10results about How to "Simple coding" patented technology

The invention discloses a crowd navigation method of a mobile robot based on a heterogeneous neural circuit strategy, which comprises the following steps: constructing a space-time diagram, and converting original local map data acquired by radar scanning into raster map data; constructing a heterogeneous neural circuit strategy network model and a reward function; inputting the time-space diagram and the raster map data into the heterogeneous neural circuit strategy network model, and outputting the action of the robot with the optimal value in the current environment by the heterogeneous neural circuit strategy network model; building a simulation environment of reinforcement learning interaction to train the heterogeneous neural circuit strategy network model, adopting a parallel PPO algorithm to accelerate the training speed of the heterogeneous neural circuit strategy network model until the training is completed, and applying the trained heterogeneous neural circuit strategy network model to an actual scene. The method has the advantages of higher navigation success rate, lower collision risk and stronger environment perception and modeling capability, and shows excellent performance in highly dynamic and crowded complex scenes.

The invention discloses a drug-target affinity prediction method based on a multi-scale convolutional neural network, and the method comprises the steps: obtaining a sequence of a target protein and an SMILES character string of a drug small molecule, obtaining an SMILES word vector matrix and a protein word vector matrix based on word vector coding, constructing the multi-scale convolutional neural network, carrying out the learning of the SMILES word vector matrix, and carrying out the prediction of the drug-target affinity. The method comprises the following steps: constructing a protein word vector matrix, acquiring chemical and structural characteristics of drug small molecules, constructing a one-dimensional convolutional neural network, learning the protein word vector matrix, acquiring structural characteristics of target protein, and fusing the chemical and structural characteristics of the drug small molecules and the structural characteristics of the target protein through splicing operation. And expressing the fused features as drug-target features, constructing an affinity prediction model, and learning the drug-target features to obtain an affinity prediction value between the drug and the protein. Compared with a graph neural network and a pre-training model, the drug-target affinity can be better predicted, and the prediction capability is better than that of a deep learning method.

The embodiment of the invention provides a single-bus communication method and device, a chip and a medium, and the method comprises the steps: enabling a host to enter an initialization mode after the host confirms that an internal power supply and a clock of a slave are stable; the host sends a wake-up code to the slave within a set time to wake up the slave, and releases the bus to enter a normal communication mode; the host sends a communication signal to the slave through the improved communication frame; after the host receives a response signal of the slave, the host releases the bus, the bus is pulled to a high level from an external pull-up resistor, and the transmission is ended; wherein the format of the improved communication frame comprises ten codes, one code corresponds to one bit, and the ten codes sequentially comprise one start bit, six address bits, one read-write control bit, one data bit and one response bit. A wake-up code is set before communication between the host and the slave, so that the slave is prevented from being mistakenly waken up. According to the communication mode, the coding mode is simplified, the chip area is reduced, and the transmission speed of the chip is also improved.

This invention discloses a data processing method, apparatus, device, and readable storage medium. The data processing method includes acquiring business data from a target business scenario and determining variables used for data transmission during business data processing. Each variable has an information identifier and a value to be determined; the information identifier characterizes the method for determining the variable value. The method inputs the variables and their information identifiers into a data processing model, which includes at least one sub-model. Each determination method has a corresponding sub-model, and different sub-models are required to determine variable values ​​based on different determination methods. The method then determines a target sub-model required to determine variable values ​​according to the determination method represented by the information identifier. Finally, the method runs the target sub-model to determine the variable values. This approach can reduce the complexity of software design.

The present invention discloses a communication method and system, and relates to the field of computer technology. A specific implementation of the method includes: establishing a connection with a partner system based on a TCP / IP information flow interface; after successfully establishing the connection, transmitting messages with the partner system in a preset message structure, wherein, after receiving a confirmation message sent by the partner system, determining that the sequence number of the confirmation message sent by the partner system is the expected sequence number and that the confirmation message sent by the partner system can be processed at present, and then sending an affirmative response to the partner system. This implementation can ensure data integrity and fast consistency processing, after fault tolerance, it can quickly self-recover, simplify message encoding, can quickly detect abnormal devices, effectively release network resources, stable and reliable communication, ensure instruction sequence and reliability, high message interaction security, support multi-threading, reduce development complexity, and avoid unpacking and sticking.

