343 results about "Intelligence analysis" patented technology

The invention discloses a system and method for constructing information-analysis-oriented knowledge maps. The system comprises a data acquisition module, a text extraction module, an entity recognition module, a semantic analysis module and an entity-relation extraction module, wherein the data acquisition module is used for carrying out cleaning and simple preprocessing on acquired data and outputting the data to the text extraction module; the text extraction module is used for carrying out data cleaning and preprocessing on structured and unstructured data and conveying clean data to the entity recognition module; the entity recognition module is used for segmenting words of a text, marking the word characteristics of the segmented words, then extracting terms and conveying extracted results to the semantic analysis module; the semantic analysis module is used for analyzing and extracting relation among bodies, generating a semantic metadata model by a body construction tool and outputting the semantic metadata model to the entity-relation extraction module; and the entity-relation extraction module is used for finally generating knowledge map language by extracting taxonomic relation and non-taxonomic relation. The system and method disclosed by the invention have the advantages that by combination of syntactic training and association rules, not only are external input and artificial intervention reduced, but also the entity relation can be continuously recognized.

As data about events and objects become more commonly available, analyzing and understanding of interrelated temporal and spatial information is increasingly a concern for military commanders, intelligence analysts and business analysts. A system and method is provided for creating a multidimensional visual representation of a group of data elements having integrated temporal and spatial properties. The data elements are included in the visual representation as corresponding visual elements, such that the data elements of the group linked by at least one association. The system includes a visualization manager for assembling the group of data elements using the at least one association and for assigning a connection visual element in the visual representation between a first visual element representing a first data element of the group and a second visual element representing a second data element of the group. The system also has a spatial visualization component, such as a sprite, configured for generating a spatial domain of the visual representation to include a reference surface for providing a spatial reference frame having at least two spatial dimensions. The reference surface is for relating the first visual element to a first location of interest in the spatial reference frame and for relating the second visual element to a second location of interest in the spatial reference frame. The system also has a temporal visualization component, such as a sprite, configured for generating a temporal domain of the visual representation operatively coupled to the spatial domain, the temporal domain for providing a common temporal reference frame for the locations of interest. The temporal domain includes a first time track, such as a timeline, coupled to the first location of interest and a second time track coupled to the second location of interest, such that the first visual element is positioned on the first time track and the second visual element is positioned on the second time track. Each of the time tracks configured for visually representing a respective temporal sequence of a plurality of the data elements at each of the locations of interest of the reference surface. In implementation of the method, the connection visual element represents a distributed association in at least one of the domains between the first visual element and the second visual element such that the visual representation is displayed on a user interface for subsequent interaction with user events, including animation of the visual elements to help in the analysis of the data contained in the visual representation.

The invention provides a humanoid robot control method based on artificial intelligence, a system and the humanoid robot. The method comprises the following steps of receiving a voice signal input by a user and / or an image signal; according to the voice signal and / or the image signal, determining a user intention; processing the user intention and feeding back a processing result as a multi-modal output mode to the user, wherein the multi-modal output mode comprises one or more of a motion output mode of the humanoid robot, an image or video output mode and an audio output mode. By using the method, according to the collected voice signal and / or image signal of the user, after artificial intelligence analysis, the humanoid robot is autonomously controlled to interact with the user as several modes so that an artificial intelligence result can be visually and effectively displayed and an affine and effective effect is achieved in propaganda, demonstration and service fields.

The invention discloses an intelligence relation extraction method based on neural network and attention mechanism, and relates to the field of recurrent neural network, natural language processing and intelligence analysis combined with attention mechanism. The method is used for solving the problem of large workload and low generalization ability in the existing intelligence analysis system based on artificial constructed knowledge base. The implementation of the method includes a training phase and an application phase. In the training phase, firstly a user dictionary and training word vectors are constructed, then a training set is constructed from a historical information database, then corpus is pre-processed, and then neural network model training is conducted; in the application phase, information is obtained, information pre-processing is conducted, intelligence relation extraction task can be automatically completed, at the same time expanding user dictionary and correction judgment are supported, training neural network model with training set is incremented. The intelligence relation extraction method can find the relationship between intelligence, and provide the basis for integrating event context and decision making, and has a wide range of practical value.

