63 results about "Smart government" patented technology

The embodiment of the invention provides a government affair data exchange method and device based on a block chain, and the method comprises the steps: carrying out the input operation of the business data of each government department according to a preset uplink data model; the input service data is audited based on a consensus mechanism, if the audit is passed, the service data is uploaded tothe block chain, and all nodes on the block chain are notified, so that the nodes can access the service data; and according to the government affair data exchange requests sent by the nodes and the data access authorities of the nodes, service data on the block chains related to the government affair data exchange requests are exchanged. According to the embodiment of the invention, the block chain technology is applied to the government affair data exchange scene, the problems of information confirmation, information confidentiality and information tamper-proofing existing in cross-domain data circulation and sharing are solved, cross-domain sharing of government affair data, multi-department communication, power-assisted supervision and collaborative promotion of execution departments are promoted, and the data fusion appeal of smart government affairs is met.

The invention discloses a government affair service intelligent question-answering method and system. The method comprises the following steps: obtaining government affair service content consulted bya user; preprocessing government affair service content consulted by the user; and matching the preprocessed user consultation government affair service content with a pre-constructed knowledge graph, and outputting the matched government affair service content. With the help of a knowledge graph technology, policy laws and regulations and business acceptance flows which are open to the public ingovernment affair services are learned and concluded, and a knowledge base model is established; through intelligent semantic understanding, user questions are sorted and concluded, and an existing knowledge base is configured; and by means of animation image design and dialogue questioning and answering, government affair service intelligent questioning and answering are provided for the public,an intelligent government service platform is created, and brand new feelings of 'smart government 'are brought to users.

The invention relates to a real estate service administration chain platform based on a block chain technology. The real estate service administration chain platform comprises at least one bank node,at least one real estate node, at least one residence bureau node, at least one tax node and a unified certificate library node, wherein the bank node, the real estate node, the residence bureau node,the tax node and the unified license library node are all provided with micro-service systems used for carrying out data reading / writing service with other nodes which belong to the real estate service administration chain platform and are not the nodes of the micro-service systems; and the micro-service system of each node in the real estate service administration chain platform is realized according to a consensus mechanism in the real estate service administration chain platform when reading / writing data. According to the real estate service administration chain platform, a user does not need to run more among functional departments, data running can be achieved, and the smart government affair internet convenience service under the block chain is completed.

The embodiment of the invention belongs to the technical field of artificial intelligence, can be applied to the field of smart government affairs and / or medical science and technology, and relates toa news recommendation method and device, computer equipment and a storage medium, and the method comprises the steps: inputting a received news document into a semantic extraction model of a preset initial recommendation model, and obtaining a semantic feature representation vector; calculating an entity feature representation vector of a single entity in the news document; aggregating all the entity feature representation vectors to obtain an aggregated representation vector; processing the aggregation representation vector, the semantic feature representation vector and a preset user vectorto obtain a prediction result; and calculating a loss function value of the initial recommendation model, iteratively training the initial recommendation model until the initial recommendation modelconverges, obtaining a trained recommendation model, and recommending news to the user based on the trained recommendation model. The trained recommendation model can be stored in a block chain. According to the invention, the news recommendation dimension is enhanced.

The invention relates to the technical field of man-machine conversation in artificial intelligence, and provides a user intention identification method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining text information provided by a user side, and obtaining a plurality of built-in verbal skills from a preset intention identification system; takingthe built-in verbal skill of which the intention similarity with the text information reaches a first preset threshold value as a candidate verbal skill; obtaining a classification result of the candidate verbal skill according to the trained positive and negative meaning classification model; obtaining a positive and negative meaning score of the candidate verbal skill based on the classificationresult; obtaining a candidate value of each candidate verbal skill according to the candidate verbal skill and the intention similarity; and selecting a candidate verbal skill as an intention recognition result according to the candidate value. According to the embodiment of the invention, the method can solve a problem that a user intention recognition technology in the prior art is lower in user intention recognition precision. The invention also relates to a blockchain technology, and the method can be applied to the field of smart government affairs, thereby promoting the construction ofsmart cities.

