58 results about "Abnormal cell" patented technology

The invention provides a self-maintenance system based on single storage battery operation state difference monitoring, which comprises a distributed monitoring module array, each monitoring unit comprises a multi-parameter fusion sensor group, and the distributed monitoring module array is used for acquiring the voltage fluctuation frequency spectrum, temperature gradient distribution, internal resistance change track and electrolyte ion migration rate of a single battery in real time; and the dynamic difference evaluation module is used for processing the multi-dimensional time sequence data by adopting a time sequence convolutional neural network and calculating the operating state difference degree among the monomers. Through the distributed monitoring module array and the multi-parameter fusion sensor group, multi-dimensional data such as the voltage, the temperature, the internal resistance and the electrolyte ion migration rate of the single batteries are collected in real time, and the operation state difference between the single batteries can be accurately quantified in combination with the time sequence convolutional neural network and the dynamic difference evaluation algorithm. Abnormal monomers are effectively identified, and a reliable basis is provided for a subsequent maintenance strategy.

The invention discloses an abnormal battery cell identification method, computer equipment and a computer readable storage medium, and belongs to the technical field of power batteries, the identification method comprises the following steps: obtaining voltage data of a plurality of battery cells, and calculating a voltage drop of each battery cell under a standing condition based on the voltage data; for each battery cell, polymerizing the voltage drops under the plurality of standing working conditions in a first preset time period to obtain a polymerization result; and identifying an abnormal battery cell from the plurality of battery cells based on the aggregation result of each battery cell. The abnormal battery cell data is identified by using the outlier degree of the voltage drop of the battery cells in the battery pack under the standing working condition, the data validity is good, the identification result accuracy is high, and the use safety of the battery pack is ensured.

The invention provides a method and device for directly carrying out HPV prediction by utilizing a cervical cell pathology image, electronic equipment, a storage medium and a program, and relates to the technical field of medical image processing, and the method comprises the following steps: S10, data acquisition: obtaining a same-period cervical cell pathology full-slide image of a detected person which has been subjected to cervical tissue pathology analysis and a conclusion of which is evaluated as ASCUS; and S20, lesion area positioning: determining an abnormal cell area in the cervical cell pathological full-slide image by using the trained target detection model. Compared with the prior art, the method has the following beneficial effects: firstly, suspicious cells are screened out through a target detection method, and an existing method in a tissue pathology all-slide image is migrated into a cell pathology image; secondly, due to application of unsupervised learning and an attention mechanism, the model can automatically learn and emphasize the most important features for HPV detection in the image; and thirdly, the HPV infection state of the ASCUS patient is directly and accurately predicted from the cervical image.

The invention discloses a multi-scale feature fusion cervical abnormal cell detection method, and relates to the technical field of medical image processing and deep learning. Firstly, a cervical lesion cell detection method based on multi-scale feature fusion is used, efficient capture of multi-scale features from local details to an overall structure in a cervical lesion cell image is achieved by providing a CSPM, the CSPM can dynamically extract the features among different scales, context information is fully utilized, and the detection accuracy of the cervical lesion cells is improved. The method comprises the following steps of: firstly, designing a multi-scale fusion attention module, so that the defect of single-scale characteristics in expression capability is overcome, the problems of large cell size change and complex background are effectively solved, secondly, the designed multi-scale fusion attention module further enhances the characteristic fusion capability, and the MSFA can adaptively adjust the weights of different-scale characteristics according to the importance of the cell characteristics, so that the fusion accuracy is improved. And local and global information is fully fused, so that the capability of sensing and identifying the abnormal cervical cells by the network is improved.

