Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

139results about How to "Improve intelligibility" patented technology

Three-dimensional geological modeling parameter optimization method and system based on deep learning

The invention provides a three-dimensional geological modeling parameter optimization method and system based on deep learning, and relates to the field of geological prospecting and modeling.The method comprises the steps that drilling data and remote sensing data of a geological prospecting area are obtained, and multi-source geological data of three-dimensional geological modeling are formed; generating geological profile map data of the geological features according to the drilling data, generating landform profile map data corresponding to the topographic features according to the remote sensing data, and extracting boundary information of the geological exploration area; carrying out gridding processing on a three-dimensional space, dividing a geologic body of the geological exploration area into a plurality of small grid units, and defining geological modeling parameters; the preliminary three-dimensional geological grid model is constructed according to the geological profile map data, the landform contour map data and the boundary information, the size and the resolution of the grid are dynamically adjusted according to the geological change area, the three-dimensional geological model is obtained through optimization and adjustment, the modeling precision is improved, manual intervention is reduced, and computing resources are saved.
Owner:崂山国家实验室

Medical data document classification and marking system

The invention relates to the technical field of medical data management, in particular to a medical data document classification and marking system which comprises a document structure analysis module, a semantic information identification module, a classification and marking module and a document intelligent label module. According to the method, document visualization and retrieval efficiency is improved by analyzing document content and extracting titles, texts and appendixes, analytic performance and operability of data are enhanced by identifying key information and semantic relations and accurately extracting and labeling medical terms, medicine research data and medical record records, storage is optimized according to priorities in combination with classification and marking, and the method is high in practicability and easy to popularize and use. Clinical values and application scenes of documents are clarified, document management processes are refined, management compatible with clinical data formats is formed through structured storage of marked data and classification label generation, storage normalization and retrieval efficiency are improved, the requirement for accurate information calling in clinical tests is met, document management capacity is improved, and the document management efficiency is improved. And support is provided for improvement of clinical decision-making and research efficiency.
Owner:BEIJING HIGHTHINK PHARM TECH SERVICE CO LTD

Construction planning visualization method and system for refuse transfer station

The invention relates to the field of construction planning visualization, in particular to a construction planning visualization method and system for a refuse transfer station. The method comprises the following steps: acquiring a satellite positioning map and a refuse transfer station design drawing of a to-be-developed area; image detail reconstruction is carried out on the satellite positioning map, road space distribution fitting is carried out, and a regional road distribution network is constructed; performing surrounding building positioning calculation on the detail optimization reconstruction satellite image based on a regional road distribution network, performing an optimal site selection decision, and extracting an optimal address region image; carrying out transfer station key feature point identification on the refuse transfer station design drawing, then carrying out three-dimensional point cloud modeling, and constructing a transfer station three-dimensional structure model; and according to the optimal address area image, carrying out corresponding foundation accurate matching on the transfer station three-dimensional structure model, carrying out spatial positioning mapping, and constructing a transfer station address twinborn model. According to the method, the operation efficiency of the transfer station is improved, and the rationality of building planning is enhanced.
Owner:URBAN PLANNING & DESIGN INST OF SHENZHEN UPDIS

Report automatic generation retrieval enhancement optimization method and system based on local knowledge base

The invention discloses a retrieval enhancement optimization method and system based on automatic generation of a local knowledge base report, and provides a reconstruction retrieval enhancement controllable generation architecture which comprises the steps of preprocessing a document, extracting a document structure, removing invalid content, partitioning the document, vectorizing the document and storing the document into a database; the question reconstruction module is used for disassembling a user question into four parts, namely a retrieval keyword, a user intention, question rewriting and question expansion; the retrieval enhancement module is used for combining, filtering, reordering, compressing and aligning retrieval results of retrieval keywords by applying a keyword search method, problem rewriting and problem expansion by applying a vector semantic retrieval method; and finally, combining a retrieval result with a user intention, and generating text content based on a local knowledge base by applying a specific prompt template. According to the method, the unstructured file is subjected to structure standardization, chart and picture information is extracted, user input is subjected to disassembly, reconstruction and extension, and a document in a specific format is generated based on local knowledge.
Owner:ANHUI UNIV OF TECH SCI & TECH PARK CO LTD

Automobile seat capable of actively reducing road noise and noise reduction method thereof

The invention discloses an active road noise reduction automobile seat and a noise reduction method thereof.The active road noise reduction automobile seat comprises an active road noise reduction system arranged in the automobile seat, and the active road noise reduction system comprises an active noise reduction signal processing controller, an active noise reduction signal processing module and an active noise reduction signal processing module; the road noise source signal sensor, the anti-phase noise elimination loudspeaker, the anti-phase low-frequency vibrator, the error microphone and the power amplifier circuit are connected with the active noise reduction signal processing controller; the road noise source signal sensor is arranged at the bottom of an automobile seat and used for collecting road noise signals. The reverse-phase noise elimination horn and the reverse-phase low-frequency vibrator are arranged on a headrest of an automobile seat or near the headrest and are used for providing reverse-phase road noise signals; the error microphone is arranged on a headrest part of the automobile seat or near the headrest part and is used for acquiring environmental noise near the headrest part. The invention discloses an automobile seat capable of actively reducing road noise and a noise reduction method thereof, and the road noise transmitted into an automobile through an automobile chassis is reduced through the active noise reduction method.
Owner:ACOUSTEER LTD