The invention discloses a threat intelligence analysis system for attack tracing. The system comprises an internal threat intelligence collection module, an external threat intelligence collection module and an attack tracing analysis module; the internal threat intelligence collection module comprises a security detection module and a security analysis module; the attack tracing analysis module comprises attacker tracing and attack host tracking; threat intelligence obtained by the internal threat intelligence collection module and the external threat intelligence collection module is uploaded to the attack tracing analysis module, the attack tracing analysis module performs attacker tracing and attack host tracking on the threat intelligence and feeds back the result to the security detection module and the security analysis module; and meanwhile, the result is performed with threat intelligence sharing and exchange with an external cooperation mechanism. The threat intelligence analysis system disclosed by the invention can not only singly and quickly accomplish threat intelligence analysis and detection, but also can provide prediction for the attacks of enterprises, the method is orientated to attack tracing, and the attack mode is analyzed from the source so as to better identify the identity of the attacker.

The invention provides a control system and method of an artificial intelligence drive robot. The system comprises a receiving module, an artificial intelligence module, a central processing unit, a cloud processing module and an executing module. The method comprises the steps that scene information of the surrounding and voice and / or visual information of a user are acquired; a comprehensive decision is made after recognition and understanding according to voice and / or visual information; the intention of the user is confirmed, and the robot gives a response; and a treatment result is outputin multiple modes including one or more of moving of the intelligent robot, action of a mechanical arm and / or a head, expression video image display on a screen, and audio playing. According to the method, artificial intelligence analysis and decision can be carried out locally or through cloud uploading according to acquired voice and / or visual information, the robot is automatically controlledto be in interactive feedback with the user in multiple manners, much hardware can be arranged outside, a designer quickly expands a machine body, and an artificial intelligence result can be intuitively and effectively achieved on the robot.

The present invention discloses a cancer pathology auxiliary diagnosis method based on an artificial intelligence technology. The method comprises the following steps of: canning a plurality of digital pathology images of a system into a computer, performing marking of diseased areas by pathologists to form a digital pathology image database; performing preprocessing of the digital pathology images to form a data set for algorithm training, performing sample collection, and forming a data subset for training; allowing a full convolutional network to use the data subset for training to performiteration training to regulate parameters, and constructing an artificial intelligence analysis module; scanning diagnosis pathology images, and decoding the diagnosis pathology images to access the artificial intelligence analysis module; and performing diagnosis and marking of the diagnosis pathology images by employing the artificial intelligence analysis module, and performing feedback of themarked pathology information to doctors. The cancer pathology auxiliary diagnosis method based on the artificial intelligence technology is high in diagnosis accuracy and can effectively assist doctors in discrimination of cancer pathology information.

The invention provides a telemarketing customer service system based on artificial intelligence and a business operation mode. According to records of various customer services and historical clients in a platform, a character model of every customer service and a character model of every historical client are generated based on emotion identification system. By adopting an artificial intelligence analysis technology, multidimensional analysis of every customer service, every task, and every client is carried out to generate the intelligent portrait of every customer service, the intelligent portrait of every task, and the intelligent portrait of every client are generated. The intelligent matching of the intelligent portrait of every customer service, the intelligent portrait of every task, and the intelligent portrait of every client is carried out according to a preset rule, and then a plurality of orders are generated, and accurate marketing among the customer services, the tasks, and the clients is realized, and therefore personalized service is provided for the clients. After the orders are finished, the intelligent vouching of the finished orders by adopting a speech recognition system and a preset vouching strategy, real-time quality inspection and real-time billing are realized, and finally, work load of workers is effectively reduced, vouching time is shortened, and the accuracy of the quality inspection is improved.

An intelligent real-time 360° enterprise performance management system and 6-step methodology, which provides an integrated way to evaluate the performance and effectiveness of specific ‘business components’ within organizations (e.g., internal functions, internal processes, and stakeholder relationships). The system serves as a highly scalable, customizable, and context-aware Unified Enterprise Performance Management Application Platform (UEPMAP) that automates static and dynamic real-time and asynchronous business intelligence gathering from employees, customers, suppliers, business partners and other key stakeholders; analyses structured and unstructured feedback data; identifies strengths and weaknesses for each business component by way of SWOT analysis; develops prioritized action plans, supported by an adaptive neuro-fuzzy inference system (ANFIS) in order to address weaknesses identified within business components.

