28 results about "Uncertain data" patented technology

The invention discloses a hypergraph feature representation method, system and device based on fuzzy logic and a medium, and the method comprises the steps: obtaining original data, and constructing a hypergraph structure containing vertexes and hyperedges according to the original data; the hypergraph structure is initialized, and an initialized hypergraph structure is obtained; and inputting the initialized hypergraph structure into a preset hypergraph convolutional fuzzy network model for feature representation processing to obtain a hypergraph structure after feature representation processing. According to the hypergraph convolutional fuzzy network model, fuzzy representation and the hypergraph technology are deeply fused, the membership core concept of fuzzy logic is introduced, the hard coding association limitation of an existing hypergraph representation learning method that no black is white is broken through, the technical problems that a traditional hypergraph model cannot capture association gradients and fuzzy semantics are lost are effectively solved, and the learning efficiency is improved. Therefore, the flexibility and accuracy of the model are effectively improved, and stable prediction is provided in an uncertain data environment.

The invention relates to the technical field of data processing and distribution, and discloses an internet of things data distribution engine algorithm. The method comprises the following steps: firstly, cleaning and standardizing collected original power data; performing feature extraction and semantic analysis, and generating a dynamic priority score representing the real-time emergency degree of the data and a static importance factor representing the inherent importance of the equipment by calculating a plurality of dynamic feature indexes of the equipment and combining the business metadata of the equipment; a hierarchical scheduling strategy is adopted, secondary judgment based on the change trend is started for uncertain data, and accurate routing of the data to channels with different priorities is achieved; finally, the system dynamically adjusts a distribution threshold value according to actual service utility feedback of data distribution, and closed-loop optimization is formed; according to the method, the problems of key information submerging, response delay and extensive resource allocation in massive Internet of Things data are effectively solved, and low-delay transmission of high-value data and self-adaptive optimization of system resources are realized.

The invention discloses an intelligent form processing method and system based on rule tree optimization and large model screening, and relates to the technical field of artificial intelligence and data automation. The problems that the processing efficiency is low due to static solidification of a rule system, redundancy of execution paths and dispersion of homogeneous rules in a traditional form processing method, and the screening accuracy is low and the labor cost is high due to the lack of effective judgment capability for complex, fuzzy or implicit condition data of semantic understanding are solved. By constructing and optimizing the rule tree structure and combining with the semantic comprehension ability of the large language model, automatic grading processing and intelligent screening of the form are realized. Firstly, deterministic rule matching and filtering are completed by a rule tree, then semantic judgment is carried out in a logic context by utilizing a large model for uncertainty data, and finally, a screening result is fused and output. According to the method, the efficiency, the accuracy and the automation level of form processing in a complex business scene are remarkably improved.

The application provides a dynamic scheduling method for uncertain data-intensive workflow in a cloud environment, solves the scheduling problem caused by the lack of transmission data size information, and helps to simultaneously reduce the cross-data center data transmission amount of the workflow and the execution cost of the workflow. First, the workflow structure is abstracted to obtain a DAG graph; then, static task pre-allocation is performed under the condition of partial data size information missing, an executable task forest graph of each data center is obtained, each task node in the forest graph is sorted according to the saved transmission data size, the task node with the largest saved data transmission size is allocated in the corresponding data center, and the predecessor node and the successor node of the node in the data center are also allocated in the data center, until all tasks are pre-allocated; then, dynamic adjustment of task allocation is performed based on the static task pre-allocation result and the actual transmission data size generated after the execution of each task in the workflow, and finally, an allocation scheme is obtained.

