the weight of a loss term by using the change ratio, and retraining the model to generate a fair repair model. Aiming at the problems that prediction fairness imbalance of a model to other sensitive attributes is easily caused by only processing a single sensitive attribute and the accuracy is influenced by deleting the sensitive attributes in the existing method, fairness repair under the condition that the model accuracy is kept is realized through training sample reconstruction and sensitive attribute weight distribution.

Embodiments of the present application provide a list data filtering method and device, electronic equipment and readable storage medium, and relate to the technical field of computer. The method comprises: determining at least one candidate list data from the to-be-filtered list according to a target screening condition, and then determining invalid attributes that do not match at least one target attribute from a plurality of preset attributes based on the at least one target attribute corresponding to the target screening condition. The attribute weight of each target attribute can be improved according to the initial weight of the invalid attribute to obtain the first attribute weight corresponding to each target attribute, and then the list data weight of each candidate list data is obtained according to the first attribute weight corresponding to each target attribute. The final valid list data is determined by judging whether the list data weight is greater than a preset list data weight threshold, thereby improving the accuracy of list data screening and making the screened list data more application valuable.

The application relates to a large-scale heterogeneous multi-attribute equipment scheme clustering decision method and medium, which comprises the following steps: converting heterogeneous attribute data in a digital twin decision information system into binary connection numbers; determining attribute weights by adopting a MEREC method; constructing attribute irreplaceable values based on the attribute weights and the binary connection numbers; generating a scheme similar network according to the attribute irreplaceable values; performing network clustering operation on the scheme similar network to output a scheme clustering result; and calculating the comprehensive target heart distance of the schemes in the cluster based on the scheme clustering result by adopting a grey target theory, and generating a final scheme score by fusing the scheme global value and the comprehensive target heart distance. The method solves the problems of heterogeneous information fusion distortion, attribute irreplaceable mechanism loss and low large-scale scheme clustering efficiency in a digital twin decision scene by constructing a 'heterogeneous data unification-attribute irreplaceable mechanism modeling-network clustering-clustered decision' mechanism.

The embodiment of the invention provides a video communication method and device, equipment, a medium and a program product. The method comprises the following steps: acquiring a first attribute set of a first communication terminal in a video communication group, wherein the first attribute set comprises attribute data of the first communication terminal associated with target video data; determining a second attribute set according to the attribute data and candidate attributes of the target video data, wherein the second attribute set comprises video indexes; determining a third attribute set according to the attribute data, the candidate attributes and the frame size of the target video data, wherein the third attribute set comprises performance indexes; and determining an attribute weight according to a service scene associated with the video communication group, and determining a target attribute associated with the target video data according to the second attribute set, the third attribute set and the attribute weight. According to the embodiment of the invention, the target attribute is determined by comprehensively considering the video index, the performance index and the service scene, and the video stream is sent according to the target attribute, so that the user experience is optimized.

The invention relates to the field of data cleaning, and discloses a multi-source heterogeneous document deduplication method and system based on attribute weighted fusion, equipment and a medium, the method is characterized in that repeatability judgment is carried out on two documents based on a key attribute set and a mapping table, so that the repeatability judgment process focuses on and weights the core attributes of the documents, and the data cleaning efficiency is improved. According to the method, the duplicate removal problem is converted from text similarity comparison to discriminant force weighted fusion decision of key attributes, non-key differences among documents are ignored, recognition of repeated contents of the documents is more accurate, accuracy and robustness of repeatability judgment are improved, and a weight mechanism allows that the repeated contents of the documents can be more accurately recognized when part of key attributes are missing or errors exist. Reliable judgment can still be made based on existing key attributes, harsh dependence on information integrity is reduced, and high-precision repeated content recognition can still be achieved in an information missing scene. Besides, by configuring different key attribute sets and mapping tables, the method can be quickly and flexibly adapted to various vertical fields, and the universality and generalization ability are improved.

This invention provides a method, apparatus, device, and medium for personalized configuration of delivery confirmation methods, including: constructing a multi-dimensional attribute library for packages; extracting package attributes corresponding to a target package based on the constructed multi-dimensional attribute library; constructing a feature vector for the target package based on the package attributes of the target package and the logical relationships between the attributes; and completing intelligent matching and decision-making of delivery confirmation rules based on the feature vector of the target package, combined with the global attribute weights corresponding to each package attribute of the target package and a digital delivery confirmation rule library. This invention addresses industry pain points such as rigid processes, insufficient intelligence, significant system performance shortcomings, and poor adaptability to complex scenarios in traditional logistics delivery confirmation models. Through a complete technical system encompassing multi-dimensional attribute modeling, weighted intelligent matching, LLM for complex scenarios, high-frequency rule caching, and high-concurrency traffic control, it achieves precise personalized configuration of delivery confirmation methods and efficient and stable system operation.

This invention discloses a comprehensive log collection and maintenance method and system, relating to the field of intelligent operation and maintenance technology. The method includes: collecting multi-source log data and performing standardization processing to generate standardized log data; calculating information gain to generate attribute weights based on the standardized log data; calculating multi-class attribute distances using K-Prototype clustering to generate a final weighted distance to obtain a clustering dataset; optimizing the GNN model using the PGNN framework combined with a graph attention mechanism to output an optimized clustering dataset; generating anomaly candidate clusters based on the optimized clustering dataset; extracting anomaly characteristics of the anomaly candidate clusters; and classifying the anomaly characteristics of the anomaly candidate clusters using a K-NN classifier to obtain the data point classification results. This invention improves the accuracy and response speed of anomaly log identification, achieving more efficient log management.