25 results about "Shared space" patented technology

The invention relates to the technical field of intelligent lighting control, in particular to a multi-user sharing-oriented self-adaptive lighting intelligent identification control method, which comprises the following steps of: identifying user identities through a multi-user feature identification system, acquiring historical use habit data, generating personalized lighting parameters based on the data and current environment data, the group preference learning system constructs similar user clusters to optimize shared space illumination; the conflict adjustment system identifies and processes multi-user demand conflicts; the priority distribution system dynamically adjusts user control authority; the feedback learning system obtains user feedback, calculates satisfaction, updates a preference model and continuously optimizes an illumination control strategy; intelligent lighting control based on user features and group preferences is achieved, conflict processing and continuous learning capabilities are achieved, rapid and accurate recognition of users is achieved through a face recognition technology, lighting parameters are automatically adjusted in combination with historical use habit data, and personalized lighting experience is provided; dynamic changes of user demands are captured, and the accuracy of illumination scene recommendation is improved.

The invention discloses a spatio-temporal context-based multi-vehicle collaborative fusion sensing method. The method comprises the following steps of: firstly, acquiring a large-scale open collaborative sensing data set; secondly, inputting metadata in the data set into a metadata sharing and feature extraction module to obtain feature representation of each vehicle; and then the self-vehicle feature representation and the feature representation of each cooperative vehicle are respectively input into corresponding neighborhood space-time modules, two hidden states are output, the hidden states pass through a position embedding input space decoding and communication module, and self-vehicle features, cooperative vehicle features, features of the cooperative vehicles in the shared space and features of the self-vehicle in the shared space are output. And finally, aligning and fusing the obtained features through a spatial adaptive fusion mechanism, outputting fused features, inputting the fused features into a regression head and a classification head, and outputting bounding box prediction information and classification prediction information. According to the invention, the automatic driving vehicle can realize more reliable and timely environment perception in a complex scene.

The invention discloses a slow space driving anti-collision early warning method based on a risk field model, and the method comprises the steps: firstly constructing a potential energy field intensity model for static objects and road traffic markings in a slow shared space on an urban non-motor vehicle lane, and then constructing a kinetic energy field intensity model for non-motor vehicles driving on the urban non-motor vehicle lane, a behavior field intensity model is constructed for non-motor vehicle drivers driving on urban non-motor vehicle lanes, then potential energy field, kinetic energy field and behavior field force models in a risk field model are calculated, and finally a comprehensive risk field model is obtained. Based on field force vector analysis, the application path of the potential energy of the risk field in the shared space of the non-motor vehicles is defined, and a conflict evaluation index under the risk field theory is provided on the basis. The index can be used for dynamically identifying potential conflicts, and provides a basis for early warning and intervention of non-motor vehicles.

This invention discloses an emotion-driven multi-region adaptive joint optimization intelligent temperature control method for open spaces. The method includes establishing a correspondence between regions and temperature control execution units, acquiring region state data, calculating the region's emotional stress index and its corresponding confidence level, establishing an inter-regional influence weight matrix to obtain coupled emotional stress indices for each region and determining influence coefficients, constructing a multi-regional joint optimization model, determining whether emotional event triggering conditions are met, solving the multi-regional joint optimization model to obtain the optimal control vector, generating and issuing control commands, and acquiring environmental parameters and temperature control interaction disturbance parameters after execution in the next control cycle, updating the method based on evaluation results. The beneficial effects of this invention are: it can achieve timely, coordinated, and stable temperature control in open, multi-user shared spaces, improving comfort and reducing fluctuations caused by human intervention.

The invention relates to a cross-modal pedestrian re-identification algorithm based on difference information perception, which realizes information matching from positive and negative texts to images by perceiving difference information between pedestrian images in the same id. The influence of different definitions and visual angles caused by limitation of shooting conditions and visual color change and target person integrity caused by environmental factors such as illumination and shielding in a traditional pedestrian re-identification method is overcome, and accurate pedestrian re-identification closer to an actual use scene is realized. According to the algorithm, features are extracted through a large model, a difference information elimination module, a negative text re-screening module and a knowledge accumulation updating module are combined, and precise fine-grained alignment between the features of the two modules is achieved in a shared space. And meanwhile, identity loss, cross-modal matching loss, negative text re-screening loss and knowledge accumulation updating loss are respectively introduced, so that the pedestrian re-recognition performance of the model is effectively improved.

