45 results about "Statistical algorithm" patented technology

The invention discloses a multi-device collaborative passenger flow statistical method and system, and the method comprises the following steps: presetting a unique identity label and a physical position index for devices, reading the unique identity label and the physical position index, and initializing the attribute information of the devices; a user datagram protocol broadcasting mechanism is started, and heartbeat information including the unique identity label, the physical position index and the online state is sent according to a preset period; monitoring the user datagram protocol broadcast message in the local area network, constructing and maintaining an online equipment list, and updating the online state of the equipment according to the heartbeat information receiving analysis condition; judging adjacent equipment based on a physical location index, and deciding whether to start a first boundary or a second boundary according to the online state of the adjacent equipment; and the decision result is transmitted to a passenger flow statistical algorithm to generate a shop-crossing detection line. According to the invention, multi-device collaborative passenger flow statistics dynamic boundary configuration is realized, the shop-crossing detection line is accurately generated, and the passenger flow statistics problems of fixed boundary configuration, easy missed counting and poor multi-device collaboration are solved.

The invention discloses a pouring planning method and device of a material distributing machine, electronic equipment and a storage medium, and the method comprises the steps: obtaining a BIM model of a pouring site, a material distributing machine model and obstacle information of the pouring site, and obtaining a feasible region of the material distributing machine corresponding to the material distributing machine model in the pouring site according to the BIM model, the material distributing machine model and the obstacle information; according to the pouring attributes of the components contained in the BIM model, the components contained in the pouring site are divided into pouring components and poured components, communication processing is conducted according to the adjacency of the pouring components, and the area where all the pouring components are located is determined as a pouring area; according to the BIM model of the pouring area and the feasible region, based on concrete flow collapse and component connectivity, a collapse statistical algorithm is used for calculation, and a pouring planning result of the material distributing machine is generated; and according to the pouring planning result, a material distributing machine is controlled to move in the pouring site so as to conduct pouring treatment on all the areas in the pouring area. And the pouring safety and the pouring efficiency are improved.

This invention discloses a discrete element method, system, medium, and equipment for simulating equivalent crystalline materials, relating to the field of numerical simulation of rock mechanics. The method includes: converting granite images into binary images using a binarization method to identify various minerals within the binary images; determining the size data of various minerals in the binary images based on a particle size statistical algorithm; extracting micromechanical parameters using nanoindentation experiments combined with a trial-and-error method, and constructing multiple sets of equivalent crystalline models based on the mineral size data; dividing each set of equivalent crystalline models into multiple regions using a Brazilian splitting experiment; determining the optimal magnification for each region of each set of equivalent crystalline models by magnifying from non-critical regions to critical regions using a magnification algorithm, obtaining differentiated equivalent crystalline models; and performing Brazilian splitting numerical simulation using these differentiated equivalent crystalline models to obtain simulation results.

A method for determining a convolution kernel for an iterative statistical algorithm based on a continuous-to-continuous data model. The method is used for image reconstruction from radiation measurements obtained in emission tomography, specifically in a Time-of-Flight Positron Emission Tomography (TOF PET) scanner. The presented method is a non-list-mode solution that reduces the computational complexity of the reconstruction problem, improves the resolution of reconstructed images, reduces the radiation dose absorbed by patients during TOF PET examinations, and / or shortens the measurement acquisition time without significantly compromising the quality of the diagnostic images. Notably, the quality of the functional images remains at the same level. These improvements are achieved by designing the convolution kernel to account for the statistical properties of the measurement signals registered during the TOF PET scanner's acquisition process.

The application relates to a multi-modal data governance method, device and equipment based on multi-agent cooperation. The method comprises the following steps: identifying the variable mode of a variable in to-be-governed data; converting mixed-mode variables into text or numerical-mode variables by using a mixed data agent; performing standardization evaluation, standard term rewriting and material type division on the text-type variable by using a text agent; dividing the numerical-type variable into a continuous type, an unordered discrete type or an ordered discrete type based on variable semantics and value characteristics by using a numerical agent; and performing corresponding statistical algorithm governance operations according to the divided material types. By using the method, semantic-level recognition and conversion of multi-modal data can be realized through multi-agent cooperation, governance strategies can be accurately matched based on fine statistical attribute classification, and the accuracy and automation efficiency of data governance can be significantly improved.