The present application relates to the technical field of intelligent adjustment of air conditioner, in particular to a kind of air conditioner resource flexible regulation and control method of simplifying easy operation implementation, including establishing adjustment model, suggestion calculation model, establishing distribution model and closed loop regulation, beneficial effect is: by introducing the numerical concept of power transfer proportion, so only need to carry out preliminary data collection, power transfer proportion can be calculated based on the preliminary collection of data, so in subsequent adjustment process, the environmental data needed to be collected, only need to be calculated based on power proportion to realize the intelligent air conditioner adjustment based on power grid, and by calculating the power proportion data of different time periods, hedge a large number of uncertain data and factors, greatly reduce the difficulty of data collection and analysis, improve the simplicity of regulation.

The invention provides a probabilistic nearest neighbor query method on high-dimensional continuous uncertain data, and relates to a method for quickly retrieving the nearest neighbor of the uncertain data by combining a locality sensitive hashing technology and probability calculation. The method comprises the following steps: firstly, constructing locality sensitive Hash for mapping, and mapping the uncertainty of a data object into a plurality of Hash tables through sampling; in a query stage, candidate adjacent objects are extracted from a given query point by using an index, and the probability that each candidate object becomes the nearest neighbor of the query point is calculated through Monte Carlo simulation. And finally outputting the neighbor object with the maximum probability and the probability value thereof. According to the method, the efficiency of high-dimensional uncertain data nearest neighbor query is greatly improved while the query accuracy is guaranteed, and the method can be widely applied to the fields of big data analysis, uncertain information retrieval and the like.

The application discloses a flotation condition recognition method and system based on a weighted K nearest neighbor algorithm, and the method comprises the following steps: setting fuzzy multi-neighbor particles for fuzzy and uncertain data and different distributions of various features in a bubble image data set; introducing the concept of entropy to calculate the information amount provided by the fuzzy multi-neighbor particles induced by a feature subset; fully considering the multiple relationships among the bubble image features under the fuzzy multi-granularity information theory framework; constructing a target evaluation function according to the multiple relationships among the features, calculating the function value of each feature, and sorting the features; weighting the K nearest neighbor algorithm by using the calculated feature function value; and selecting the feature subset with the highest classification accuracy as the optimal feature subset for the flotation condition recognition. The application fully considers the multiple relationships among the bubble image features, can fully utilize the useful information provided by the features, and has high classification efficiency and classification accuracy.

The invention relates to the technical field of operation and maintenance anomaly detection, and discloses an intelligent operation and maintenance anomaly detection method and system based on fuzzy logic, and the method comprises the steps: carrying out the modeling of operation and maintenance data through the fuzzy logic, so as to process the uncertainty and fuzziness of the data; analyzing the operation and maintenance data by using a fuzzy logic model to identify an abnormal mode; and outputting an anomaly detection result. According to the method, the fuzzy logic is deeply integrated into the whole anomaly detection process, an intelligent operation and maintenance anomaly detection mechanism with accuracy, adaptability and interpretability is constructed, the limitation of a traditional method in processing uncertain data is effectively overcome, and the intelligent level and fault response efficiency of an operation and maintenance system are remarkably improved.

A pumped storage power station intra-day optimization scheduling method considering multi-source input comprises the steps that multi-source uncertainty data such as wind power, load and electricity price are collected and preprocessed, historical data are dynamically captured through a sliding window, time development trends and key parameters such as a mean value and covariance are calculated, a future uncertain source interval is predicted based on historical fluctuation, and optimal scheduling of a pumped storage power station is achieved. The method comprises the following steps of: establishing a water pumping and power generation power scheduling scheme, deducing a prediction interval of power generation and water pumping power, optimizing the accuracy of the interval through parameter adjustment, finally establishing an optimization model by taking economic cost minimization and power grid net power stability maximization as targets, generating the water pumping and power generation power scheduling scheme, and improving the robustness and scheduling efficiency of a system to deal with uncertainty. The method not only can adapt to complex scenes with frequent climate anomalies and effectively expand the application range of the optimization scheduling method, but also can adjust time development trend data and key parameters of historical uncertain sources and effectively cope with strong fluctuation characteristics of wind power.

