38 results about "Standard score" patented technology

The invention discloses an intelligent auxiliary method, a medium and equipment for constructional engineering title review. According to the method, key feature information of unstructured text data in a declaration material is extracted by using a natural language processing technology, image data features are analyzed by using a ResNet-50 deep learning model, and a comprehensive quantitative scoring mechanism of a construction engineering performance material is established. And integrating education background, working experience, scientific research achievements and multi-modal performance data, constructing a constructional engineering title review rule base, setting a standard score threshold based on historical declaration data, and generating a title simulation review score and a review prediction result. And finally, aiming at the model, designing a feature weight analysis layer, and automatically outputting improvement suggestions of the declaration material defects according to the simulation review score after being associated with the associated review rule base. According to the method, automatic feature extraction and quantitative evaluation of the unstructured material are realized, the problems of low manual auditing efficiency and fuzzy standard are solved, and the objectivity of title evaluation is improved through the rule base and the evaluation prediction model.

The invention belongs to the technical field of underwater unmanned cluster evaluation and grading, and discloses a method for intelligent evaluation and grading of an underwater unmanned cluster and a related device. The method for intelligent evaluation and grading of the underwater unmanned cluster comprises the steps of determining an evaluation task type and obtaining environmental parameter statistics, task parameter statistics and technical feature statistics based on a function type of the underwater unmanned cluster to be subjected to intelligent evaluation and grading; based on the obtained standard score of the environment difficulty index and the standard score of the task effect index, calculating to obtain an external weight; multiplying the obtained external weight by the technical feature original score to obtain an improved technical feature score; and performing evaluation and grading based on the obtained improved technical feature score to obtain an underwater unmanned cluster intelligence evaluation and grading result. According to the technical scheme disclosed by the invention, the problems of subjective evaluation, generalization application, fuzzy definition and solidification classification in the prior art can be solved.

The invention relates to the technical field of knowledge base generation, and particularly discloses an education knowledge base content generation method and system based on AI big data. The method comprises the following steps: comparing user answer content with answer information to obtain a matching degree, calibrating a positive sample and a negative sample to train an evaluation model, and determining a reference standard score according to a quantitative relationship between the positive sample and the negative sample; and screening the plurality of candidate knowledge contents based on the reference standard score and the tolerance threshold to calibrate the candidate knowledge contents as stable knowledge contents or to-be-corrected knowledge contents, and outputting the stable knowledge contents or the to-be-corrected knowledge contents. According to the method, the evaluation system based on the real answer data of the user and the evaluation standard reflecting the actual application effect of the knowledge content are constructed, and the evaluation standard is automatically calibrated according to data distribution, so that objective screening and continuous iteration of the knowledge content are realized, and the accuracy and reliability of the knowledge base content are improved.

The invention belongs to the field of evaluation assistance, and particularly relates to an interactive teaching evaluation assistance system and device based on multi-modal fusion, and the system collects multi-dimensional information through a portrait module, and constructs a user training action portrait library in combination with multi-modal feature extraction and a knowledge graph algorithm; the strategy recommendation module generates an optimal guidance scheme through a correction scheme matching model according to the portrait library, the real-time information and the teaching guidance strategy library; the auxiliary adjustment module collects training action images in real time, and obtains a guided continuous correction action sequence and a standard score by using a spatial-temporal feature extraction model and an evaluation algorithm; the traceability feedback module is combined with the action standard knowledge base to obtain transverse and longitudinal spatial-temporal change chains of non-standard actions through a forward reasoning model, and feeds back the transverse and longitudinal spatial-temporal change chains to the instructor to adjust the scheme in real time until the actions reach the standard; according to the method, accurate evaluation and personalized scheme matching of multi-modal data fusion are realized, and scientificity and interactivity of evaluation assistance are effectively improved.

