955 results about "Intelligent decision making" patented technology

The invention relates to a multi-information-fusion-based high precision localization method for an unmanned vehicle, and the multi-information-fusion-based high precision localization method can be applied to environment perception and intelligent decision-making of the unmanned vehicle. Through cooperation of an offline map and online sensing information, high-precision real-time positioning can be realized. The offline map records road traffic information of a driving area of the unmanned vehicle. The online sensing information includes lane lines and road boundaries. When the unmanned vehicle runs in a map area, according to location information given by an inertial combined navigation system, an approximate location of the vehicle is determined, a local map near the approximate location is obtained, the lane lines in front of the vehicle and the road boundaries on both sides of the vehicle can be detected by a vehicle sensor, the relative position of the vehicle and the lane lines and the road boundaries can be determined, by contrast of the location of the vehicle in the map, deviation is calculated, a location error is corrected, and high-precision localization can be achieved.

The invention provides a question-answering system based on man-machine integration. The question-answering system based on man-machine integration comprises an input module, a denoising module, a semantic parsing module, an information processing module, an intelligent decision-making module, an output module, a manual customer service processing module and a training module. The invention further provides a question-answering method based on man-machine integration. The method comprises the steps of inputting questioning information; converting the questioning information into standard text formatting information; carrying out denoising and module structuralization on the text formatting information; carrying out semantic parsing on the questioning information; judging an information processing result and making a decision; generating an answer and inputting the answer if the answer is correct; presenting the question to manual customer service to be processed if no answer is available or the answer is wrong, judging again according to a processing result and making a decision, training judging capacity and decision making capacity, and outputting a correct answer. According to the question-answering system and the question-answering method based on man-machine integration, self-learning capacity and self-improving capacity are improved, humanization and intelligentization are improved, and the accuracy and the timeliness of the system are guaranteed.

The invention relates to an intelligent community health care system control method based on the Internet of things. The method is mainly used for supplying intelligent medical services, such as physical check-up data report analysis, self-service emergency aid, medical rehabilitation program and the like, to community people of four kinds, namely sub-health people, old people, rehabilitation patients with severe illness and handicapped people. A system comprises an intelligent healthcare terminal device and an intelligent healthcare platform, wherein the intelligent healthcare terminal device which is used for monitoring data is connected with a terminal interface of the intelligent healthcare platform through a wireless network. Acquired real-time healthcare information is managed and analyzed through an expert system by means of data analyzing and mining, knowledge base, intelligent decision making and the like, and intelligent decisions are provided in real time in a medical expert simulated manner; alarm is realized through a call center by using a wireless communication technology, a GPS (Global Positioning System) positioning technology and a wireless data transmission technology; possible invisible diseases of individuals and potential incidence trends of people are discovered through a data warehouse by using a database management technology and a data mining technology.

The invention provides a power demand response intelligent decision method based on price and excitation. The method includes the steps of (a) collecting a sample, (b) obtaining an industrial load, (c) obtaining a moment load, (d) building safe operation constraint conditions, (e) building tolerance constraint conditions, (f) obtaining controllable load gross, (g) solving payback load gross, (h) building a basic demand relation, (i) building controllable time constraint conditions, (j) building a user benefit constraint function, (k) building a comfort degree optimal function, (l) building an electricity cost constraint function, (m) building a participation cost constraint function, (n) building a fairness constrain function, and (o) solving an optimal solution. By means of the intelligent decision method, an electric use time interval is adjusted to be a low-electricity-cost time interval, electricity consumption is reduced in a high-electricity-cost time interval, and electric charge is reduced; a user reduces power demands when a system needs or during power shortage, so that a peak load shifting function is achieved, and normal power supply is guaranteed.