Systems and methods are disclosed that assist in making decisions, valuing a choice or action, promoting creative solutions, and reducing risks. Among other situations, the systems and methods consider situations where the user or users are evaluating a possible single choice or several alternative choices. The criteria to evaluate the decisions are input into a grid, and the user or users rate the one or more alternatives against the different criteria. Given several alternative choices or options, the system and method provides the probability each alternative is the right selection. In one embodiment, the system implements a Bayesian approach. The systems and methods may estimate the value of an option or choice, where the value might be financial or other metric, and may estimate the value of a risk, opportunity or factor that might influence the result. The systems and methods may estimate the amount the chance of being surprised or missing some relevant consideration has been reduced by the analysis. The possibility of black or gray swans can also be estimated, in the phraseology of Nassim Taleb. Systems and methods so disclosed may be employed in financial analyses, project or strategy selection, betting, resolution of disagreements, intelligence analysis, and so on.

The invention discloses a big data tax-related information analysis system. The system comprises the following modules: a data acquisition module which performs incremental acquisition on data in the internet by adopting a crawler acquisition mode, a data cleaning module which performs data cleaning in ways of unrelated field cleaning, price and discount price filtering, time stamping and currency automatic conversion, a data analysis module which performs multi-dimensional analysis on tax-related information data through online analysis processing and data mining technologies, a data storage module which dispersedly stores the data in a plurality of independent devices by adopting a distributed storage policy and an extendable system structure, and a data output module used for outputting the data required by a user according to a specific rule. According to the big data tax-related information analysis system, a large amount of tax-related information data is provided for taxation collection and management in real time, and a tax-related information law is found and future tax avoidance and tax evasion trends are predicted by utilizing trend indexes.

The invention provides a smart city big data management system, and relates to the technical field of smart cities, and the system comprises: a big data center station which is used for collecting city big data provided by city infrastructures, carrying out the preprocessing of the city big data to obtain preprocessed big data, and storing the preprocessed big data to form a city brain database; acollaborative sharing platform which is used for carrying out capacity encapsulation and protocol adaptation on the capacity components, abstracting the capacity components into atomic energy, and providing services to the outside through an open communication interface so as to support business applications of different technical systems to call and interact with the preprocessed big data; and an auxiliary decision application which is used for carrying out artificial intelligence analysis according to a pre-generated adaptive decision analysis engine set and the preprocessed big data, and displaying an analysis result to an urban manager through an urban instrument panel so as to monitor an urban operation state in real time and provide technical support for decision making of the urbanmanager. According to the invention, the city can self-discover problems to the greatest extent and assist in solving the problems.

Method of and system for analysing a set of exhaustive and exclusive hypotheses, including assessing and assigning base rates for each hypothesis; determining a set of items of evidence that are relevant to, have a causal influence on, or would disconfirm more than one hypothesis; assessing and assigning base rates for each item of evidence; deciding, for each item of evidence, whether the item should be treated as being a causal influence or diagnostic indicator with respect to the set of the hypotheses; if the item of evidence is to be treated as a causal influence—making a judgement as to the likelihood of each hypothesis, both if the evidence were true, and also if the evidence were false; if the item of evidence is to be treated as a diagnostic indicator—making a judgement as to the evidence being true if the hypothesis were true; assessing the belief for each item of evidence being true; deciding a set of interim beliefs in each hypothesis for each individual item of evidence by:employing a conditional inference operator for evidence that is to be treated as a causal influence; andemploying a reverse conditional inference operator for evidence that is to be treated as a diagnostic indicator; anddeciding the overall belief in each hypothesis by employing a consensus operator on the respective set of interim beliefs.