The purpose of the present invention is to improve the reliability of an image processing system by taking into account the distribution of positive solution data corresponding to the output of a learning model and determining the output of the learning model while containing a deviation. For example, the present invention is provided with: a model application unit for generating an estimated high-quality image by applying a machine learning model to a low-quality image; an evaluation value calculation unit that calculates an evaluation value for the estimated high-quality image; and a determination unit that determines the estimated high-quality image on the basis of the evaluation value of the estimated high-quality image, the determination unit determining the estimated high-quality image using a deviation range of the evaluation value of a high-quality image obtained by capturing the low-quality image with high quality, the deviation range being acquired in advance and corresponding to the evaluation value of the estimated high-quality image. It is determined whether the speculated high quality image is uncertain data.

The invention relates to a method for determining the recruitment process of pilots using artificial intelligence-based fuzzy multi-criteria decision-making models, which creates an artificial intelligence-based decision-making model by considering numerous criteria such as socio-cognitive abilities, performance competencies, communication skills, visual perspective perception, and spatial working range in the selection process of airline pilots; processes and evaluates uncertain, vague, and subjective data with fuzzy logic techniques (fuzzy TOPSIS, fuzzy VIKOR, and fuzzy PROMETHEE) and enables the ranking of candidates; transforms non-numerical linguistic terms into fuzzy mathematical models; ensures the integration of qualitative and quantitative data and the transformation of uncertain data into reliable results in pilot selections; facilitates the successful ranking of candidate pilots and the selection of competent personnel for safe operations by companies; improves the recruitment process of pilots and utilizes an artificial intelligence-based decision-making model application in their selection

The invention provides a data estimator determination method and device based on fuzzy self-adaption, and relates to the technical field of data processing, and the method comprises the steps: obtaining an uncertain data set comprising a plurality of data observation values; calculating a mutual distance value between every two data observation values, and superposing the mutual distance values to obtain a mutual distance sum value; in combination with the mutual distance value and the mutual distance sum value, introducing an index coefficient greater than 1 to calculate the fuzzy membership degree of each data observation value relative to the uncertain data set estimator representing the trend of the data observation value; and determining an uncertain data set estimator, namely a data estimator, through a weighted median algorithm and an HL estimator algorithm according to the fuzzy membership degree. According to the method, the influence of abnormal values and data pollution on the estimator can be effectively reduced, the robustness of the estimator is improved, the real trend of the data can be accurately reflected, and particularly, the robustness and the accuracy are relatively high when the method faces uncertain or noise data.

The present application relates to the technical field of data center demand response, solves the technical problem of uncertain data center load regulation capacity, and particularly relates to a multi-agent game method considering uncertain data center demand response regulation capacity, comprising: constructing a data center user load optimization model; solving a microgrid operator optimization model to obtain a microgrid operator optimization strategy, and solving a non-data center user load optimization model to obtain a non-data center user load optimization strategy; inputting the non-data center user optimization strategy and the microgrid optimization strategy into the data center user load model for solving. The present application supports the participation of data centers in demand response through demand side resources of microgrid parks and non-data center user load regulation, solves the problem of uncertain data center load regulation capacity, thereby improving the flexibility of the power system, ensuring the safe and stable operation of the power system, and promoting renewable energy power consumption.

This invention discloses a duplicate data fusion detection method based on pre-trained active learning. The method includes generating candidate pairs in a labeled dataset and serializing these candidate pairs to obtain a serialized dataset; inputting the serialized dataset into a NER model to identify known types and using regular expressions to identify specific types; preprocessing the serialized dataset; inputting the preprocessed serialized dataset into a pre-trained BERT model, selecting the most uncertain data in the unlabeled dataset for labeling, and then inputting the labeled data into the labeled dataset; using the R-Drop strategy to augment the labeled dataset from step 4; and iterating through the augmented labeled dataset to obtain the final labeled dataset. This invention combines active learning algorithms, selecting the most valuable data for manual annotation, reducing the cost of manual annotation, and rapidly improving model quality with a small amount of data.