The application belongs to the field of evaluation assistance, and particularly relates to an interactive teaching evaluation assistance system and device based on multi-modal fusion. The system collects multi-dimensional information through a portrait module, combines multi-modal feature extraction and a knowledge graph algorithm to construct a user training action portrait library. A strategy recommendation module generates an optimal guidance scheme from a portrait library, real-time information and a teaching guidance strategy library through a correction scheme matching model. An auxiliary adjustment module collects training action images in real time, uses a space-time feature extraction model and an evaluation algorithm to obtain a continuous correction action sequence and a standard score after guidance. A traceability feedback module combines an action standard knowledge base, obtains a horizontal and vertical space-time change chain of non-standard actions through a forward reasoning model, and feeds back to the instructor to adjust the scheme in real time until the action meets the standard. The application realizes precise evaluation and personalized scheme matching of multi-modal data fusion, and effectively improves the scientificity and interactivity of evaluation assistance.

The invention discloses a data processing method and device for a network security competition. The method comprises the following steps: acquiring initial score data corresponding to a plurality of stages in a target network security competition; performing normalization processing on the initial score data corresponding to the plurality of stages to obtain standard score data corresponding to the plurality of stages; determining weights respectively corresponding to the plurality of stages; and based on the weights, performing weighted addition on the standard score data corresponding to the multiple stages to obtain total score data of the target network security competition. According to the invention, the technical problem that the result of directly summarizing score data for processing is not accurate enough due to different score standards and score ranges of matches at different stages is solved.

The invention relates to the technical field of data processing, and provides a piece-counting task performance dynamic evaluation system based on variable weight, which comprises a piece-counting task performance evaluation subsystem and a backtracking historical data execution weight dynamic evaluation subsystem, and the backtracking historical data execution weight dynamic evaluation subsystem comprises a statistical test module. If it is considered that the confidence level is 95%, the weighted score of the current period significantly changes compared with that of the previous period, and if the rising amplitude of the mean value of all scores on a certain dimension in the current period exceeds a preset rising threshold value compared with that of the previous period, the weighted score of the current period does not significantly change; and if yes, reducing the evaluation dimension weight coefficient of the evaluation dimension to a preset evaluation dimension weight coefficient value. According to the invention, by introducing innovative methods such as adaptive variable weight and standard score conversion, a more flexible and fair performance evaluation effect of a piece counting task is realized.

The present invention discloses a new urban construction integration project evaluation method and system based on multiple dimensions, which relates to the field of urban construction evaluation and multidimensional data modeling and analysis technology, including collecting the original value and score of the same indicator in multiple new urban construction integration projects, and constructing an indicator scoring point set. The score values ​​in the indicator scoring point set are normalized, and the influence of outliers is eliminated. Multi-class scoring function models are fitted and the goodness of fit is calculated, and the standard scoring function form is determined according to the goodness of fit. A scoring function template is established based on the standard scoring function form and function parameters, and stored in a scoring function template library. The method of the present invention realizes a scientific, unified, and reusable quantitative evaluation mechanism for new urban construction integration projects, effectively overcoming the problems of strong subjectivity of scoring rules, difficulty in migration, and inconsistent evaluation standards in existing methods, and improving the objectivity, flexibility and intelligence of the evaluation system.

The invention provides a dynamic optimization method, system and device for a network security guarantee strategy and a medium, and relates to the technical field of network security, and the method comprises the steps: collecting and preprocessing the security operation data of an enterprise, extracting multi-dimensional monitoring indexes, carrying out the standardization and standardization score smoothing of each index, and obtaining a corresponding index smoothing standard score; setting a weight for each index, weighting the index smoothing standard score corresponding to each index according to the corresponding weight to obtain an index comprehensive factor, matching the index comprehensive factor with a set threshold, and if the matching is successful, triggering a risk review mechanism; and substituting the comprehensive factor into a preset strategy adjustment function, and generating a dynamic optimization scheme of the current network security guarantee strategy in combination with a strategy mapping table. According to the method, the matching degree of a network security protection strategy and a real-time risk situation can be improved, a risk-driven forward feedback mechanism is constructed, and the overall security toughness is enhanced.

