Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

87results about How to "Solve costly technical problems" patented technology

Air conditioner filth blockage detecting method and device and computer readable storage medium

The invention provides an air conditioner filth blockage detecting method and device and a computer readable storage medium. The air conditioner filth blockage detecting method comprises the steps that an air conditioner is controlled to operate when a filth blockage detecting instruction is received, and under the situation that the current indoor temperature is not changed, the first time interval of reducing a preset temperature value of an indoor heat exchanger in the air conditioner is calculated; the current indoor temperature of the air conditioner is obtained, the standard time interval of reducing the preset temperature value of the indoor heat exchanger is determined according to the current indoor temperature in pre-stored data; and the first time interval is compared with the standard time interval, and whether filth blockage of the indoor heat exchanger occurs or not is judged according to a comparative result. According to the air conditioner filth blockage detecting method, by comparing the first time interval with the standard time interval, whether filth blockage of the indoor heat exchanger occurs or not is judged; and operation is simple, any cost does not need to be increased, and the technical problem that an existing air conditioner filth blockage detecting method is high in cost is solved.
Owner:GD MIDEA AIR-CONDITIONING EQUIP CO LTD +1

Self-adaptive car following method, device and equipment of automatic driving car and storage medium

The invention belongs to the technical field of automatic driving vehicles, and discloses a self-adaptive vehicle following method, device and equipment of an automatic driving vehicle and a storage medium. The method comprises the following steps: when an obstacle exists in a current driving path, acquiring an obstacle distance with the obstacle; obtaining an emergency braking distance corresponding to the current vehicle speed according to the emergency braking distance curve, and comparing the obstacle distance with the emergency braking distance; when the obstacle distance is greater thanthe emergency braking distance, acquiring a preset vehicle following safety distance corresponding to the current vehicle speed; determining an expected vehicle speed according to a preset vehicle following safety distance and a preset vehicle following safety distance formula; and carrying out segmented braking according to the difference value between the expected vehicle speed and the current vehicle speed so as to realize self-adaptive vehicle following. According to the method, the expected vehicle speed under the preset vehicle following safety distance is deduced through a formula, segmented braking is conducted based on the difference value between the expected vehicle speed and the current vehicle speed, dependence on the number of sensor signals and signal quality is reduced, andthe self-adaptive vehicle following function is achieved.
Owner:ANHUI JIANGHUAI AUTOMOBILE GRP CORP LTD

Novel rice seed processing method and production line of rice seeds

The invention belongs to the field of seed processing, and particularly relates to a novel rice seed processing method and a production line of rice seeds. The method comprises the following effectivesteps that a, firstly utilizing wind screening equipment is used to remove most of heavy impurities, large impurities, light impurities or lesion seeds from the rice seeds; b, a vibration sorting machine is used for sorting the rice seeds subjected to wind screening so as to select rice seeds with larger grain diameters, and then excess material is conveyed to a specific gravity separator; c, rice seeds with large grain diameters and large gravity are selected after the excess material is subject to sorting of the specific gravity separator, and then are mixed with the rice seeds selected bythe vibration sorting machine; and d, the mixed rice seeds are conveyed to a packaging machine for packaging completion. According to the novel rice seed processing method, a sorting procedure is added before traditional specific gravity selection is carried out, and a mixing procedure is added before packaging, so that production capacity is greatly improved, and the technical problem that the production line cost is increased due to the fact that production efficiency is low in existing rice seed processing is further solved; and meanwhile, the processing method is reasonable in design, simple, remarkable in effect and suitable for large-scale popularization and application.
Owner:QINGDAO YANUO MACHINERY ENG

Article reading comprehension answer retrieval system and device based on machine learning

ActiveCN111241848ASolve the technical problem of high accuracy but high cost of labeling corpusModerate accuracySemantic analysisMachine learningManual annotationNetwork model
The invention provides an article reading comprehension answer retrieval system and device based on machine learning. The method comprises the steps: extracting keywords of different sentences and question sentences in an article according to a semantic rule, and obtaining core words corresponding to the different sentences and question core words; vectorizing the core words of the sentences and the question core words according to a pre-trained statement model and obtaining core word vectors of the sentences and a question core word vector; calculating the similarity between the question coreword vector and the core word vectors of different sentences according to the cosine distance, and obtaining the similarities of different sentences; judging the similarities of different sentences;and taking sentences with high similarities as training corpora and inputting the training corpora into a neural network combined by a recurrent neural network and a multi-layer perceptron for training to obtain an answer retrieval neural network model. The technical problem of manually annotating corpora in the prior art is solved, machine annotation is generated by adopting a fixed rule, and thetechnical effects of moderate accuracy, no need of manual annotation and cost saving are achieved.
Owner:文灵科技(北京)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products