The invention discloses a real-time acquisition and storage method for key operating parameters of frequency converters, which belongs to the technical field of frequency converters, and comprises the following steps: aiming at the characteristics of concurrent access of multiple frequency converters, various data types, out-of-order arrival and continuous growth, performing acquisition, time alignment and packaging according to the data types on the operating parameters at an edge side; and a logic storage address is constructed on the center side based on the time interval, the equipment identifier and the data type, and mapping and ordered writing of the logic address and a physical storage position are realized through a storage positioning mechanism, so that the problem that the operation data of the plurality of frequency converters cannot be uploaded under the conditions of high concurrency and disordered uploading is solved. The technical problems of complete acquisition, stable storage and rapid positioning query are solved, the integrity of the original operation data is ensured, the network transmission pressure is effectively reduced, storage disorder caused by an uncertain data arrival sequence is avoided, and the storage efficiency and query efficiency of the operation data of the large-scale frequency converter are improved.

The invention provides a diabetes mellitus morbidity probability prediction method, which comprises the steps of expanding a probability dependence model by adopting a dynamic Bayesian network, fusing new evidence information to update a conditional probability of interaction influence, and judging an updated morbidity probability evaluation value; comparing the disease probability evaluation value with a historical data track, when the deviation is greater than a preset threshold value, acquiring additional environment exposure uncertain data, supplementing the additional environment exposure uncertain data into the model, and determining an adjusted prediction complexity amplification coefficient; optimizing a tree depth parameter of a random forest algorithm according to the adjusted prediction complexity amplification coefficient, and retraining an integrated model for multi-level random factors to obtain an optimized uncertainty capture framework; and processing random event quantitative data input in real time by adopting the optimized uncertainty capture framework, and dynamically updating a probability prediction mechanism to output a final diabetes morbidity probability evaluation result.

The application relates to a time synchronization method and device for multi-sensor data, electronic equipment, a storage medium and a computer program product. The method comprises the following steps: after receiving sensor data sent by any sensor (target sensor) in a plurality of sensors, updating a receiving count value of the target sensor; after the updating, detecting whether a preset time synchronization condition is met based on the receiving count values of the sensors in the plurality of sensors; and when the condition is met, performing time synchronization processing on a plurality of target sensor data according to the receiving time of the target sensor data, so as to divide the batches to which the target sensor data belong. Through the above method, the batches to which the target sensor data belong can be divided, a master sensor does not need to be set, time synchronization errors caused by uncertain data reaching sequences of the master sensor are avoided, and the accuracy of time synchronization is improved.

This invention provides a method and system for path optimization and operation mode adjustment for ensuring power supply to critical users, relating to the field of resource planning and allocation technology. By constructing a complete technical closed loop from multi-dimensional risk perception and dynamic hierarchical attribution to adaptive robust optimization, it provides a method for path optimization and operation mode adjustment that improves the accuracy, interpretability, and system robustness of power supply guarantee decisions for critical users. Through precise risk tracing, it achieves a shift from passive response to proactive elimination of risk root causes, improving the transparency and traceability of decision-making. By introducing dynamic risk transmission factors, it makes risk assessment results closer to the physical reality of the power grid, enhancing the accuracy of decision-making. Through adaptive multi-objective fusion optimization, it enhances the stability and reliability of the decision-making system under complex operating conditions and uncertain data environments.