The invention provides a cross-media intelligence target element association analysis system and an association analysis method thereof. The invention can remarkably improve the analysis ability of the target object and the application value of the analysis result to the user. The invention is realized by the following technical scheme: the user interactive operation module selects a decision treemodel corresponding to the purpose of information analysis, a goal-centered model of target elements is established, the user requirement information is sent into an association expansion processingmodule, Reads the target element model of the initial retrieval intelligence set according to the index, obtains the structured data of the attribute items of the intelligence data input into the database module, uses the domain prior knowledge and element expansion rules provided by the external data support module to carry out element expansion, and obtains the new extended target element and element expansion intelligence; Retrieves all the information, and outputs the correlation results of the target events to the support service module, and outputs the target analysis results including the target correlation and the target activity law.

The invention provides a method and device for detecting and identifying stored grain insects. The method comprises the steps of inputting an original stored grain insect image into an artificial intelligence analysis model to perform location positioning and category judgment on insects, wherein the artificial intelligence analysis model is a convolutional neural network which is trained and verified according to a data set formed by the stored grain insect image; and labeling the insect location and category on the original stored grain insect image according to a location positioning and category judgment result. According to the invention, a model capable of correctly positioning and identifying various stored grain insects is trained according to a deep leaning based target detectionalgorithm and collected stored grain insect data, thereby avoiding the drawbacks of poor robustness and generalization of manual design features, and improving the accuracy and efficiency of detectionand identification.

Systems and methods are disclosed to assist in making decisions. The systems and methods consider situations where the user is determining which of several alternatives is the best choice. The criteria to evaluate the decisions are input into a grid, and the user rates the different alternatives against the different criteria. Given several alternative choices or options, it provides the probability each alternative is the right selection. In one embodiment, the system implements a Bayesian approach. The systems and methods may estimate the chance some important consideration was missed thereby reducing the chance of being surprised or blindsided. The system and method may also examine the inputs to a decision analysis in order to detect entries that might reflect bias, assumptions or unusual reasoning, thereby increasing the chance of obtaining the correct answer. The systems and methods may also identify the factors that were predictive. The systems and methods do not accept information as valid and correct; rather, they allow cross-checking and verification, and further employ sub-systems and sub-methods to reduce mistakes. Systems and methods so disclosed may be employed in financial analyses, intelligence analysis, etc.

The invention provides a fan gear box fault diagnosis model establishing method used for establishing a fan gear box fault diagnosis model. The method comprises a step of obtaining a vibration signal of a fan gear box and then carrying out smoothing and denoising processing on the vibration signal, a step of decomposing the processed vibration signal and extracting the characteristic vector of the vibration signal, a step of dividing the characteristic vector of the vibration signal into a training data set and a testing data set, and a step of using a Drosophila algorithm to optimize a parameter of a radial basis function (RBF) neural network model, inputting the characteristic vector of the vibration signal in the training data set to obtain the optimal value of the parameter, generating the fan gear box fault diagnosis model based on a radial basis function neural network and carrying out test. In the scheme, the optimization algorithm is introduced for the characteristic of the RBF neural network, through introducing the artificial intelligence analysis technology, the extracted characteristic value is processed further, thus the efficiency of fault diagnosis is improved, and stop losses caused by faults are reduced.

Methods and apparatus compress data, comprising an In-phase (I) component and a Quadrature (Q) component. Statistical characteristics of the data are utilized to convert the data into a form that requires fewer bits in accordance with the statistical characteristics. The data may be further compressed by transforming the data and by modifying the transformed data in accordance with a quantization conversion table that is associated with the processed data. Additionally, redundancy may be removed from the processed data with an encoder. Subsequent processing of the compressed data may decompress the compressed data in order to approximate the original data by reversing the process for compressing the data with corresponding inverse operations. Interleaved I and Q components can be processed rather than separating the components before processing the data. The processed data type may be determined by providing metadata to retrieve the appropriate quantization table from a knowledge database.

The invention discloses a task processing method based on heterogeneous computing and a software and hardware framework system. The task processing method comprises that: an artificial intelligence analysis task is decomposed into one or more stages of subtasks, and the artificial intelligence analysis task is completed in a hierarchical data flow mode through one or more analysis function unit services corresponding to the one or more stages of subtasks, wherein the types of the sub-tasks of different levels are different, the sub-tasks of the same type correspond to one analysis function unit service, and each analysis function unit service uniformly schedules a plurality of heterogeneous units to execute the corresponding sub-task.

