24results about How to "Choose accurately" patented technology

The invention discloses a multi-modal ultrasonic image recognition method and device, which effectively combines an ultrasonic image and a corresponding task text, and improves the recognition precision of the ultrasonic image by utilizing the interaction of visual information and language information. By preprocessing the ultrasonic image and the task text and generating a visual Token sequence and a language Token sequence, data of different modalities can be effectively fused to generate a multi-modal sequence. The sequences are subjected to context interactive fusion of a multi-head attention model to obtain a multi-modal embedded representation containing visual and language information, so that the model can accurately analyze a task instruction while understanding the image content, and the recognition accuracy is improved. And furthermore, through selection and weighted fusion of dynamic experts and in combination with background knowledge provided by static experts, the processing capability of the model is improved. And finally, the output result is adjusted and optimized by using the fusion control parameters, so that the efficiency and the accuracy of ultrasonic image recognition are improved.

The invention discloses an ultra-wideband weak signal detection method and system based on all-optical oscillation and phase-amplitude conversion. The method comprises the steps that spontaneous radiation light generated by an erbium-doped optical fiber amplifier is used as an optical carrier; modulating a weak radio frequency signal to be measured received by an antenna to the optical carrier through an optical modulator to form a modulated optical signal; the modulated optical signal is injected into an all-optical oscillation circuit composed of double loops, the all-optical oscillation circuit generates multimode optical oscillation by adjusting an optical attenuator, and the all-optical oscillation circuit comprises a double-loop interference structure; performing phase-amplitude conversion by adjusting the delay difference of the two light paths in the double loops to form an equivalent microwave photon filter so as to select and amplify the modulated light signal corresponding to the radio frequency signal of the set frequency band; and converting the selected and amplified modulated optical signal into an electric signal, and performing spectral analysis to detect the weak radio frequency signal to be detected.

The application provides a national encryption and international algorithm compatible method for eUICC card and eIM platform public key interaction and an eUICC card, relates to the technical field of Internet of Things communication, and comprises the following steps: configuring configuration data information corresponding to multiple eIM platforms in the eUICC card, wherein the configuration data information contains the platform unique identification and service public key data of each eIM platform, the service public key data contains service information verification public key and an added algorithm type field, and the algorithm type field is used for uniquely identifying national encryption algorithms or international algorithms; in a business interaction process, the eUICC card matches corresponding configuration data information through the platform unique identification in a service data packet message sent by a target eIM platform, and then performs signature verification on the service data packet information based on the national encryption algorithms or international algorithms selected through the algorithm type field and the service information verification public key, so as to realize the security verification of the business interaction with the target eIM platform. The beneficial effect is that the accurate compatibility of national encryption and international algorithms in the public key mode is realized.

The application provides a rotating machinery impact fault feature extraction method, device and storage medium, and belongs to the technical field of equipment fault diagnosis. The method comprises the following steps: acquiring an impact response vibration signal; calculating the envelope spectrum kurtosis of each sub-band signal, wherein the sub-band signal is a sub-band signal at different levels decomposed from the impact response vibration signal; marking the non-cyclostationary frequency band according to the envelope spectrum kurtosis; calculating the square envelope autocorrelation kurtosis of the unmarked sub-band signal; determining the frequency band of the sub-band signal corresponding to the maximum square envelope autocorrelation kurtosis as the optimal demodulation frequency band; and performing envelope demodulation on the impact response vibration signal in the optimal demodulation frequency band to obtain the impact fault feature of the rotating machinery. The method disclosed in the application sequentially evaluates the impact characteristics and cyclostationarity characteristics of the impact response vibration signal, selects the optimal fault frequency band, and realizes accurate extraction of the impact fault feature.