Power knowledge question-answering system construction method and system in combination with engineering ethical analysis

The invention discloses an electric power knowledge question-answering system construction method and system combined with engineering ethical analysis, and the construction method comprises the steps: constructing all modules, and carrying out the fine adjustment of a large language model based on a P-Tuning method, so as to construct an electric power system question-answering knowledge base; the question understanding and classification step is responsible for receiving input questions of a user and performing semantic analysis, technical classification and ethical risk identification on the input questions; searching background knowledge; carrying out engineering ethical analysis; generating questions and answers; and a feedback and improvement step: entering a model tuning stage, and carrying out adaptive tuning on the model by adopting a reinforcement learning framework. According to the method, comprehensive engineering ethical analysis can be carried out on technical schemes and operation suggestions, finally, answers generated by the system are accurate and feasible in technology and have ethical compliance at the same time, it is ensured that a user can balance technical requirements and ethical responsibility in practical application, the intelligent level of an electric power knowledge question-answering system is remarkably improved, and the user experience is improved. And important support is provided for safe operation and sustainable development of the power industry.
Owner:STATE GRID HUBEI ELECTRIC POWER INFORMATION & TELECOMMUNICATION COMPANY

Heterogeneous multi-source frozen circle big data exploration and analysis method and system based on space-time segmentation

The invention discloses a heterogeneous multi-source frozen circle big data exploration and analysis method and system based on space-time segmentation, and belongs to the technical field of data analysis. The method comprises the following steps: collecting and preprocessing freezing ring data; dividing the research area into space-time grid units; performing heterogeneous data fusion on the frozen circle data in each time space grid unit; and identifying modes and anomalies in the space grid units based on the fused frozen circle data, and / or predicting the future change trend of the frozen circle. According to the invention, high-efficiency exploration and analysis of frozen circle big data are realized.
Owner:COMP NETWORK INFORMATION CENT CHINESE ACADEMY OF SCI

Long-distance ad hoc network full duplex voice communication system for fire fighting

The invention discloses a fire-fighting long-distance ad hoc network full-duplex voice communication system, which relates to the technical field of voice communication, and realizes whole-staff real-time voice acquisition through cooperative work of a microphone array module, a noise sensing module, a noise filtering module, a communication state evaluation module and a signal gain adjustment module. Two-way voice communication between firefighters and between the firefighters and a command center is ensured, in a fire rescue site, the noise sensing module can accurately recognize various background noise in a fire environment, such as explosive sound or equipment operation sound, and noise interference areas are classified and marked in time. The noise filtering module can dynamically adjust the noise suppression coefficient according to the noise type and intensity through a self-adaptive noise suppression algorithm, interference signals are effectively removed, and through real-time and dynamic noise suppression, firemen can clearly receive command information in a complex environment, and misunderstanding or communication faults caused by noise interference are reduced.
Owner:NANJING ZHENGZE TECH

Equipment operation manual vector knowledge base construction method

PendingCN119128219Aachieve unified representationBreaking through the limitations of being unable to efficiently process multi-source heterogeneous dataBiological modelsOther databases indexingSemantic vectorEngineering
The invention provides an equipment operation manual vector knowledge base construction method. According to the method, heterogeneous multi-modal data such as texts, images, videos and three-dimensional models related to equipment are collected, semantic vector coding is conducted on the multi-modal data through a large pre-training model, the multi-modal data are fused into a unified vector space, and vector representation of equipment knowledge is constructed. An efficient index is established based on vector representation, and intelligent retrieval and association services of a semantic level are supported. And an interpretable vector coding technology is also introduced, so that the semantic interpretability of the vector is endowed, and a visual interface is provided for analyzing a vector distribution mode. And continuous expansion and optimization of the knowledge base are realized through active learning and online learning strategies. According to the method, heterogeneous data integration, intelligent semantic service, interpretability enhancement and knowledge automatic updating are realized, intelligent knowledge service support is provided for the fields of equipment operation and maintenance and the like, and the method has important application value.
Owner:SHENHUA HOLLYSYS INFORMATION TECH CO LTD

Voice noise reduction system in multi-noise environment

The invention discloses a voice noise reduction system in a multi-noise environment, and particularly relates to the technical field of voice noise reduction, which comprises a basic division module for dividing voice data into a plurality of basic voice segments with the same duration; the rationality analysis module judges whether segmentation points of adjacent fragments are reasonable or not, and if the segmentation points are not reasonable, the optimization marking module searches for new segmentation points for optimization; the loop module repeatedly verifies the optimization result until all the voice segments are reasonably segmented; the noise reduction module extracts voice and noise features, and performs noise reduction processing by using a noise reduction strategy selection model; the recombination module recombines the voice segments after noise reduction into complete voice output; according to the invention, the voice signal is divided into a plurality of segments, the most suitable noise reduction algorithm can be matched for each segment according to the noise feature of each segment, and the method can cope with a more complex and unstable noise environment through a dynamically adaptive noise reduction strategy, and guarantees that the voice quality is better improved in various scenes.
Owner:HANGZHOU HUA TING TECH CO LTD