The invention provides a monomer sampling abnormity processing method. The monomer sampling abnormity processing method comprises the following steps: sampling voltage values of monomer cells in a battery pack; judging whether the voltage values of two adjacent single battery cells in the battery pack conform to abnormal characteristics or not; when the voltage values of the two adjacent single cells conform to the abnormal characteristics, judging the type of the battery pack in the sampling abnormal state according to the voltage values of the two adjacent single cells conforming to the abnormal characteristics; according to the judgment result, sampling abnormity processing is conducted on the voltage values of the two adjacent single battery cells meeting the abnormal characteristics, the driving experience of a terminal user is ensured, the performance continuity, stability and reliability of a battery pack are enhanced, a processing mechanism under the single sampling abnormity condition is optimized, and safety and performance are improved.

The invention relates to the technical field of battery detection, in particular to a lithium battery self-discharge detection method, system and equipment. According to the detection method, firstly, feature extraction is carried out on formation data of a to-be-detected sample to obtain a feature set of a to-be-detected sample set, then physical self-discharge detection is carried out on the feature set of the to-be-detected sample set through a physical self-discharge cell detection model, and after first abnormal cell data and first cell data are output, the first abnormal cell data and the second abnormal cell data are obtained. Carrying out chemical self-discharge detection on the first battery cell data through a chemical self-discharge battery cell detection model, outputting second abnormal battery cell data and normal battery cell data, and taking the battery cell corresponding to the first abnormal battery cell data and the second abnormal battery cell data as an abnormal battery cell through the above detection. And finally outputting the battery cell corresponding to the normal battery cell data. According to the scheme, different types of abnormal battery cells can be accurately distinguished, and the detection precision of the abnormal battery cells is effectively improved.

A vehicle, system and method for monitoring an occurrence of thermal runaway in a battery pack of the vehicle. The system includes a plurality of voltage sensors and a processor. The plurality of voltage sensors obtains a plurality of voltage measurements at each of a plurality of battery cells of the battery pack. The processor is configured to determine a mean value based on the plurality of voltage measurements, compare a voltage measurement obtained from a selected battery cell to the mean value, and generate a notification signal when a difference between the voltage measurement from the selected battery cell and the mean value is greater than or equal to a prognostic threshold.

The invention discloses a model training method and a cell capacity prediction method and device, and relates to the field of batteries. The model training method comprises the steps that a first feature set is acquired, the first feature set is used for representing features associated with cell capacity in production parameters of sample cells, and the sample cells comprise normal cells and abnormal cells; screening features of which the distinguishing degree of the normal battery cell and the abnormal battery cell exceeds a first preset threshold value from the first feature set, and determining a second feature set; balancing the number of sample battery cells of which the battery cell capacities are located in each preset capacity interval in the second feature set, and determining a third feature set; and screening features having contribution to model training from the third feature set, determining a fourth feature set, and training the cell capacity prediction model through the fourth feature set. According to the method, the data for model training can be optimized, and the data quality is improved, so that the trained model can accurately predict the cell capacity of various capacity intervals.

The present disclosure relates to bioactive conjugates and preparation methods and uses thereof, and specifically discloses a ligand-drug conjugate represented by formula XV, a preparation method thereof, and its use in preventing and / or treating diseases associated with abnormal cell activity, including but not limited to preventing and / or treating tumor diseases. #imgabs0#

The invention belongs to the technical field of power battery detection, and particularly relates to a power battery abnormal monomer detection method, which comprises the following steps of: completing a data preprocessing step through parameter setting, working condition segmentation and sampling steps; and the model calculation step is completed through the steps of data set setting, value rate calculation, value rate filtering, abnormal coefficient A calculation, Boolean matrix conversion and abnormal monomer judgment. According to the method, the voltage fluctuation degree of each monomer in each message is represented through an abnormal coefficient A, Boolean matrix conversion is used, the voltage fluctuation conditions in the data blocks are aggregated, and finally the judgment of the abnormal monomers is obtained. And the voltage fluctuation condition of each message is analyzed in a detailed manner, so that the accuracy of abnormal monomer judgment can be effectively improved.

The present invention provides compounds that degrade SMARC A2 via the targeted ubiquitination of SMARCA2 and subsequent proteasomal degradation. These compounds are useful for the treatment of SMARCA2- or SMARCA4-mediated disorders, for example a SMARCA2- or SMARCA4-mediated abnormal cellular proliferation, including tumors and cancer.

