60 results about "Object search" patented technology

Provided in the present disclosure are a commodity object search method and apparatus, and an electronic device and a storage medium. According to the embodiments of the present disclosure, on the basis of a search request triggered on the basis of a client, search basis data for searching for a commodity object may be acquired first; then, on the basis of the search basis data, a first prompt word corresponding to a commodity object search scenario is generated, and interaction with a large language model is performed by means of the first prompt word, so as to obtain search intent information corresponding to the current commodity object search; and finally, on the basis of the search basis data and the search intent information, a second prompt word corresponding to the commodity object search scenario is generated, and interaction with the large language model is performed by means of the second prompt word, so as to obtain a search result corresponding to the current commodity object search. By using the solution, interaction can be performed with a large language model, so as to deeply analyze and understand a search intent of a client user in searching for a commodity object, and provide a more accurate commodity object recommendation scheme on the basis of the search intent.

The invention discloses a household robot article searching method and system based on a multi-source pre-built map, and the method comprises the following steps: S1, controlling a household robot to move in a household scene through employing an autonomous synchronous positioning and mapping technology, obtaining environment data obtained by a multi-source sensor carried by the household robot, and storing the environment data in a database; constructing an environment map fusing the ground occupation information and the overlook visual information, wherein the environment map is used as a multi-source pre-established map for subsequent article search; s2, calculating three types of scores of each landmark in the home scene; calculating the comprehensive score of each landmark according to the three types of scores of each landmark, and selecting the first K landmarks with the highest comprehensive score to construct an associated landmark set; and S3, in combination with the multi-source pre-established map and the associated landmark set, constructing a high-low layer collaborative target exploration mechanism, and realizing layer-by-layer reasoning from region planning to action execution. According to the method, the semantic reasoning result is accurately sent to the ground, the actual navigation behavior is driven, and the accuracy of target positioning and the efficiency of path planning are improved.

Embodiments of the present application provide a data retrieval method, device and equipment and storage medium, relating to the technical field of data analysis. The method comprises: in response to a retrieved request, determining a target search term and a request object; based on an object search term library corresponding to the request object and a pre-constructed business system search term library, performing word segmentation processing on the target search term respectively, and based on the word segmentation processing result corresponding to the business system search term library and a pre-set priority label, establishing a corresponding search index; and based on the business system corresponding to the request object, the word segmentation result obtained based on the object search term library and the search index, obtaining a search result. The embodiments of the present application solve the problem that the search result cannot meet the user's expectation when the search engine searches diversified data in the prior art.

An image search device includes at least one processor and at least one memory storing instructions, where, by executing instructions stored on the at least one memory, the at least one processor is configured to: receive a plurality of images and a plurality of metadata from a plurality of camera devices through a communication interface; receive an object search command and a property search command inputted by a user; extract objects corresponding to the object search command based on the plurality of metadata, and extract properties of the extracted objects; generate a search interface including a property search menu which displays a list of the extracted properties for selection through the property search command; and display the generated search interface, where, based on the object search command being changed, the properties displayed in the property search menu are changed in the search interface according to the changed object search command.

The invention discloses an intelligent object searching and cleaning method based on SLAM and RRT technologies, belongs to the technical field of intelligent robots, and aims at solving the problems that an existing product is single in function, poor in environmental adaptability, low in intelligence and lack of industrial standards. The robot comprises an object searching module, a cleaning module, a control module, an interaction module and an industrial standard adaptation module, the object searching module achieves differentiated grabbing through multi-sensor fusion, SLAM + improved RRT navigation and optimized YOLOv5s recognition in cooperation with a replaceable mechanical arm, the cleaning module comprises a replaceable cleaning assembly and a material self-adaption and stain detection unit, a robot body is designed in an IP67 waterproof and foldable mode, the robot body is adapted to a wet / narrow space, and the robot body is provided with an intelligent control module. The interaction module achieves real-time control through APP dual connection and H.265 low-delay video transmission, indexes are standardized through modularization, and a valuables payment mechanism is established. Cleaning and object searching are integrated, the object searching efficiency is improved, the coverage rate of cleaning blind areas is high, the robot is suitable for family and commercial scenes, industry standardization is promoted, and the robot has high practicability and market value.