The invention provides a statistical process control method and system based on a large language model. The system comprises the large language model and a statistical process control model. Decoupling the statistical process control model and the large language model on the architecture; the large language model is used for receiving an analysis request input by a user; reasoning the analysis request, and determining an analysis intention and an input parameter of the user; according to the analysis intention, a predefined Schema parameter mode of a target analysis tool and an input parameter, generating a tool calling instruction for the target analysis tool in the statistical process control model; sending the tool calling instruction to a statistical process control model, and receiving returned analysis data determined based on a statistical algorithm library; and analyzing the analysis data, generating an analysis result in a natural language form, and feeding back the analysis result to the user. In this way, the problems that in the prior art, a statistical process control analysis tool is complex in operation process, high in requirement for professional knowledge of a user, low in use efficiency and unreliable in calculation result of a universal AI model can be solved.

The invention discloses a double-granularity drug recommendation method (LLM-CIDGMed) based on large language model driven causal reasoning, which is used for solving the key limitation of the existing drug recommendation system in the aspects of medical knowledge driven causal reasoning, patient perception multi-granularity drug characterization fusion and long sequence time sequence modeling. The method aims at solving the problems that a traditional statistical algorithm lacks deep understanding of medical field knowledge, drug representation learning lacks a multi-granularity information integration mechanism perceived by a patient, and a traditional time sequence modeling method loses long-term historical information of the patient. Experimental results show that the method is remarkably superior to an existing method in the aspects of accuracy, safety and calculation efficiency, and more reliable intelligent support is provided for clinical decision making.

The application provides a multi-dimensional cognitive state vector simulation agent digital textbook dynamic adaptability evaluation method, and relates to the technical field of artificial intelligence assisted education. The method comprises the following steps: extracting teaching entities and semantic relationships between the entities in a source file of a digital textbook to be evaluated through a multi-modal analysis model, and constructing a knowledge graph; initializing multiple groups of virtual learning agents based on a pre-trained large language model, and configuring differentiated cognitive state vectors for each group of virtual learning agents; driving each group of virtual learning agents to traverse the teaching knowledge graph according to a topological sorting by using a knowledge boundary mask mechanism, obtaining understanding feedback of each node by each group of virtual learning agents, and generating confusion degrees and thought chains in the understanding feedback process; calculating a cognitive block index and an adaptability distribution curve of the source file of the digital textbook by using a weighted summation algorithm, and generating an evaluation report. The application simulates human cognitive processes by using a large language model agent, and evaluates the quality and adaptability of a digital textbook.

This invention provides a method, apparatus, device, and storage medium for inferring a single-sample ncRNA regulatory network, relating to the field of gene identification technology. The specific implementation includes: acquiring ncRNA and target gene transcriptome data of a matched sample; for each target sample in the matched sample, calculating a first regulatory relationship strength matrix and a second regulatory relationship strength matrix of ncRNA and target gene before and after removing the target sample using a preset statistical algorithm; obtaining the fusion regulatory relationship strength matrix of ncRNA and target gene corresponding to the target sample based on the first and second regulatory relationship strength matrices; and inferring the single-sample ncRNA regulatory network of the target sample based on the fusion regulatory relationship strength matrix of ncRNA and target gene corresponding to the target sample. This invention can reflect the regulatory relationship strength between ncRNA and target gene at the single-sample level by constructing statistical correlation values, thereby inferring the single-sample ncRNA regulatory network.

The invention relates to the technical field of data processing and anomaly detection, in particular to an anomaly detection method and device, electronic equipment and a storage medium. Statistical characteristics of a historical data sequence are extracted, and a target algorithm is automatically selected from multiple candidate statistical algorithms according to the statistical characteristics; and zero manual intervention and dynamic adaptive selection of the anomaly detection algorithm are realized. The method has the beneficial effects that the optimal algorithm can be automatically matched according to the data distribution characteristics of the indexes, the limitation of manual adjustment participating in a fixed threshold value is thoroughly eliminated, the accuracy, robustness and operation and maintenance efficiency of anomaly detection are remarkably improved, and a universal solution is provided for automatic monitoring of large-scale and multi-type business indexes.

