271 results about "Crowdsourcing" patented technology

A system and method for flexibly incorporating machine learning models into applications using a marketplace platform and distributed computational graph (DCG) architecture. The DCG enables dynamic selection, creation and incorporation of trained models with data sources and marketplaces for data, algorithms, simulation models, ontologies, knowledge corpora, and crowd or expert judgment. Multiple models can be used in series or parallel. An expert judgment marketplace allows human and artificial intelligence (AI) experts to score the accuracy of training data and model outputs. Consumers can select and rank AI agents or experts based on the helpfulness of their judgments. A symbolic knowledge corpora and retrieval augmented generation (RAG) marketplace enables selling access to proprietary datasets as RAGs and knowledge bases. The system includes knowledge corpora and RAG marketplaces with domain-specific components and user experience customization.

The invention discloses a crowdsourcing acquisition map data desensitization method and system based on deep learning. According to the method, a'high-precision map desensitization rule and target sensitivity level table 'is constructed for grading and classifying a to-be-desensitized target, and a desensitization method is specified and comprises a shape type, a privacy type and a character type. For shape type and privacy type sensitive targets in a high-precision map, the positions of the sensitive targets are detected by using a sensitive target detection algorithm based on Faster RCNN, and different desensitization methods are used according to the sensitive levels of the sensitive targets. For character sensitive targets in a high-precision map, all character areas in the map are detected by using a natural scene text detection model I3CL, the text areas are recognized by using a text recognition model SVTR to obtain text contents of the character areas, sensitive characters in the character areas are matched through a sensitive word matching module, and the sensitive characters in the text areas are matched through a sensitive word matching module; and a sensitive area removing model based on LaMa is used for the sensitive character area, and sensitive characters are removed from the graph.

The invention provides a defect image incremental learning method and system under unmanned aerial vehicle cloud-side cooperation, and the method comprises the steps: constructing a distributed cloud-side cooperation power transmission line defect recognition platform, arranging an inference and semi-automatic labeling system at an edge end, and constructing a multi-model incremental training system at a cloud end through a digital twin technology; the center cloud and the edge nodes cooperate with each other, and the labeling efficiency and the model accuracy can be improved through incremental learning. Meanwhile, samples are marked manually or with the assistance of other systems, and then the model is trained in an incremental mode again. If the incremental training model is significantly improved in accuracy compared with an original model, the incremental training model can be deployed to an edge node to update the original model. According to the method, a mechanism is achieved for the assembly line task in a crowdsourcing mode, the semi-automatic labeling task is divided into a plurality of small assembly line tasks, the labeling work is executed more efficiently through assembly line work, and the obtained labeling result is more accurate by integrating the characteristics of different models.

The invention relates to the technical field of network monitoring, in particular to a radio spectrum measurement system based on mobile crowdsourcing, which comprises a crowdsourcing acquisition module, a time sequence processing module, a space optimization module and a dynamic fusion module. According to the method, periodic scanning is combined with a multi-source heterogeneous data encapsulation protocol, timestamps, geographic coordinates, a signal-to-noise ratio and equipment voltage are integrated, multi-dimensional data standardized acquisition and dynamic association are achieved, time sequence weight parameters are calculated through a time sequence alignment algorithm, high and low frequency event distinction degree is enhanced, time noise is restrained, space weight coefficients are calculated through a DBSCAN algorithm, and multi-dimensional data acquisition and dynamic association are achieved. The method has the advantages that comprehensive credibility is generated through linear weighting, space-time coupling precision and evidence theory sorting credibility are improved, correlation between the credibility and the signal-to-noise ratio is analyzed, Kalman filtering is used for compensating voltage fluctuation, multi-source data fusion and error suppression are achieved, spectrum feature anti-interference capacity is enhanced, positioning deviation is reduced, and spectrum allocation efficiency and monitoring system stability are improved.