Embodiments of the present disclosure provide a software upgrading method, system, electronic device and storage medium. The software upgrading method comprises: adopting a first prediction model to predict an abnormal probability of a cell associated with a first terminal based on first space-time information of the first terminal, wherein the first prediction model is obtained by training a network behavior data collected by a second terminal on a server; and performing a corresponding avoidance operation on an abnormal cell with an abnormal probability greater than a probability threshold.

The embodiment of the invention provides a cell installation detection result display method, system and device and a storage medium, and relates to the technical field of battery manufacturing. The method comprises the following steps: acquiring an installation result and an installation image of a battery cell module; when the installation is normal, generating a correct installation picture based on the state of the battery cell module, the model of the battery cell module, the total number of the battery cell modules and the installation image; when the installation is abnormal, generating an abnormal reason, a solution and the number of abnormal battery cells based on an abnormal type in an installation detection result; marking the battery cell which is installed abnormally to obtain a marked image; and generating an installation abnormity picture based on the abnormity reason, the solution, the number of the abnormal cells, the cell state, the cell model, the total number of the cells and the mark image. Therefore, by marking the abnormal cells, the number of the cells, the polarity arrangement sequence of the cells and the cells with abnormal placement angles are identified, and specific reasons, solutions and the number of the abnormal cells of the abnormality are displayed, so that reasons for abnormal installation of the cell module are conveniently checked.

A multi-scale dual-stream abnormal cervical cell detection method that integrates pathological knowledge. The present invention relates to the problem of sparse features and difficulty in detecting abnormal cells of different sizes in the technology of abnormal cell detection in panoramic images of cervical cell pathology. Early detection of abnormal cervical cells in cervical cancer screening can increase the chance of timely treatment, but manual detection requires experienced pathologists, is time-consuming and prone to errors. The technology of abnormal cell detection in panoramic images of cervical cell pathology has the problem of sparse features of abnormal cells in panoramic images and difficulty in detecting abnormal cells of different sizes. To improve this problem, the present invention proposes a multi-scale dual-stream abnormal cervical cell detection method that integrates pathological knowledge. Experiments show that this method can effectively integrate pathological knowledge, significantly improve the quality of multi-scale detection area suggestions, robustly detect cells of different sizes, and improve the accuracy, sensitivity and specificity of cervical cell detection. It provides effective and efficient technical support for cervical cancer screening and improving pathology workflows, helping pathologists make more accurate diagnoses. The present invention is mainly used for abnormal cell detection in panoramic images of cervical cell pathology.

The present invention discloses an abnormal data analysis method, system and storage medium in an electronic document, including obtaining the coordinates and content of each cell of a table in an electronic document to be analyzed, identifying cells with consistent content; obtaining the minimum table matrix of two tables, when the minimum table matrix of the first table has N more rows than the minimum table matrix of the second table, but the same number of columns, or the number of columns is N more than the minimum table matrix of the second table, but the number of rows is the same, and N is less than a preset value, obtaining the N rows or N columns with the most inconsistent cells in the minimum table matrix of the first table, and entering each cell in the N rows or N columns into an abnormal cell group; after removing the N rows or N columns from the minimum table matrix of the first table, a transition table matrix is ​​formed, and the contents of each cell in the corresponding position of the transition table matrix and the minimum table matrix of the second table are compared in turn, and if they are different, they are supplemented and entered into the abnormal cell group. Finally, the number of abnormal data cell results presented to the user is reduced, so that the user can quickly check and find errors and abnormal tables.