The invention relates to an intelligent decision simulating experimental system based on multi-Agent technology, belonging to the crossed field of computer simulation, artificial intelligence and management experiment, and being the breakthrough and the development of a management experimental methodology and an intelligent decision support system on the concept, the theory, the technology and the function. The system is a large-scale experimental platform for carrying out simulation assisted prediction and decision on discrete events in management activities of the real world. In the method, an isomerized Agent and the group collaboration thereof are creatively used as leading roles of transparent processing of a decision experiment and a system simulation, four functional sub-systems, four layers of Agent system structures and four types of local databases are established, and predictions and decisions of four simulating experimental methods are applied to unify a system module. The invention is based on an internet, synthetically uses several new technologies of cloud computing and the artificial intelligence, increases functions of games of strategy, machine planning, knowledge discovery and logic self-building, and has super experimental capability. The invention is a new way for developing the management experimental technology and the intelligent decision support system.

The invention discloses an auditory perception and intelligent decision making system of an unmanned vehicle. The auditory perception and intelligent decision making system includes an auditory perception system and an intelligent decision making system; the auditory perception system includes a sound source positioning system and a sound identification system. The sound source positioning system positions the location and relative direction of a sound emitting source and transmits positioning results to the sound identification system and the intelligent decision making system; the sound identification system classifies and identifies sound source positioning information and transmits results to the intelligent decision making system; the information acquisition module of the intelligent decision making system receives sound information transmitted by the sound source positioning system and the sound identification system; an information processing and decision making module analyzes and processes the sound information and calculates lane changing and avoidance schemes of the unmanned vehicle; and a control execution module controls the behaviors of the unmanned vehicle and makes effective response.

The invention discloses an intelligent decision-making assisting system based on multi-modal ULTRASOMICS. Firstly, ultrasonic data from different signal sources of an instrument is acquired, an interactive or manual dividing method is adopted to locate an interested area in an ultrasonic image, data of morphology, blood perfusion and hardness science of diseases is obtained, and a multi-modal ultrasonic characteristic database is constructed; through the combination of relevant clinical information, laboratory checking information and gene chip information, ultrasomics data is mined, a machinelearning method is utilized to construct different models, the recurrence rate and the survival rate are predicted, the curative effect and the radiotherapy and chemotherapy sensitivity are judged inthe early stage, and the correlation of ultrasomics, genomics, proteomics, transcriptomics and metabonomics is analyzed. As macroscopic ultrasomics, the intelligent decision-making assisting system provides a repeatable evaluation means for noninvasive individualized precise medicine.

The invention discloses a utility tunnel intelligent management system, which comprises a system maintenance module, an operation department service C / S management module, an operation department service M / S management module, a pipeline department service module, a data interface module, an intelligent decision-making support module and a unified database, and is characterized in that the system maintenance module is used for performing support management on a utility tunnel intelligent operation management platform; the operation department service C / S management module is used for performing management on a desktop terminal used by a utility tunnel operation department in the process of operating utility tunnels; the operation department service M / S management module is used for performing management on daily operation and maintenance services of the utility tunnels; the pipeline department service module is used for performing management on an operating system of a utility tunnel using department; the data interface module is used for performing data exchange with a utility tunnel inner bottom monitoring system; the intelligent decision-making support module is used for providing auxiliary decision-making support for utility tunnel operation management; and the unified database is used for storing data in full life cycle of the utility tunnels. The utility tunnel intelligent management system realizes intelligent operation management for the utility tunnels by using advanced information technologies, can avoid occurrence of major disaster accidents as far as possible, and promotes sustainable development of the utility tunnel operation work.

