21results about How to "Strong subjectivity" patented technology

The invention belongs to the technical field of computer vision, and discloses an arm movement automatic evaluation system and method for dyskinesia of a cerebral palsy patient, and the system is characterized in that a data collection module carries out the movement data collection of the movement task of the arm of the patient through a smart phone camera; the posture estimation and key point detection module uses a posture estimation algorithm to automatically detect and track arm movement of a patient and recognize key points of a human body, and after coordinate data of the key points are obtained, data preprocessing is carried out; the muscular dyskinesia feature extraction module extracts muscular dyskinesia features from the motion data of the arm of the patient and constructs a corresponding feature set; the automatic scoring module uses a multi-layer feedforward neural network model to automatically calculate the score of the muscular dystonia based on the arm movement characteristics of the patient; the report generation module is used for generating an evaluation report. The method is suitable for arm movement evaluation of myodynia of cerebral palsy patients, and an objective, convenient and efficient evaluation tool is provided for clinicians.

The invention provides a carbon integral pricing model construction method and device, and belongs to the technical field of reinforcement learning, and the method comprises the steps: constructing a reinforcement learning model through employing a DDPG algorithm; setting an environment required by learning training of the reinforcement learning model; generating a plurality of experience tuples according to continuous interaction between the reinforcement learning model and the environment, and storing the plurality of experience tuples in an experience pool; training the reinforcement learning model based on the experience tuple in the experience pool until the reinforcement learning model converges; and extracting an Actor network from the convergent reinforcement learning model as a carbon point pricing model so as to determine the carbon point pricing for each type of carbon point seller according to the carbon point number of each type of carbon point seller. According to the construction method and device of the carbon point pricing model, a more scientific and reasonable carbon point pricing scheme can be provided, and healthy development of the whole carbon market can be promoted.

The invention relates to the technical field of knee joint rehabilitation, in particular to a knee joint postoperative adaptive progressive rehabilitation training method based on pain detection, which comprises the following steps: initializing a knee joint rehabilitation machine, and enabling a patient to wear myoelectricity acquisition equipment and the knee joint rehabilitation machine; the patient drives the rehabilitation machine to conduct active knee joint flexion, and knee joint active movement angle data are recorded; the rehabilitation machine conducts passive knee joint flexion motion, and training data needed by the pain detection model are collected; preprocessing and feature extraction are carried out, and a classifier is trained to obtain a pain detection model; selecting a rehabilitation training mode to train the patient; after the patient finishes all training, the knee joint flexion is actively performed again, and active movement angle data of the knee joint are recorded. According to the application, pain detection is carried out by using the surface electromyogram signals of the patient, automatic identification of the knee joint movement range is realized, multi-mode training is carried out according to the training condition of the patient, and the problem of resource shortage of rehabilitation physicians is relieved.

The invention provides a global distribution knowledge guided cabbage leaf ball section type region division method and device and a medium, and belongs to the technical field of agricultural informatization. The method comprises the following steps: collecting spectral information of regions with different color types of a cabbage leaf ball profile, and performing feature analysis; calculating hyperspectral characteristic indexes of different types of regions of the cabbage leaf ball section based on the original wave band reflectivity; the method comprises the following steps: acquiring a hyperspectral image of a cabbage leaf ball section by using a hyperspectral imager, and obtaining initial spectral features of different types of regions of the cabbage leaf ball section by using a hyperspectral feature index calculation method; constructing a Chinese cabbage leaf ball section type region division model; inputting the initial spectral features into a Chinese cabbage leaf ball section type region division model to train the model; and collecting a to-be-detected cabbage leaf ball section hyperspectral image, and inputting the image into the model for region division. According to the invention, rapid and accurate division and identification of different types of areas of the cabbage leaf ball profile can be realized, and the division precision and the working efficiency are greatly improved.

This invention relates to the field of fluid machinery testing technology, and in particular to a performance testing system shared by circulating pumps and submersible pumps. The system includes a data acquisition and control unit, a drive unit, a load adjustment unit, and an intelligent control and analysis server, configured to perform: startup and intelligent identification, digital twin model construction and test planning, adaptive basic performance sampling, boundary performance exploration, real-time safety monitoring and prediction, synchronous acquisition of multi-source heterogeneous information, and digital profile generation and model training. Before physical testing begins, this invention pre-calculates key feature points under all operating conditions through numerical simulation. Based on these pre-calculated key points, the system can automatically generate a dynamic test sequence that balances safety and efficiency, enabling subsequent real-world testing to be targeted and precise, capturing the core performance framework of the pump with the fewest possible tests, greatly improving the scientific rigor and efficiency of the testing.