The invention discloses a digital twinning model for a manufacturing process of a flexible circuit board. The digital twinning model of the flexible circuit board manufacturing process is composed ofthree parts, namely a physical space, a virtual space, a data information chain and a data processing system, wherein the physical space is the manufacturing process of the flexible circuit board, wherein the virtual space is a flexible circuit board manufacturing process model, and a virtual entity system model capable of representing the full life cycle of flexible circuit board manufacturing isconstructed in the virtual information space. The data information chain and the data processing system are information transmission chains connected with the physical space and the virtual space, and the transmitted information is subjected to artificial intelligence analysis through the information processing system. According to the digital twinning model for the manufacturing process of the flexible circuit board, real-time monitoring, fault prediction and process parameter optimization are carried out on the full-life-cycle production process, the yield of the flexible circuit board is improved, the production cost of products is reduced, and the production efficiency is improved.

The present invention provides a malicious domain detection method and device based on intelligence analysis. The method comprises the steps of obtaining communication data in a network; analyzing the communication data to extract the IP of a source host, domain names searched by the source host query and time of searching the domain names; a domain risk level database is searched to determine the domain names searched by the source host is in the domain risk level database; if the domain names searched by the source host is in the domain risk level database, a risk level result corresponding to the domain names is taken out from the domain risk level database and presented; and if the domain names searched by the source host is not in the domain risk level database, evaluation is carried out on domain risk levels and the risk level evaluation result is presented. The risk level evaluation result includes search engine recording status analysis and Internet archive analysis. The malicious domain detection method and device provided by the invention can precisely detect unknown malicious domains.

The present invention provides Artificial Intelligence, Internet of things and blockchain based systems and methods for supply chain management. The system and method identify reasons of failure of procured item / object based on performance data analysis. The system and method further determine optimization characteristics required for a required item / object based on Artificial intelligence analysis using prediction algorithms.

The invention relates to a crossing-traffic-state dynamic detection system based on video intelligence analysis and a method thereof. The system comprises an acquisition unit used for collecting crossing traffic flow video images. The acquisition unit is connected to an analysis unit so that the collected crossing traffic flow video images are transmitted into the analysis unit. The analysis unit receives the traffic flow video images and lays virtual auxiliary lines on each real-time entrance driveway image of the traffic flow video images. And the analysis unit analyzes a vehicle passing state in each real-time entrance driveway image according to the virtual auxiliary lines so as to acquire a traffic flow parameter of each entrance driveway. An intelligent video analysis technology is used to analyze a crossing traffic state, a problem existing in a traditional coil is solved, detection performance of a crossing traffic flow parameter and a traffic state are increased and a monitoring capability of a crossing traffic state is improved.

The invention discloses an interactive teaching system based on a PC. The system comprises an information acquisition module, an artificial intelligence processing module and an information feedback module, the information acquisition module is used for acquiring and storing facial and eyeball information of a student, the artificial intelligence processing module is used for carrying out artificial intelligence analysis on data collected by the information collection module and calculating the collected data by constructing an eyeball movement model and a face recognition model to obtain a calculation result, and the information feedback module is used for receiving the artificial intelligence analysis result and knowing the learning state of students. According to the invention, the teacher terminal and the student terminals are connected by using a novel technology, the teaching process is realized anytime and anywhere, and through the application of eyeball recognition and face recognition technologies, the classroom interaction frequency between teachers and students is increased, the learning interestingness of students is improved, and the teaching content is richer.

The invention discloses a take-out pickup management system and method. The invention comprises a detection platform used for scanning order information of meals, and collecting and recording relateddata of the meals by a sensor and a camera. a storage area used for temporarily storing meals; and a server which matches the related data acquired by the detection platform with order data, and judges state and integrity of the meals by artificial intelligence analysis. Meanwhile, storage suggestions are given through artificial intelligence analysis, and a delivery man is prompted to place the meals to the designated position of the storage area; after meals are stored in the storage area, a delivery instruction is sent to customers through the server, and the customers are reminded to takemeals in time. The management system can effectively check and accept meals through the detection platform. the invention further provides a storage plate with a weight sensor, the take-out storage capacity can be effectively improved, operation efficiency of the whole system is improved, and the installation and use cost of the system can be further reduced while meals are correctly received.