The invention discloses an automatic inspection method, system and storage medium for drug application documents, including obtaining the coordinates and contents of each cell of two tables in the drug application document to be analyzed and identifying cells with consistent contents; when the first table has N more rows than the second table but the same number of columns or N more columns but the same number of rows, and N is less than a first preset value, obtaining additional columns or additional rows in the first table that are all inconsistent cells; after removing the M rows or M columns from the minimum table matrix of the first table, a transition table matrix is ​​formed, and the contents of each cell at the corresponding position of the transition table matrix and the minimum table matrix of the second table are compared in turn, and if they are different, they are supplemented and entered into an abnormal cell group; if the additional column or additional row is not located in the minimum table matrix of the first table, the coordinates and contents of all cells of the additional column or additional row are recorded, and supplemented and entered into the abnormal cell groups of the two tables. Finally, the number of abnormal data cell results presented to the user is reduced, so that the user can quickly check and find errors and abnormal tables.

The invention discloses a battery anomaly detection method, device and equipment based on a sliding-mode observer, and relates to the technical field of batteries, the method comprises the following steps: obtaining real-time operation data of a to-be-detected battery, determining a real-time discharge rate according to the real-time operation data, and determining the real-time discharge rate of the to-be-detected battery according to the real-time discharge rate; calling a matched open-circuit voltage value-battery charge state mapping curve according to the real-time discharge rate; constructing an equivalent model, and constructing a nonlinear system model according to the equivalent model; constructing a sliding-mode observer according to the nonlinear system model, and predicting a predicted value of each state variable of each cell at each time node; and obtaining a measured value of the state variable of each cell at each time node in the operation cycle, marking abnormal cells according to the predicted value and the measured value of the state variable, and determining an abnormal detection result of the to-be-detected battery according to the number of the abnormal cells. According to the invention, the problem of insufficient capability of identifying hidden and slow anomalies such as soft faults and gradual faults can be solved, so that effective early warning of abnormal batteries can be realized.

The application discloses a kind of based on UMLC and ICA's electrochemical energy storage cell health state rapid detection method, medium and program product, belong to electrochemical energy storage power station monitoring and battery management technical field.This method is by BMS real-time acquisition battery cluster in each cell monomer voltage, monomer temperature and battery cluster current and other operating data, constructs the characteristic vector containing voltage and temperature mean, standard deviation and deviation, and is combined with the unsupervised machine learning clustering (UMLC) and incremental capacity analysis (ICA) and other technologies not dependent on historical training data, identify and extract the key features of abnormal cell, to quickly diagnose cell health state.This method does not need historical data, with higher detection efficiency and interpretability, can be directly applied to on-site energy storage power station, realize to cell fast and accurate consistency analysis screening and positioning abnormal cause.

A normal set of cells is characterized using flow cytometry. A centroid and radius are defined for a set of clusters in an n-dimensional space corresponding to a normal maturation for a cell lineage in the normal set of cells. A test set of cells is characterized using flow cytometry and the characterization is compared to the defined set of clusters. Support Vector Machine (SVM) subroutines are employed to identify reference populations of interest by generating multidimensional boundary definitions. These boundary definitions may be used to identify reference populations to use in defining or refining a centroid line or a radius or radii defining a set of normal clusters, and to characterize and compare a test set of cells to the defined set of normal clusters.

The invention relates to a method for identifying abnormal battery cells in a battery pack. The method comprises the following steps: step S1, acquiring accumulated equalization time of each single battery cell in the battery pack in a preset time window; s2, for each single cell, calculating a relative self-discharge rate based on the accumulative equalization time; s3, for each single cell, judging whether the relative self-discharge rate exceeds a preset threshold value or not; and S4, under the condition that the relative self-discharge rate exceeds the preset threshold value, determining that the corresponding single battery cell is an abnormal battery cell. According to some embodiments of the invention, an algorithm for online calculation of the relative self-discharge rate of a single cell based on the accumulative equalization time is provided, so that a suspicious cell can be recognized online in real time, whether the suspicious cell is abnormal can be judged, early warning can be performed in combination with means such as remote diagnosis, and the accuracy and the reliability of the system are improved. Therefore, the abnormal condition of the battery cell is effectively prevented.