The invention discloses an unknown environment-oriented household robot article searching method and system, and belongs to the technical field of robots. The method comprises the following steps: constructing a multi-dimensional map comprising a semantic map, a historical track map and a visual correlation map; evaluating and determining an optimal leading-edge exploration point based on a perception-prior-behavior multi-dimensional scoring mechanism; carrying out local path planning by using a fast marching method, and generating a navigation action to realize autonomous navigation; and judging the existence of the target object through a dual verification mechanism combining semantics and vision. According to the system, by fusing a multi-dimensional map and a multi-dimensional scoring strategy, the efficiency, the success rate and the intelligent level of article search of the robot in an unknown home environment are remarkably improved.

The invention discloses an object searching and lighting system and method based on Bluetooth AOA positioning, and relates to the technical field of Bluetooth positioning, the system comprises a Bluetooth tag module, the Bluetooth tag module is installed on a target object, a low-power-consumption Bluetooth chip is arranged in the Bluetooth tag module, and the Bluetooth tag module is used for periodically broadcasting unique ID information; and a positioning base station array module, wherein the positioning base station array module is deployed in an indoor environment. According to the system, Bluetooth AOA positioning and multi-mode feedback are integrated, accurate object searching guiding is achieved, the coordinates of an object are calculated through AOA positioning, six-color light and a buzzer are combined, and the feedback mode is dynamically adjusted according to the distance; a sleep wake-up mechanism reduces power consumption and improves equipment endurance; a multi-base station synchronization and Kalman filtering algorithm supports multi-label concurrent positioning, and the anti-interference capability is enhanced; direction deviation prompting and shielding response are realized, object searching experience in a complex environment is optimized, and the low-power-consumption and high-efficiency intelligent object searching system is constructed.

The embodiment of the invention provides an object search method, a display method, equipment, a storage medium and a program product, and the method comprises the steps: determining a target image provided by a user in response to an object search request; identifying a first object from the target image, and identifying object features of the first object; searching at least one second object which meets a matching requirement with the first object according to the object characteristics; and outputting a search result of the at least one second object. According to the technical scheme provided by the embodiment of the invention, the object searching efficiency and accuracy are improved.

The disclosure relates to an interaction method and apparatus, an electronic device, and a storage medium. The method includes: displaying a video playback page, where the video playback page is used for playing a target video, and the target video is associated with a target object; displaying a target object search result display page and / or a guidance page if first operation information on the video playback page by a user satisfies a preset trigger condition and a target object search instruction is collected, where the guidance page includes search prompt information, and the search prompt information is used for showing an entry into the target object search result display page; and the target object search result display page is used for displaying search results related to the target object.

The invention relates to an object searching method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps of obtaining at least one target historical selected object associated with a target search term; based on the target search word and the target historical selected object, extracting to obtain an information inquiry intention corresponding to the target search word; at least one information object and an information providing intention corresponding to the information object are obtained, the information providing intention is extracted based on a target historical search word corresponding to the information object, and the information object is a historical selected object associated with the target historical search word; and based on the target search word, the information inquiry intention, each information object and the information providing intention of each information object, determining the matching degree of each information object and the target search word. By adopting the method, the search accuracy can be improved.

The invention discloses a communication method, device and system, a storage medium and a program product. The method comprises the following steps: a second device receives a request or a trigger message for acquiring position information of a first environment Internet of Things device from a third device; the second device sends an acquisition instruction of the position information of the first environment Internet of Things equipment to the first device according to the request or the trigger message; the first device sends position information of the first environment Internet of Things equipment to the second device according to the acquisition instruction; and the second device sends the position information of the first environment Internet of Things equipment to a third device. According to the scheme of the invention, the second device can obtain the position information of the first environment Internet of Things equipment through the first device, thereby achieving the object searching and positioning based on the Internet of Things, and improving the positioning accuracy.

This application discloses a smart home system based on security technology, relating to the fields of smart home and smart elderly care technology, including: a terminal acquisition layer, a network edge computing layer, a cloud platform layer, and an interactive application layer; the terminal acquisition layer integrates elderly care wristbands, environmental sensors, fall radar, smart cameras, door magnets, positioning tags, and companion robots; the cloud platform layer deploys a data fusion engine, an AI big data model, a video analysis module, and a positioning service engine. This invention achieves functions such as health anomaly monitoring and medication reminders, environmental safety early warning and automatic control, anti-wandering voice reminders, dangerous area protection, real-time positioning of people and objects, multimodal fall detection, voice control of home appliances and monitoring of abnormal electricity use, intelligent object search, AI big data model video retrieval, and community-linked missing person search. Through multimodal data fusion and AI big data model-driven interaction, it achieves proactive smart monitoring of the elderly's lives, improving the level of intelligence in elderly care monitoring and the user experience.