The invention discloses a fault distinguishing method and system for an oil chromatography online monitoring device, and belongs to the technical field of fault detection of the oil chromatography online monitoring device. Full-period data of operation of the oil chromatography online monitoring device is analyzed, and a multi-layer fault classification system is systematically constructed; according to the method, logic progression from a macroscopic system fault to a microcosmic module fault is realized, so that the fault positioning definition is improved, a fault source is conveniently and quickly found, and meanwhile, a robust statistical algorithm is adopted to carry out iterative calculation on working condition data, so that a judgment reference parameter is obtained to carry out quantitative judgment on the fault, and the fault form is quantized; the method gets rid of the dependence on artificial experience, avoids misjudgment, improves the fault judgment efficiency and precision, reduces the labor cost, and meets the intelligent and precise operation and maintenance requirements of a power system.

This invention relates to the field of new energy power generation technology and discloses a multi-model fusion wind speed correction method and apparatus. The method includes: constructing a first wind speed correction model based on radar three-dimensional wind field data, numerical weather prediction data, and measured wind speed data at wind turbine hub height; constructing a second wind speed correction model using statistical algorithms based on wind speed forecast data and wind speed observation data; constructing a third wind speed correction model using data-driven algorithms based on wind speed forecast data, wind speed observation data, and terrain data; acquiring real-time wind condition data; and performing wind speed correction based on the real-time wind condition data using the first, second, and third wind speed correction models to obtain the wind speed correction result. This invention effectively solves the adaptability problem under complex meteorological conditions and improves the accuracy of wind speed correction.

This invention discloses a method, system, equipment, and medium for identifying wind-induced fatigue points in power transmission lines, relating to the field of disaster prevention and mitigation for power transmission lines. The method includes: dividing the continuous pulsating load data of the conductor into multiple wind speed intervals; selecting typical pulsating loads from the continuous pulsating load data in each wind speed interval using a statistical algorithm; applying the typical pulsating loads of each wind speed interval to a constructed finite element model of the conductor insulator; calculating the total cumulative damage rate of the conductor using a dynamic damage integration algorithm; performing a life assessment based on the total cumulative damage rate to obtain the fatigue life of the conductor; and if the fatigue life determines that the conductor belongs to a high-risk line section, then fatigue point identification is performed on the conductor. This method not only improves the efficiency of detection and the accuracy of fatigue life calculation, reducing the workload of manual inspections, but also promptly detects potential fatigue damage, thus providing strong protection for the safe operation of power lines.

This application relates to the field of maintenance data processing technology, providing a maintenance data processing method, system, medium, and product. The method includes: acquiring raw maintenance data of a train through a data acquisition module; standardizing the raw maintenance data through a preprocessing module to obtain standardized maintenance data; statistically analyzing the standardized maintenance data using a preset statistical algorithm through an analysis module to obtain statistical results under at least one statistical indicator; predicting the standardized maintenance data using a preset prediction model through an analysis module to obtain prediction results under at least one prediction indicator; and displaying the statistical results and prediction results through a display module. Based on this application, the utilization rate of maintenance data can be improved, and effective maintenance guidance information can be provided.

The invention discloses an expert classification and grading method based on artificial intelligence driving and related equipment, and can be applied to the technical field of artificial intelligence. According to the method, after the first expert classification system is expanded based on the dynamic field expansion rule to obtain the target classification system, feature extraction is performed on the unstructured text data of the to-be-classified and graded experts based on the preset weighted statistical algorithm to obtain the weighted feature vectors; and then calculating the cosine similarity between the weighted feature vector and all domain vectors in the target classification system, and determining a target classification result corresponding to the to-be-classified and graded expert in the target classification system according to the cosine similarity, thereby effectively improving the expert classification accuracy. Meanwhile, according to the unstructured text data, after the multi-dimensional comprehensive score corresponding to the expert to be classified and graded is calculated through the multi-dimensional comprehensive evaluation system, the expert grading result corresponding to the expert to be classified and graded is analyzed according to the multi-dimensional comprehensive score, and therefore the expert grading accuracy can be effectively improved.

