175 results about "Objective analysis" patented technology

A system and method for numerical risk of loss assessment of an insured property, in general, comprising the steps of evaluating one or more risk criteria and category for each property area, subsystem or sub-area utilizing objective evaluation criteria and matrix to assess the risk of loss numerical rating for each criteria and category from 1-10 based on an objective analysis of the property's subsystems or sub-areas; averaging the risk criteria ratings across each property area, subsystem, or sub-area for each risk criteria to arrive at a category average); and averaging the category averages for each of the one or more category to arrive at an overall total risk of loss rating or score for the property.

The invention discloses a monitoring system for improving driving behavioral habits, which is used for monitoring travelling information in travelling and giving out a prompt. The monitoring system comprises a vehicle speed collector, a vehicle distance collector, an audio and video collection module, a voice broadcast device, a satellite positioning module and a processor, and is characterized in that the vehicle speed collector is used for collecting speed information in driving of a vehicle; the vehicle distance collector is used for collecting vehicle distance information between the vehicle and a front/back vehicle; the audio and video collection module is used for collecting video information and audio information of the front, the interior and the back of the vehicle; the voice broadcast device is used for broadcasting bad driving behaviors and reminding information in real time; the satellite positioning module is used for acquiring longitude and latitude coordinates of the geographical position of the vehicle; and the processor is internally provided with an electronic map unit, and is used for interactive, coordinated and comprehensive analysis and processing of all information. By adopting the monitoring system disclosed by the invention, all collected driving behavior information can be combined with road condition information and position information, and local and objective analysis is carried out on the information, so that a driver is ensured to prevent occurrence of traffic accidents in advance sufficiently and effectively in actual traffic road conditions.

The invention relates to a method for comprehensively evaluating network performance based on subjective and objective combination evaluation, which comprises the following steps: A, selecting a comprehensive evaluation index of the network performance, collecting network performance data, and establishing a decision matrix; B, evaluating the network performance by using a subjective analysis method, and calculating the comprehensive evaluation value of the network performance; C, evaluating the network performance by using an objective analysis method, and calculating the comprehensive evaluation value of the network performance; and D, performing combined evaluation on the comprehensive evaluation values obtained by the subjective and the objective analysis methods respectively to obtain the final comprehensive evaluation value of the network performance. The method has the advantages that probable insufficient data information content by singly using the objective analysis method is avoided, subjective randomness caused by singly using the subjective analysis method is also avoided, and simultaneously, the subjective and the objective analysis methods are combined together to evaluate the network performance so that the evaluation is more scientific and comprehensive, and the method has reasonable design and strong practicability and provides a basis for monitoring and evaluating the practical network performance.

The invention relates to a fruit sorting device, which comprises a machine frame, a driving unit, a conveying unit, an image acquisition and processing unit, a sorting control unit, and a separating unit. The sorting control unit controls the driving unit to drive the conveying unit so as to convey fruits to the area of the image acquisition and processing unit which acquires the image information on the fruits, shoots a plurality of images containing effective information of the fruits, and judges the comprehensive quality of the images through a computer vision technique; and the sorting control unit tracks, detects and finally separates out the bad fruit so as to achieve the fruit sorting. The device adopts non-touch type judgment and has the advantages of simple structure, low price, and accurate and objective analysis.

Disclosed embodiments include a complete integrated system designed to support continuous monitoring and objective analysis of movement disorders. According to one embodiment the integrated system allows for continuous monitoring of movement disorders during normal daily activities in home and other normal daily environments, as well as in the clinic. The integrated system comprises: 1) wearable movement monitoring devices including a plurality of inertial sensors, 2) a docking station with wireless capabilities, 3) a secure web-enabled data server, and 4) statistical signal processing methods, all of which are integrated to enable monitoring and analysis of movement disorders.

The invention relates to a safe broadcast monitoring method based on video and audio comparison, which comprises the following steps: (a) receiving two paths of signals, wherein the two paths of signals are broadcasted by the same broadcast signal source; (b) aligning the two paths of signals according to a time stamp mechanism; (c) accumulating video and audio data of the two paths of signals; (d) extracting the video and audio data, and comparing the signals; and (e) processing the comparison results. By introducing the method of comparing two paths of signals, the automatic objective analysis of the technical index of the last-stage broadcast signal is realized in a broadcast channel sub-control system. When the signal difference exceeds the limited threshold range, a warning message is automatically released to the related workstation in the system to prompt the related personnel to carry out the necessary processing operation, thereby finishing the quick processing of faults. The invention is not limited by the subjective judgment capability of the personnel, greatly relieves the workload and the mental pressure of the broadcast personnel in a television station, effectively avoids the occurrence of broadcast accidents, and greatly improves the broadcast safety.