The application discloses a safety-critical software failure mode identification method based on a large language model, comprising the following steps: constructing a safety-critical field knowledge base, injecting the safety-critical field knowledge base into an initial large language model through a P-Tuning v2 technology to obtain a large language model after first-time fine-tuning; constructing an instruction optimization data set, and performing multi-round iterative training on the large language model after first-time fine-tuning by using the P-Tuning v2 technology to obtain a large language model after second-time fine-tuning; using the large language model after second-time fine-tuning to predict failure modes of industrial failure text data, and based on the failure text data of the prediction failure, constructing a thinking chain data set, and using the thinking chain data set to continue training the large language model after second-time fine-tuning to obtain a safety-critical field specific large language model with ideal final effect; inputting failure text data of a failure mode to be identified into the safety-critical field specific large language model to obtain a failure mode identification result.

A fire prediction and evaluation method, system, device and medium based on explainable machine learning assistance of multiple types of sensors, uses multiple types of sensors for different scenes, collects and integrates a large amount of fire data sets, covers multiple different fire scenes, namely different time, places and the like, and divides the data sets into a training set and a test set; constructing a convolutional neural network sub-model, and training the model by using a data set to realize universal modeling of fire prediction; a principal component analysis method is used and an entropy weight method is combined to carry out disaster situation evaluation on a place where a fire is predicted to occur, so that accurate universality evaluation on the disaster degree is realized; according to the method, disaster assessment is carried out by combining the convolutional neural network sub-model with the principal component analysis (PCA) and the entropy weight method, fire situations of different types and scales can be accurately analyzed and predicted, the accuracy and operability of disaster assessment are improved, and meanwhile the data processing capacity and the output interpretability of the model are enhanced.

This invention belongs to the field of remote sensing technology and discloses a method for optimizing habitat quality parameters in the InVEST model based on Remote Sensing Ecological Indices (RSEI). This invention overcomes the technical bottleneck of traditional InVEST models, which rely on manual experience to set parameters and are difficult to update dynamically over time. By constructing a multi-source remote sensing data-driven RSEI, and utilizing its statistical characteristics and spatial distribution patterns across different land use types, it achieves objective quantification and dynamic updating of four key parameters: habitat suitability, threat weight, threat attenuation distance, and habitat sensitivity. Without requiring data from ecological monitoring stations, it directly incorporates continuous changes in ecological environment quality into the InVEST parameter system, resulting in higher objectivity, temporal consistency, and spatial autocorrelation in habitat quality calculations. This provides a novel technical approach for the automated and time-series assessment of regional-scale habitat quality.

The invention relates to the technical field of lithium ion battery manufacturing, in particular to a pole piece component floating judgment method. The method comprises the following steps: selecting a to-be-detected pole piece after coating and drying and before rolling, and performing gradient scraping to obtain a plurality of samples with different thickness layer areas; performing an electrochemical test on the sample in each layer region to obtain the first discharge capacity of the sample; and judging whether a component floating phenomenon exists or not according to the capacity change trend of each layer area, if the gram capacity continuously rises along with the increase of the scraping depth and the difference value of the adjacent layer areas is greater than or equal to 1mAh / g, judging that floating exists, and further dividing a mild grade, a moderate grade and a severe grade according to the capacity difference value delta C of the deepest layer and the outermost layer. The method is high in sensitivity, quantitative in result and suitable for quality control and process optimization of the negative pole piece of the lithium ion battery.

The present invention discloses a detection device for the risk of intracranial aneurysm rupture based on multidimensional feature fusion, comprising: an automatic segmentation module, used to obtain a segmented aneurysm image by introducing a preset segmentation model of a lesion-aware attention mechanism and a multi-level semantic supervision mechanism; a three-dimensional reconstruction module, used to establish a three-dimensional model of the aneurysm using the segmented aneurysm image as input to obtain a three-dimensional model of the aneurysm; a multidimensional feature extraction module, based on angiography images, segmented images and a three-dimensional model of an aneurysm of an object to be detected as input, extracts multidimensional features related to the risk of aneurysm rupture; a risk detection module, used to eliminate irrelevant features in a multidimensional feature set according to a preset optimal feature set, and then input the remaining features of the object to be detected into a preset detection model, and finally obtain the rupture risk of the aneurysm of the object to be detected. The present invention combines the aneurysm segmentation and recognition task with the rupture risk detection task to reduce the interference of irrelevant information.