This invention provides an air conditioning load forecasting method based on eigenvalue selection, belonging to the fields of machine learning and building energy conservation technology. This eigenvalue-based air conditioning load forecasting method selects eigenvalues ​​through the coordinated integration of mathematical mutual information and physical redundancy, and evaluates the selected eigenvalues ​​using a posterior method of the prediction model, accurately determining the optimal input eigenvalues ​​for the model. This eigenvalue-based air conditioning load forecasting method can quantitatively capture the dynamic characteristics affecting real-time air conditioning load values, ensuring high prediction accuracy. It can improve the accuracy of the air conditioning load forecasting model by 5.62% in the correlation coefficient and reduce the average error by approximately 16%–22%, while essentially without increasing computational costs, demonstrating significant practical application value.

There are provided a linker compound, for which a glutathione concentration at which a disulfide bond dissociates can be designed by molecular design, and which can accurately identify a cancer cell, is stable outside a target cell, and can effectively release a drug compound in the target cell, and a complex compound containing the same. The linker compound is used for a complex compound containing a drug compound and has a structure represented by the following Formula (1). (In Formula (1), R is a compound containing hydrogen, carbon, oxygen, or a halogen element, or a derivative thereof.

The application discloses a multi-link intelligent switching method, which comprises the following steps: starting link state monitoring through a server, periodically starting an adaptive learning mechanism after being online on a wireless link; periodically sending a probe message through each wireless link, and a client replying a response message carrying a request serial number, a client unique identifier and corresponding link index information; introducing a multi-dimensional weighted scoring mechanism to calculate the comprehensive scores of each link and sort them based on the information reported by the client and comprehensive scoring weights; selecting the link with the highest score as a primary link; when the comprehensive score of a standby link is higher than that of the current primary link, or when the primary link is not responded within a timeout period, triggering link switching to the standby link with the highest score, sending a switching instruction through a link notification mechanism, and executing switching by the client and feeding back a confirmation; after learning, adjusting the comprehensive scoring weights according to the adaptive learning result, and updating the adjusted comprehensive scoring weights to the link scoring calculation.

The invention discloses an optimized query method based on multi-table statistical information cardinality estimation. The method comprises the following steps: constructing a star structure in an offline stage, and converting historical multi-table connection query into virtual key connection between nodes in the star structure; calculating and counting a structure cardinal number and a degree sequence in the star-shaped structure through a merged degree sequence, and compressing and outputting a finally obtained degree sequence through a streaming degree sequence; at the present stage, according to the connection condition of the multi-table connection query input in real time, the multi-table connection query is decomposed into a plurality of star structure instances, and after the degree sequence obtained in each corresponding offline stage is queried, the final cardinality upper bound estimation value of the whole query is obtained through middle structure merging iteration. According to the method, on the premise that the upper bound is estimated, the precision and efficiency of multi-table connection cardinal number estimation are remarkably improved, and the method is suitable for a query optimization scene of a relational database.

This application provides a method, apparatus, electronic device, computer program product, and computer-readable storage medium for collaborative control of a supply chain. The method includes: parsing heterogeneous data packets using a preset semantic communication protocol to obtain scheduling requests, constraint parameters, and real-time status of physical resources from business nodes; determining resource status anomaly events caused by the real-time status in the future based on a dynamic knowledge graph of the supply chain in the time dimension; performing conflict detection on the scheduling requests based on multiple constraint parameters and resource status anomaly events to obtain conflict detection results; determining the optimal action from a set of candidate actions when the conflict detection results indicate a conflict; generating an execution instruction based on the optimal action and the preset semantic communication protocol, and sending the execution instruction to the business node. This application can improve the accuracy of collaborative control of the supply chain.

The invention discloses an edible fungus strain low-temperature preservation and rapid recovery device, and relates to the technical field of strain recovery, the edible fungus strain low-temperature preservation and rapid recovery device comprises a box body, a preservation cavity, a recovery cavity, a selection cavity and a bottom cavity are arranged in the box body, the box body is located on the upper side of the bottom cavity, the preservation cavity is located in the middle of the box body, a plurality of bin positions are arranged in the preservation cavity, and a selection device is arranged in the selection cavity; a sealing device is arranged in the storage cavity, a feeding port and a discharging port are formed in one side of the box body, the selecting device comprises a selecting mechanism and a pushing mechanism, the selecting mechanism penetrates through one side of the box body and one side of the selecting cavity, the selecting mechanism is located on one side of the pushing mechanism, and the selecting device can select a culture bin at a proper bin position outside the device. According to the low-temperature preservation device, the low-temperature preservation environment of all the bin positions can be effectively maintained, temperature fluctuation caused by frequent opening and closing of the bin doors is avoided, and the stability and survival rate of strain preservation are improved.