The invention relates to a micro-grid energy management method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: constructing an energy management model based on a network topology structure of a micro-grid; constructing a robust optimization model based on the uncertain data of the DC load and the photovoltaic output of the micro-grid; converting a nonlinear constraint condition containing an uncertain variable in the robust optimization model into a deterministic linear constraint to obtain a reconstructed robust optimization model, and applying the reconstructed robust optimization model to an energy management model to obtain a final energy management model; and inputting the photovoltaic output data of each node in the micro-grid, the DC load data of each line, the AC load data of each line, the output parameter data of the energy storage equipment and the maximum capacity of the energy storage equipment into the final energy management model to obtain the output data of the micro-grid, the output data of the energy storage equipment and a day-ahead scheduling plan of the micro-grid. By adopting the method, safe and economical operation of the micro-grid can be ensured.

The application provides a multi-optical storage and charging station sharing energy storage capacity optimization method based on multi-source heterogeneous data information fusion, step one: multi-source uncertainty heterogeneous data fusion based on DS evidence fusion theory, obtaining a fusion feature vector and a risk intensity parameter.Step two: the fusion feature vector and the risk intensity parameter are directly used as the input of step two, obtaining a shared energy storage power interval demand and an interval cumulative energy trajectory.Step three: the shared energy storage power interval demand sequence and the interval cumulative energy trajectory are introduced into a shared energy storage capacity optimization model, obtaining a shared energy storage rated power and rated capacity configuration result.The application can first perform credible fusion on multi-source heterogeneous uncertain data, then predict the shared energy storage interval demand based on the fusion result, and further obtain the shared energy storage rated power and rated capacity under the interval demand constraint, thereby improving the adaptability of the configuration result to new energy fluctuation and charging load disturbance.

The present application relates to the technical field of data processing, in particular to a data analysis and processing operation method based on data source format uncertainty, which can realize data acquisition, analysis, storage and use for the data source with uncertain data field format, content and sequence. The present application designs data storage table and data mapping table according to the number, format and type of data field of data source, and completes data collection by analyzing and storing the content and relationship of data field in data source. When using data, the data field format item and unique identifier corresponding to the identification information of input data are searched in the data mapping table according to the identification information, and the target data is obtained by comparing the data field format item and unique identifier in the data storage table to complete data use. The present application solves the technical problem of low data access efficiency, improves the data access efficiency, and can be applied to data analysis and processing, storage and use of data source format variability.

The application discloses a kind of medicine chemical reaction synthesis and conversion rate prediction combined optimization method, comprising: obtaining the SMILES expression of reactant, the SMILES expression of reactant is tokenized, and the tokenization feature of the SMILES expression of reactant is obtained by embedding expression;The tokenization feature of the SMILES expression of reactant is hierarchically sequentially encoded;Chemical reaction synthesis prediction and conversion rate prediction two tasks are combined, and two tasks are trained simultaneously to realize chemical reaction synthesis and conversion rate prediction combined optimization.The application combines chemical reaction synthesis prediction and conversion rate prediction two tasks, introduces hierarchical sequence modeling technology, and the model interpretability parameter optimization of two tasks guides each other, to improve the training efficiency and performance of model.The application introduces uncertainty estimation to cope with the interference brought by model to uncertain data in real situation.

The application provides an abnormal value-containing uncertain data target classification method and system, which comprises the following steps: obtaining abnormal value-containing uncertain data; inputting the uncertain data into an abnormal attribute detection model to obtain a first generation matrix, and obtaining the positions of abnormal attributes in the uncertain data according to the reconstruction errors between each generation value in the first generation matrix and the corresponding attribute value and a set threshold, and generating a mask matrix; replacing the abnormal values in the uncertain data by using the mask matrix and a random noise matrix to obtain replacement data, inputting the replacement data into an abnormal attribute correction model to obtain a second generation matrix; replacing the abnormal values in the uncertain data by using the mask matrix and the second generation matrix to obtain correction data, and inputting the correction data into a target classifier to obtain a target classification result corresponding to the uncertain data. The application realizes the detection and correction of specific abnormal attribute values in the uncertain data, and improves the accuracy of target recognition.