The invention discloses a ship collision risk and risk degree evaluation method capable of associating with avoidance behaviors. The method comprises the following steps that: establishing a ship potential risk evaluation threshold value SDA (Safe Distance of Approach) quantization model, a ship potential risk evaluation model, a ship collision risk degree judgment threshold value model and an initial reference ship judgment model; through the established models, carrying out avoidance effect prediction on an approach situation and an avoidance scheme; if the avoidance effect is under a safe,secondary safe or under-safe level, proving that the avoidance scheme is feasible; and if the avoidance effect is under an unsafe level, starting an immediate risk coordination avoidance scheme. Through the above method, an urgent degree of a current ship to adopt a measure under a current approach situation can be evaluated, and the avoidance effect of an avoidance decision formed through a PIDVCA (Personifying Intelligent Decision-making for Vessel Collision Avoidance) decision algorithm can be evaluated to guarantee that the current ship is safely avoided. Objectivity and subjectivity are combined, the practical approach scene is comprehensively considered through ship relative motion vector geometric graphic analysis, a redirection avoidance behavior is associated, and a final avoidance decision is safe, economic and scientific.

The invention discloses an intelligent roadbed and pavement roller compaction system which comprises a quality detection system, an intelligent decision making system, an unmanned roller compaction system and a remote monitoring center. The quality detection system is used for detecting the compaction quality of various filled layers of roadbeds and pavements; compaction quality data can be analyzed by the intelligent decision making system, and roller compaction construction parameters of next procedures or new roller compaction construction regions can be obtained by the intelligent decisionmaking system; the unmanned roller compaction system can be combined with a single unmanned roller compaction machine or a group of unmanned roller compaction machines according to the roller compaction construction parameters, so that construction operation can be synergistically accomplished; real-time communication service, operation region planning, navigation routes and group scheduling service can be provided by the remote monitoring center, field operation conditions can be displayed by the remote monitoring center, and operation data can be stored by the remote monitoring center. Theintelligent roadbed and pavement roller compaction system has the advantages that the compaction quality of the different filled layers and different filling materials of the roadbed and the pavementscan be detected by the intelligent roadbed and pavement roller compaction system in an online manner, roller compaction construction operation can be controlled by means of machine decision making, accordingly, influence of human factors can be prevented, detection, analysis, decision making and control cycle can be implemented in a closed-loop manner, and the intelligent roadbed and pavement roller compaction system is particularly applicable to all-weather roadbed and pavement roller compaction construction operation scenes in hazardous regions or under extreme conditions.

The invention discloses an autonomous operation forestry robot platform, which comprises a robot body and a control system, wherein the robot body has a four-wheel drive structure and comprises a vehicle chassis, a vehicle roof platform, a vehicle frame and the like; and the control system of a robot can finish complex control and data processing algorithms and is provided with various sensors such as a navigation positioning sensor, a laser measurement sensor, a binocular vision sensor and the like so as to perform information detection and intelligent navigation on an autonomous forestry robot operation environment. An autonomous operation forestry robot has a simple structure and high four-wheel drive capability, can flexibly and reliably move under the condition of complex terrain in a forest district, has intelligent decision-making and environmental modeling capabilities and can finish an information detection task in the working environment of the forest district; and various operation manipulators can be arranged on the robot, so that forestry production operation tasks such as forestry pruning, intermediate cutting, logging, shipping and the like can be further finished autonomously.

The utility model relates to a streaming media on-demand system with intelligent data access which can reduce manual interference as possible, improve the efficiency of system and reinforce intellectualization of system, which comprises a media operational environmental module, an additive information module, an intelligent storage strategy module, a breakpoint continuous transmitting-file module, a breakpoint loading-media module, a periodical deleting-file module, a data analysis and recovery module, a system recovery module and a foreground on-demand system. The utility model actively performs background data generation and controls automatic storage, continuous file transmission and various malfunction analysis of media file, and then according to the analysis result, the intelligent recovery of the system is made, thereby reducing manual interference as possible, improving the efficiency of system, and reinforcing the intellectualization of system. The utility model has the advantages that manual intelligent decision-making support system and the design integrating with the technique of concentrative database system enable the intellectualization and safety performance of the system is more outstanding.