The application provides a kind of distribution terminal single-phase ground fault research and judgment capability test method and system based on true type test platform, builds encrypted wireless communication environment and terminal hardware detection system, constructs the true type test field of adjustable network frame and grounding mode and selects overhead-cable hybrid test line;In the middle section, end and overhead-cable transition node of line, set up collaborative fault point, trigger multiple types of single-phase ground fault through fault simulation device, after collecting terminal response data, by master station according to the quantitative evaluation of differentiated scoring and multidimensional ranking rule realizes the quantitative evaluation of research and judgment capability.The application also constructs the test system containing six functional units, realizes the systematic and standardized test of distribution terminal single-phase ground fault research and judgment performance under highly realistic environment, solves the problems that traditional test and field working condition are disconnected, single in assessment dimension and lack of objectivity in evaluation, provides reliable basis for equipment selection, algorithm optimization and distribution network fault handling capability improvement.

The invention relates to a Pu'er tea beverage processing control method, device and equipment and a medium, and relates to the field of processing control, and the method comprises the following steps: obtaining a sample data set; predicting the ratio of tea polyphenol to caffeine of the Pu'er tea soup image in the soaking processing process of the Pu'er tea leaves by adopting a tea soup concentration prediction model trained by a sample data set, and filtering Pu'er tea leaf residues when the ratio of the tea polyphenol to the caffeine reaches a preset ratio threshold value of a target Pu'er tea beverage so as to obtain the Pu'er tea beverage. Determining the current Pu'er tea soup; calculating and determining a comprehensive score value of the current Pu'er tea soup according to the fragrance score value, the taste score value and the ratio of tea polyphenol to caffeine of the current Pu'er tea soup, and if the comprehensive score value is within a preset threshold range, determining the target Pu'er tea beverage as a qualified product. According to the method, multiple indexes such as the content of tea polyphenol and caffeine, fragrance and taste can be accurately controlled, and the quality of the Pu'er tea beverage is remarkably improved.

The utility model relates to the technical field of chemical indicator cards, in particular to a chemical indicator card for electronically interpreting a sterilization effect. The chemical indicator card for electronically interpreting the sterilization effect comprises a card body, a sterilization identification area and an indication ink area are arranged on the card body, a character information area and a character description area are arranged on the two sides of the indication ink area respectively, and an identification code area is arranged in the indication ink area. The two-dimensional codes or bar codes with the same color are printed on the indicating ink, at the moment, the two-dimensional codes or bar codes cannot be scanned out, after sterilization is qualified, the indicating agent becomes different colors, the two-dimensional codes or bar codes on the indicating ink are displayed, and sterilization is qualified through electronic scanning. The bar code or the two-dimensional code can also trace product information in the package, so that the situation that whether the sterilization effect is qualified or not is judged through comparison of a standard color or a comparison card, the subjectivity is high, and misjudgment or bad judgment is likely to occur is avoided.

The invention provides an in-situ correction roadway loose zone testing method based on a DeeplabV3 + language segmentation algorithm, and relates to the field of roadway loose zone testing, and the method comprises the following steps: drilling a hole underground, obtaining a rock core, obtaining a test drill hole, and obtaining a wave velocity-double collection time-test depth curve graph of the loose zone test drill hole by using a single-hole ultrasonic velocity measurement method; analyzing according to the wave velocity-double receiving time-test depth curve graph to obtain the longitudinal wave velocity of the original rock mass; utilizing the obtained rock core to obtain the position of a rock mass deep loose circle by combining a co-location discrimination method with a wave velocity-double receiving time-test depth curve graph; a drilling optical electron microscope method based on a DeeplabV3 + language segmentation algorithm is utilized to identify cracks and lithology data on the surface of a hole wall, and the lithology data are combined to analyze surface cracks actually influencing the surrounding rock loose circle; and the real range of the roadway surrounding rock loosening circle is given by combining the position of the rock mass deep loosening circle and the cracks and lithology of the hole wall surface. The method disclosed by the invention has certain guiding significance on supporting and optimized supporting of the roadway.

The application relates to the technical field of knee joint rehabilitation, in particular to a knee joint postoperative adaptive gradual rehabilitation training method based on pain detection, which comprises the following steps: initializing a knee joint rehabilitation machine, and making a patient wear an electromyographic acquisition device and the knee joint rehabilitation machine; the patient drives the rehabilitation machine to actively bend the knee joint, and records knee joint active activity angle data; the rehabilitation machine performs passive knee joint flexion movement, and collects training data required by a pain detection model; preprocessing and feature extraction are performed, a classifier is trained, and the pain detection model is obtained; a rehabilitation training mode is selected to train the patient; after the patient completes all the training, the patient actively bends the knee joint again, and records the knee joint active activity angle data. The application utilizes surface electromyographic signals of the patient to perform pain detection, realizes automatic identification of a knee joint activity range, and performs multi-mode training according to the training condition of the patient, thereby relieving the problem of tight resources of rehabilitation doctors.