This invention provides a method and apparatus for rapidly generating standard resistance curves for resistance spot welding, relating to the field of resistance spot welding of steel plates. The method includes the following steps: acquiring a set of resistance data during the resistance spot welding process; constructing an original set of resistance curves based on the resistance data set; filtering the original set of resistance curves for effective resistance curves to obtain a set of effective resistance curves; calculating and filtering the effective resistance curves in the set of effective resistance curves to obtain a first candidate set of resistance curves; calculating and filtering the effective resistance curves in the first candidate set of resistance curves for Pearson coefficients to obtain a second candidate set of resistance curves; and constructing standard resistance curves based on the effective resistance curves in the second candidate set of resistance curves using a median statistical algorithm.

The invention discloses a power transmission line alarm prediction method based on remote sensing image interpretation and power business, and the method comprises the steps: firstly carrying out the unsupervised classification of all types of ground features in a remote sensing image through a remote sensing image interpretation algorithm in combination with sample information, extracting edge information, and standardizing the edge information into a JSON file; combining tower coordinate information in a power transmission service ledger by using a drop point statistical algorithm, and resolving an actual distance between the classified ground feature and the tower; and finally, in combination with scene perception data and a distance early warning guide rule, judging a ground feature threat level and generating early warning push. According to remote sensing image classification, a K-means algorithm optimized by an elbow algorithm is adopted, the distance measurement precision is improved through precise coordinate calculation and drop point matching, and integration with a monitoring platform is supported to achieve multi-scene thematic early warning. According to the invention, the limitation of traditional manual inspection is broken through, the large-range, dynamic and non-contact intelligent monitoring of the power transmission line and channel environment is realized, and the threat identification accuracy and the emergency response efficiency are remarkably improved.

A system and method for filesystem data compression using codebooks, that measures in real-time the probability distribution of an encoded data stream, compares the probability distribution to a reference probability distribution, and uses one or more statistical algorithms to determine the divergence between the two sets of probability distributions to determine if an unusual distribution is the result of a data intrusion. The system comprises both encoding and decoding machines, an intrusion detection module, a codebook training module, and various databases which perform various analyses on encoded data streams. Further, the system comprises a system for integrating the compression into a filesystem for both system-wide compression on a per-file or filegroup basis, and intrusion or alteration detection of files.

The invention belongs to the technical field of batteries, and particularly relates to a method for evaluating a battery alarm function, which comprises the following steps of: acquiring operation data and a corresponding actual alarm signal when a battery state is abnormal from a cloud end, and generating a corresponding expected alarm signal according to the operation data and a claimed threshold provided by a manufacturer. Four states of correct alarm, false alarm, missing alarm and no alarm are identified according to the difference between the actual alarm signal and the expected alarm signal, so that the false alarm times and the missing alarm times are identified and counted by using a sliding window statistical algorithm. Furthermore, the false alarm rate is calculated according to the false alarm times and the actual alarm times, and the missing alarm rate is calculated according to the missing alarm times and the expected alarm times. And finally, judging whether the corresponding alarm function meets the standard of the supervision platform according to the missing report rate and the false report rate. According to the invention, the relative state of the claimed threshold and the implicit threshold of the battery alarm function can be evaluated according to the actual operation data of the battery so as to verify whether the alarm function is safe and reliable.