The present invention discloses a wafer-based system and its power state configuration, feedback, and control method, and relates to the field of wafer-level processors. The key points of its technical solution are: including a main controller and a plurality of slave controllers arranged one by one with module groups, the main controller is used to obtain the power state configuration data of each module group through an external interface connected to the main controller for communication, and send it to the corresponding slave controller, or to receive power state feedback data and send it through an external interface; the slave controller is used to send the power state configuration information to the corresponding core grain, or to receive the power state feedback information uploaded by the core grain; the core grain is used to set the power state according to the power state configuration information, or upload the power state feedback information to the slave controller. It is characterized in that it can accurately control the power state of each core grain of the wafer-based system and complete the state feedback, which is safe and convenient, saves hardware resource overhead, reduces system power consumption, and improves the efficiency of power state configuration.

The application provides a quantum dot magnetic fluorescent encoding microsphere and a preparation method thereof. The quantum dot magnetic fluorescent encoding microsphere comprises a parent sphere, N layers of child spheres on the surface of the parent sphere; N is an integer greater than 1; each layer of child sphere only contains quantum dots of one wavelength, and different layers of child sphere contain quantum dots of different wavelengths; the child sphere is connected with the parent sphere through a chemical covalent bond formed by the reaction of carboxyl and amino, and the child sphere is connected with the child sphere of the adjacent layer through a chemical covalent bond formed by the reaction of carboxyl and amino; the synthesis of the child sphere is achieved by taking mesoporous silica nanospheres or solid silica nanospheres as templates, loading quantum dots on the surface of the templates, and then coating silica to obtain the child sphere; the quantum dots of each layer of child sphere are the same, the N layers of child sphere contain m kinds of quantum dots, and m is less than or equal to N. The quantum dot magnetic fluorescent encoding microsphere has a smaller variation coefficient and a higher encoding capacity.

The present invention provides a lateral boundary turbulence synthesis method for numerical simulation of complex terrain wind field, including: determining the microscale calculation domain boundary of the meso-microscale coupling mode, obtaining the lateral boundary surface coordinates of the microscale calculation domain; establishing a mesoscale model simulation of the complex terrain wind field, determining the longitude and latitude and geographic coordinates corresponding to the reference point of the meso-microscale coupling mode; converting the lateral boundary surface coordinates of the microscale calculation domain into the longitude and latitude and altitude corresponding to the mesoscale calculation domain according to the terrain projection mode and the reference point position; extracting the wind speed, temperature and turbulent kinetic energy time series data corresponding to the lateral boundary surface coordinates of the microscale calculation domain from the mesoscale numerical simulation results; synthesizing the lateral boundary turbulence time series pulsating wind speed of the microscale calculation domain for microscale numerical simulation. The present invention improves the simulation accuracy of unsteady flow in complex terrain wind field based on the meso-microscale coupling mode, and is more suitable for the refined evaluation of wind resources in complex terrain.

The invention discloses a CNN-LSTM missing data estimation method based on a sparrow algorithm, and relates to the field of computers, and the method comprises the following steps: carrying out the complementation processing of original missing data based on obtained data; converting the processed data into a three-dimensional data format, and constructing a convolutional neural network-long and short-term memory network model based on the converted three-dimensional data format in combination with a sparrow algorithm; based on a sparrow algorithm, optimizing the number of convolution kernels of a convolution layer of the convolutional neural network, the number of neurons of a long-short-term memory network layer and a learning rate of the convolutional neural network-long-short-term memory network model, and determining an optimal hyper-parameter combination; and based on the convolutional neural network-long and short-term memory network model, comparing the models before and after optimization of the sparrow algorithm, and outputting an optimal estimation completion result. According to the method, the time and space features are extracted from the diet data of the user and are analyzed, so that personalized healthy diet suggestions are provided for the user.

The embodiment of the invention discloses a parameter tree design method and device, electronic equipment and a storage medium. According to the scheme, all parameters in the operation process can be arranged according to a hierarchical structure, the hierarchical structure comprises a root node and child nodes, the child nodes of different hierarchies have a father-child relationship, the hierarchical structure is initialized, the types and numerical values of the father nodes in the hierarchical structure are defined, and the types and numerical values of the father nodes in the hierarchical structure are calculated. And according to the hierarchical structure, defining types and numerical values of sub-nodes in the parameter tree layer by layer to obtain a parameter tree, expressing the parameter tree through a parameter vector, and executing a corresponding operation flow according to the parameter vector. According to the embodiment of the invention, the basic tree structure of the parameters is designed, the characteristics and the calculation mode of the parameter tree are defined, simple modular process design and coding can be carried out according to the characteristics of each node, and the development efficiency is improved.