The invention relates to the technical field of data query, and can be applied to a smart government affair scene. The invention discloses a structured and unstructured data query method, device and equipment, and a storage medium. The method comprises the following steps: receiving a data query request carrying a service type identifier sent by a query terminal, obtaining a target form corresponding to the service type identifier from a target database based on the data query request, the target form comprising a structured field and an unstructured field, and performing classification querybased on the service type to improve the data query efficiency; according to the structured field and the unstructured field, querying structured data and unstructured data from a first preset database and a second preset database respectively, sending the structured data and the unstructured data to a query terminal. On the basis of the structured data and the unstructured data, the data query efficiency is improved while the data security is considered.

The invention relates to the technical field of data analysis, and particularly discloses an interface flow control method and device, computer equipment and a computer readable storage medium. The method comprises the following steps: extracting request information carried by an interface request by intercepting the interface request sent by a client; based on the request information, acquiring user dimension information of the client, wherein the request information comprises a uniform resource locator and a request parameter; determining whether to perform flow control on the client according to the uniform resource locator, the request parameter and / or the user dimension information; and if it is determined that flow control is performed on the client, sending interception informationto the client, thereby realizing flexible configuration according to the user dimension, not only protecting the system, but also improving the user experience of the whole platform. Meanwhile, the invention also relates to a blockchain technology, and the method can be applied to the fields of smart government affairs, smart education, smart medical treatment and the like, thereby further promoting the construction of smart cities.

The embodiment of the invention belongs to the blockchain technology, is applied to the field of smart government affairs, and relates to a numerical verification method based on a blockchain, which comprises the following steps: receiving a numerical verification request sent by a user terminal, the numerical verification request being used for generating a preset processing condition; obtainingauthorization information of the user terminal according to the numerical verification request; obtaining an encryption numerical value from a blockchain node authorized by a user terminal according to the authorization information, the encryption numerical value being data calculated according to the preset processing condition; calculating an encryption numerical value through zero knowledge proof to obtain a result numerical value; and verifying the result value according to the verification condition to obtain a value verification result, wherein the privacy information / result data numerical value verification result of the user can be stored in the block chain. The invention further provides a numerical verification device based on the block chain, computer equipment and a storage medium. The technical problem that in the prior art, the authenticity and safety of numerical values cannot be guaranteed in numerical value verification is solved.

The invention relates to the field of artificial intelligence, and discloses a language model training method, which comprises the steps of inputting a modified MLM task and a modified NSP task into afirst Bert model for training to obtain a first model parameter corresponding to the first Bert model; applying the first model parameter to a second Bert model, and training the second Bert model through the modified MLM task and the modified NSP task; judging whether an output result of the second Bert model reaches a preset condition or not; and if so, judging that the second Bert model reaches the use standard. A structure and a training method of a Bert model are improved, the application range and accuracy of migrating the pre-trained language model to the specific application scene areexpanded, and the improved Bert model is trained under the current optimized task data, so that the training model can be more suitable for the specific application scene or field, the recognition effect is better, and the specific application scene according to the real-time request is ensured. The method is also suitable for the field of smart government affairs, thereby promoting the construction of smart cities.

The embodiment of the invention belongs to the technical field of semantic analysis in artificial intelligence, is also suitable for the field of smart government affairs so as to promote the construction of smart cities, relates to a quality evaluation method and device applied to telephone customer service, computer equipment and a storage medium, and further relates to a blockchain technology.Question and answer audio data of a user can be stored in the block chain. According to the quality evaluation method applied to the telephone customer service provided by the invention, the telephoneservice content of the customer service staff is collected, and the telephone service operation of the customer service staff is comprehensively evaluated from two directions of verbal skill flow andverbal evaluation, so that the defect that the traditional method depends on subjective evaluation of a customer object is overcome; and evaluation is carried out objectively from the service process, the reference value of customer service evaluation is effectively improved, and meanwhile customer service staff are effectively promoted to continuously improve the service quality of themselves.