The invention discloses a classification model channel extracting seismic facies clustering analysis method, which comprises the steps of acquiring an initial classification model channel through neural network and particle swarm clustering calculation based on seismic waveform data; acquiring a new classification model channel through correlation analysis based on the initial classification model channel, carrying out clustering analysis on original data by using the new classification model channel, and acquiring a seismic facies classification figure; and predicting distribution of oil gas underground based on the seismic facies classification figure. According to the invention, the classification model channel is optimized through a two-step method, thereby effectively ensuring the stability of a classification result and effective discrimination of classes of neurons, finally realizing objective analysis for the seismic facies, and enabling a large amount of information in the seismic data to be interpreted accurately.

The invention discloses a power supply reliability fuzzy comprehensive evaluation method based on an improved membership degree function. The method comprises the following steps: (1) selecting N basic level indexes capable of reflecting a current situation of a power supply reliability of a power distribution network to establish an evaluation index system; (2) dividing quality grades of N evaluation indexes into six quality grades, which respectively are "optimal", "excellent", "good", "mean", "qualified" and "unqualified"; (3) determining a comprehensive weight for each of the evaluation indexes in the evaluation index system by employing subjective and objective analysis methods which combine an improved hierarchical analysis method with a variation coefficient method; and (4) carrying out scoring on each evaluation index to obtain a scoring value of the each evaluation index. According to the method disclosed by the invention, the problem that a relation is established difficultly between two quality grades of the evaluation indexes in power supply reliability fuzzy comprehensive evaluation field is solved; and meanwhile, the problem that when index data are similar, evaluation results are consistent and cannot be distinguished is solved, and more fine power supply reliability fuzzy comprehensive evaluation is realized.

The invention provides a multi-classifier combined weak annotation image object detection method. The method comprises the steps that M weak annotation image sets with different labels are input, objective analysis is conducted on all images in the image sets, and an objective region set is generated; image features are generated for the region set, and clustering is conducted on different label feature sets; a middle region classifier is trained for each clustered region set according to a clustering result; a category attribute is calculated for each classifier; a test image is input, objective analysis is conducted to obtain a region block, and region features are generated. A multi-classifier is used for conducting combined detection, and the region containing the category object is judged. The multi-classifier combined weak annotation image object detection method has good performance on the aspect of multi-category image object combined detection and can be applied to fields of image object automatic annotation, image object identification and the like.

The invention relates to a well logging permeability interpretation method. The well logging permeability interpretation method includes the first step of conducting granularity interpretation, porosity interpretation and water saturation interpretation, the second step of conducting permeability interpretation through a permeability interpretation model, and the third step of verifying the permeability interpretation model through granularity comparison, permeability model actual measurement inspection and permeability model actual measurement production characteristic inspection. The well logging permeability interpretation method integrates static experiments, well logging and dynamic testing data, the scientific method of mathematical statistics is used, an interpretation result is verified after objective analysis evaluation based on geological conditions, and the model result is objective, real and convenient to use.

The invention discloses a method and a device for evaluating client credit. The method comprises the following steps of: acquiring basic data of a client, wherein the basic data of the client comprise basic information and manpower information of the client; calling a preset client evaluation parameter model; and evaluating the credit of the client according to the basic data of the client and the evaluation parameter model corresponding to the client. According to the embodiment of the invention, the method and the device have the advantages that: because a mediation device serving as a third party is provided and a transaction party is evaluated through the mediation device before on-line transaction, the transaction credibility of double transaction parties is improved, and the failure rate of the on-line transaction is reduced; the problems of non-objectivity, inaccuracy and non-equal service levels of evaluation personnel in the prior art are solved; and consistent, objective and comparable measurement of the client credit is obtained by objective analysis of the client information, and the client credit is effectively and accurately quantified.

The invention relates to a small sample relay protection reliability parameter estimation method based on a SVM (Support Vector Machine). The method comprises the following steps: 1, using an empirical formula to calculate the empirical reliability of an original failure sample and performing linear processing; 2, using a SVM algorithm to perform regression of failure data and performing prediction to generate a new enlarged sample; 3, performing linear fitting of the original failure data to obtain a parameter estimation value as a new iteration initial value; and 4, performing least square fitting of the enlarged new sample to obtain a final reliability parameter estimation result. Compared with the prior art, the method provided by the invention can effectively solve problems that priori knowledge and statistical samples are extremely in shortage as the operation time of an intelligent transformer station is short, and is beneficial for objective analysis and evaluation of reliability of a protection system.