The present invention discloses a contact detection method, device and medium for human-machine collaborative grinding, which belongs to the field of target detection and classification. The method includes: obtaining original force data; obtaining force data of a preset time length from the original force data in combination with the current timestamp; calculating a continuous score based on the obtained force data; if the continuous score is higher than the first standard score, calculating an amplitude score based on the obtained force data; if the continuous score is lower than the first standard score, determining that the grinder has not contacted the workpiece; if the amplitude score is higher than the second standard score, determining that the grinder has contacted the workpiece; if the amplitude score is lower than the second standard score, determining that the grinder has not contacted the workpiece. The present invention provides a method for realizing contact detection based on original force data, which is not only simple and convenient, but also has accurate and reliable detection results; in addition, no additional hardware costs are required.

This specification discloses an anomaly detection method, device, and storage medium for time series data. In this method, multiple key metrics of time series data within a specific time period can be comprehensively considered, including the amplitude difference (i.e., the difference between the maximum and minimum values of the data within that time period), the cumulative amplitude sum, the over-mean rate, the peak value, and the trough value. And for these metrics, calculations are performed according to different time window scales, thus forming a multi-dimensional metric system. The anomaly index calculated through multiple dimensions can more sensitively detect tiny anomaly intervals. It is also possible to screen different metric values by calculating the standard score sequence, thereby effectively removing the influence of outliers in the metric values.

The invention provides a real-time data visualization method for LED packaging production, and belongs to the technical field of industrial internet. According to the method, key parameters of colloid thickness, temperature, pressure and vibration frequency in LED packaging production are obtained; and identifying positive correlation influence factors among the parameters through correlation analysis, calculating standard scores of the production parameters, judging whether the standard scores exceed a preset safety threshold value or not, and if the standard scores exceed the preset safety threshold value, judging that potential risks exist in LED packaging production. Then, early warning of different risk degrees is carried out through graded vibration feedback and visual feedback, it can be ensured that an operator rapidly understands the abnormal property and the emergency degree from the two perspectives of touch sense and visual sense, and the response decision time is shortened; according to the invention, early discovery and early intervention of production abnormity are realized, response efficiency and adaptivity are improved, and powerful support is provided for high quality and visualization of LED packaging production.

The invention relates to a competition review method and device based on standard score adjustment and a medium. The method comprises the steps that the intersection of review works of any two experts is determined; calculating a review score difference of each work in the review work intersection under the score of any two experts; according to all other experts having the review work intersection with the target expert, adding and averaging the review score difference of the target expert, and quantifying the review tendency of the target expert; constructing a standard score calculation model, introducing the quantized review tendency as an adjustment factor into standard score mean value calculation, and generating an adjusted standard score calculation formula; and setting a value range of influence parameters in a standard score calculation formula, and optimizing the parameters based on a genetic algorithm to maximize a correlation coefficient of adjusted work sorting and expert negotiation sorting. According to the method, subjective tendency of experts is systematically quantified, scoring parameters are dynamically adjusted, and abnormal data processing capability is enhanced, so that limitation of a traditional standard scoring model is effectively solved.

The invention discloses a time series data anomaly detection method and device and a storage medium. In the method, a plurality of key indexes of the time sequence data in a specific time period can be comprehensively considered, and the key indexes comprise an amplitude difference (namely, a difference between a maximum value and a minimum value of the data in the time period), an accumulated amplitude sum, an over-average value rate, a crest value and a trough value. And aiming at the indexes, calculation is carried out according to different time window scales, so that a multi-dimensional index system is formed. According to the abnormal indexes obtained through multi-dimension calculation, tiny abnormal intervals can be detected more sensitively. And different index values can be screened by calculating a standard score sequence, so that the influence of abnormal values in the index values can be effectively removed.

The present invention provides a method for improving the efficiency and stability of full-scale data queries in a distributed database, comprising: setting a timed task framework based on a distributed database; obtaining the data volume of each physical node of the distributed database as a variable value of a sample of each physical node; obtaining the average of the data volume of different physical nodes of the distributed database based on the variable value; determining the standard deviation of the degree of discreteness of data volume differences of samples of different physical nodes of the distributed database based on the variable value, the number of physical nodes, and the average of the data volume of different physical nodes; determining a standard score for calculating the degree of discreteness of each data volume of samples of different physical nodes of the distributed database based on the standard deviation; identifying the query efficiency and stability differences between physical nodes with different data volumes based on the standard score, and determining a decision-making mechanism; and determining the amount of data that needs to be queried and cached in advance based on the variable value and the standard score.