The invention provides a deep neural network interpretation method and device, a terminal and a storage medium. The invention relates to the technical field of artificial intelligence, and the methodspecifically comprises the following steps: determining all target data from a plurality of input data through a result output by a deep neural network; and respectively inputting the target data intoan interpretation factor prediction model to obtain a group of interpretation factors corresponding to each piece of target data, performing statistics on the occurrence frequency of each interpretation factor in the plurality of groups of interpretation factors, performing sorting, and screening a target number of interpretation factors with the highest rank as target interpretation factors of apreset target category. According to the invention, the explanation factor of the prediction result is obtained through the pre-trained explanation factor prediction model, so main factors influencing the deep neural network prediction result are explained; the invention can be applied to smart government affairs, smart city management, smart communities, smart security and protection, smart logistics, smart medical treatment, smart education, smart environmental protection and smart traffic scenes, so that the construction of smart cities is promoted.

The embodiment of the invention belongs to the field of image processing, is applied to the field of smart government affairs, and relates to a document image copying detection method, which comprisesthe steps of performing sampling processing on a document image to obtain a sampled image; filtering the sampled image to obtain a first document sub-image, a second document sub-image and a third document sub-image which are obtained through low-pass processing, horizontal high-pass processing and vertical high-pass processing respectively; integrating the first document sub-image, the second document sub-image and the third document sub-image to obtain a to-be-detected image; performing molar feature extraction on the to-be-detected image to obtain a first fixed length vector; and inputtingthe first fixed-length vector into a trained linear classifier, and outputting to obtain a copying detection result of the document image. In addition, the invention also relates to blockchain technology, and document images are also stored in the blockchain. The technical problem of reshooting and false detection in the prior art is solved.

The invention relates to the technical field of artificial intelligence, is applied to the field of smart government affairs, and provides a work order information processing method, device andequipment and a storage medium, which are used for improving the efficiency of abnormal work order identification and processing. The work order information processing method comprises the steps: carrying out target abnormal work order field selection and data cleaning on a historical work order information table, and obtaining to-be-processed data, wherein the historical work order information table comprises an information piece table, an information provider table, a related subject table and a related customer body surface; training a preset initial decision tree work order recognition model through the to-be-processed data to obtain a target decision tree work order recognition model; performing target abnormal work order field analysis on the to-be-processed work order information through a target decision tree work order identification model to obtain a work order analysis result; and executing a business process corresponding to the target business process information corresponding to the work order analysis result. In addition, the invention also relates to a block chain technology, and the historical work order information table can be stored in a block chain.

The invention discloses a question and answer library construction method. The method comprises the steps of obtaining a customer service dialogue statement; performing statement extraction on the customer service dialogue statement according to a preset keyword to obtain a questioning statement; carrying out vector conversion on the questioning statement to obtain a statement vector; according toa preset mass point vector and the statement vector, carrying out incremental clustering on the questioning statement to determine a category corresponding to the questioning statement; and constructing a customer service question and answer library according to the questioning statement and the category corresponding to the questioning statement. The invention further provides a question and answer library construction device, electronic equipment and a storage medium. The construction speed of the question and answer library can be increased. Moreover, the invention relates to the technicalfield of data processing and artificial intelligence, also relates to a blockchain technology, and the content of the question and answer library can be stored in blockchain nodes, and meanwhile, theinvention can also be used in the fields of smart government affairs, smart medical treatment or smart education, thereby promoting the construction of smart cities.

The invention relates to the technical field of artificial intelligence, and provides an information identification method based on weak supervised learning. The method comprises the following steps:acquiring a plurality of common question answering FAQ data in a government affair scene, and constructing a first label data set based on the plurality of FAQ data; performing multi-label text classification on the first label data set by using a first convolutional neural network CNN to obtain a multi-label CNN model; acquiring a plurality of second label data sets, and adjusting the multi-labelCNN model by using the plurality of second label data sets to obtain a final multi-label classifier; receiving an input user question; inputting the user question into the final multi-label classifier to obtain a plurality of government affair entities matched with the user question; and outputting the plurality of government affair entities. The invention also relates to a blockchain technology,and the plurality of government affair entities can be uploaded to a blockchain. The method can be applied to the fields of smart government affairs, smart communities and the like needing information identification, so that the development of smart cities is promoted.