The invention discloses an under-vehicle air braking system and a rail vehicle, and relates to the technical field of vehicle engineering. The under-vehicle air braking system comprises a mounting framework; the brake control module and the mounting framework are sequentially arranged in the first direction; the air path control module is fixed below the mounting framework, and in the first direction, the air path control module is connected to the end, away from the brake control module, of the mounting framework; and the pipeline module comprises a first connecting pipeline, the first connecting pipeline is arranged above the mounting framework, and the two ends of the first connecting pipeline extend downwards to be connected with the brake control module and the gas path control module correspondingly. At least part of the pipeline is distributed above the installation framework, the pipeline can be supported by means of the installation framework, the situation that the pipeline shares space with equipment below the installation framework is avoided, sub-area arrangement of components is achieved, and therefore assembling and overhauling can be more convenient.

The invention discloses an emotion-driven multi-region adaptive joint optimization intelligent temperature control method for an open space, and the method comprises the steps: building a corresponding relation between a region and a temperature control execution unit, and obtaining the state data of the region; calculating a regional emotion pressure index and a confidence coefficient corresponding to the regional emotion pressure index; establishing an inter-region influence weight matrix, obtaining a coupling emotion pressure index of each region, and determining an influence coefficient; constructing a multi-region joint optimization model; judging whether an emotional event triggering condition is met or not, solving the multi-region joint optimization model, obtaining an optimal control quantity vector, generating a control instruction and issuing the control instruction; and acquiring the environment parameters and the temperature control interaction disturbance parameters after execution in the next control period, and performing updating according to the evaluation result. The method has the beneficial effects that the timely, coordinated and stable adjusting effect on partition temperature control can be achieved under the operation environment of an open type multi-person shared space, the comfort is improved, and fluctuation caused by manual intervention is reduced.

The utility model relates to the technical field of outdoor sharing space capsules, and particularly discloses an outdoor sharing-based assembly type space capsule which comprises a bottom plate part, a wall plate part with the bottom end assembled and connected to the top surface of the bottom plate part and a top plate part with the bottom surface assembled and connected to the top end of the wall plate part, and the bottom surface of the bottom plate part is fixedly clamped on a supporting frame; each adjustable supporting leg comprises a bottom supporting plate, a vertical beam with the bottom end vertically fixed to the middle of the top face of the bottom supporting plate, a sleeve arranged on the vertical beam in a sliding and sleeving mode, a spherical shell arranged at the top end of the sleeve, a sphere rotationally arranged in an inner cavity of the spherical shell in a sleeving mode, a connecting column with the bottom end fixed to the top of the sphere and a cross-shaped clamping groove with the middle connected to the top end of the connecting column in a sleeving mode. The cross-shaped clamping groove is fixedly clamped to the bottom of the supporting frame. The problem that the outdoor shared space capsule is inconvenient to level and install is well solved.

The present invention discloses a cross-modal grouping alignment method for integrated multimodal pedestrian re-identification, comprising the following steps: S1, using a shared image feature extractor to extract features from RGB images and sketches, and using a text feature extractor to extract features from texts; S2, using a fusion feature extractor to fuse features of sketches and texts; S3, filtering out redundant features from local features through filtering processing, and then deeply fusing fine-grained features between modalities through a cross-modal domain contrast learning module to achieve fine-grained feature alignment; S4, using a hyperplane constraint module to constrain the distribution of global features of three modalities of the same pedestrian ID in a shared space to a hyperplane; S5, aligning the three modalities through contrast learning of the global features in the same hyperplane, and finally achieving text retrieval of RGB images, sketch retrieval of RGB images, and text fusion sketch retrieval of RGB images.

The article to which this design relates is a monument to be installed in a shared space, etc., as shown in the reference drawings showing the state of use.

The application relates to a non-motor vehicle track reconstruction method in a motor-non-motor shared space, and the method steps comprise the following: extracting an initial track through a CV algorithm; adopting an LSTM to predict and complete a track missing due to occlusion, and matching the track before and after occlusion through a Hungarian algorithm to complete a complete track; adopting a three-layer cyclic social force particle filtering algorithm constructed by integrating a social force model representing non-motor vehicle driving behavior into a particle filtering framework to denoise the completed complete track to obtain a reconstructed track. Compared with the prior art, the application can effectively improve the performance of a video detector in acquiring high-precision track data, provide more fine perception data for a holographic intersection and a traffic control system, and has great application value in the industry.