The invention provides a multi-target tracking detection method and device based on Darkflow-DeepSort, and a storage medium, and relates to the technical field of intelligent decision making. The multi-target tracking detection method comprises the following steps: S110, carrying out the training through employing a YOLOv3 algorithm, and obtaining a Darkflow-based target detection model; S120, inputting the detection image into a trained Darkflow-based target detection model to obtain apparent characteristics of a plurality of targets, wherein the detection image is obtained by decoding a monitoring video; S130, inputting the apparent characteristics of the plurality of targets into a trained DeepSort-based target tracking model, wherein the target tracking model is obtained by training adata set MOT16Challenge of multi-target detection; and S140, performing frame-by-frame data association processing on the monitoring video by using a Kalman filter of a target tracking model to realize multi-target tracking in the monitoring video. By utilizing the multi-target tracking detection method, the multi-target tracking detection speed can be increased, and multi-target tracking is completed under the condition that the detection accuracy is not lost.

The invention discloses a collision avoidance system and an automatic braking method of an electric automobile. The collision avoidance system comprises an information collecting module, an information processing module, an intelligent decision making module, a regenerative braking module and a mechanical braking module, wherein the information collecting module is used for real-timely collecting the distance between the electric automobile and a front vehicle or an obstacle and a current running speed; the information processing module is used for real-timely calculating rear-end time of the electric automobile and the front vehicle or the obstacle, regenerative braking safe time and mechanical braking safe time; the intelligent decision making module is used for deciding whether normal running is continuously kept or whether a regenerative braking mode is started or whether a combined braking mode of the regenerative braking mode and a mechanical braking mode is started according to the rear-end time of the electric automobile and the front vehicle or the obstacle, the regenerative braking safe time and the mechanical braking safe time; the regenerative braking module is used for starting regenerative braking for the electric automobile according to a regenerative braking mode starting signal provided by the intelligent decision making module; and the mechanical braking module starts mechanical braking for the electric automobile according to a combined braking mode starting signal provided by the intelligent decision making module.

The invention relates to a cognitive wireless network system with a cognitive radio function and a method for transmitting cognitive streams thereof. Base stations or wireless access points and terminals of the cognitive wireless network are all additionally provided with corresponding functional entities at a physical layer, a radio link layer and a high layer through a layering protocol stack, a centralized physical transmission channel and a distributed physical transmission channel are respectively established, based on a general control channel of the cognitive streams, data and parameters obtained by cognitive nodes through a physical channel are unifiedly represented as information which can be processed by the functional entities for intelligence reasoning and decision-making in the wireless system, and efficient, integral and reliable transmission scheme for cognitive information is realized by joint processing of the functional entities and the channels to lay a foundation for intelligent decision-making and dynamic reconfiguration inside the cognitive nodes in a network. In the invention, as a layering realization mechanism is adopted, the cognitive wireless network system can be flexibly adapted to changes of the network structure and the wireless environment; in addition, the cognitive wireless network system disclosed by the invention is highly compatible with the existing wireless protocol structure, thus having good popularization and application prospects.

The application relates to the field of intelligent decision making. An emotion recognition model is trained based on deep learning. The invention particularly discloses a training method of the emotion recognition model, an emotion recognition method, an emotion recognition device, equipment, and a storage medium. The method comprises the following steps: acquiring voice information of a user anda corresponding data tag; constructing sample data according to the voice information and the corresponding data tag; performing pre-processing on the voice information in the sample data to obtain acorresponding frequency spectrum vector according to a pre-processing rule; extracting a pre-set recurrent neural network, wherein the recurrent neural network comprises an attention mechanism, and the attention mechanism is used for enhancing part area in the voice information; based on the recurrent neural network, performing model training to obtain the emotion recognition model according to the frequency spectrum vector corresponding to the voice information and the data tag. According to the method, the generalization of the emotion recognition model can be improved, and the accuracy ofmodel recognition can be improved.