The invention discloses a cross-modal travel knowledge graph construction system based on a large language model, and relates to the technical field of knowledge graph construction and processing. Comprising a dynamic real-time acquisition and processing module, an intelligent knowledge verification and fusion module, a block chain credible record and multi-source verification module, a self-adaptive update strategy making module and a reinforcement learning optimization module. According to the method, by means of multi-source collection and cloud computing, the average knowledge updating time is shortened from 10 days to 2 days, and the problem of timeliness is solved; crowdsourcing, professional auditing and a model algorithm are combined, the auditing accuracy is improved, and the atlas is ensured to be complete and accurate; the credibility and authority of the knowledge graph are enhanced by applying a block chain technology; a model is established and a strategy is designed according to the multi-dimensional data, so that different user requirements are met; and a reinforcement learning algorithm and a scoring mechanism are introduced, so that the satisfaction degree is increased from 60% to 80%, the practicability is improved, and users are better served.

The present disclosure provides a method and apparatus for automatically producing map data. The method includes: performing track rectification on crowdsourcing tracks based on corresponding standard tracks, and locating each map element included, based on depth information of track point images included in the rectified crowdsourcing tracks; comparing a latest map element obtained based on the rectified crowdsourcing tracks locating and an old map element at a corresponding locating position using a pre-built entity semantic map; determining, in response to a change in the latest map element compared to the old map element, a target processing method according to a processing standard of a changed map element pre-abstracted from a map element update specification; and processing the latest map element according to the target processing method to obtain a processed latest map.

A data processing system for generating training data for a multilingual NLP model implements obtaining a corpus including first and second content items. The first content items are English-language textual content, and the second content items are translations of the first content items in one or more non-English target languages. The system further implements selecting a first content item from the first content items, generating a plurality of candidate labels for the first content item by analyzing the first content item with a plurality of first English-language NLP models, selecting a first label from the plurality of candidate labels, generating first training data by associating the first label with the first content item, generating second training data by associating the first label with a second content item of the second content items, and training a pretrained multilingual NLP model with the first training data and the second training data.

A crowdsourced energy system includes a plurality of distributed energy resources managed by crowdsourcees of the system, a power network to which the distributed energy resources are connected, and a system operator that manages energy trading transactions and energy delivery within the system, the system operator operating at least one computing device configured to: obtain day-ahead peer-to-peer energy trading transaction requests from crowdsourcees for energy to be delivered from the distributed energy resources, estimate day-ahead energy load and solar forecasts, determine optimal power flow for the delivery of energy, and schedule delivery of energy from the distributed energy resources across the power network based upon the energy trading transaction requests, the estimated forecasts, and the determined optimal power flow.

The invention belongs to the technical field of fresh food delivery, and particularly relates to an intelligent fresh food delivery system and method based on the Internet of Things, and the method comprises the following steps: step 1, collection of a fresh food delivery technology, step 2, construction of a delivery model, step 3, edge AI quality detection, step 4, group intelligent crowdsourcing delivery, and step 5, interaction and feedback. And step 6, system optimization and a feedback mechanism. Through the Internet of Things technology and the digital twinborn model, a large amount of data is collected and analyzed in real time, data-driven decision support is provided for enterprises, future delivery requirements are predicted according to historical order data and market trends, inventory management and resource allocation are optimized, the quality of fresh food is detected in real time through edge AI equipment, and the quality of the fresh food is improved. By combining the dynamic optimization function of the digital twin model, potential problems can be found and processed in time, the loss rate of fresh products in the distribution process is remarkably reduced, and social resources are efficiently utilized through a swarm intelligence algorithm and a crowdsourcing distribution network.