The embodiment of the invention belongs to the field of image processing, is applied to the field of smart enterprises or smart government affairs of smart cities, and relates to a needle type printing character image generation method, which comprises the following steps: receiving a character image generation request which comprises a character string; selecting at least one picture from a preset picture library as a background image according to the character string; based on the background image, the character string and the font file, character image synthesis being carried out in a detection resampling mode, and an initial image being obtained; and performing disturbance processing on the initial image through a moving least square method to obtain a target needle type printing character image. The invention further provides a needle type printing character image generation device, computer equipment and a storage medium. In addition, by adopting the method, the technical problem that in the prior art, for character printing distortion caused by paper unevenness, the generated needle type printing character image cannot meet the requirement of model training is solved.

The embodiment of the invention belongs to the technical field of artificial intelligence, and relates to a picture information extraction method and related equipment, which can be applied to the field of smart government affairs, and comprises the steps of obtaining a target picture, and detecting an information bounding box of each element in the target picture; performing coarse sorting on theelements according to the information bounding box to obtain a coarse sorting element table, and obtaining a high-confidence line of the target picture based on the coarse sorting element table; calculating the central coordinate of each element in the high-confidence row, and calculating the slope of the high-confidence row according to the central coordinate; obtaining center coordinates of allelements in the target picture, and determining row fragments of the elements belonging to the same row and column fragments of the elements belonging to the same column according to the center coordinates and the slope; and reordering all the elements according to the row fragments and the column fragments to obtain a structured information table corresponding to the target picture. In addition,the invention also relates to a blockchain technology, and the structured information table can be stored in the blockchain. According to the method, accurate extraction of the picture information isrealized.

The invention relates to the field of artificial intelligence, can be applied to the field of smart government affairs, and discloses a food safety risk assessment method, device and equipment and a storage medium, which are used for improving the efficiency and accuracy of food safety risk assessment. The method comprises the following steps: acquiring risk characteristic data of a plurality of catering enterprises; determining a positive sample and a negative sample according to the risk characteristic data; generating a training set according to the positive sample and the negative sample,and inputting the training set into a preset decision tree model for training to obtain a target decision tree; respectively obtaining a path from a root node of the target decision tree to each leafnode, and generating a corresponding food safety risk feature combination according to each path, calculating a corresponding risk assessment value, marking the risk assessment value on a corresponding leaf node of the target decision tree to obtain a food safety risk assessment model, and performing food safety risk assessment on the catering enterprise to be assessed, wherein the risk characteristic data of the catering enterprise can be stored in the block chain.

The invention relates to the technical field of artificial intelligence, and can be applied to the field of smart government affairs, thereby promoting the construction of smart cities. The inventionprovides a seal printing method and device, electronic equipment and a storage medium, and the method comprises the steps: receiving a seal printing instruction which carries a to-be-printed file; ifthe file format of the to-be-printed file is inconsistent with a preset file format, performing format conversion on the to-be-printed file to obtain a target file; if the file size of the target fileis greater than a preset file size threshold, performing double-page cutting on the target file to obtain a plurality of cut files; and if the file sizes of the plurality of cut files are all smallerthan or equal to the preset file size threshold, performing seal printing on the plurality of cut files to obtain a seal file. The seal printing efficiency can be improved. In addition, the inventionfurther relates to a blockchain technology, and the seal file can be stored in a blockchain.

The embodiment of the invention belongs to the technical field of big data, is applied to the field of smart government affairs, and relates to an interface performance early warning method based on a linear regression model and related equipment thereof. The interface performance early warning method comprises the steps of obtaining interface performance feature data of an API interface corresponding to each agent node of each distributed monitoring system based on a preset time window; performing statistics on the interface performance feature data of each API interface according to the dimensions of the data to obtain a target feature value of each dimension, and constructing a target linear regression model based on the target feature values; predicting an interface feature value of a next time window based on the target linear regression model; and judging whether the interface characteristic value exceeds a characteristic threshold value or not, and if the interface characteristic value exceeds the characteristic threshold value, executing an early warning operation to remind a developer to debug the API, wherein the target linear regression model can be stored in the block chain. According to the invention, the interface with potential performance reduction can be early warned in advance.