This invention discloses a risk assessment method and system for large language model (LLM) vulnerabilities, relating to the fields of artificial intelligence security and network security technology. The method includes the following steps: semantic-driven vulnerability modeling, constructing a large language model vulnerability feature identification model from three dimensions: attack mechanism, model behavior, and propagation impact; constructing a scoring system, introducing three key indicators—semantic manipulation complexity, model behavior impact, and attack propagation potential—onto the CVSS standard scoring mechanism; designing a scoring transfer judgment mechanism to calculate the score, obtaining the CVSS basic score, constructing an AI-extended risk factor for score transfer, the AI-extended risk factor being calculated from the quantified values ​​of the three key indicators and their corresponding weights, and using the AI-extended risk factor and the CVSS basic score to establish a comprehensive scoring function to obtain the comprehensive score. This invention achieves quantitative assessment and automated scoring of LLM vulnerabilities by extending new risk indicators based on CVSS.

This invention discloses a method and system for intelligent evaluation of blasting effects, relating to the field of information processing technology. The method includes: acquiring the pre-blast step profile line and the corresponding post-blast pile outline of the target object from a server; extracting post-blast pile change feature values; normalizing the post-blast pile change feature values ​​to obtain standard score values; constructing a mapping space between the standard score values ​​and engineering indicators to obtain engineering indicator evaluation scores; weighting the engineering indicator evaluation scores to obtain a comprehensive score; and determining the blast pile morphology level based on the comprehensive score and a preset grading threshold. This invention improves the adaptability and domain transferability of intelligent blasting effect evaluation by extracting and normalizing blast pile change features; it enhances standardization by using a dimensional projection matrix to map low-dimensional morphological features to high-dimensional engineering indicators; and it improves adaptability by introducing a multi-indicator matrix evaluation method and a quality grading method, allowing for flexible configuration of evaluation preferences according to actual needs.

The invention provides a work order quality evaluation method and device and a work order quality evaluation system, and the method comprises the steps: 1, obtaining a standard score of each work order according to a scoring standard, and obtaining a work order score of each work order according to the standard score of each work order and an artificial score; training an SVR model by using the spatial feature vector and the work order score of each work order to obtain a work order scoring model; thirdly, inputting the spatial feature vectors into a work order scoring model to obtain model scores of all work orders, and adjusting scoring standards according to the model scores of all the work orders and manual scores; a repeating step: sequentially repeating the first step, the second step and the third step at least once to obtain a plurality of work order scoring models; determining the work order scoring model with the minimum average scoring error as a final work order scoring model; and scoring the new work order by adopting the final work order scoring model. According to the method, the problem of relatively low efficiency caused by the fact that work order scoring depends on manual scoring in the prior art is solved.

The invention relates to the technical field of low-voltage distribution areas, in particular to a low-voltage distribution area state index weighting comprehensive evaluation method and system, and the method comprises the steps: constructing a low-voltage distribution area state comprehensive evaluation index system; standardization processing is carried out on each index result value, and a Delphi method is adopted to design a standard score conversion rule of the index value at the bottommost layer; the subjective and objective weights are synthesized through a Lagrange multiplier method, and the comprehensive weight of each index is obtained; and obtaining a comprehensive score of the state of the low-voltage distribution area by adopting weighted calculation. The method has the beneficial effects that the subjectivity of the analytic hierarchy process can be reduced by fusing the comprehensive index weighting method of the anti-entropy weight method, and meanwhile, the objectivity and accuracy of evaluation are improved by reflecting the fluctuation of the weight through data change. The anti-entropy weight method serves as an objective weighting method, can reflect information content characteristics provided by data, and can reduce the limitation of a single method when being used in combination with the analytic hierarchy process.

The application belongs to the technical field of underwater unmanned cluster evaluation grading, and discloses a method for underwater unmanned cluster intelligence evaluation grading and related devices; wherein the method for underwater unmanned cluster intelligence evaluation grading comprises the following steps: based on the function type of the underwater unmanned cluster to be evaluated and graded, determining the evaluation task type and obtaining the environmental parameter statistics, task parameter statistics and technical feature statistics; based on the standard scores of the obtained environmental difficulty index and the standard scores of the task effect index, calculating the obtained external weight; multiplying the obtained external weight with the technical feature original score to obtain the improved technical feature score; based on the obtained improved technical feature score, performing evaluation grading to obtain the underwater unmanned cluster intelligence evaluation grading result. The technical scheme disclosed by the application can solve the problems of subjective evaluation, generalization application, fuzzy definition and solidification classification existing in the prior art.