The invention belongs to the technical field of mobile object cooperative control and path planning, and particularly relates to a heterogeneous multi-agent mobile object search and rescue planning method and system. According to the method, a search and rescue task is completed by searching a moving object, confirming the moving object and rescuing the moving object through partition cooperation and a dynamic task allocation mechanism. The heterogeneous division and partition strategy avoids duplication of labor and resource conflicts, and specialized division of labor enables various mobile objects to exert the maximum efficiency.

The invention provides an interaction control method and device for object display and electronic equipment. The method comprises the steps that in response to a rolling control instruction, an object display area is controlled to display a plurality of virtual objects in a rolling mode; the rolling speed of the virtual object is obtained, and an object search control matched with the rolling speed is displayed; wherein the object search control is used for searching virtual objects in a specified attribute range of specified object attributes; the range size of the specified attribute range is matched with the rolling speed; and in response to a trigger instruction for the object search control, displaying the virtual object in the specified attribute range in the object display area. In the mode, after the multiple virtual objects are controlled to be displayed in the object display area in a rolling mode, the object search control is displayed in the object display area according to the rolling speed of the virtual objects, and the specified virtual object can be displayed in the object display area after the object search control is subjected to the triggering operation, so that the efficiency of searching the specified object is improved, and the user experience is improved. And the interactive experience of players is improved.

The application belongs to the technical field of computer communication, and particularly relates to an object search method and device, a computer readable medium and an electronic device. The method comprises the following steps: obtaining an object search request initiated by a current subject for an unrelated object, the current subject being an object entity registered on a current communication platform, and the unrelated object being another object entity which has not established a data communication association relationship with the current subject; searching for a target object matched with the object search request in a first object database and a second object database respectively; the first object database is used for recording object entities registered on the current communication platform, and the second object database is used for recording object entities registered on another communication platform which performs data communication with the current communication platform. The application realizes cross-platform user search, widens the search range of users, and improves the search efficiency of users.

The invention relates to the technical field of intelligent robots with bodies, and provides a semantic object searching navigation method, system and device based on multi-sensor fusion and a storage medium. The method comprises the following steps: in a process of constructing an environment map, positioning and identifying an article by fusing radio frequency identification (RFID) perception information and 3D visual perception information to obtain identification information, multi-semantic attribute information and spatial position information of the article; marking the identification information, the multi-semantic attribute information and the spatial position information of the article as points of interest in an environment map; in response to a received object searching instruction, analyzing the object searching instruction to determine a target object, and matching a target interest point corresponding to the target object from the environment map; performing path planning according to the position of the target interest point, and controlling the robot to move to the position of the target object. According to the method provided by the invention, the positioning precision and stability are improved, and high-precision autonomous object searching navigation from the object searching instruction to the accurate arrival of the target object position is realized.

This invention relates to the field of motion trajectory tracking technology, specifically to a method and system for object motion trajectory tracking based on visual features. The method includes: acquiring continuous target object search image information and target object template image information based on an object motion video stream; performing information interaction processing on template features and search features; obtaining candidate predicted target object bounding boxes based on temporal features and the information-interacted search features; determining whether the candidate predicted target object bounding boxes meet the selection accuracy requirements based on the average coverage of the candidate predicted target object bounding boxes; extracting 3D point cloud data of the target objects within the predicted target object bounding boxes; performing inverse density sampling processing on the 3D point cloud data to obtain a set of points to be processed; and generating an object motion trajectory vector based on the set of points to be processed. This method can improve the accuracy and robustness of object motion trajectory tracking.

It is often desirable to perform a search for objects in a scene. Specifically, it is useful to determine whether objects are located within a search area and / or to identify the nearest objects to a search point. Ray tracing systems have capabilities that are nearly sufficient to perform such a search. For instance, ray tracing systems build acceleration structures such as bounding volume hierarchies (“BVHs”) that help to accelerate the evaluation of a ray. These BVHs are also useful for performing object searches. Ray tracing hardware includes functionality related to performing a ray-box test, which can be adapted for searching whether an object is within a search area. Ray tracing hardware also includes functionality related to instances. In ray tracing, instances are copies of geometry, with an instance transform (e.g., scale, shear, rotation) applied. As objects being searched for may be instances, the instance-related functionality is useful for object searching.