The invention discloses an autonomous operation forestry robot intelligent control system applied to the technical field of intellectualization of forestry equipment. The autonomous operation forestry robot intelligent control system comprises a central control computer, a motion control module, a navigation positioning module, a laser measurement module, a binocular vision module, a motor-driven module, a wireless communication module, a power supply module and a CAN (controller area network) communication module. Complex task scheduling and control algorithms are realized in the central control computer, and simpler control algorithms with high real-time requirements are realized in the motion control module and the motor-driven module, thus the whole processing capacity and real-time property of the system are ensured. Redundancy design is adopted on the motion control module, thus the reliability of the system is improved. The task requirements of the autonomous operation forestry robot for intelligent decision making and environmental modelling can be met, the system has the characteristics of high data processing capacity and high automation of intelligence and reliability; and the automation of intelligence of the traditional forestry robot control system is improved.

The present invention discloses an automatic-driving small car belonging to the field of unmanned vehicles and comprising a car body, a sensor module, a controller and a traveling executing device. The sensor module acquires the position information and the environment information of the car body and transmits the information to the controller; the controller proposes traveling path information which is transmitted to the traveling executing device; the traveling executing device controls the traveling of the car body; and the controller has an intelligent decision-making module built therein, wherein the intelligent decision-making module proposes a driving route according to the location information and the environment information collected by the sensor with consideration of priori information. The driving mode is continuously learned and improved according to the prior information, so that the most safe and fast driving mode can be selected in the condition of complex or special traffic conditions.

Systems and methods for embodiments of a graph based artificial intelligence systems for identity management are disclosed. Embodiments of the identity management systems disclosed herein may utilize a network graph approach to analyzing identities or entitlements of a distributed networked enterprise computing environment. Specifically, in certain embodiments, an artificial intelligence based identity governance systems may include an intelligent decision support agent to provide an approval or denial recommendation for an access request. To provide an approval or denial recommendation, the intelligent agent may utilize a classifier trained on historical certification data. The intelligent agent may utilize features which represent relevant signals to the approval or denial decision including features that may be associated with a network graph of the identities and entitlements of the enterprise computing environment.

The invention relates to an artificial intelligence power repair system and method based on big data, and the system is characterized in that the system comprises a data information collection modulewhich collects data of power equipment, fault repair, meteorological information, traffic conditions, repair vehicle tracks, repair processing, and service evaluation in real time; a data platform building module which is used for building a Hadoop big data platform by applying a MapReduce technology, a Hive technology and an HDFS technology; a learning optimization module which is used for searching rules and knowledge from the data, realizing basic functions of fault image recognition, voice recognition, fault type study and judgment, future fault quantity prediction, intelligent order distribution and ETA estimation, and providing accurate basic information for intelligent decision making; And a decision providing module which is used for providing active decision and reminding servicefor rush-repair personnel through a full-process application voice assistant based on electric power rush-repair full-service scene recognition and prediction, and liberating the hands of the rush-repair personnel.

The invention relates to an IRS-assisted unmanned aerial vehicle communication joint optimization method based on a DDPG algorithm. By deploying coordinates of an intelligent reflecting surface and a plurality of ground users, a moving track is designed according to the principle that two-dimensional coordinates of the initial position and the final position of the unmanned aerial vehicle form a line at two points under the condition that the unmanned aerial vehicle carries a plurality of antennas, and beam forming and a track with the maximum rate are obtained through an intelligent decision-making method which can be autonomously learned and is high in generalization ability. The invention has the advantages that the transmission rate of an air-ground communication system established by an unmanned aerial vehicle air base station can be remarkably improved, a single-link channel from an unmanned aerial vehicle to a single user is approximated to a multi-link channel through an intelligent reflecting surface (IRS), the purpose of enhancing communication signals and improving the user service performance is achieved, and the method adopts a deep deterministic policy gradient (Deep Deterministic Policy Gradient) algorithm for joint optimization, and a joint optimization solution can be obtained at the same time by carrying out joint optimization on the DDPG algorithm.