Provided in the present application are a road network construction method and apparatus, and an electronic device. The method comprises: acquiring crowdsourced trajectory information and environment sensing information; processing the crowdsourced trajectory information in layers on the basis of a plurality of preset height ranges, so as to obtain a crowdsourced trajectory corresponding to each preset height range; for each preset height range, constructing a corresponding region image on the basis of the corresponding crowdsourced trajectory and corresponding environment sensing information; performing image recognition on the region image, so as to obtain a regional road network within the preset height range; and connecting regional road networks within the plurality of preset height ranges, so as to obtain a target road network. In the method provided in the present application, by means of processing crowdsourced trajectory data in layers, a regional road network in each layer can be determined on the basis of crowdsourced trajectory data and environment sensing information that correspond to each layer, and then a road network is obtained by means of connecting regional road networks in layers, thereby improving the accuracy of the road network.

The invention provides an indoor positioning method and an indoor positioning system for multi-modal data fusion based on RMLICT. The method comprises the following steps: firstly, in a mapping stage, constructing a fingerprint map from unbalanced crowdsourcing trajectory data; in the off-line stage, track data enhancement, dimension reduction and clustering processing are carried out. In the on-line positioning stage, direction matching filtering is firstly carried out, and then the mapping relation between the RSS signal and the single-step motion is established by using enhanced particle filtering. According to the method, by optimizing data preprocessing and adopting an advanced particle filtering algorithm, the positioning precision and robustness are improved, the real-time performance of the system is remarkably improved, and the method is suitable for various complex indoor environments such as scenes with serious multi-path effects and signal shielding.

The invention discloses a differential privacy-based multi-dimensional dynamic load balancing scheduling scheme (DP-DMAPSA), which is constructed on a DPDK framework and is oriented to high-concurrency scenes such as a security crowdsourcing platform and the like. According to the scheme, multi-dimensional indexes such as queue depth, CPU utilization rate and processing delay are introduced, differential privacy mechanisms such as Laplacian and Gaussian are combined, noise disturbance is performed on load data, and reasoning attacks are prevented. In scheduling, the system dynamically selects a processing core according to a weighted hash value and a privacy index to realize flow consistency and load balancing. Meanwhile, a self-adaptive sub-flow granularity adjustment mechanism is designed, dynamic adjustment can be carried out along with flow and load changes, and the scheduling precision and the resource utilization rate are improved. Experimental results show that the scheme improves the system throughput while guaranteeing the data privacy, and is suitable for scenes of security crowdsourcing, data centers, edge computing and the like.

The invention discloses a space crowdsourcing task allocation regulation and control method for crowd-sourcing cooperative service, and provides a model ACPtrNet based on deep reinforcement learning. The model not only can consider the benefits of a task requester, a crowdsourcing worker and a crowdsourcing platform at the same time, but also combines the advantages of the powerful function fitting capability of deep learning and the decision-making capability of reinforcement learning. The ACPtrNet generates a worker-task matching degree by using an Actor network based on a pointer network, and calculates a real reward value; using a Critic network based on RNN and an attention mechanism to predict an award value which can be obtained by the Actor network; actor and Critic are mutually guided, and strategy gradient descent and stochastic gradient descent are respectively used for parameter updating. Finally, the Actor network can generate a reliable worker-task matching degree, and the task with the highest matching degree with the worker is allocated to the worker. The space crowdsourcing task allocation method has the advantages of being general and suitable for task allocation of multiple scenes in space crowdsourcing.

The invention discloses a policy information crowdsourcing-oriented multi-level verification system and method, and relates to the technical field of data verification. A data source verification module; a content identification module; a distributed consensus verification module; and an abnormal behavior detection module. According to the policy information crowdsourcing-oriented multi-level verification system and method, the problem of data authenticity verification in government policy information crowdsourcing is solved, a four-level cascade protection framework is adopted as the core, and through four-level verification of data source verification, content identification, distributed consensus verification and abnormal behavior detection, the data authenticity verification efficiency is improved. The authenticity and compliance of the government policy information crowdsourcing data are ensured, the efficient, low-delay and anti-cheating system performance is achieved through algorithm optimization, and finally the core targets of 95% verification accuracy, 90% cheating detection rate and the like are achieved.