The invention relates to the technical field of artificial intelligence, is applied to the field of smart government affairs, and provides a text region recognition method, device and equipment and a storage medium, which are used for improving the recognition accuracy of a business bill key text region. The text region recognition method comprises the steps of performing region segmentation on a to-be-processed business bill image and performing direction adjustment to obtain a preprocessed business bill image; performing text distribution type classification on the preprocessed business bill image through an image classification network based on an attention mechanism to obtain target text distribution type information; performing textbox detection on the preprocessed business bill image based on the target text distribution type information through a preset text detection network to obtain a target textbox; and performing optical character recognition on the target textbox through a preset end-to-end text recognition network to obtain text region recognition information. In addition, the invention also relates to a block chain technology, and the to-be-processed business bill image can be stored in a block chain.

The invention provides a government affair second batch service realization method and a service system, and belongs to the field of smart government affairs. The implementation method comprises the following steps: constructing a second batch service database based on big data; performing second abortive item configuration on the second batch service database; receiving item data and service dataof a user by the second batch operation management module, generating service circulation data and sending the service circulation data to the second batch service management module. The service circulation data is subjected to second batch auditing and certification in a second batch service management module, and then a second batch result is pushed to the user; and meanwhile, by updating and storing the data in real time, business query, item query and second abortive business statistics are realized. According to the system and the method, online application of government affairs, unmanned intervention automatic approval service and second batch government affairs service to which approval results are actively and timely sent are realized, approval efficiency is improved, dynamic comparison and verification of approval states of applicants are realized by business departments, and data support is provided for in-event and after-event supervision.

The embodiment of the invention belongs to the technical field of big data, is applied to the field of smart government affairs, and relates to an in-job employee portrait generation method and device, computer equipment and a storage medium, and the method comprises the steps: cleaning historical resume data, and obtaining a historical dimension factor, a historical dimension factor weight, a historical dimension factor label and a historical dimension factor label weight; extracting a keyword in the resume of the employee, and obtaining a target dimension factor; obtaining a target dimension label according to the target dimension factor, and calculating a personal factor score based on the target dimension factor, the historical dimension factor weight, the target dimension label and the historical dimension factor label weight; subtracting the personal factor score from a preset classification score to obtain a difference value, and determining a candidate position according to the difference value and the personal factor score; and obtaining a position dimension factor corresponding to the candidate position, and generating a target portrait of the employee based on the position dimension factor. Historical dimension factors may be stored in a blockchain. According to the invention, a more accurate employee portrait is constructed.

The invention relates to the technical field of data processing, and is applied to a smart government affair scene, thereby promoting the construction of a smart city. A document generation method comprises the following steps: receiving a document generation instruction; determining a target template according to a template identifier carried by the document generation instruction; according to avariable carried by the document generation instruction, replacing elements in the target template to obtain a replacement document; and according to a preset label of the replacement document, performing corresponding processing on the replacement document to generate a target document, the processing including display processing, hiding processing and logic judgment processing. The invention further provides a document generation device, electronic equipment and a storage medium. According to the invention, the document generation efficiency can be improved. In addition, the invention alsorelates to a blockchain technology, and the target document can be stored in a blockchain.

The invention relates to the technical field of artificial intelligence, can be applied to the field of smart government affairs, and provides a material data processing method and device, computer equipment and a storage medium.The method comprises the steps of obtaining an input material package; splitting the material bag to obtain a plurality of parts of materials; generating a keyword set corresponding to each material; acquiring a specified material guide standard corresponding to each material from a guide standard database; based on each keyword set, respectively calculating a matching degree value of each material and a target material guide standard; determining a target material corresponding to a target material guide standard from all materials based on the matching degree value; and obtaining a target material category of the target material guide standard, and executing uploading processing on the target material based on the target material category. The processing efficiency of material uploading can be improved, and the accuracy of material uploading is ensured. The method and device can also be applied to the field of block chains, and the target material can be stored on the block chain.