An autism identification system and method with combined coarse and fine granularity is disclosed.SOLUTION: A coarse-grained feature extraction module, configured to perform statistics on a plurality of images in each slice based on a preset statistical algorithm, and calculate a coarse-grained feature of each slice based on a statistical result; a fine-grained feature extraction module, configured to select the slice to be input into one of a plurality of different fine-grained feature extraction models based on the coarse-grained feature of the slice, to obtain a fine-grained feature of each slice; and a feature fusion and recognition module, configured to perform feature fusion on the coarse-grained feature and the fine-grained feature of the slice to obtain a fused feature, and perform autism recognition based on the fused feature. The present invention can comprehensively describe the facial behavior of autism, and effectively improve the reliability of autism recognition.SELECTED DRAWING: Figure 1

The invention discloses a transaction risk detection method and device and a program product, and relates to the field of artificial intelligence, and the method comprises the steps: collecting commercial tenant information and transaction flow information of a target commercial tenant, and collecting external channel information from a preset channel, and obtaining a commercial tenant information set; performing data cleaning on information in the merchant information set based on the data type or the data meaning, and performing correction processing on abnormal information in the cleaned merchant information set to obtain processed information; performing feature extraction on the processed information based on multiple dimensions, and fusing the extracted features according to a target weight to obtain a fused feature vector; and inputting the fusion feature vector into a target detection model to obtain a detection result output by the target detection model. Through the method and the device, the problem that the detection accuracy is relatively low due to the fact that the transaction behavior characteristics of the commercial tenant with the financial risk are difficult to capture when the financial risk of the commercial tenant is detected based on a business rule or a statistical algorithm in the related technology is solved.

The invention relates to the technical field of business ticket cashing management and control, and discloses a risk management and control method for a business ticket cashing platform, and the method comprises the steps: fusing an enterprise identification code and a hierarchical code to form a composite identification, and building a group hierarchical identification system; performing hierarchical storage on the enterprise data according to hierarchical codes based on a distributed database; establishing a hierarchical index tree for the stored data according to hierarchical codes; performing statistics on change data of each hierarchy through a hierarchy increment statistical algorithm, and automatically generating a hierarchy summary result in combination with historical baseline data of each hierarchy; different permission levels are given to the users according to the level codes, and the high-level users can call the data of the low-level users. According to the scheme, the business ticket cashing risk management and control efficiency is improved, the user operation complexity is reduced, and the use experience is optimized.

A system and method for filesystem data compression using codebooks, that measures in real-time the probability distribution of an encoded data stream, compares the probability distribution to a reference probability distribution, and uses one or more statistical algorithms to determine the divergence between the two sets of probability distributions to determine if an unusual distribution is the result of a data intrusion. The system comprises both encoding and decoding machines, an intrusion detection module, a codebook training module, and various databases which perform various analyses on encoded data streams. Further, the system comprises a system for integrating the compression into a filesystem for both system- wide compression on a per-file or filegroup basis, and intrusion or alteration detection of files.

A method for determining a convolution kernel for an iterative statistical algorithm based on a continuous-to-continuous data model for image reconstruction from radiation measurements obtained in emission tomography, specifically in a Positron Emission Tomography (PET) scanner. The method improves the resolution of reconstructed images, reduces the radiation dose absorbed by patients during PET examinations, and / or shortens the measurement acquisition time without significant loss in the quality of the diagnostic images obtained. Specifically, the quality of the functional images remains at the same level. These improvements are achieved through the design of the convolution kernel, which takes into account the statistical properties of the measurement signals registered during the acquisition process in the PET scanner.

The invention relates to the technical field of ultrasonic measurement, and particularly provides an ultrasonic meter zero drift online calibration method, an ultrasonic water meter and a medium, and the method comprises the following steps: initializing parameters and single still water statistics; collecting downstream and countercurrent flight time of the meter, calculating a downstream and countercurrent time difference, and updating a time difference average value, a variance accumulated value and a time difference sample number through an iterative statistical algorithm; judging whether the variance and the time difference average value are effective; performing difference verification on the current time difference average value and the historical time difference average value, and updating the historical time difference average value if a continuous difference threshold is met; when the average value calculation times reach the maximum average value calculation times, the still water times are accumulated, and the average value calculation times are reset; and when the number of times of still water reaches the maximum number of times of still water, updating the null drift by updating the historical time difference average value, and completing online updating of the ultrasonic meter. According to the method, still water and small-flow water flowing can be distinguished, misjudgment caused by small leakage is eliminated, and the robustness of null drift calculation is enhanced.