The application provides a system and method for realizing space diversification of thermal environment based on a single air conditioner, and relates to the technical field of indoor environment regulation, comprising: a positioning module for determining the corresponding relationship between air supply outlets and control areas and inputting the space coordinates of each control area; a calculation module for calculating the initial value of the air supply parameter of each air supply outlet according to the space coordinates in the positioning module and the thermal demand of personnel; an adjustment module for obtaining the initial value of the air supply parameter, making each air supply outlet of the air conditioner start air supply to the control area with the initial value of the air supply parameter, and adjusting the air supply parameter in real time according to the difference between the feedback value and the target value of the control area; and a mixed air module for obtaining the air supply parameter of each air supply outlet in the adjustment module and adjusting the return air ratio of each air supply outlet according to the air supply parameter. The application can realize the purpose of creating different thermal environments in different areas of the same room by using a single air conditioner, and meet the thermal demand of different personnel in the shared space.

The invention discloses a scale adaptive traffic target detection method and device based on roadside multi-mode fusion, and a medium, and belongs to the technical field of intelligent traffic and computer vision. The method comprises the following steps: firstly, extracting multi-scale features of a laser radar point cloud and a camera image, and carrying out geometric alignment through camera parameters; a learnable deep embedded network is used to generate a weight, and deep adaptive weighting is carried out on the image features; then, the weighted bimodal features are mapped to a shared potential space, interaction and fusion are carried out through correlation modeling and an attention mechanism, and layer-by-layer optimization is carried out by adopting a multi-scale cycle strategy; and finally, converting the fusion features into an aerial view for target detection. According to the invention, through deep fusion of depth self-adaptive feature weighting and shared space, the problem that far and near target scales change drastically due to a wide view angle of a roadside scene is effectively solved, and the detection precision and robustness of a full-scale target in a complex environment are remarkably improved.

The invention relates to the technical field of illumination, and discloses an environment design illumination adjustment interaction method and system, and the method comprises the steps: receiving an illumination adjustment instruction sent by a user, and obtaining the task intention of the user based on the instruction; and when the task intentions have conflicts, the system can process the conflicting task intentions so as to obtain and execute the lighting target. According to the method, the problem that in the prior art, illumination demand conflicts in a multi-user shared space are difficult to coordinate is effectively solved, the situation that the illumination environment is unstable due to instruction conflicts is avoided, and the working experience of the users and the trust of the users to the system are improved. Through an intelligent conflict processing mechanism, the stability and comfort of the lighting environment can be ensured, so that the user satisfaction and practicability of the intelligent lighting system are remarkably improved.

The application relates to a cross-modal pedestrian re-identification method and system based on high-order structure modeling, which comprises the following steps: 1) extracting VIS pictures and IR pictures of multiple pedestrians from a data set in pairs to form a VIS-IR picture pair training data set; 2) constructing a cross-modal pedestrian re-identification network model, wherein the cross-modal pedestrian re-identification network model mainly comprises a backbone network for extracting basic features of an image, a short-long range feature extraction module for extracting features in different range scales, a high-order structure learning module for learning high-order structure information in an image, and a shared space learning module for reducing the difference of pedestrians in different modalities; the model is trained by using the training data set to obtain generalizable model parameters; and 3) applying the trained cross-modal pedestrian re-identification network model to cross-modal retrieval to realize pedestrian re-identification between different modalities. The method and system are beneficial to obtaining more stable, robust and accurate cross-modal pedestrian re-identification results.

Embodiments of the present application provide a communication method, a communication system, an electronic device and a readable storage medium, and relate to the field of unmanned driving. The application is applied to a communication system, the communication system comprising a client, a vehicle terminal and a server. The client responds to at least one preset operation being triggered. For each preset operation, a message containing at least one target identifier, a target instruction and a topic identifier is generated according to the preset operation, and the message corresponding to the preset operation is uploaded to the server. The server stores the message in a shared space corresponding to the target topic identifier. The target vehicle terminal acquires the message in response to the storage content of the shared space being updated. If it is determined that the at least one target terminal identifier contained in the message contains the terminal identifier of the target vehicle terminal, the target instruction is executed. The target vehicle terminal is a vehicle terminal subscribing to a topic of the target topic identifier. The application reduces the memory occupation and the end-to-end delay in the communication process.