The invention relates to a feeling processing evaluation method and device for children of 3-6 years old and a storage medium, and is applied to the technical field of child feeling processing ability evaluation.The method comprises the steps that existing feeling processing related items are screened to obtain a theoretical evaluation scale; acquiring scores of the target test population for the theoretical evaluation scale, performing question quality inspection and screening on the theoretical evaluation scale based on the questionnaire scores, and obtaining a scale factor model for expressing social behaviors of children and a feeling processing model for expressing feeling processing ability based on the screened questions, standard score conversion is carried out through the original score ranking of the screened questions in the test crowd, so that a standardized norm is obtained; standard scores of a to-be-tested child about all questions are obtained, and then scores of the to-be-tested child in all dimensions of social behaviors and feeling processing ability are obtained and used for quantitatively evaluating the feeling processing function of the to-be-tested child. And the problem of relatively low accuracy of an evaluation result caused by subjective experience judgment of the feeling processing ability of the child is avoided.

The invention provides a person and post matching quantitative evaluation method based on a competency model. According to the method, a unified competency evaluation model containing 15 secondary indexes in total in three dimensions of core ability, general ability and professional ability is constructed, post weights are calculated by adopting an analytic hierarchy process to generate standard scores, and comprehensive employee scores are generated in combination with 360-degree evaluation data and performance adjustment coefficients. And through the cosine similarity and the Euclidean distance, a man-post matching coefficient is calculated, and accurate diagnosis and personalized development recommendation are realized. The problems that in the prior art, post evaluation and employee evaluation data standards are heterogeneous, matching results are fuzzified, and system linkage is poor are solved.

The invention provides a copy number variation degree analysis method and device and a storage medium, and relates to the technical field of bioinformatics analysis. The method comprises the following steps: determining a copy number baseline of each chromosome region through a reference sample set; according to the copy number baseline of each chromosome region, determining a Z standard score of the corresponding window-level chromosome region, and summing the Z standard scores of which the absolute values are greater than a set threshold value to obtain a whole genome cumulative score; determining threshold values of normal samples and abnormal samples in the whole genome cumulative fraction by using an ROC curve method; after the to-be-detected sample is calculated according to the method to obtain the whole genome cumulative fraction, the result is judged according to the whole genome cumulative fraction threshold value, the risk that the analysis result deviates from reality can be reduced, and the reliability of the method in clinical application can be improved.

The application relates to the technical field of knowledge base generation, and particularly discloses an education knowledge base content generation method and system based on AI big data. The method comprises the following steps: comparing user answer content with answer information to obtain a matching degree, calibrating positive samples and negative samples to train an evaluation model, and determining a reference standard score according to the quantity relationship between the positive samples and the negative samples; based on the reference standard score and a tolerance threshold, a plurality of candidate knowledge contents are screened to calibrate them as stable knowledge contents or to-be-corrected knowledge contents, and are output. By constructing an evaluation system based on user real answer data and an evaluation standard reflecting the actual application effect of the knowledge content, and automatically calibrating the evaluation standard according to the data distribution, objective screening and continuous iteration of the knowledge content are realized, and the accuracy and reliability of the knowledge base content are improved.

This invention provides a sensor data fusion method and apparatus. The method includes: acquiring multiple indicator measurement data collected by multiple sensors in real time for each monitoring indicator; obtaining standard scores for each sensor based on the indicator measurement data at the current time; determining instantaneous weights corresponding to the standard scores of each sensor based on the mapping relationship between the standard scores and instantaneous weights; obtaining fusion weights based on the instantaneous weights and the cumulative reliability scores of each sensor at the current time; estimating indicator prediction data for the current time based on the indicator fusion data obtained by each sensor at the previous time using an adaptive weighted Kalman filter algorithm; constructing a measurement noise model for the current time based on the fusion weights to obtain the Kalman gains; and fusing the indicator prediction data and the indicator measurement data at the current time to obtain indicator fusion data. This invention can improve the accuracy of data fusion.