The invention provides a cell traffic mutation detection method and device and a medium, and relates to the technical field of networks. The method comprises the following steps: acquiring a same-time characteristic service data sequence of a cell; preliminarily screening out suspected abnormal cells in which abnormal mutation occurs in the same-time characteristic service data sequence based on Pettitt inspection; and judging whether the suspected abnormal cell is a comprehensive abnormal cell or not according to the same-time characteristic service data sequence of the suspected abnormal cell in combination with test related data obtained by Pettit test and associated data of cell service metadata. According to the method and the device, the same-time characteristic service data sequence of the cell is selected, the suspected abnormal cell is quickly and preliminarily screened out by using the Pettitt test, finally, the cell abnormity is comprehensively researched and judged by fusing multi-dimensional information, the Pettitt test is high in speed, small in burden and suitable for full-amount scanning, the data analysis amount of subsequent comprehensive research and judgment can be reduced, the analysis efficiency is improved, and the method and the device are suitable for large-scale popularization and application. Deep analysis is carried out on a small number of suspected targets through comprehensive research and judgment, and the recognition precision is improved.

The present invention relates to automation of urine analysis or urinalysis (UA) with conventional cytopathological assessment tests and methods using an artificial intelligence (AI) based urine diagnostic apparatus or device or system and methods employing said apparatus or device or system for fully automated preparation of raw samples by automating and streamlining conventional laboratory processes and examination of urine samples, automated data collection, automated analysis of data using digital image recognition, and finally, automated screening for cancer suspicion in a non-invasive, non-human or pre-pathologist intervention-based automatic examination and analysis of such samples using AI based on said data analysis for preparing reports intimating to the subject or patient automated negation if no abnormal cells are detected / identified, or to forward suspicious samples from the subject or patient to confirm the possibility of suspicion for cancer risk of cancers routinely and otherwise detected based in examination of urine samples by a trained pathologist.

The invention relates to the field of intelligent medical treatment, and discloses a pathological recognition analysis method and system based on a blood detection sample. The method comprises the following steps: acquiring a blood smear microscopic image and extracting a cell contour; performing texture analysis on the interior of the contour to obtain morphological characteristics; judging a potential abnormal region based on the features; carrying out local enhancement on the abnormal region and extracting subtle difference features; based on the difference features, obtaining quantitative pathological descriptors through a deep learning model; identifying abnormal cells according to a matching result of the descriptors and the feature library; and comprehensively analyzing according to an identification result to obtain pathological quantitative indexes. Through a mode of combining local enhancement, a deep learning model and feature library matching, the problems of low blood smear abnormal cell recognition precision and poor efficiency are solved, and the accuracy and automation level of pathological analysis are improved.

The invention discloses a cell abnormal fluorescence signal intelligent identification system based on dynamic labeling, and relates to the technical field of cell detection, the system comprises an information input module, a detection control module, a scatter diagram extraction module and an abnormal signal identification module, the information input module inputs basic information and is connected with the detection control module, and the scatter diagram extraction module is connected with the abnormal signal identification module; the detection control module comprises a detection device, the detection control module sends an instruction to the detection device and starts detection, and after the detection device completes detection, the scatter diagram extraction module obtains white blood cell five-classification scatter diagram data from the detection device and converts the white blood cell five-classification scatter diagram data into an image format which can be recognized by software; and the abnormal signal identification module identifies the image transmitted from the scatter diagram extraction module, and transmits the result through an intelligent identification system.

The invention discloses a base station cutover quality evaluation method and device, electronic equipment and a computer program product. The method comprises the following steps: acquiring first cell communication data corresponding to a first base station and second cell communication data corresponding to a second base station as target cell communication data under the condition that the first base station is cut to the second base station; determining a target evaluation index corresponding to the duration in a plurality of preset evaluation indexes for evaluating the cutover quality of the base station according to the duration after the first base station is cut to the second base station; acquiring to-be-evaluated data from the target cell communication data according to the target evaluation index; and under the condition that the to-be-evaluated data accords with an abnormal threshold condition corresponding to the target evaluation index, determining that a communication cell corresponding to the second base station is an abnormal cell, and determining that the quality of base station cutover from the first base station to the second base station is unqualified. The technical problem that the cutover quality of the base station cannot be actively monitored in the prior art is solved.

