50results about How to "Reduce data collection costs" patented technology

The present invention relates to a system and method for assessing the impact of an ailment on a health related quality of life domain of a patient using a standardized common metric. The standardized common metric of the present invention enables the impact of various ailments to be compared.

The invention relates to artificial intelligence, and discloses a song synthesis method which comprises the steps: obtaining lyric recitation audio and music score information; performing duration labeling on the lyric recitation audio through a preset voice recognition model and a lyric pinyin text to obtain recitation duration; analyzing initial acoustic parameters from the lyric recitation audio through a preset vocoder; extracting singing duration from the lyric pinyin text according to a preset initial consonant variable speed dictionary, the rhythm information and the beat information; performing speed change processing on the initial acoustic parameters according to a preset speed change algorithm, the recitation duration and the singing duration; performing formant enhancement processing on the frequency spectrum envelope after speed change to obtain an enhanced frequency spectrum envelope; performing correction processing based on the pitch information, the singing duration and the fundamental frequency after speed change to obtain a corrected fundamental frequency; and performing song synthesis processing on the processed acoustic parameters through the preset vocoder. The invention also relates to a blockchain, and the synthesized song is stored in the blockchain.

The invention provides a hospitalization service performance evaluation method of medical institutions. The 20th chapter in codes of international classification of diseases ICD-10 is used as main disease classification MDC, for the diseases in each MDC, grouping is conducted continuously according to the top three of the ICD codes of disease categories, standardized processing is conducted on all indexes through the disease category grouping DCGs method, the medical technology difficulty and the service capacity, efficiency and quality of hospitals are evaluated, and therefore the total hospitalization service performance is obtained. The method involves a hospitalization service capacity evaluation method, a hospitalization service efficiency evaluation method, a hospitalization service quality evaluation method and a total hospitalization service performance evaluation method. Through the methods, a hospital performance evaluation model based on hospitalization medical record home page information is established according to core contents of medical service performance, and the purpose of analyzing and studying hospital service performance is achieved.

The invention relates to a pipeline leakage acoustic emission signal processing method based on compressed sensing and HHT in a mask signal method. The method can be mainly applied to leakage acoustic emission signal detection of pipelines and boilers. The method mainly includes the processing steps that firstly, acoustic emission original signals are obtained, and high-frequency noise exceeding a leakage acoustic emission signal frequency domain is filtered out by means of a digital filter; secondly, a compressed sensing theory is brought in to carry put compressed sampling on leakage acoustic emission signals; thirdly, the compressed signals are precisely reconstructed through an OMP algorithm; fourthly, EMD of the mask signal method is adopted to decompose the acoustic emission signals, and components of different frequency in the signals are sorted out from high frequency to low frequency one by one; fifthly, Hilbert transformation is conducted on the frequency components of the acoustic emission signals to determine starting time and ending time of the acoustic emission signals.

The invention relates to a control method for an overhead signal based on checkpoint data. The method comprises the following steps: 1) acquiring an overhead index change rule, 1.1) calculating the change trend of the overhead blocking index and 1.2) calculating the change trend of the resource required by the ramp; 2) calculating and treating the checkpoint data; 3) calculating the passing requirement of the upper ramp, wherein the ramp passing requirement is the sum with each ground road passing requirement adjacent to the upper ramp and each ground road passing requirement is the product of the total amount of the ground road vehicles multiplying by the proportion of the resource required by the ramp calculated in the step 2); 4) estimating the queuing length: the queuing length is the quantity of the vehicles waiting for entering into the overhead on the upper ramp port; 5) calculating the control rate of the upper ramp; 6) calculating the green ratio of the signal lamp of the ramp. The control method for the overhead signal based on the checkpoint data, provided by the invention, has the advantages of high calculation speed, higher robustness, lower cost, higher control flexibility and high instantaneity.

The invention is applicable to the technical field of data patch, a parking data patching method, a device, equioment and storage medium based on DCGAN are provided. The method comprises: the parkinglots in the collection of city parking lots are clustered into parking lot clusters, car parks include sample car parks and car parks to be repaired, according to the parking data of the sample parking lot, according to the vacancy rate curve image of the sample car park in the car park cluster, training the generative countermeasure network based on depth convolution, to generate a vacancy rate curve simulation image of each parking lot cluster, these empty car rate curve simulation images are processed and mapped to corresponding one-dimensional empty car rate data, according to the one-dimensional empty vehicle rate data, the parking lot to be repaired in each parking lot cluster is repaired, so that the parking lot to be repaired is repaired with more accurate data when the prior knowledge of the parking lot to be repaired is not relied on, the parking data repairing at the city level is realized, and the data collection cost of the parking lot is saved.