This invention belongs to the field of spare parts management technology, specifically relating to a spare parts quota management auxiliary decision-making method based on the historical usage of spare parts in nuclear power plants. It includes the following steps: acquiring work orders and material requisition data; classifying historical maintenance spare parts requirements based on material information and relevant imported data, including categories such as preventative replacement, corrective replacement, or no replacement; acquiring and classifying lifespan data, with data types including complete data, left-truncation data, right-truncation data, and interval data; estimating lifespan distribution parameters; importing planned maintenance spare parts requirements; and forecasting spare parts requirements. Its advantages are: by applying the method of this invention, the difficulty of spare parts quota management can be effectively reduced, decision-making efficiency and accuracy can be improved, and ultimately, while ensuring the safe operation of the unit, spare parts inventory can be kept at a minimum level, thus reducing spare parts management costs.

The invention belongs to the technical field of biology, and particularly relates to a microbial marker combination for evaluating the genuine nature of polygonatum sibiricum and application, the microbial marker combination comprises one or more of Escherichia. Shigiella, Acremonium, Pseudomonas, Serratii a, Mortierella, Wallemia, Engydonium, Sporidesmium, Ceratobasidium, Clonostachys and Ralstachys, an evaluation method for the genuine nature of the polygonatum sibiricum is established, the sensitivity is 91.7%, the specificity is 100.0%, the AUC is 93.8%, and the application of the microbial marker combination to the evaluation of the genuine nature of the polygonatum sibiricum is established. The method has the characteristics of high sensitivity, strong specificity and high accuracy, can judge whether the production area of the rhizoma polygonati is a genuine production area of the rhizoma polygonati, and can be widely applied to genuine evaluation of the rhizoma polygonati.

A dynamic real-time planning method for collaborative search scenarios is proposed. Based on the initial position of the swarm and the boundary of the unfamiliar area to be explored, the method estimates the total search path length of each unmanned surface vessel (USV) unit through an optimization algorithm and autonomously arranges the search areas of each unit in the USV swarm. Compared with existing technologies, this invention enables the USV swarm to grasp the global situational information of the area to be explored as quickly as possible, while autonomously deciding the task status and path planning of each unit in the swarm based on the current situation. This mitigates the impact of uncertainties in the actual exploration process and ultimately minimizes the total time for multi-target search.

The utility model relates to the technical field of vaporized hydrogen peroxide sterilization, in particular to a vaporized hydrogen peroxide sterilization chemical indicator card. The chemical indicator card for vaporized hydrogen peroxide sterilization comprises a card body, the card body is provided with a sterilization mark, a character information area and a character description area, and a first gradient contrast color area, a second gradient contrast color area, a third gradient contrast color area and a fourth gradient contrast color area are sequentially arranged between the character information area and the character description area. The first gradient contrast color area is located on the side close to the sterilization mark, and the third gradient contrast color area and the fourth gradient contrast color area are each provided with a color changing indication color area. The indicator card adopts a mode of combining a gradient contrast color and a color-changing indicator color, so that the conditions that whether the sterilization effect is qualified or not is judged through comparison of a standard color or a contrast card, the subjectivity is relatively strong, and misjudgment is easy to occur or the judgment is difficult are avoided.

The application discloses a kind of civil aviation control system sub-security state hawk-dove game regulation methods, step 1) collection air traffic control system operating data;Step 2) according to the information obtained in step 1) establishes hawk-dove game model;Step 3) according to system operating data, the key variable in the above model is valued;Step 4) calculate risk disturbance and fitness take hawk strategy Nash equilibrium probability;Step 5) calculate the probability that the control system changes to different states, and provide corresponding regulation method.The civil aviation control system sub-security state regulation method provided by the application is an objective evaluation method in the field of air traffic control safety, which can quantitatively analyze the operation trend of the control system in the sub-security state, move the risk control threshold forward, avoid the occurrence of unsafe events, and realize the transformation of the control system from the sub-security state to the security state.

The present invention discloses an automatic scoring method for immunohistochemical images of breast cancer HER2. First, the image block set is inferred using a cell nucleus instance segmentation model and a tumor tissue semantic segmentation model to output a cell nucleus segmentation map and a tumor region segmentation map; then the tumor region contour in the tumor region segmentation map is extracted and the convex hull ratio and curvature features are calculated; then the invasive cancer region and the carcinoma in situ region are classified by a Gaussian mixture model and a naive Bayes classifier; then the cell membrane segmentation of the cell nucleus segmentation map is performed to obtain the cell membrane region and the cell staining degree is classified to obtain tumor cells with different staining levels in the invasive cancer region; finally, counting and proportion statistics are performed and the HER2 scoring of the breast cancer immunohistochemical image is completed according to the clinical guidelines. The present invention reduces human errors, ensures the consistency and reliability of the results, greatly shortens the diagnosis time, and provides immediate support for clinical decision-making.