5results about How to "Reduce idle rate" patented technology

This invention discloses a MaaS dynamic bus route and station planning method and a trip optimization method based on spatiotemporal clustering. The MaaS algorithm based on spatiotemporal clustering, within a defined boundary area of ​​no more than 25 square kilometers, determines bus routes and stops based on existing public transport demand where both origin and destination are within this area, according to established spatiotemporal clustering rules. It then returns the determined bus routes, stops, and estimated arrival times to passengers using the planned bus routes and stops. The application of this invention maximizes the convenience of public transport, reduces unnecessary waiting time and connection distances, increases bus occupancy rates, reduces the probability of empty bus runs, and minimizes stops at unnecessary stops, thereby improving operational efficiency.

The application discloses a new energy heavy truck cargo matching system and method based on battery health, and relates to the technical field of truck cargo matching.The method comprises the following steps: based on current battery data of a vehicle, a dynamic transport capacity image is constructed and the maximum cumulative operating mileage of the day is predicted; according to the current SOC, the cumulative operating mileage of the day and the cargo weight to be matched, the equivalent endurance capability is determined by referring to the cargo weight sensitive factor corresponding to the energy consumption level of the to-be-matched route; the upper limit of the available mileage is determined in combination with the remaining available quota; the round-trip energy consumption characteristic value of the to-be-matched route is extracted and the estimated energy consumption mileage is calculated; the available mileage upper limit, the image and the route energy consumption level matching and the cumulative discharge depth corresponding threshold are pre-screened, and the qualified ones are included in the feasible route set; the total number of trips of the screened orders is controlled, and the orders are sorted and pushed according to the image adaptation degree and the historical matching success rate of the route.

The application relates to the field of encrypted data collaborative processing, and discloses a privacy protection-oriented encrypted data collaborative processing system and method, wherein the privacy protection-oriented encrypted data collaborative processing method comprises the following steps: converting clear data of each subject into cipher text through secure multi-party computation, and accessing a system through a trusted execution environment; performing parallel computation on the cipher text data through a privacy computation special acceleration chip of a Chiplet architecture; combining a chip and a software platform to integrate a national encryption algorithm, an international standard algorithm and a federal learning framework, and constructing a cipher text computation processing environment; uniformly scheduling chip and memory resources through a privacy computation all-in-one machine server, forming a cipher text computation resource pool; homomorphically decrypting the computation result, and outputting the decrypted data to a user through a unified operation interface and a data flow circulation platform to generate a decrypted structured data set. The application has the advantages of improving computation efficiency and reducing operation cost.

This invention belongs to the field of agricultural machinery operation scheduling technology, specifically involving an agricultural machinery operation scheduling method, system, equipment, and medium based on EDIM and NMPD, which can balance uncertainty modeling, high-quality scheduling solution capabilities, and engineering feasibility. This invention achieves a dynamic adaptive balance between global exploration and local development through the directional guidance of the EDIM mechanism and the multi-level neighborhood mining of the NMPD mechanism, effectively avoiding premature convergence. This allows for the generation of scheduling schemes with significantly shorter total travel distances in various real-world farmland scenarios, resulting in a significant improvement in operational efficiency. The system of this invention, by integrating the core optimization engine of the aforementioned scheduling method, can automatically process large-scale farmland and agricultural machinery data and output high-quality scheduling schemes with low empty-running rates.

This invention provides a method for dynamic urban renewal based on deep reinforcement learning, relating to the field of urban renewal. The method includes: step S1, data acquisition; step S2, state prediction; step S3, hierarchical decision-making; step S4, execution feedback; and step S5, iterative optimization. Hierarchical decision-making, based on the urban state data in step S1 and the predicted state in step S2, implements hierarchical update schemes for macro-level, meso-level, and micro-level intelligent agents. This method transforms urban renewal from a one-time static planning process to dynamic adaptive decision-making that evolves with the urban system, thereby achieving dynamic adaptation of infrastructure and public services and avoiding negative impacts such as environmental damage, facility idleness, resource waste, and increased costs caused by mismatch.