This invention provides a weakly supervised object detection method and system for images, comprising: feature extraction from the input image; performing self-refining enhancement features; extracting suggestions from the input image; extracting region features of the suggestions through an ROI Pooling layer; applying a fully connected layer to the region features to obtain a feature matrix; performing softmax and element-wise product on two different dimensions, class and suggestion, respectively, to obtain all suggestion scores; and obtaining the image score on class c. The suggestion score is associated with a saliency prior module, a multi-object search method, a refinement branch, a bounding box regression branch, and an area-guided weighting strategy. This invention directly uses the original image for training, effectively training an end-to-end object detection model without introducing additional high-complexity models into the main network; and it significantly outperforms existing algorithms in detecting non-rigid targets.

The invention relates to the field of intelligent glasses, in particular to an object searching method of intelligent glasses, electronic equipment and a storage medium. The method comprises the following steps: in response to an instruction of searching a target article by a wearer, obtaining pre-stored position information of the target article; and according to the position information, determining a first space where the target object is located and the position of the target object in the first space, and indicating the wearer.

Embodiments of the present application provide a similar object determination method and device, electronic equipment and storage medium, belonging to the field of artificial intelligence. The method comprises: obtaining candidate characteristic values of multiple object attributes for each candidate object respectively; determining data distribution information of the object attributes according to the candidate characteristic values; sorting the multiple object attributes according to the data distribution information to obtain attribute sorting information; obtaining target characteristic values of the multiple object attributes of a target object, expanding the target characteristic values of the object attributes of the target object in turn according to the attribute sorting information, and obtaining at least one target characteristic range of the object attributes; and matching the target characteristic values of the at least one target characteristic range and the target characteristic values not expanded with the candidate characteristic values of the corresponding object attributes, and determining a similar object of the target object from the multiple candidate objects according to a matching result. The embodiments of the present application can determine key information affecting similar object searching, and improve the explainability and accuracy of the determination method.

The invention discloses an intelligent liquid cup, system and method, and belongs to the field of intelligent home and auxiliary appliances. According to the intelligent cup, a multi-sensor fusion control system and a multi-mode man-machine interaction mechanism are integrated aiming at three pain points of difficulty in object searching, difficulty in alignment and difficulty in sensing when a visually impaired person pours liquid; the system comprises an article positioning subsystem which is realized through voice wake-up and sound vibration linkage; the cup mouth guiding subsystem is used for detecting liquid inflow based on an infrared light curtain and triggering guiding; the liquid level sensing subsystem is used for monitoring the liquid level in real time by adopting a Hall sensor and a magnetic floater and providing tactile feedback through the linear change of the vibration frequency; and a temperature sensing and early warning subsystem. The full-flow closed-loop guidance from cup searching, alignment, dumping and cup filling is realized, and the safety, independence and user experience of operation are remarkably improved through complementary feedback of touch and hearing.

The invention discloses an object identification and early warning method and system for a public transport site, and the method comprises the steps: obtaining an original image of an object at a preset position of the public transport site, recognizing the state features of the object, and generating a feature tag of the object; synchronously uploading the feature tag to the user side and the platform side; according to an object search request initiated by a user side, determining a historical motion record of the user side, so as to extract a motion image of the user side in a public traffic place from a platform side, and determining an abnormal event of an object in combination with a feature tag; and according to the local environment image during the occurrence period of the abnormal event, possible transfer path information of the object is identified, so that an early warning notification message is sent to a related edge end subordinate to the platform end. According to the method, the feature tag of the object in the original state is identified, the object is traced and identified in combination with the historical motion condition, the possible space transfer condition of the object is positioned, and reliable, timely and accurate object identification is realized by using a distributed tracking search mode.

Provided in the embodiments of the present disclosure are an information interaction method and apparatus, an electronic device, a storage medium and a program product. The information interaction method comprises: in response to an object search request, acquiring object search information corresponding to the object search request, and displaying a live stream entry of at least one live stream associated with the object search information, livestream presenting objects associated with the live stream comprising target search objects associated with the object search information; in response to an entry triggering operation for the live stream entry, displaying a live streaming page of the live stream corresponding to the triggered live stream entry; and when the number of the target search objects reaches a preset number, receiving an object display request by means of the live streaming page, displaying in the live streaming page an object presenting page, and displaying in the object presenting page search feedback information corresponding to the target search objects.