This invention discloses a method and system for quantitative diagnosis of website GEO readiness. The method includes the following steps: S1: collecting raw indicator data for multiple evaluation dimensions; S2: mapping the raw indicator data of each dimension to standard score intervals; S3: calculating the subjective weight vector and objective weight vector of each dimension to obtain the adaptive weight vector of each dimension; S4: constructing a directed acyclic graph G of causal dependencies between each dimension and calculating the dependency decay factor of each dimension; S5: weighted summation to obtain a comprehensive score, and classifying each dimension into different priorities. This invention provides multi-dimensional quantitative diagnosis of the readiness of a website in generative AI search engines, overcoming the shortcomings of existing technologies such as single evaluation dimensions, linear scoring methods, assumptions of independence between dimensions, fixed weights, and lack of predictive ability.

The embodiment of the present application provides a hospital grade assessment method, a server end, a mobile end and a readable storage medium, which relates to the field of hospital management. In this method, review data is obtained, and the review data includes multiple items to be inspected and the standard scores corresponding to each item to be inspected; feature extraction is performed on the items to be inspected in the review data, and multiple inspection items and department groups corresponding to each inspection item are generated, and each inspection item is scored and assigned to obtain the inspection score corresponding to each inspection item; according to the department grouping, the corresponding inspection items are sent to the mobile ends of the multiple inspection departments; the department inspection results returned by the mobile ends of each inspection department are received, and the department inspection results are automatically statistically calculated to obtain statistical results; the hospital assessment grade is determined based on the statistical results and the standard scores. The embodiment of the present application can automate the review process of each department, reduce personnel participation, and greatly facilitate the inspection and review work.

A computing system retrieves historical hole-by-hole data for a plurality of holes of a plurality of golf tournaments for a plurality of players. The historical hole-by-hole data includes a code number for each hole and a standard score associated with each hole. The computing system clusters the plurality of holes into a plurality of clusters of hole types. The computing system generates a score per hole type metric for the hole-by-hole data for each player. The computing system adjusts the score per hole type metric based on a strength field metric associated with each tournament. The strength field metric represents a strength of the field of players in a given tournament. The computing system generates a ranking of the plurality of players based on the adjusted score per hole type metric.

The invention relates to the technical field of speech recognition, in particular to a foreign language pronunciation evaluation system and method based on machine learning, and the method comprises the steps: obtaining a language selected by a user and a pronunciation evaluation mode, and obtaining the pronunciation data of the user; processing the pronunciation data by adopting a corresponding sub-evaluation model in a preset foreign language pronunciation evaluation model to obtain a comprehensive evaluation result containing a plurality of evaluation indexes; and when it is detected that information that the score of the evaluation index is smaller than a preset standard score exists in the comprehensive evaluation result, a preset strategy generation model is adopted to analyze and match the comprehensive evaluation result, so that a learning strategy meeting user requirements is obtained. By means of the method, the problems that in the foreign language pronunciation evaluation technology, a comprehensive score calculation mode lacks emphasis, the spoken language ability of a practicer cannot be reflected in a targeted mode, and an improvement scheme cannot be given are solved.

The application relates to a method, device, equipment and medium for evaluating an air quality prediction model, comprising the following steps: acquiring prediction data and measured data output by each air quality prediction model, wherein the prediction data comprises pollutant concentration prediction values and air quality index prediction values, and the measured data comprises pollutant concentration actual values and air quality index actual values; determining a primary pollutant according to the measured data; calculating the values of each model with respect to each first index in a first evaluation index system according to the concentration prediction values and the actual values of the primary pollutant; calculating the values of each model with respect to each second index in a second evaluation index system according to the air quality index prediction values and the actual values; calculating the standard scores of each model with respect to each first index; performing importance evaluation on the first evaluation index system according to the values of the first index and the second index, so as to obtain the weights of each first index; and performing weighted summation on the standard scores and the weights of the first index, so as to obtain the final scores of each model.