The invention discloses a data processing method and device for map construction, equipment and a medium, and relates to the technical field of crowdsourcing maps, and the method comprises the steps: obtaining a local vectorization semantic map of a vehicle driving on a target road section, and a historical crowdsourcing map corresponding to the target road section; the local vectorization semantic map is constructed based on sensor data collected by a sensor of the vehicle, and the sensor data comprises positioning data, sensing data and sensor parameters of the vehicle; obtaining a first confidence coefficient and a second confidence coefficient based on matching alignment processing of the historical crowdsourcing map and the local vectorization semantic map; based on the first confidence coefficient and the second confidence coefficient, determining whether to collect a processing strategy of target data for constructing a global crowdsourcing map, the target data including a local vector semantic map and positioning data; therefore, the data for crowdsourcing map construction can be accurately, economically and efficiently collected, the data volume is reduced, and the crowdsourcing map construction efficiency is improved.

The application relates to a semantic map updating method, device and computer storage medium. The method comprises the following steps: when a corresponding semantic map exists in an updating collection area, determining a first point cloud object of a crowd-sourced map newly collected by the collection area and corresponding first semantic information; when a matching point cloud object exists in the semantic map and matches the first point cloud object, obtaining second semantic information of the matching point cloud object; performing semantic average processing on the first semantic information and the second semantic information to obtain average semantic information of an updated point cloud object; and updating the semantic map according to the average semantic information. The method can improve the map updating precision.

The invention provides a confidence-guided adaptive graph representation reinforcement learning method, equipment and a medium, and relates to the technical field of label prediction and electric data processing. The method comprises the following steps: acquiring a crowdsourcing data set composed of multi-source heterogeneous electronic data, and inputting an adaptive graph representation learning model; mapping the crowdsourcing data set to construct an original bipartite graph; based on the original bipartite graph, generating a trimmed view and an enhanced view through dynamic confidence trimming and conservative edge addition; performing feature extraction, adaptive information enhancement and learning on the worker node and the task node through a dual-channel heterogeneous adaptive network, and performing prediction through a predictor to obtain an initial prediction label; and in combination with the original bipartite graph, performing label correction on the initial prediction label to obtain a final prediction label. The method can effectively suppress noise interference, capture local features and adapt to a dynamic environment, is remarkably superior to the prior art in the aspects of accuracy, robustness and calculation efficiency, and is suitable for the fields of multi-source heterogeneous intelligent labeling and the like.

The invention discloses a crowdsourcing task processing method and system based on multi-agent cooperation, and relates to the technical field of artificial intelligence, and the method comprises the steps: receiving a user order which comprises a service type, a starting point address, an end point address and the arrival time; decomposing all user orders according to a preset rule to generate a task package; determining the predicted arrival time of each task package according to the pickup address and the delivery address, and generating an optimal allocation scheme according to the real-time state of the worker and the predicted arrival time of each task package; and performing task pushing according to the optimal allocation scheme. Intelligent decomposition and dynamic allocation of tasks are achieved through cooperation of large language model agents, the completion efficiency and quality of crowdsourcing tasks are remarkably improved, predicted arrival time is dynamically calculated through path planning agents, execution of time-sensitive tasks is optimized, and delay is reduced.

The invention relates to the technical field of mobile crowdsourcing, in particular to a mobile crowdsourcing implicit dynamic excitation method and system based on an anchoring effect. The method comprises the following steps: constructing an LSTM task price prediction model, namely a TP-LSTM model; task price prediction and service quality prediction are carried out based on tasks by using a TP-LSTM model; performing task information anchoring based on a prediction result; and performing worker recruitment optimal incentive based on task information anchoring, wherein the worker recruitment optimal incentive comprises the optimal incentive of the initial recruitment process and the optimal incentive of the emergency recruitment process. The TP-LSTM model is utilized to significantly improve the accuracy of task price prediction, a time sequence mode in data can be identified and utilized, prediction errors are effectively reduced, and more reliable decision support is provided for a platform.