1. The name of the design product: pavilion (module shared space pavilion). 2. The use of the design product: for building. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The invention provides a vehicle-mounted man-machine interaction method, device and equipment and a storage medium, and the method comprises the steps: shooting environment images through high-definition cameras installed at the head and the tail of a train, and collecting environment data through an integrated sensor; aligning the environment image and the environment data in a shared space at the front end to generate perception information; in the back end, using the first artificial intelligence model to judge the current operation complex condition, calling the matched computing resource according to the current operation complex condition, and using the computing resource to execute the second artificial intelligence model to perform fault prediction based on the perception information to obtain an early warning result; a man-machine interaction mode is set in a vehicle-mounted interface, a detection unit for displaying an early warning result, a blind area detection unit for displaying an environment image and units for controlling train driving are deployed, and the display sequence of the units in the vehicle-mounted interface is adjusted in real time by using an online learning algorithm. A personalized layout adjustment mode is provided, and the flexibility is improved.

1. The name of the design product: intelligent interactive tourism sharing space guide device. 2. The use of the design product: the design product is used for immersive virtual reality interactive tourism experience. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The present application relates to the technical field of AGV car navigation, and relates to an AGV car adaptive navigation method and system, wherein a sensor array installed on the AGV car is used to monitor the environment around the AGV car in real time, sensor data is analyzed by the control system of the AGV car, the actual environmental position of the pedestrian is identified, and the actual distance between the AGV car and the pedestrian at each moving time point is determined; if the actual distance between the AGV car and the pedestrian at a certain moving time point is less than the set minimum comfortable social distance, the moving time point is recorded as a reference time point, and the obstacle avoidance path of the AGV car is automatically planned; finally, the AGV car is navigated and controlled by the control system of the AGV car, and the appropriate social distance can make people feel more comfortable when sharing space with robots, reduce people's nervousness and insecurity, and the AGV car can avoid pedestrians and reduce the risk of collision accidents when sharing the working environment with people, protect the safety of pedestrians, and improve the intelligent level of the AGV car.

The article to which this design relates is a monument to be installed in a shared space, etc., as shown in the reference drawings showing the state of use.

The present invention discloses a method for anti-collision warning in slow-moving spaces based on a risk field model. First, a potential energy field strength model is constructed for stationary objects and road traffic markings in slow-moving shared spaces on urban non-motorized vehicle lanes. Then, a kinetic energy field strength model is constructed for non-motorized vehicles traveling on urban non-motorized vehicle lanes. A behavioral field strength model is constructed for non-motorized vehicle drivers traveling on urban non-motorized vehicle lanes. Then, the potential energy field, kinetic energy field, and behavioral field force models in the risk field model are calculated, and finally, a comprehensive risk field model is obtained. Based on field force vector analysis, the present invention clarifies the application path of risk field potential energy in non-motorized vehicle shared spaces, and on this basis, proposes a conflict assessment index under risk field theory. This index can be used to dynamically identify potential conflicts and provide a basis for early warning and intervention of non-motorized vehicles.

The invention belongs to the technical field of intelligent operation and maintenance of high-speed train transmission, and discloses a high-speed train transmission system fault type inherent characteristic decoupling and generalization diagnosis method, which comprises the following steps of: decomposing a transmission system state into a working condition factor and a type factor; extracting multi-granularity local and global features by constructing patch-level feature adaptive aggregation and learnable condition masks; parallel decoupling branches are constructed, and type factor and working condition factor features are extracted respectively; in a type gene decoupling branch, cross attention based on Earth Mover's Distance is designed, a type factor specific channel is enhanced, and interference of a working condition factor is inhibited. In the online diagnosis stage, only the type decoupler and the classifier are adopted, and robust diagnosis of unknown operation conditions is achieved. Different from an existing field generalization method, the method overcomes the limitation that multi-domain data are forcibly aligned to a single shared space, generalization performance and engineering applicability are improved, and safe operation and maintenance decision making of a train transmission system are facilitated.

The article to which this design relates is a monument to be installed in a shared space, etc., as shown in the reference drawings showing the state of use.

A controller and a method of operating a controller for a shared space air treatment apparatus configured to control air treatment in one or more zones comprises a recognition system operable to identify the presence of a person at a location associated with an air treatment zone of the shared space air treatment apparatus; a comparator operable to compare a stored air characteristic value associated with the person and a sensed air characteristic value associated with the zone; and a transceiver operable to send at least one adjustment instruction to adjust a target air characteristic value for the associated zone based on the comparison of the stored air characteristic value and the sensed air characteristic value.