86results about How to "Implement automatic build" patented technology

The invention relates to a unit selection speech synthesis method based on an acoustic statistical model. The method consists of an extraction of each acoustic feature in training corpus, a training of the statistical model that is corresponding to all kinds of acoustic features combining with the symbol information as syllabic segment and rhythm of each sentence in training corpus and the requirement of statistical model of each acoustic feature corresponding to each phoneme in awaiting synthesis sentences through the text analysis of input text when synthesizes. Based on the norm of maximumlikelihood value between acoustic parameters in awaiting selection unit sequence and acoustic statistical model of awaiting synthesis sentences, the best awaiting selection unit is searched. A KLD between acoustic statistical models is used for achieving fast beforehand selection of synthetic units. Finally, the synthetic speech of a sentence is acquired through smoothing and splicing of best awaiting selection unit waveform of each phoneme.The invention improves the quality of synthetic speech and synthetic effect of traditional splicing and synthetic method and achieves an automatic establishment of the system and an independence of the language kind.

The invention provides a humanoid patrol operation method and system for a semantic intelligent substation robot. The robot humanoid patrol operation method for the semantic intelligent substation comprises the following steps: autonomously constructing a three-dimensional semantic map of an unknown substation environment; based on the three-dimensional semantic map, combining the inspection / operation task and the current position of the robot to autonomously plan the walking path of the robot; controlling the robot to move according to the planned walking path, and carrying out an inspection / operation task in the advancing process; in the process of carrying out the inspection / operation task, adjusting the pose of the mechanical arm carrying the inspection / operation tool in real time, sothat the image of the equipment to be inspected is automatically collected and recognized at the optimal angle or the operation task is automatically executed at the optimal angle, and the full-autonomous inspection / operation task of the transformer substation environment is completed.

The present invention discloses an auto building method and system of a Wi-Fi position fingerprint map. The method comprises the steps of acquiring crowdsourcing data, building the Wi-Fi position fingerprint map by using a pedestrian navigation reckoning method and a machine learning method, and screening according to an indoor map to obtain Wi-Fi strength information with a position tag; and using the Wi-Fi strength information with the position tag as a training sample of a Gaussian process, so as to obtain a function relationship between the signal strength and the position information, resolving a super parameter in the Gaussian process, and predicting according to the super parameter so as to obtain Wi-Fi strength information of a poor constraint area of the indoor map. Regression is performed by using the Gaussian process, the Wi-Fi position fingerprint of a wide area is predicted based on the Wi-Fi position fingerprint information of a high constraint area of the map, so that the Wi-Fi position fingerprint map of the whole indoor area is built automatically.

The invention discloses a surface defect detection and three-dimensional modeling method, comprising the following steps: 1) collecting original surface point cloud data; 2) dividing the original defect point cloud data into defects to obtain a defect-free part and a defect part; 3) registrating a defect-free part to obtain a defect model; 4) performing top segmentation of that defect model; 5) filtering that spurious points on the top of the defect model; 6) smoothing the defect model; 7) Surface modeling, which reconstructs the point cloud defect model to obtain the surface model of the defect region. The surface defect detection and three-dimensional modeling method of the invention can realize the automatic detection of the surface defect of the object to be detected and the automaticconstruction of the three-dimensional model. It can be used to realize the automatic repair of industrial surface, and can be applied to the modeling of skin tissue damage on the surface of human bodyto provide a three-dimensional model for skin three-dimensional printing.

The invention provides a role-based access control model constructing system, which comprises a database, a weight module, a role module, a restriction module, a result display module, a user right distribution and management module and an audit management module, wherein the weight module comprises a similarity module and a weight calculation module; the role module comprises a role generation module and a role hierarchy generation module; the restriction module comprises a role restriction module, a right restriction module, a user restriction module and a mutual exclusion restriction module; and the result display module comprises a role display module, a restriction display module and a result adjustment module. In the invention, the importance of the user right is measured, the restriction to a role-based access control model is generated, and therefore the accuracy of the role and the safety of the system are improved. When the system is adopted, the construction of the role-based access control model can be realized, and the automatic and semi-automatic construction of the role-based access control model is ensured; moreover, the system has the characteristics of high safety, high interpretability and easy extendibility.