The invention relates to the technical field of artificial intelligence, can be applied to the field of smart government affairs of smart cities, and provides a data final settlement method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining to-be-final settlement data through a system interface and a preset data warehouse; according to a preset first final settlement formula, performing final settlement on the to-be-final settlement data to obtain final settlement data; verifying the final settlement data to obtain a verification result, the verification mode including verification according to a preset verification formula, and / or according to a preset access rule, and / or using a table connection operation; if the verification result is that the final settlement data passes the verification, summarizing the final settlement data to obtain summarized data; and sending the summarized data to a preset terminal. In addition, the inventionalso relates to a blockchain technology, and the summarized data can be stored in a blockchain. According to the invention, the accuracy of final settlement data can be ensured, and the efficiency ofdata final settlement is improved at the same time.

The invention provides a smart city planning and design method, comprising the following steps: (1) adopting a set theory method to define a triple spatial entity of a smart city modular model; 2, design that internal space of each unit body in the modularization; 3, design a connection mode of each unit body in that modularization; 4, design a smart city model, wherein that smart city model relates to the smart city management, the smart community, the smart transportation, the smart education, the smart government and the smart medical treatment, and each aspect comprise a computing module and a service module. This method adopts digital design tool, based on modularization, The smart city construction scheme has parallel abstractness, flexibility and scalability, reasonable granularity,feasibility, lower coupling between components, and higher reuse rate of design method, because the module is organically linked with the function module of smart city by grid and three-dimensional bottom-up design of combination law and unit conceptual design.

The invention discloses a multi-platform authority unified management method and device, a terminal and a storage medium, and the method comprises the steps: obtaining user information provided by a third-party platform, wherein the user information comprises label information, and the label information is set when the user information is built; receiving at least one label expression fed back bythe third-party platform and permission configured for the label expression; after a target user group corresponding to each label expression is inquired, configuring corresponding permission for thetarget user group to acquire permission configuration information; and synchronizing the authority configuration information to the third-party platform. According to the invention, the authority is configured through the label expression and based on the label expression and the label information of the user, so that different platforms can carry out personalized authority configuration, and theauthority configuration method can be applied to smart government affairs, smart city management, smart communities, smart security and protection, smart logistics, smart medical treatment, smart education, smart environmental protection and smart traffic scenes. Therefore, the construction of a smart city is promoted.

The embodiment of the invention belongs to the field of big data, is applied to the field of smart government affairs / education, and relates to a knowledge graph-based guidance and instigation corpusdetection method and related equipment, and the method comprises the steps of receiving a standard corpus data set, performing feature extraction on the standard corpus data set, and obtaining standard corpus features, wherein no guidance and instigation information exists in the standard corpus data set; constructing a first knowledge graph based on the standard corpus features; receiving to-be-detected corpora, performing named entity identification on the to-be-detected corpora to obtain to-be-detected entities, and performing deduction on each to-be-detected entity in the first knowledge graph; and when the to-be-detected entities fail in deduction, taking the to-be-detected entities failing in deduction as guidance and instigation entities, taking to-be-detected corpora correspondingto the guidance and instigation entities as guidance and instigation corpora, and outputting the guidance and instigation corpora, wherein the first knowledge graph can be stored in a blockchain. According to the method, the guidance and instigation corpus can be quickly identified, so that the guidance and instigation behavior is detected.

The invention discloses a policy file processing method and device based on a knowledge graph, a storage medium and computer equipment, relates to the field of artificial intelligence, and can be applied to the field of smart cities or smart government affairs. The method comprises the steps of obtaining a target policy file and a contrast file of the target policy file; according to the policy knowledge graph, obtaining at least one piece of difference information of the target policy file and the contrast file; generating contrastive analysis suggestion information of the target policy fileaccording to the at least one piece of difference information and the annotation information of the at least one piece of difference information in the policy knowledge graph. According to the method,the target policy file and the contrast file are processed according to the policy knowledge graph, and the contrastive analysis suggestion information is automatically generated according to the difference information and the annotation information, so that various key information and difference information in the target policy file and the contrast file can be effectively captured, the policy file analysis processing efficiency is improved, user workload is reduced.