The invention belongs to the technical field of Internet crowdsourcing platforms, and particularly relates to an automatic task pushing method based on a crowdsourcing human platform, which comprises the following steps: S1, data collection: collecting executor information and task information; s2, data analysis and modeling: models constructed in the step comprise an executor portrait model, a task model and a matching algorithm model; s3, automatic pushing: based on the task information and the comprehensive matching score, automatically pushing a corresponding task to an executor according to a pushing rule; and S4, feedback and optimization: collecting feedback information and optimizing the executor portrait model, the task model and the matching algorithm model according to the feedback information. According to the method, through multi-dimensional data collection and analysis, an accurate executor portrait and a task model are constructed, high matching of the task and the executor is realized through a multi-dimensional matching algorithm, and the task completion quality and efficiency are improved.

Techniques for augmenting transparency of published transaction data are described. The techniques can include one or more of associating a financial account with an account of a user at a transaction management platform, receiving transaction data from the financial account, categorizing the transaction data, publishing the transaction data, assigning permission levels to user for different levels of access to the amount and granularity of published transaction data, storing an immutable record of transaction data from which changes to the transaction data can be determined, and enabling crowd intelligence about the entity, account, or transactions by recording interaction of users of the published transaction data.

The present invention belongs to the technical field of high-precision map quality evaluation for autonomous driving. The present invention provides a crowdsourced map evaluation method and device based on lane lines, wherein the method includes: obtaining a sequence of lane line points based on crowdsourced data, using a custom distance calculation method between lane lines, hierarchically clustering the lane lines collected multiple times to obtain multiple clusters; for each cluster, performing polynomial fitting on the lane lines within the cluster, calculating the distance from each lane line to the fitted lane line, and mapping the distance to between 0 and 1 using a custom function to obtain the cluster-internal confidence; and calculating the global confidence of the map based on the confidence within each cluster and the total length of the lane lines. In the absence of a true map value, the present invention performs relevant calculations and processing on the lane lines to obtain the local and global confidence of the crowdsourced map, thereby respectively evaluating the local and global quality of the crowdsourced map.

A distributed computer system comprises one or more patient system, configured to be operated by patients seeking provider services, a front-end web server to interface to the one or more patient system, a back-end server system coupled to the front-end web server to receive patient information, a healthcare provider system that provides information about a procedure needed by a patient unable to pay for the procedure, providing the information to the back-end server system, and a donor computer system, for accepting and receiving messages from the back-end server system about funding patient procedures.

The invention relates to the technical field of task allocation, in particular to a space-time crowdsourcing multi-objective optimization task allocation method and system based on an intelligent vehicle. The method comprises the steps that attribute sets of crowdsourcing vehicles and crowdsourcing tasks are acquired respectively, the attribute set of the crowdsourcing vehicles comprises social attributes, and the attribute set of the crowdsourcing tasks comprises space-time attributes and position information; performing trajectory prediction on the crowdsourcing vehicles according to the social attributes to obtain predicted trajectories of the crowdsourcing vehicles; formulating a task allocation strategy based on the prediction trajectory, the space-time attribute and the position information; and dynamically adjusting a task allocation strategy by using a multi-objective optimization algorithm to obtain a task allocation optimal solution. According to the method, crowdsourcing task allocation optimization can be realized.

In a wireless communication system, at least one UE detects GNSS signal spoofing / jamming and reports a detected spoofing / jamming attack to a server in the network apparatuses using an extended LPP GNSS error reporting format with an additional error cause and an attack probability metric. Further, the network apparatuses may take an implementation-dependent decision depending on crowd-sourced information of one or more spoofing / jamming attack reports received from one or more UEs.