The application discloses a signal state segmentation method based on distribution difference. When a human body is at different distances from a transceiving link, the signal distribution of CSI data has obvious difference, and the segmentation of the signal state can be realized by using the distribution difference. Firstly, the number of human body motion segments is acquired, that is, the data of non-fading states is removed, and the number of motion segments including reflection state segments and shadow state segments is obtained; then, the starting time point and the ending time point of each motion segment are found, so that the segmentation of each motion segment is realized; finally, the method based on the distribution difference is used to find the starting time point and the ending time point of the shadow state segment in each motion segment, so that the segmentation of the reflection state segment and the shadow state segment in each motion segment is realized. The application can accurately extract the effective data related to human body motion in the monitoring time, so that the problems of large data volume and large calculation cost in the traditional population counting algorithm are greatly solved.

The application provides a network service guarantee method, device and equipment, the method comprises the following steps: predicting target users needing network service guarantee through a scoring model based on historical service data and subscription package levels of users; collecting network index historical data of the target users, and obtaining a guarantee priority evaluation value by processing and weighting different categories of network indexes through corresponding statistical algorithms according to the network index historical data; determining a service guarantee order according to the guarantee priority evaluation value of the target users; establishing an elastic GBR resource pool, which is configured to share resources when idle and exclusively provide the GBR resources to the target users according to the service guarantee order when congested.

The application relates to the technical field of ultrasonic metering, and particularly provides an ultrasonic meter zero drift online calibration method, an ultrasonic water meter and a medium. The method comprises the following steps: initializing parameters and single-time static water statistics; collecting meter forward flow and reverse flow time of flight, calculating a reverse-to-forward flow time difference, updating a time difference average value, a variance cumulative value and a time difference sample number through an iterative statistical algorithm; judging whether the variance and the time difference average value are effective; carrying out difference check on the current time difference average value and a historical time difference average value, updating the historical time difference average value when a continuous difference threshold is met; when the average value calculation frequency reaches a maximum average value calculation frequency, accumulating a static water frequency and resetting the average value calculation frequency; when the static water frequency reaches a maximum static water frequency, updating the zero drift by updating the historical time difference average value, and completing online updating of the ultrasonic meter. The application can distinguish static water and small flow water, eliminate misjudgment caused by slight leakage, and enhance the robustness of zero drift calculation.

The application discloses a signal peak value detection method and system based on an adaptive prominence threshold, relates to the technical field of electric digital data processing, and comprises the following steps: smoothing preprocessed data of spectrum data to obtain smooth curve data; performing bottom noise shaping on the smooth curve data based on the preprocessed data to obtain a bottom noise shaping result; performing multi-scale peak value detection on the bottom noise shaping result based on an AMPD algorithm; for each peak value candidate point, calculating the prominence of the peak value candidate point relative to the bottom noise shaping result based on a watershed algorithm to obtain a prominence value list corresponding to all peak value candidate points; calculating an adaptive prominence threshold based on an IQR statistical algorithm according to the prominence value list; and screening the peak value candidate set based on the adaptive prominence threshold to retain peak values with a prominence not less than the adaptive prominence threshold. The application can realize full-adaptive processing, has strong noise resistance, high accuracy, good robustness, high calculation efficiency and low algorithm complexity.

This invention discloses a method, device, and electronic equipment for on-site temporary power management in highway service areas, relating to the field of construction equipment management. The method includes: acquiring data to be processed, identifying and repairing the data to be processed, and obtaining repaired data to be processed; including: using statistical algorithms to identify abnormal voltage data in voltage data and abnormal current data in current data, and using a mean-filling algorithm to repair the abnormal voltage and current data; using a before-and-after data comparison method to identify abnormal cumulative electricity consumption data, using a before-and-after value filling algorithm to repair a single abnormal cumulative electricity consumption data, and using a linear interpolation algorithm to repair multiple consecutive abnormal cumulative electricity consumption data; and performing alarm monitoring and / or three-dimensional visualization based on the repaired data to be processed. This invention can perform differentiated processing on data generated from different root causes, ensuring high-quality and high-reliability data.