The invention discloses a vector-propelled small four-axis underwater robot control system. The system can be divided into a man-machine collaboration layer, a decision making layer, a planning layer and an executive layer, wherein the man-machine collaboration layer is composed of a land-based / boat load monitoring system and used for sending an AUV (Autonomous Underwater Vehicle) course control signal, receiving sensor data and displaying the sensor data in upper computer monitoring software in real time; the decision making layer comprises a multi-sensor information collection and fusion system which is used for receiving the course control signal and collecting and fusing sensor data; an intelligent decision making system is used for receiving the sensor data and the course control signal fused by the multi-sensor information collection and fusion system and processing the fused sensor data and course control signal through a decision algorithm to generate a decision instruction; the planning layer comprises a gait generation system in charge of planning movement gaits of the robot according to the decision instruction and collaborating data communication between an upper layer and a lower layer; and the executive layer comprises a driving and executing system and is used for controlling a steering engine and a direct-current water spraying motor in real time. The vector-propelled small four-axis underwater robot control system is high in reliability, excellent in flexibility, easy to expand and maintain, and wide in application prospect.

This invention that provides system, method & apparatus for Real Time integration and Analytics (RETINA) to enable proactive decision synchronization in real time in order to minimize the operational risk and maximize the process productivity for process industries such as Oil & Gas Exploration and Fossil fuel power plants is disclosed. RETINA generates and synchronizes the decisions that affect the performance and profitability of business operations in real time and helps in analysis that are essential for any successful business operations. RETINA provides methods and apparatus that combines data from several types of data sources, build models for identifying impending failures, predicting a future state of the process from currently measured process data and provide decision options to business users so that any unwanted opportunity loss such as downtimes or critical equipment failures that are operations risks would be eliminated. RETINA provides methods and apparatus to ensure that correct decisions are taken at the appropriate instant of time with right amount of data to the pertinent personnel to eliminate inefficiencies in operations and performance resulting in tangible profitability.

The invention discloses a tunneling robot for tunneling and a remote mobile terminal command system. The robot comprises a body tunneller of the tunneling robot, a sensing unit arranged on the tunneller, an intelligent decision-making unit and a control unit, wherein the sensing unit is communicatively connected with the intelligent decision-making unit, the intelligent decision-making unit is communicatively connected with the control unit, the sensing unit senses a current cycle in real time, the tunneller obtains tunneling operation data during the tunneling operation according to tunnelingparameter setting information, the intelligent decision-making unit receives the tunneling operation data sent by the sensing unit and generates tunneling parameter setting information of a next cycle according to a preset prediction algorithm, the tunneling operation data and desired tunneling effect prediction, and the control unit receives the information and controls the tunneller to executethe next cycle of the tunneling operation according to the tunneling parameter setting information. The robot can execute on-line monitoring, independent decision-making feedback control and unmannedtunneling operation in the tunneling process and achieves unmanned operation or remote control of the tunneller.

The invention discloses a fault cause determination method and system based on a space-time analysis log. The method comprises the following steps: step 1) collecting syslog logs generated by all network equipmentin a network system; 2) monitoring syslog logs generated by all equipment in the network and periodically performing feature analysis on the logs based on time space in real time; 3) performing time-based feature extraction and analysis on the running state of the network equipment, and checking hidden dangers and fault time points of the network equipment; (4) obtaining space topology information, (5) extracting related equipment logs in combination with the space topology information to construct a feature matrix of abnormal events, and (6) obtaining a fault propagation chain and root causes through an intelligent decision algorithm, and displaying detailed information of a fault influence surface and the root causes.