The application discloses a mechanical hand warehousing intelligent unstacking control system and device based on machine vision and relates to the technical field of image data processing.The mechanical hand warehousing intelligent unstacking control system based on machine vision comprises the following modules: a mechanical hand warehousing clamping monitoring module, a mechanical hand clamping effect quantification module and a mechanical hand clamping force control module.The application monitors the influence of the mechanical hand warehousing on point cloud data when the mechanical hand warehousing intelligently unstacks a specified soft packaging box stack, selects whether to take a soft packaging influence compensation measure, then quantifies the clamping effect of the mechanical hand clamping the specified soft packaging box stack to determine whether to perform clamping point correction adjustment, and finally performs qualification judgment on the successful rate of clamping to determine whether to take a clamping force control adjustment strategy, thereby improving the accuracy of the mechanical hand unstacking control, and solving the problem that the existing technology has low mechanical hand unstacking control accuracy due to the interference of soft packaging boxes on machine vision scanning results.

The invention provides a multi-modal data security sharing method and system, and relates to the technical field of computer science, and the method comprises the steps: obtaining a traditional database; constructing a database agent according to a traditional database; the method comprises the following steps: constructing a multi-modal metadata semantic space through a database agent; the method comprises the following steps: screening out participants of an adaptive task through a multi-modal metadata semantic space; performing cross-modal retrieval on the participants through an AI ready-oriented multi-modal analysis query language query method to obtain a retrieval result; locally constructing a neural network model at a participant through an adaptive machine learning modeling mechanism; according to the domain knowledge base and the knowledge graph, updating hyper-parameters and retrieval results of the neural network model; performing credible convergence on the updated neural network model through a credible execution environment module; and based on a credible convergence result, sharing the multi-modal data to each participant through a database agent.

The present application relates to the technical field of data processing, and especially to a multi-dimensional reconciliation method and system based on a group meal platform, which comprises the following steps: determining the state of a sub-node according to a steady-state metric value and a correlation index, and determining a reference data selection method according to the state of the sub-node; in the single-node direct selection, the sub-node corresponding to the maximum comprehensive evaluation value is selected as the reference data; in the multi-node compensation selection, a compensation method is determined according to a steady-state mutual correlation degree and a steady-state balance coefficient to select the reference data; and a reconciliation sub-node selection method is determined according to a reference comparison coefficient and a cross-correlation coefficient of the sub-node corresponding to the to-be-reconciled data and the reference data; and the present application can improve the reconciliation processing efficiency.

The invention discloses a heat dissipation assembly type selection method and system based on three-dimensional simulation and PINN collaborative optimization. The problems that an existing radiator model selection method needs a large amount of calculation resources and time and is low in precision are solved. The method comprises the following steps: constructing a heat dissipation system three-dimensional model comprising a heat dissipation assembly, and simulating the three-dimensional model according to different working conditions of the heat dissipation assembly; acquiring working conditions and simulation output data to establish sample data; constructing a physical information neural network model, and training to obtain a heat dissipation performance prediction model; inputting the working condition data of the to-be-tested heat dissipation assembly into the heat dissipation performance prediction model to obtain heat dissipation performance prediction data; and the optimal heat dissipation assembly is selected by integrating the heat dissipation performance, the cost and the space limiting factors. According to the method, three-dimensional simulation and physical information neural network training are combined for application, and the radiator assembly meeting the heat dissipation requirement can be accurately and efficiently selected.