The invention relates to a data conversion method from EBOM (Engineering Bill of Material) to MBOM (Maintenance Bill of Material). The data conversion method comprises the following steps of: 1) classifying material parts into inheriting parts, intermediate parts and dummy parts based on basic data of EBOM; 2) traversing nodes of a material part collection by adopting a BOM tree traversal algorithm, if the material parts are intermediate parts, adding combined nodes; if the material parts are the dummy parts, deleting the nodes; if the material parts are inheriting parts, directly inheriting to MBOM; 3) judging whether the traversing process is finished; if not, turning back to step 2) for data conversion of the next node; if so, generating the MBOM. Compared with the prior art, the data conversion method from EBOM to MBOM realizes the conversion process from EBOM to MBOM, realizes the automatic establishment of MBOM, and plays a promotion role for the establishment of the whole intelligent maintenance system. The development efficiency of the whole system is improved, and the production intelligent maintenance operation of enterprises is optimized.

The invention provides a software project construction method and device, a storage medium and electronic equipment, and relates to the technical field of computers. The method comprises the steps: when it is monitored that a slave code warehouse of a target software project is updated, triggering the callback of the slave code warehouse; compiling codes in the slave code warehouse based on the update file in the slave code warehouse obtained by callback to generate a first compiled file; synchronizing a configuration file having a dependency relationship with a main code warehouse in the slave code warehouse to the main code warehouse; compiling codes in the main code warehouse according to the configuration file to generate a second compiled file; and obtaining an executable file of thetarget software project based on the first compiled file and the second compiled file. According to the invention, automatic construction of a plurality of code warehouses can be realized based on callback of the code warehouses, so the development and construction efficiency of software projects is improved.

The invention provides an index system construction system and method of business environment evaluation. The system includes: a text data acquisition module, which is used for acquiring a text data set related to business environment data; a lexicon feature determination module, which is used for determining lexicon features of all text data in the text data set; a data clustering module, which is used for clustering the text data set on the basis of the counted lexicon features to obtain a plurality of text data subsets after clustering; and an index system establishment module, which is used for determining keyword information of all the text data subsets, and establishing an index system, which is used for evaluating a business environment, on the basis of the determined keyword information. According to the system, automated construction of the index system of business environment evaluation is realized through text data feature extraction and corresponding clustering analysis technology, non-objectivity and limitation brought by artificial index stipulation are avoided, and accuracy and adaptability are better.

The invention discloses a family atlas automatic construction method based on a multi-task joint neural network model. The method comprises the following steps: firstly, establishing the multi-task joint neural network model; training an end-to-end joint neural network model; optimizing the end-to-end joint neural network model to obtain a final model; and finally, constructing a family atlas through the final model. According to the multi-task joint model disclosed by the invention, relationship classification between every two entities is avoided, and the redundancy of model output is greatly reduced. The joint extraction method provided by the invention can also be applied to other data fields, and can reflect good time efficiency and accuracy on an information extraction task. According to the method, the performance of entity extraction and relationship classification tasks is improved from two aspects of efficiency and precision, and the method can be flexibly expanded to other tasks needing entity extraction except for family atlas construction tasks and performing relationship classification.

The invention discloses a service framework supporting multi-internet service center construction and operation, and relates to a service framework to solve the problem that a data storage mode of the architecture of current service type software cannot adapt to multi-iSC (internet service center) operation under the same system. The service framework supports multi-iSC automatic construction and operation, and also supports component dynamic scheduling and analysis; by establishing two different modes of a memory data base, a service framework for operation of different iSC data can be realized by using a unified data mapping mode, and the service framework supports multi-iSC automatic construction; and a data base mapping component ORCom in the original component is split into two components, namely ORCom and GORCom, wherein the new ORCom component is in charge of the access of the memory data base, the GORCom component is in charge of the access of a global data base, and a data base engine is introduced to realize association and mapping of the memory data base and the global data base. The service framework is used for constructing and operating internet service centers.

The invention relates to the field of artificial intelligence, and discloses a medical inquiry data processing method, device and equipment and a storage medium, which are used for full-process development and deployment of graphic processor resource management, data annotation, data quality inspection, model training, model evaluation and online release, and the processing efficiency of medical inquiry data is improved. The medical inquiry data processing method comprises the following steps: receiving a resource application request of a graphics processor, and carrying out resource allocation to obtain resource allocation information; performing data annotation, quality detection and classification on the medical inquiry training data to obtain classified data; performing model training and evaluation on a preset machine learning model to generate a target machine learning model; and calling the target machine learning model to perform keyword recognition and association degree matching on the to-be-processed medical inquiry data to obtain target treatment information. In addition, the invention also relates to a block chain technology, and the target doctor seeing information can be stored in a block chain node.