An information collection apparatus collecting data sensed by a plurality of mobile sensors, the information collection apparatus comprises a condition setting unit configured to set a target area and a target time period in which data is to be collected; a position information storage unit configured to acquire and store position information of the mobile sensors; a mobile sensor selection unit configured to select, based on the history of position information of the mobile sensors and the target time period, a plurality of the mobile sensors for collecting a given amount of data sensed in the target area; and a collection unit configured to collect data from the plurality of selected mobile sensors.

The invention provides a method for testing intelligence of an unmanned vehicle based on a bench. The method comprises the following steps of: arranging the unmanned vehicle to be tested on the test bench to simulate driving; constructing a virtual scene and each data type in the virtual scene; acquiring, by a host vehicle, operation parameters of the unmanned vehicle to be tested and road surfaceinformation simulated by the test bench and simulating the host vehicle into the virtual scene; interacting the host vehicle with the each data type in the virtual scene to generate virtual driving behavior data; and taking the driving behavior data generated by the host vehicle as a sample set, and adopting a random forest algorithm to take a category with most output times in the decision treeas the category of the test sample. The data acquisition cost is low due to the driving behavior data between the host vehicle and the each data type is acquired by adopting data driving, the providedoriginal data has higher authenticity, and the controllability of the data realizes reproduction of the detection scene.

The invention relates to a virtual lidar data generation method based on a virtual world, comprising the following steps: step S100, acquiring scene information of the virtual world; step S200, analyzing the scene cache information obtained in step S100 to generate scene point cloud data; step S300, analyzing the scene target information obtained in step S100, and generating a scene target point cloud index set; S400, downsampling the scene point cloud data to compose the true value data to generate the virtual lidar data. The invention provides a lidar point cloud data source containing truevalue data for the development of an autopilot sensing algorithm based on a lidar sensor, point cloud data can be collected efficiently without any restrictions and the algorithm development processcan be sped up; at the same time, the consumption of human time costs caused by data acquisition and annotation in the development process is greatly reduced.

The invention discloses a seabed sediment temperature and pressure in-situ measuring instrument and a data acquisition method thereof. The seabed sediment temperature and pressure in-situ measuring instrument includes a shroud, a variable weight weight, a sealed electronic compartment, a variable length extension rod and a needle-point temperature and pressure probe, a shroud, a weight, and a sealed electronic chamber. The bin, the extension rod, and the temperature and pressure probe are connected sequentially from top to bottom; the shroud is used to connect with a load-bearing head of a winch located on the sea surface; the sealed electronic bin is equipped with an inclinometer, an accelerometer, a communication module, A data acquisition module and a power supply, the data acquisition module is used to transmit the data output by the inclinometer, the accelerometer and the temperature and pressure probe to the data processing equipment on the winch through the communication module; in the seafloor sediments. The invention can solve the problems of poor real-time performance, inability to monitor temperature and pressure continuously for a long time.

The invention discloses an operation data collection and fault response method based on WIFI, and the method employs a system which at least consists of the following units which achieve the data interconnection based on the WIFI technology through a public network platform: a wireless data collector, a plurality of terminal devices with the built-in wireless network cards, a wireless router, a modem, and an equipment data collection and maintenance ERP cloud server. The wireless router manages a local area network which consists of the plurality of terminal devices and one wireless data collector. The plurality of terminal devices enables the real-time operation data and fault information to be transmitted to the wireless data collector through the wireless router. The wireless data collector enables the operation data and fault information to be gathered, transmits the gathered data to the public network platform through the wireless router and the modem and transmits the gathered data to the equipment data collection and maintenance ERP cloud server. The method is shorter in fault response time, is higher in speed, is more accurate in data collection and fault reaction, and is lower in cost.

The invention provides a pedestrian attribute recognition model training method, a pedestrian attribute recognition method, electronic equipment and a storage medium. The pedestrian attribute recognition model training method comprises the following steps: constructing a training data set comprising pedestrian pictures marked with attributes and pedestrian pictures marked with IDs; constructing apedestrian attribute recognition network, wherein the pedestrian attribute recognition network comprises a backbone network, a spatial information branch network and a semantic information branch network, and respectively inputting the output of the backbone network into the spatial information branch network and the semantic information branch network; and training the pedestrian attribute recognition network by using the training data set to obtain a pedestrian attribute recognition model, wherein the pedestrian attribute recognition model is used for recognizing attributes in a picture according to the input picture. According to the method and device provided by the invention, comprehensive and robust information is learned through model training, a large amount of attribute labeling work is omitted, and the good pedestrian attribute recognition model is obtained with low data acquisition cost.