Embodiments of the present disclosure provide a cell avoidance method, system, electronic device and storage medium. The cell avoidance method comprises: using a first prediction model to predict an abnormal probability of a cell associated with a first terminal based on first space-time information of the first terminal, wherein the first prediction model is obtained by training a network behavior data collected by a second terminal on a server; and performing a corresponding avoidance operation on an abnormal cell with an abnormal probability greater than a probability threshold.

The present invention discloses a method, apparatus, computing device, and storage medium for detecting anomalies in a subway cell. The method comprises: generating a bidirectional reference table based on sweep frequency data of two running directions of a subway line; the bidirectional reference table records the cell identifiers of coverage cells detected in the two running directions corresponding to each position data block, wherein each position data block is obtained by dividing the cell identifiers by starting from a base station of the subway line and using a preset distance as a granularity; for any coverage cell recorded in the bidirectional reference table, if the number of coverage position data blocks corresponding to the coverage cell in both running directions exceeds a preliminary judgment threshold, the cell is determined to be a preliminarily judged abnormal cell; for any preliminarily judged abnormal cell, determining the coverage status of the preliminarily judged abnormal cell based on the bidirectional reference table, and determining the abnormality of the preliminarily judged abnormal cell based on the coverage status. This method can improve the efficiency and accuracy of determining anomaly in subway cells.

The application provides a short video traffic monitoring method and device and a server, and relates to the field of communication. The method comprises the following steps: a server associates one-time online browsing of the same user to one browsing record according to information in a service code stream. The server processes the browsing record according to a preset service model to obtain an experience index of each browsing record. The server determines whether a wireless cell is a wireless side abnormal cell according to the experience index in each wireless cell. When the wireless cell is the wireless side abnormal cell, the server splices the browsing record and a corresponding quality report to obtain a composite document. The server determines abnormal information of the wireless side abnormal cell according to the composite document in the wireless side abnormal cell. The server locates an abnormal cause of the wireless side abnormal cell according to the abnormal information. The method provided in the application improves the accuracy of abnormal positioning of the wireless cell and improves the accuracy of optimization.

The utility model belongs to the technical field of cervical abnormal cell screening, and discloses a safe cervical abnormal cell screening kit which comprises a support, rotating grooves are formed in the two sides of the surface of the support, mounting cylinders are rotationally connected into the rotating grooves, servo motors are fixedly mounted in the mounting cylinders through mounting plates, and the servo motors are connected with the rotating grooves. A rotating rod is fixedly installed at the output end of the servo motor, a cross is fixedly installed at one end of the rotating rod, and placing cylinders are fixedly installed at the four ends of the cross. In the using process, a servo motor is powered on by a worker, the output end of the servo motor drives a rotating rod to rotate, the rotating rod drives placing cylinders at the four ends of a cross to rotate, reagent tubes in the placing cylinders rotate along with the rotating rod, and when the reagent tubes transversely rotate, the worker rotates a connecting assembly; and the reagent tube rotates longitudinally while rotating transversely, so that a reagent and detection liquid in the reagent tube are fully mixed, and the detection accuracy is improved.

The invention relates to a cell switching method and device, electronic equipment and a storage medium. The cell switching method comprises the following steps: determining that a first cell meets a preset condition, wherein the preset condition represents uplink data jamming due to occurrence of advanced timing abnormity; according to the abnormal information of a target cell in a first tracking area, determining a second cell, the first tracking area being a tracking area to which the first cell belongs, and the target cell being a cell having advanced timing abnormity; and switching from the first cell to the second cell. According to the method, switching to other abnormal cells can be avoided while the abnormal serving cell is quitted in time, the problem of uplink data jamming caused by abnormal timing in advance of the serving cell is remarkably solved, and the user experience is improved.