The invention relates to an electrical system of an electric intelligent vehicle, for a centralized architecture controller and electricity supply redundancy. The electrical system comprises a high-voltage battery, a battery management system (1), a key switch (16), an electricity supply unit, an intelligent decision-making and control unit, a sensor unit and an actuator unit, wherein the high-voltage battery is connected with the battery management system (1) through an electrical circuit; the key switch (16) is provided with an OFF gear, an ACC gear, an ON gear and a START gear; the electricity supply unit comprises a main accumulator (12) and an auxiliary accumulator (11); the electrical circuit comprises a main ACC circuit, an auxiliary ACC circuit, an ON circuit, a START circuit and a constant electric circuit which is connected with a positive pole output terminal of the main accumulator (12). Compared with the prior art, the electrical system disclosed by the invention has the advantages that requirements of a control unit and a wire-controlled system of the electric intelligent vehicle for redundancy are met, hardware redundancy and electricity supply redundancy are designed for critical components including a steering unit, a braking unit, a central control unit and the like in the driving of vehicles, and the safety of autonomous vehicles is improved.

The invention discloses a wireless cognitive network knowledge base constructing method based on a Bayesian network. A Bayesian network model is constructed by using perceived network performance parameters, so that the dependence among the parameters is obtained, and the conditional probability dependence is transformed into knowledge in a wireless cognitive network to be stored in a knowledge base for guiding a process of intelligent decision making. The process of constructing the knowledge base mainly comprises the steps of: perceiving the network performance parameters, discretizing and analyzing the parameters, constructing the Bayesian network model and transforming the knowledge to construct the knowledge base. The network performance parameters are collected through a perceiving process, and data is discretized and analyzed. Through a structure learning and parameter learning process, the Bayesian network model is constructed by using historical data. The conditional dependence among the parameters in the Bayesian network is transformed into the knowledge so that the knowledge base is constructed and updated.

The invention relates to a method for detecting obstructive sleep apnea syndrome. The method includes the following steps: using a photoelectric plethysmography (PPG) sensor for oxygen saturation information collection, using a snore sensor for snore information collection, and using a respiration signal sensor for respiration information collection; processing collected respiration information to acquire an average respiration rate and average respiration strength; processing collected snore information to acquire average snore strength within a time period before current moment; performing high-pass filtering on collected PPG signals; according to an artificial intelligent decision-making theory, building a fuzzy element set by the respiration information, the snore information and the oxygen saturation information after being processes, establishing a subordinate function, creating a fuzzy grade list and a fuzzy function set, building a multi-factor evaluation matrix and judging whether a person has the obstructive sleep apnea syndrome or not according to a maximum subordinate principe. The invention further relates to a system for detecting the obstructive sleep apnea syndrome.

The invention relates to the technical field of intelligent decision making, and provides an intelligent project recommendation method, an electronic device and a storage medium. The method comprisesthe following steps: receiving a request for logging in a declaration project of a user, identifying a unit name and project responsible person information of the user from the current declaration project, and querying from a database according to the unit name and the project responsible person information of the unit to obtain historical project declaration information of the unit; according tothe key index selected from the declaration project information, calculating the similarity between the project currently declarated by the user and the historical project by utilizing a preset calculation formula; and screening out historical projects of which the similarity exceeds a threshold value from the historical projects, and outputting and feeding back the historical projects as similarprojects of the current declaration project to a user. Through the preset similarity algorithm, the historical projects with high similarity with the current declaration project can be automatically matched for user reference, and intelligent recommendation of related information is realized.

The invention discloses an intelligent decision-making assistance system for predicting, diagnosing, treating and controlling hospital infection. The intelligent decision-making assistance system comprises an epidemiological model database module, a patient data collecting module, a hospital infection management information collecting module and an analyzer, wherein the analyzer calculates the probability of the hospital infection risk of each part according to the information collected by the patient data collecting module and the hospital infection management information collecting module and an epidemiological model in the epidemiological model database module and provides information for predicting the risk, assistant decision-making information for preventing the risk and assistant decision-making information for treating and controlling the broken-out infection. By the intelligent decision-making assistance system, the infection probability of a patient can be effectively pre-judged according to the medical record of the patient, the measures taken by hospital management staff and the epidemiological model, and corresponding diagnosis and treatment advice can be made.