The application belongs to the technical field of network services, and discloses a high-availability big data stream processing request placement method in a serverless edge network. The purpose is to meet the reliability requirements of users while minimizing processing delay. An effective algorithm is designed to find a suitable number of instances for the function of each data stream processing request, and to place the request while minimizing the average delay experienced by each user while meeting its reliability requirements. After the request is placed, the input data rate may change and is uncertain. An online learning algorithm is designed to predict the method to predict the data rate and dynamically adjust the standby instances to absorb the uncertain data rate. Based on the experiment of a real data set, it is shown that the placement problem of big data stream processing in the edge serverless network is effectively solved.

This invention belongs to the field of artificial intelligence technology and discloses a method for integrated management and intelligent rendering of multi-source geological map data. This invention utilizes a multi-hypothesis generation method to proactively generate multiple competing but all reasonable geological interpretation schemes for areas with uncertain data, leveraging generative AI and geological knowledge graphs. Subsequently, through an interactive interpretive rendering mode, when a user queries geological elements in any scheme, the system can dynamically redraw the map, highlighting key evidence, darkening irrelevant backgrounds, and linking knowledge graph rules to visually reveal the AI's decision-making basis. This invention elevates AI mapping from an automated tool to an interactive and interpretable scientific verification partner, improving the scientific rigor and reliability of geological decision-making.

The application discloses a kind of reactance state evaluation methods based on game theory combination weight and improved TOPSIS method, it is related to electrical equipment and mechanical equipment technical field, the subjective and objective weights of each evaluation index are calculated by analytic hierarchy process and entropy weight method respectively, the uncertainty and complexity in the operation data of the reactance of the evaluation method of the application are effectively handled, the cloud model theory is introduced, the correlation between each state index is quantitatively analyzed by expectation, entropy and hyper-entropy parameter, multi-dimensional operation data is converted into the comprehensive description of fuzzy and probability, this processing mode can more comprehensively capture the various characteristics of the operation state of the reactance, even in the case of uncertain data, a reasonable decision matrix can also be constructed, at the same time, the improved TOPSIS method introduces grey correlation degree to redefine relative closeness, further improve the accuracy and reliability of the evaluation result.

The invention discloses a dynamic situation updating and obtaining method based on a multi-modal knowledge graph, and belongs to the technical field of natural language processing, and the method comprises the steps: collecting multi-source and multi-modal data; preprocessing the multi-source and multi-modal data to generate standardized data with a timestamp and a position label; a body is defined, cross-modal feature alignment and semantic mapping are realized, a multi-modal knowledge triple is generated, and a multi-modal knowledge graph is constructed; and in combination with a data increment threshold and a time period, realizing automatic increment updating and timing full-quantity verification of the multi-modal knowledge graph, and based on data credibility weighting and multi-source modal verification, outputting a high-credibility updating result to realize minute-level updating of the situation. According to the method, the problems of weak multi-modal data fusion capability, insufficient dynamic updating efficiency and accuracy and lack of uncertain data processing in the prior art are solved. According to the method, the utilization rate of multi-modal data can be improved, the situation updating delay is reduced, the situation credibility is improved, and the situation interpretability is enhanced.

The application relates to the technical field of data processing distribution, and discloses an Internet of Things data distribution engine algorithm, which comprises the following steps: firstly, original power data collected is cleaned and standardized; then, feature extraction and semantic analysis are carried out; dynamic priority scores representing data real-time urgency and static importance factors representing inherent importance of equipment are generated by calculating a plurality of dynamic feature indexes of the equipment and combining business metadata of the equipment; further, a hierarchical scheduling strategy is adopted, and secondary judgment based on change trend is started on uncertain data, so that accurate routing of data to different priority channels is realized; finally, the system dynamically adjusts distribution thresholds according to actual business utility feedback of data distribution, so that a closed-loop optimization is formed; the application effectively solves the problems of key information submergence, response delay and extensive resource allocation in massive Internet of Things data, and realizes low-delay transmission of high-value data and adaptive optimization of system resources.