The invention provides an automobile wind vibration noise sound quality objective annoyance degree evaluation index and a calculation method thereof. The objective annoyance degree is equivalent to the subjective annoyance degree and can reflect the subjective feeling of people on the automobile wind vibration noise. The method comprises: firstly, establishing an automobile wind vibration noise model, conducting wind vibration noise simulation on the model, and obtaining wind vibration noise data at key positions under different working conditions; secondly, performing sound quality objectiveanalysis and subjective evaluation on the wind vibration noise data to obtain eight objective acoustic parameters and a subjective annoyance degree; then, using eight objective acoustic parameters asinput, using the subjective annoyance degree as output, and training a BP neural network; and finally, obtaining influence weight coefficients of the eight objective acoustic parameters by using the trained BP neural network so as to establish a wind vibration noise objective annoyance degree calculation model. After the objective annoyance degree calculation model is obtained, only eight objective acoustic parameters need to be used for calculation to obtain the objective annoyance degree, a large number of subjective evaluation tests are avoided, the development period is shortened, and thecost is reduced.

The automatic and optimal selection of coding parameter values according to analyses of coding trials is disclosed. The Neural Encoding Model (NEM) provides a method for providing a quantitative measure of the likelihood that a human observer can distinguish an original sensory signal from an approximation thereof, thus providing a metric by which the effect of various coding parameters may be analyzed and optimized. Optimal coding parameters can be defined for an entire data set, such as a digitized audio file, or for discrete portions of the data set. A trial coded data set or portion thereof is analyzed to determining if certain coding parameters have been assigned optimal values. If not, parameter manipulation is performed in an intelligent order and the objective analysis is repeated until predetermined objective perceptual distance criteria are achieved.

The invention relates to a word trademark registrability judging method based on big data, which is applied to a user terminal. The method comprises the steps of: receiving word trademark informationto be registered input by a user; sending the word trademark information to a server, so that the server determines a classification group of commodities or services to which a trademark to be registered belongs according to the word trademark information; searching for prior word trademarks and related information thereof existing in the classification group in a database; judging whether the trademark to be registered is identical with or similar to the prior word trademarks; and receiving a registration suggestion report given by the server, wherein the registration suggestion report is given based on an identical or similar judgment result of the trademarks. The word trademark registrability judging method adopts a big data algorithm for searching and analyzing the trademark to be registered, is not prone to miss searching, has objective analysis result, can significantly improve the success rate of registering the trademark of an enterprise, saves the cost of trademark registration for the enterprise, and has high reference value.

The invention provides a method and system for recognizing sleep quality. The system comprises a terminal. The terminal comprises a high-precision sensor module, a recorder module, an acquisition module and a processor module. The high-precision sensor module is used for sensing pulses and actions and converting the pulses and the actions into electric signals. The recorder module is used for receiving, storing and recording the electric signals of the high-precision sensor module. Subjective indexes of a user are input manually through the acquisition module. The processor module is used for processing data of the processor module and/or processing data of the acquisition module. The method and system have the following advantages that by means of the method, large instruments and professionals needed by an objective analysis method are avoided, the characteristics that subjective arbitrariness and the high human factor influence degree are caused by the fact that a subjective analysis method is used purely are avoided, subjective analysis and objective analysis are combined for evaluation, the evaluation is more scientific and comprehensive, and the method is reasonable in design and easy and convenient to use, so that high practicality is achieved.

The invention provides a driving performance test apparatus and method for a P2 configuration hybrid electric vehicle. The device comprises an upper computer, a data collection device, a longitudinalacceleration sensor, a three-axis acceleration sensor, a current sensor, a vibration sensor and a power CAN bus, wherein the upper computer is connected with the data collection device, the data collection device is fixed on a seat and is connected with the sensors, and output lines of the sensors and the power CAN bus are connected to the data collection device to transmit data to the upper computer so as to provide quantitative data for the measurement of the upper computer. By means of the cooperative use of the data collection device, the longitudinal acceleration sensor, the three-axis acceleration sensor, the current sensor, the vibration sensor and the CAN bus, the driving performance test apparatus provided by the invention provides an objective evaluation signal for the driving performance test of the P2 configuration hybrid electric vehicle, and performs objective analysis and performance control on the feature performance of the vehicle, so that subjective evaluation errorsof a driver on the driving performance of the vehicle can be avoided to a certain extent.

The invention provides a personal character analysis method, a device and a computer readable storage medium. The method comprises the following steps of collecting sample videos and annotating character types; extracting the image features and audio features of each sample video, and combining to obtain the video features of each sample video; constructing a neural network using the Softmax classifier as an output layer; annotating and training the neural network based on video features and character types, optimizing training parameters, and obtaining a personal character analysis model; collecting a face video of an to-be-analyzed object for a predetermined duration; extracting the image features and the audio features of the video of the to-be-analyzed object, and combining to obtain the video features of the video of the to-be-analyzed object; inputting the of the video features of the video of the to-be-analyzed object into the personal character analysis model to obtain a probability value corresponding to each character type of the to-be-analyzed object; and adopting a character type with the largest probability value as the character type of the to-be-analyzed object. According to the invention, the personality of a person can be objectively analyzed.