The invention provides a field knowledge base establishment method and device. After a core concept in a current to-be-established field and a target text in which the core concept is located are obtained, at least one non-core concept can be obtained from the target text and the similarity between the core concept and the non-core concept can be obtained; when the similarity satisfies a preset condition, whether the non-core concept is the same to the concept existing in a field knowledge base of the to-be-established field or not is judged; if the non-core concept is different from the concept existing in the field knowledge base of the to-be-established field; the non-core concept is reserved in the field knowledge base of the to-be-established field; the non-core concept is taken as a new core concept, a target text in which the new core concept is located is obtained; the step of obtaining the at least one non-core concept form the target text is carried out again; and after all concepts in the knowledge base of the to-be-established field are obtained, a relation between any two concepts is obtained, so the field knowledge base of the to-be-established field is obtained, and the knowledge base of the to-be-established field is established automatically.

The invention relates to an automatic construction method of an intelligent contactor dynamic model. A sub-model for solving speed and a sub-model for inversely solving current of a contactor based on the neural network are trained by introducing the neural network technology and collecting actual running data of the contactor, so that the automatic construction of a contactor dynamic model is achieved; on the basis, the integrated simulation technology is adopted, point-by-point closed-loop simulation of an intelligent control module and a dynamic simulation program of the contactor is conducted, so that the automatic construction of the intelligent contactor dynamic model is achieved. By means of the method, the automatic construction of the intelligent contactor dynamic model can be achieved, and the development period of the intelligent contactor can be shortened.

The invention discloses a question and answer pair construction method, system and device and a computer readable storage medium. The method comprises the steps of: extracting sentences of potential question and answer pairs in a text paragraph; arranging sentences of the potential question-answer pairs to generate candidate question-answer pairs; and scoring and screening the candidate question and answer pairs to obtain question and answer pairs of which the scores are higher than a set threshold. By means of the mode, the potential question and answer pairs in the document are automaticallyextracted to construct the high-quality question and answer pairs, the construction rapidness and accuracy of the question and answer pairs are improved, and the quality of the question and answer knowledge base is improved.

The invention provides a water supply pipeline leakage point detection system and method based on a flexible pipeline robot, and relates to the technical field of water supply pipeline leakage point detection. The system comprises the flexible pipeline robot and an upper monitoring terminal; the flexible pipeline robot is used for performing real-time positioning in a walking process to obtain real-time positioning time and real-time position information, and outputting pressure abnormal change time and real-time position information when pressure abnormal change of a water supply pipeline isdetected; and the upper monitoring terminal comprises a track generation module used for generating a walking track according to the real-time positioning time and the corresponding real-time positioninformation, a first marking module used for giving a leakage point mark on the walking track according to the real-time position information corresponding to the pressure abnormal change moment; anda second marking module used for marking the walking track containing the leakage point marks on a pre-generated water supply pipeline electronic map. Tiny pipeline leakage points can be accurately captured and positioned, and a GIS system of an underground water supply pipe network can be calibrated and automatically constructed; and the labor and equipment cost are effectively reduced.

The invention provides a method and a device for automatically establishing a classification rule for cross-language. The classification rule of a source language is converted into more than one AND relationship rule, and the following steps are executed for each AND relationship rule: determining a key word of a judgment condition in the current AND relationship rule; determining a target language candidate word set corresponding to each key word, wherein the set includes a target language translation word, a target language word containing the key word in a character string when the target language is translated to the source language and the keyword; selecting a candidate word with a document coverage condition meeting the preset requirement from each target language candidate set as a target language key word corresponding to each key word; and adopting the target language key word to substitute the corresponding key word in the current AND relationship rule through an OR relationship to obtain the AND relationship rule of the target language. By adopting the method and device, the classification rule is only established for one language, so that the labor cost and workload can be greatly reduced.

The invention discloses a three-dimensional technological procedure guiding type method and system based on structured knowledge. The method comprises the following steps of: creating working procedures and working steps under a technological model structure tree; acquiring manufacturing resource information and inspection information of the working procedures or the working steps, and selecting typical geometric features with the similarity larger than a set threshold value from a model feature library; inserting the typical geometric features into the process model structure tree and performing attaching to the model geometry, determining the sizes of the typical geometric features, and completing model geometric feature construction; and based on the manufacturing resource information, the inspection information or the structured process knowledge base of the working procedures or the working steps, acquiring the process symbols of the model geometric features. According to the method, the enterprise-level structured process knowledge base reflecting the process design logic relation is established, automatic construction of the three-dimensional process procedure design process is achieved, and the process procedure design efficiency is improved.