The embodiment of the invention discloses a data collection method and device, electronic equipment and a storage medium, and the method comprises the steps: determining an associated data collection instruction corresponding to an associated data collection request when the associated data collection request is received; determining at least two data query statements according to the associated data acquisition instruction, and positioning each data query statement to a corresponding to-be-acquired database, each to-be-acquired database comprising at least two types of databases; and obtaining to-be-processed data corresponding to each to-be-collected database query result, integrating each to-be-processed data, and storing the integrated to-be-processed data in the target database. According to the technical scheme provided by the embodiment of the invention, the acquisition of the associated data of the multiple types of databases is realized in a single acquisition task, the data acquisition cost is reduced, and the efficiency of the acquisition operation is improved.

The invention discloses a cloud monitoring service system. The system comprises a first receiving unit used for receiving at least one datum uploaded through at least one terminal and collected by at least one terminal, an aggregating unit used for aggregating the received data in the set time period and obtaining a data upgrade patch, and a first sending unit used for sending the data upgrade patch to the terminals for data updating. The data collected by the terminals are aggregated, the data upgrade patch is formed and sent to the terminals for data updating, and therefore data points in the range where the terminals are located can be automatically and rapidly corrected, the false report and miss report phenomena caused when the data are not updated in time are avoided, the data can be collected without a special device, and the data collecting cost is low.

The invention relates to a chip detection method, electronic equipment and a storage medium. The method comprises the following steps: using a black and white high-resolution camera to shoot a rough detection image of a to-be-detected chip under a low-magnification objective lens; performing preliminary defect type analysis based on the rough detection image; using a color high-resolution camera to shoot an upper surface image and a lower surface image of the to-be-detected chip under a high-magnification objective lens; fusing the upper surface image and the lower surface image into one image by using an image fusion algorithm to obtain a recheck image with superimposed depth-of-field information; and performing defect analysis on the reinspection image by using a defect analysis algorithm, and identifying a defect type corresponding to the target defect image. According to the scheme provided by the invention, the black and white high-resolution camera can be used for completing rough inspection under the low-magnification objective lens, and the color high-resolution camera can be used for completing reinspection under the high-magnification objective lens, so that the data acquisition cost for acquiring the to-be-analyzed image in the early stage is reduced, and the efficiency of the whole defect analysis and treatment process is improved.

Embodiments of the present invention disclose a method and apparatus for participating in sensing data collection. The method comprises: for each of multiple user equipments, calculating probabilities that the user equipment is located in respective subareas of a predetermined area at a predetermined time by using historical movement information of the user equipment; determining types of sensing data to be collected when the user equipment is located in the respective subareas, based on capability information of the user equipment for collecting sensing data; and obtaining a utility value of the user equipment associated with sensing data collection within the predetermined area, based on the probabilities calculated for the respective subareas and the determined types of sensing data. The method further comprises selecting one or more user equipments from the multiple user equipments for collection of participatory sensing data, based on multiple utility values obtained for the multiple user equipments. By means of the method and apparatus according to the embodiments of the present invention, it is possible to efficiently select user equipments participating in sensing data collection, increase the efficiency for sensing data collection, and reduce the cost for data collection.

The invention provides a vehicle queuing length detection method, device and equipment and a readable storage medium. The method comprises the steps of obtaining trajectory data of an intelligent vehicle and trajectory data of surrounding vehicles collected by the intelligent vehicle; performing noise reduction processing on the trajectory data of each vehicle to obtain reconstructed trajectory data of each vehicle; identifying key points of the reconstructed trajectory data of each vehicle, summarizing the key points belonging to the same aggregation wave or evanescent wave, and pairing the aggregation wave and the evanescent wave belonging to the same congestion to obtain a first aggregation wave and a first evanescent wave belonging to the same congestion, and obtaining the wave velocity of the first aggregation wave and the wave velocity of the first dissipation wave; and determining a linear equation of the first aggregation wave or the first evanescent wave based on the space-time position of the vehicle passing through the first aggregation wave or the first evanescent wave and the wave velocity of the first aggregation wave or the first evanescent wave, and further determining the queuing length. The queuing length detection accuracy can be improved, and the practicability is high.