The application discloses a high-cold power networking scene intelligent fusion terminal data processing method and system, comprising: collecting multi-source networking state data and performing preprocessing to generate a networking communication flow state set; extracting link dynamic characteristics according to terminal numbers and link numbers, constructing a low-temperature communication recession image and generating a sample sequence; performing token division on the sample sequence and injecting low-temperature index information, inputting an improved FlowFormer network to output a prediction result; predicting bandwidth temperature based on the pre-degradation result and the forwarding score, generating an elastic flow queue; when a link is abnormal, sending data fragments in window order and selecting a cooperative node, performing relay transmission and recording a relay path; after link recovery, performing data consistency reconstruction processing operation, generating complete networking data flow and updating model parameters. The application realizes reliable transmission and adaptive scheduling of high-cold networking data through low-temperature recession modeling and improved FlowFormer prediction.

The invention provides an RU information acquisition method and a container scheduling method and device based on RU information. The RU information acquisition method comprises the steps that first equipment acquires information of RU equipment managed by schedulable nodes in a network cluster; and the first device sends the information of the RU device to a second device, so as to determine a target scheduling node in the schedulable nodes. Therefore, the capability of the existing second equipment is enhanced, the collection of the RU information is supplemented, and the node selection is performed on the to-be-scheduled container based on the collected RU information of the schedulable node, so that the condition that the to-be-scheduled container, especially the to-be-scheduled container of a high-real-time task, is scheduled to the node which does not meet the RU requirement of the to-be-scheduled container is avoided, and the scheduling efficiency of the to-be-scheduled container is improved. Compared with the prior art, the method can be better applied to container scheduling in a high-real-time RU demand scene, not only can proper nodes be more accurately selected for container scheduling, but also the overall reliability of the network, the user experience and the resource utilization efficiency can be improved.

This invention discloses biomarkers for oral angina pectoris (OAB) caused by vitamin D deficiency and their applications. Specifically, it is the first time that human myelin basic protein and human trans-2,3-enoyl-CoA reductase-like protein have been used as biomarkers for OAB in children, especially OAB caused by vitamin D deficiency. This has significant guiding significance for the clinical prognosis of OAB, particularly in children, and can better guide clinical treatment and prognosis assessment. The biomarkers of this invention can be obtained solely through urine collection, are non-invasive, inexpensive, and provide rapid and convenient diagnosis, improving work efficiency and facilitating the diagnosis and treatment of OAB in children. They have good clinical diagnostic potential and widespread application value.

An authentication system (1) is provided with: a first imaging apparatus (3) that obtains a first image (300) used for an authentication by capturing an image of a first imaging range; a second imaging apparatus (3) that obtains a second image (200) by capturing an image of a second imaging range that is wider than the first imaging range; and a control apparatus (6) that selects a target person (Ta) for the authentication on the basis of a target area (TA) in the second image that includes a predetermined portion (TP) of a person (T) and a reference area (RA) in the second image that corresponds to the first imaging range.

The application discloses a kind of complex fine-grained sedimentary rock reservoir evaluation method, which comprises the following steps: step 1: the reservoir to be studied as target reservoir;Step 2: target reservoir is stratified according to lithology category and thickness;Step 3: gas-bearing property in target reservoir is analyzed, and favorable stratigraphic system is preliminarily selected according to gas-bearing property characteristics;Step 4: favorable stratigraphic system, carry out stratigraphic system development scale characterization, stratigraphic system reservoir property characterization, organic matter abundance characterization and gas-bearing property characterization analysis, according to reservoir evaluation parameter and the weight corresponding to each parameter and determine the gas-bearing property evaluation index REI value of the stratigraphic system type;Step 5: according to the type of target reservoir, establish the evaluation system of complex fine-grained sedimentary rock reservoir.The application considers the heterogeneity of fine-grained sedimentary rock reservoir internal structure, and proposes a reasonable reservoir property evaluation parameter calculation method.