The invention discloses a method and system for synchronizing data of power equipment as well as a power resource management server. The invention is characterized in that the power resource management server is additionally provided with an interface, the interface is communicated with a B interface of a moving-ring monitoring system, and the power resource management server logins in the moving-ring monitoring system by the interface and acquires the latest data of power equipment from the moving-ring monitoring system. The method, system and server provided by the invention have the advantage of enhancing the instantaneity and accuracy of the data of power equipment on the power resource management server.

The invention provides a method and device for clustering government and enterprise customers. The method for clustering the government and enterprise customers, which is provided by the invention, comprises the steps of: obtaining government and enterprise customer data and list customer data; respectively carrying out word segmentation on first government and enterprise customer names and firstlist customer names to obtain a first word set and the first word set; and calculating a deviation degree score of the first word set and the second word set and if the deviation degree score is lessthan a preset deviation degree score, regarding the first government enterprise customer names and the first list customer names to be successfully matched. The method for clustering the government and enterprise customers, which is provided by the invention, has the advantages that the automatic construction of the intelligent clustering of the government and enterprise customers is realized; andthe processing efficiency and the accuracy of clustering results are greatly increased.

The invention relates to the field of remote-sensing image segmentation, and discloses a method of automatic construction of a remote-sensing image segmentation reference library. The method of automatic construction of the remote-sensing image segmentation reference library includes: step 1, screening public-source vector data to remove ground objects of which ground object areas are smaller thana preset area; step 2, carrying out registration superposition on a remote-sensing image and public-source vector data after screening to obtain A; step 3, clipping the remote-sensing image in the Ainto a plurality of preset-pixel-size small-range image blocks, setting the small-scale image blocks as units, judging, through image coordinates, whether the public-source vector data are located inimage block ranges, and generating masks of which sizes are the same as sizes of the original image blocks; and step 4, combining the masks and the original image to obtain the remote-sensing image segmentation reference library. According to the method, problems that in the prior art, efficiency of constructing reference libraries by manual labeling is low, and scales are smaller at the same timeare overcome, and automatic construction of the remote-sensing image segmentation reference library is realized.

The invention relates to the field of computer security, and particularly relates to a malicious program behavior feature library construction method and device. Aiming at the problems in the prior art, the invention provides a malicious program behavior feature library construction method and device. According to the malicious program behavior feature library construction method and device provided by the invention, behaviors are automatically extracted by a machine, and according to a malicious value sequence of the behaviors, a malicious program behavior feature library is automatically constructed, so that behavior extraction efficiency of a malicious program can be greatly improved, and a manual participation degree is reduced. According to the malicious program behavior feature library construction method and device provided by the invention, behavior operations of n sample files in a sample file set are acquired; then the behavior operations of all the sample files are subjected to merging of similar behavior operations; a malicious value of each behavior, i.e. the malicious value is equal to tf*ldf*vf, is calculated, wherein tf represents a occurrence frequency of each behavior, ldf represents a reverse sample frequency of each behavior, and vf represents a malicious frequency number of the calculated behaviors; sorting is carried out according to the malicious values of the behaviors; malicious behavior features are determined; and the malicious program behavior feature library is constructed.

The embodiment of the invention relates to a method and device for realizing automatic model construction, electronic equipment and a storage medium. The method for realizing the automatic model construction comprises the steps of obtaining related data of a specified task based on the specified task of a specified service scene; responding to an AI application creation instruction of the specified task, and obtaining AI application configuration information; based on the AI application configuration information, creating an AI application, wherein the AI application is a service program instance and is at least used for performing model scheme exploration based on the related data and the AI application configuration information to obtain a model scheme; in response to a starting instruction of the AI application, deploying the AI application online to obtain online related data of the specified task, wherein the AI application is further used for performing model self-learning basedon the online related data and the model scheme to obtain an online model. Thus, for personnel without machine learning professional knowledge, automatic model construction can be realized by specifying service scenes, tasks and AI application configuration information, and the model construction cost is reduced.

The invention discloses a power distribution network planning monitoring system which comprises an acquisition module, a communication module and a master control module. The master control module comprises a central processor, a hard point table modification submodule, a power grid structure model construction submodule and a parameterized DMU power grid model building submodule. Through the master control module, according to collected power grid data, a hard point table is modified, then a hard point grid construction model is established based on the modified hard point table, the parameterization of the hard point grid construction model is carried out to obtain a power grid dynamic parameterization model, and the automatic construction of a power grid model and the real-time monitoring of a power grid are achieved. The time of constructing each monitoring end power grid model can be reduced, thus the effectiveness of power grid control is improved, and the smoothness and efficiency of a safe operation are improved.