The invention, which belongs to the technical field of train seat adjustment information processing, discloses a train seat comfort evaluation method and system based on multi-source physiological signals. After combination of physiological signal data of a subject and a subjective evaluation scale, a train seat comfort database for a group is established by combining a mainstream subjective evaluation method with a physiological-signal-based objective evaluation method; and a train seat comfort evaluation model is established by selecting a LightGBM gradient boosting tree which is a machine learning modeling method with multiple characteristics of rapidness, distribution and high performance. According to the invention, physiological signal data of a tester are inputted into the established train seat comfort evaluation model to obtain a comfort evaluation result. Therefore, the evaluation deviation caused by subjectivity of evaluation personnel is effectively reduced. The irrationality caused by a direct objective analysis method is avoided; and the comfort evaluation accuracy and feasibility of the train seat are greatly improved.

It is an object of the present invention to provide a mapping-data analyzing method that can display a map in which sufficient information is extracted from the spectra of obtained mapping data to enable objective analysis. The mapping-data analyzing method of the present invention is used for analyzing mapping data obtained by measuring, with a spectrometer apparatus, spectra at a plurality of points on a specimen surface. The method comprises a principal-component calculating step and a grouped-map display step. In the principal-component calculating step, spectral data obtained at each point on the specimen surface is defined as an individual sample and principal component analysis, in which values at a plurality of wave numbers of each spectral data set serve as variables, is performed to calculate the scores of a plurality of principal components for each individual sample. In the grouped-map display step, the points on the specimen surface are divided into a plurality of groups based on the scores of a plurality of principal components calculated in the principal-component calculating step and a two-dimensional or three-dimensional map indicating to which group each point on the specimen surface belongs is displayed on a display device.

The invention discloses a multi-terminal long-distance education and training system based on AI video analysis. The multi-terminal long-distance education and training system includes three or more terminals, clients, cloud servers, teacher ends and management ends, the clients are installed on intelligent terminals with camera functions, so that the clients can monitor the state of customers inthe whole process of watching video through an artificial intelligence video analysis method, objective analysis is realized, and thus personalized learning advice is provided for the customers.

The invention provides a car-networking-based intelligent evidence adducing method of a traffic incident. The method comprises: different road traffic information of a vehicle is collected, alarm information is extracted and extracted alarm information is reported to a server, and evidence adducing information is collected; business classification is carried out on traffic alarm information and the classified traffic alarm information is submitted to a corresponding business server; the business server carries out a big data analysis by using a cloud platform to determine whether any record is made; if so, the evidence adducing information is released; and if not, the evidence adducing information is submitted and an operator is informed of collection of assisted evidence adducing information; a WEB business system determines whether the assisted evidence adducing information is uploaded; if so, the assisted evidence adducing information is uploaded; and if not, the assisted evidence adducing information is released; and the WEB business system performs corresponding business processing based on the submitted information. According to the invention, traffic violation event identification, an objective analysis, and intelligent traffic violation reporting are carried out by means of dynamic sensing, so that unnecessary conflicts are reduced and driving safety is guaranteed; and the traffic violation reporting operation flow is simplified and the reporting quality is improved.

The invention provides a security customer loss prediction method and system based on Logistic regression, and the method comprises the steps: determining a customer loss index and a data range; screening the customer data according to the customer loss index and the data range; calculating the initial variable according to the screened customer data; carrying out the preprocessing of the initial variable; carrying out the prediction calculation of the customer loss according to the preprocessed initial variable through a Logistic regression model, so as to obtain a customer list with the loss probability being greater than a preset loss probability threshold value. The method achieves the objective analysis of the selected customer data through the Logistic regression model, so as to accurately and objectively predict the customer loss.

The invention discloses a formalized modeling based software security requirement acquisition method. The method includes functional requirement acquisition, security environment analysis, security objective analysis, security requirement elicitation and final generation of a system security requirement file, wherein the file at least includes information of system asset, behavioral sequence, defects, threats, security strategies, security assumptions, security objectives, security requirement levels, security guarantee levels, security functional modules and security guarantee modules. Compared with the prior art, the formalized modeling based software security requirement acquisition method has the advantages that automation in acquisition of software security requirements is realized while precision in acquisition of the security requirements is greatly improved; the problems of failure in realization of computer processing, ambiguity and fuzziness of security knowledge bases in natural language description are solved to lay the foundation for automatic elicitation of the software security requirements; the method which is a typical software security requirement acquisition method is applicable to different types of software systems and high in universality.