The invention provides an energy consumption prediction method and related equipment. The method comprises the following steps: acquiring a path; energy consumption change information of the thermal management system in the path is determined, and the energy consumption change information is used for representing information that energy consumption changes along with time; and predicting the energy consumption of the thermal management system based on the energy consumption change information of the thermal management system in the path. The method provided by the invention helps to improve the accuracy of energy consumption prediction of the thermal management system in the vehicle.

This invention provides a multidimensional collaborative enhanced graph clustering method. It extracts preliminary node embedding representations from each view in multi-view attribute graph data, employs three-level collaborative contrastive learning (3C-CL), calculates contrastive losses at three granular levels (node, group, and global), and obtains a unified embedding representation that integrates multi-view features. Gradient norms are used to dynamically adjust the loss weights of the contrastive losses at each level, and a clustering loss optimization network based on the Student's t-distribution is jointly used to output the final graph clustering assignment result. In sparsely connected views, the receptive field is automatically expanded to capture higher-order neighbor information, while in densely connected views, the aggregation depth is limited to avoid excessive information smoothing. This complementary system of structural information from micro to macro levels significantly improves cross-view semantic consistency, identifies difficult samples with similar attributes to the target node but different potential categories, and achieves more accurate sample selection.

The invention discloses an automatic marking method and system for a focus in a medical image, and relates to the technical field of medical equipment, and the method comprises the following steps: collecting and preprocessing medical images of different modal types, and manually marking a focus region to obtain a marked medical image; calculating feature parameters of the grayed labeled medical image to obtain a classification intensity coefficient, thereby dividing initial training data and dynamic training data, constructing a focus recognition sub-model for each modal type, training by using the initial training data, performing forward propagation reasoning, reading a focus prediction probability value, and performing prediction on the focus. And calculating the pixel prediction offset degree based on the prediction probability value, adjusting the learning rate, inputting the dynamic training data into the sub-model, and carrying out iterative execution until the offset degree is lower than a preset threshold value, thereby finally realizing automatic focus marking of the to-be-marked medical image, providing a more accurate marking result, and enhancing the recognition precision of a fuzzy focus.

The utility model provides a kind of positioning device of mould, belong to mould manufacturing technical field, the positioning device of this mould includes positioning seat body, positioning column, adjusting mechanism, locking mechanism and guiding mechanism;Positioning seat body is hollow cylinder, bottom is equipped with bottom surface, and circular through-hole is opened in the center of bottom surface;Stepped positioning column is composed of lower section cylinder and the upper section cylinder of greater diameter;Adjusting mechanism contains adjusting seat and adjusting screw rod, adjusting seat is fixed in seat body side wall, adjusting screw rod passes through adjusting seat and extends into seat body interior, and its end abuts on the side wall of upper section cylinder to adjust height;Locking mechanism is composed of locking bolt and locking block, locking block is placed in seat body, locking bolt is connected with locking block by thread in radial through seat body side wall, and locking block inner arc surface and upper section cylinder outer wall are pasted to realize lock solid;Guiding mechanism contains guide sleeve and guide rod, guide sleeve is fixed in seat body top end, guide rod passes through guide sleeve and is fixedly connected with the top end of upper section cylinder, and it is ensured that column lifting direction is accurate and unbiased.

The application discloses a complex blade type cutter machining process chatter prediction method based on digital twinning, which comprises the following steps: S1, based on the digital twinning model, the milling process of the complex blade type cutter is simulated, and the meshing area CWE of the cutter and the workpiece in the machining process is obtained; S2, the cutter rotation period and the cutting blade participating in cutting are discretized, the meshing information of the cutter and the workpiece in the machining process is extracted, the material properties and the dynamic characteristics of the cutter are combined, and the chatter stability lobe diagram of the complex blade type cutter under a given working condition is calculated and obtained; S3, the stability lobe diagrams of different blade type cutters are compared, and the optimal blade type cutter under the given working condition is selected. The complex blade type cutter machining process chatter prediction method based on digital twinning disclosed by the application is based on the digital twinning model, the cutter rotation period and the blade are discretized, the material and the cutter characteristics are combined for calculation and analysis, and the stability lobe diagram is drawn.