The invention discloses a method and device for creating a portrait of a party. The method comprises the steps that a target party is looked up from a pre-established judicial domain body, wherein thejudicial domain body includes a body concept and structure data for describing attributes of the body concept, and the body concept includes the party; after the target party is looked up, structuredata for describing attributes of the target party in the structure data input by a user is selected or received from the structure data for describing attributes of the body concept; according to theselected or received structure data for describing the attributes of the target party, the portrait of the target party is established. The technical problem is solved that the portrait of a party cannot be automatically established in the related art.

The invention discloses an OPC UA information model automatic construction method based on a structured database, which mainly solves the problems of high professional knowledge requirement, large workload and the like of manual construction of an OPC UA information model during traditional factory interconnection and interworking upgrading and reconstruction, and comprises the following implementation steps: importing an existing structured database of a production line; analyzing database mode information containing equipment and attributes, and mapping the database mode information into a triple set; generating an OWL file based on the triple; mapping to generate an XML file; converting to generate an information model XML file conforming to the OPC UA specification; generating a. C file and a. H file; creating an OPC UA server, and instantiating the information model. Starting from the requirement of automatically and efficiently constructing the OPC UA information model, the information model is automatically constructed according to the defined mapping rule on the basis of the existing structured database, so that the tedious operation of manually constructing the informationmodel one by one during OPC UA data communication transformation is greatly reduced, the transformation efficiency is improved, the practicability is high, the practicability is high, and wide application prospects are realized.

The invention discloses a power distribution network planning monitoring system which comprises an acquisition module, a communication module and a master control module. The master control module comprises a central processor, a hard point table modification submodule, a power grid structure model construction submodule and a parameterized DMU power grid model building submodule. Through the master control module, according to collected power grid data, a hard point table is modified, then a hard point grid construction model is established based on the modified hard point table, the parameterization of the hard point grid construction model is carried out to obtain a power grid dynamic parameterization model, and the automatic construction of a power grid model and the real-time monitoring of a power grid are achieved. The time of constructing each monitoring end power grid model can be reduced, thus the effectiveness of power grid control is improved, and the smoothness and efficiency of a safe operation are improved.

The invention relates to a BERT-based film and television work regional knowledge graph construction method, and the method comprises the steps of collecting film and television work text data, constructing a regional domain dictionary, carrying out the preprocessing and word segmentation of the text data, and obtaining the regional associated data of the film and television work; defining entities in the regional associated data, and establishing an association relationship between the entities; marking entities and entity relationships in the regional associated data of the film and television works; training the BERT model; extracting the unlabeled film and television works by utilizing a BERT model to obtain an entity relationship of the film and television works; and storing the obtained entity relationship of the film and television works into a graph database to obtain a regional characteristic knowledge graph of the film and television works. The invention further discloses a corresponding knowledge graph construction system. According to the invention, automatic construction of the regional characteristic knowledge graph is realized, and the constructed regional characteristic knowledge graph of the film and television works is beneficial for culture propaganda personnel and researchers to establish visual impressions of regional characteristics of the film and television works and analyze regional differences of the film and television works.

The invention provides a behavior constrained indoor three-dimensional scene automatic construction method, which comprises the steps of determining a room, parameters of the room and first behavior semantic according to input information; acquiring a corresponding first object category according to the first behavior semantic; determining a corresponding first reference layout map and three-dimensional models of objects in the room according to the first object category and the parameters of the room; and guiding to generate an indoor three-dimensionsl scene of the room according to the firstreference layout map and the three-dimensional models.

The invention relates to a big data information collection system, and the system comprises a first database which is used for storing data collected from external data to the first database through a first transmission channel at a transmission speed V10; a collecting module which is connected with the first database through a second transmission channel and used for screening data matched with the key character string from the first database according to the input key character string, the collecting module comprises an establishing unit and a screening unit, the establishing unit is used for establishing the second transmission channel, the screening unit is used for transmitting the data screened from the first database to the acquisition module through a second transmission channel at a second transmission speed V20; and a central control module which is connected with the first database, the collecting module and the display module. By adjusting the first transmission speed and the second transmission speed, transmission speed matching is carried out according to the data transmission quantity during storage after transmission and data screening, efficient transmission of data is realized, and the data acquisition efficiency is improved.