Techniques and systems are provided for vehicle positioning. For example, a method may include obtaining a point corresponding to a target in an environment, the point indicating a location of the target in the environment, and wherein the point is a non-semantic point used with a non-semantic layer (NSL) of a map; obtaining pose information indicating the course of the vehicle; generating map points based on the quantization of the obtained points; and outputting the generated map point to a map server. For another example, a method may include obtaining an NSL of a map of an environment, the NSL including map points corresponding to targets in the environment, where the points are non-semantic points; determining that the target is related to the vehicle based on a comparison between the pose information and the heading information; and transmitting the map point to the vehicle.

A method for predicting, for a vehicle that is connected to a current cellular access point and is traveling on a road network, at least one characteristic associated with a modification of the linkage conditions of the vehicle to the cellular network. The method includes: training a first prediction model associated with the current access point from crowdsourced data collected from at least one training vehicle, the data comprising at least a first location, a speed and a direction of the training vehicle as well as a second location of the training vehicle collected when a disconnection from the current access point is detected; and predicting a third location at which a second vehicle will be disconnected from the current access point while traveling on the road network by applying the prediction model to a location, a speed, and a direction of the second vehicle.

1. Name of the product of this design: A graphical user interface for displaying talent information on a cost crowdsourcing platform for electronic devices. 2. Purpose of this design product: an electronic device. 3. The key design point of this design product lies in the interface content of the graphical user interface. 4. The picture or photo that best illustrates the design points: Interface change state diagram 4. 5. Other designs are conventional designs and other views are omitted. 6. Purpose of the graphical user interface: The graphical user interface of this design product is used to display talent information on the cost crowdsourcing platform. 7. Description of the changing states of the graphical user interface: The main view is the initial interface of the program. Pull down the main view to interface change state diagram 1; pull down interface change state diagram 1 to interface change state diagram 2; pull down interface change state diagram 2 to interface change state diagram 3; click the person's name in interface change state diagram 3 to jump to interface change state diagram 4; pull down interface change state diagram 4 to interface change state diagram 5; pull down interface change state diagram 5 to interface change state diagram 6; pull down interface change state diagram 6 to interface change state diagram 7.

The application provides a meteorological anchor point-based cross-modal asynchronous data alignment method, system, device and storage medium, which comprises the following steps: acquiring multi-modal data of a target area, and performing spatial alignment on the multi-modal data; constructing a unified anchor point time axis based on the meteorological predicted water depth grid sequence; based on the unified anchor point time axis, performing nearest time point matching and time decay on a remote sensing grid observation sequence and a GIS risk grid observation sequence respectively to obtain a time-aligned remote sensing grid observation sequence and a time-aligned GIS risk grid observation sequence; based on the unified anchor point time axis, performing time window aggregation on a social crowdsourcing point observation sequence to obtain a time-aligned social crowdsourcing point observation sequence; generating metadata of each modal data for each anchor point timestamp on the unified anchor point time axis, and outputting the time-aligned multi-modal data and the metadata.

Automated system and method for processing online idea submissions (with crowdsourcing and anonymity functions), formal complaints and anonymous complaints. The system receives and processes registration information, creates a unique coding entry, and generates an associated keyword database. When the system receives input data from a user, it utilizes the unique coding identifier to relate to the organization, searches the keyword database in any communications involving the registered entity, automatically analyzes the received data, and preforms a zone of reliability verification analysis on the received data. The system also removes private personal information (PPI) for anonymous users, and “locks” and / or encrypts the version with PPI, preventing unauthorized access, and unseals the dataset with PPI information only after receipt of an unsealing order from a court or a governmental entity. The system also automatically generates and transmits reports to governmental entities and others based on the analysis of the reported complaints and legal requirements and guidelines. The system also calculates and utilizes a rating score as part of the engagement process with the registered entity, performs analysis and reporting of the overall industry, and connects the entity with the experts in the area of concern based on the analysis.