In one aspect, a first device includes a processor assembly and storage accessible to the processor assembly. The storage includes instructions executable by the processor assembly to access a semantic map, receive input from a first camera on an Internet of things (IoT) device, and update the semantic map based on the input.

The invention discloses an object searching method and device, and the method achieves the targeted release and privacy isolation of object searching information through the classification of public information and encrypted information of the object searching information, avoids the leakage of the privacy information of a searched object, guarantees the privacy right of the searched object, and improves the privacy of the searched object. The infringement risk of the first user is reduced; an information verification mechanism ensures that the encrypted information can only be accessed by the second user meeting the condition, so that the exclusive right and the security of information access are guaranteed; meanwhile, the publication of the public information on the preset platform can attract more attention to assist in searching the searched object, the exclusive access of the encrypted information ensures the privacy of the core information, and finally, the accuracy and the efficiency of searching the searched object are improved on the premise of not leaking the privacy, so that the user experience is improved. And the dual requirements of the first user for spreading the object searching information and efficiently searching the searched object on the basis of privacy protection are met.

The invention discloses a dynamic environment object searching method based on common sense and memory enhanced reasoning, and belongs to the technical field of robot object searching. The method comprises the steps that a robot obtains an article search task and historical interaction data input by a current user; rGB-D images of the surrounding environment are collected in real time, and various object instances are recognized; establishing a functional three-dimensional scene graph comprising a container layer, a movable object layer and a region layer according to the detected environment and object information; a hierarchical action space comprising a macroscopic level and a microscopic level is designed, a macroscopic action planning cue word is input into LLM according to current scene information, and the optimal next-step action of the robot is obtained; and repeating the steps until the task is completed or failed. According to the method, functional three-dimensional scene graph construction, layered action planning and a dynamic environment response mechanism are organically combined, and efficient target searching in a dynamic environment can be achieved.

A method and system for task planning for visual room rearrangement under partial observability is disclosed. The system or the robotic agent utilizes a visual input to efficiently plan a sequence of actions for simultaneous object search and rearrangement in an untidy room, to achieve a desired tidy state. Unlike search networks in the art that follow ad hoc approach, the method discloses a search network utilizing commonsense knowledge from large language models to find unseen objects. A Deep RL network used for task planning is trained with proxy reward, along with unique graph-based state representation to produce a scalable and effective planner that interleaves object search and rearrangement to minimize the number of steps taken and overall traversal of the agent, and to resolve blocked goal and swap cases. Sample efficient cluster-biased sampling is utilized for simultaneous training of the proxy reward network along with the Deep RL network.

The application discloses an orphan object searching method and device and a readable storage medium, and is applied to the field of data processing. The orphan object searching method provided by the application finds out a head object by traversing a storage pool where the head object is located, acquires metadata of the head object, finds and records a tail object having the corresponding head object according to the metadata of the head object. Then, the tail object is found out by traversing a storage pool where the tail object is located, tail objects having the corresponding head objects are filtered out, and the remaining tail objects are determined as orphan objects. Because the corresponding tail object can be found according to the head object, and the corresponding head object cannot be found according to the tail object, the scheme finds the head object and the tail object having the corresponding relationship through the head object first, and the tail objects are normal tail objects. Then, the normal tail objects are filtered out from all the tail objects, and the remaining tail objects are orphan objects. Compared with the original scheme, the application reduces invalid comparison and improves the searching efficiency of the orphan objects.

The invention provides a device searching method based on a LoRa technology, a scanning device and a terminal device. The device searching method comprises the following steps: starting a Sub-GHz LoRa mode to carry out scanning operation, and obtaining an RSSI correction value corresponding to each terminal device; the target terminal device and the target RSSI correction value of the target terminal device are matched from the plurality of terminal devices based on the target device ID of the target terminal device, and under the condition that the scanning device moves forwards along the current direction, if the target RSSI correction value is greater than or equal to a preset RSSI threshold value and the current distance is greater than or equal to a first preset distance threshold value, the target RSSI correction value of the target terminal device is determined to be the target RSSI correction value of the target terminal device. And if so, switching to the 2.4 GHz LoRa mode to search the target terminal equipment. Through dual-frequency cooperative work of the Sub-GHz LoRa and the 2.4 GHz LoRa, the object searching problem in different distance ranges is solved, the object searching automation degree is high, and the object searching efficiency is remarkably improved.