Data retrieval method and system for gene bank and storage medium

The invention relates to the technical field of bioinformatics, in particular to a gene pool data retrieval method and system and a storage medium. The method comprises the following steps: acquiring multi-source genome data, performing quality control on the multi-source genome data based on an FAIR principle, and performing efficient storage and indexing by utilizing a distributed storage system so as to obtain a distributed genome database; performing cross-species homology analysis on the distributed genome database, and constructing a multi-level evolutionary tree model, so as to obtain evolutionary relationship map data; mapping gene structures and functions among different species according to the evolutionary relationship map data so as to obtain cross-species gene mapping data; receiving retrieval query data input by a user; and performing query type identification on the retrieval query data to obtain optimized query data. Through the multilevel evolutionary tree model and cross-species gene mapping, gene function comparison and prediction among different species are realized.
Owner:SHENZHEN RAPHA BIOTECHNOLOGY CO LTD

Saline-alkali soil carbon sink estimation system based on machine learning

The invention discloses a saline-alkali soil carbon sink estimation system based on machine learning. The saline-alkali soil carbon sink estimation system comprises a data preparation module used for obtaining remote sensing image data of a target saline-alkali soil area, physicochemical properties of soil and vegetation, meteorological data, hydrological data and man-made data; the feature processing module is used for extracting key features; the model calculation module is used for constructing a saline-alkali soil carbon sink estimation model and obtaining a carbon sink estimation value based on the key features and the saline-alkali soil carbon sink estimation model; and the display module is used for displaying the carbon sink capacity and the change trend thereof in a chart form. By integrating the remote sensing technology, the ground survey, the environment monitoring and the machine learning algorithm, the accuracy and the efficiency of carbon sink estimation are remarkably improved, the ecological value and the improvement potential of the saline-alkali soil can be better evaluated, and a scientific basis is provided for sustainable management and utilization of the land.
Owner:NINGXIA UNIVERSITY

Sound processing method, system and device based on hearing aid and storage medium

The invention provides a sound processing method, system and device based on a hearing aid and a storage medium, and the method comprises the steps: collecting sound signals, including background noise and voice signals, of a hearing aid use environment in a large scale; the sound signals are preprocessed, abnormal values and missing values are processed, the abnormal values and the missing values are scaled into a unified scale, and the sound signals are divided into a training set and a test set; adjusting and optimizing parameters of the standard adaptive filtering model by using an improved gradient descent optimization algorithm, wherein the parameters comprise a filter order, a maximum number of iterations, an initial step length and a regularization coefficient; and inputting the test set into the optimized algorithm to realize optimization processing of the sound signal. According to the invention, the voice definition and the background noise suppression capability can be improved, and the use effect and the user experience of the hearing aid in a complex environment are improved.
Owner:BOYIN HEARING TECH (SHANGHAI) CO LTD

Intelligent layout method and system for underground space

The invention discloses an underground space intelligent layout method and system, and the method comprises the following steps: S1, generating an initial layout through employing a graph theory method based on preset underground space layout knowledge and constraint conditions inputted by a user; s2, optimizing the initial layout through a comprehensive evaluation index by using a multi-objective optimization algorithm; and S3, visually displaying the layout result and the evaluation data. The layout system comprises a layout module, an optimization module and a visualization module, and the optimization module uses a multi-objective optimization algorithm to optimize the generated initial layout through comprehensive evaluation indexes. According to the method, the efficiency of underground space layout design is greatly improved, multiple key indexes such as function compatibility, people flow organization efficiency, average accessibility and space utilization rate are comprehensively considered, and it is ensured that the generated layout scheme achieves optimal balance in all dimensions.
Owner:CHINA RAILWAY SIYUAN SURVEY & DESIGN GRP CO LTD

Multichannel voice signal enhancement method

The invention discloses a multi-channel voice signal enhancement method, and belongs to the technical field of multi-channel voice enhancement. According to the method, the problems that the background noise is difficult to be effectively suppressed and the consumption of computing resources is difficult to be reduced while the voice enhancement effect is ensured, and the generalization ability is insufficient in a complex noise environment and a low signal-to-noise ratio environment in an existing method are solved. According to the method, the voice segment and the noise segment in the signal are determined through the instantaneous energy, the voice signal after first enhancement is obtained through beam forming, the Fusion RNNoise network is suitable for noise segment signal enhancement, and the MCRA-OMLSA method is suitable for signal segment signal enhancement, so that the voice signal after first enhancement is obtained. Therefore, in combination with a FusionRNNoise network and an MCRA-OMLSA method, the voice signal after the first enhancement is enhanced for the second time, and a finally enhanced voice signal is obtained. The method can be applied to the field of multi-channel speech enhancement.
Owner:PEOPLE CN CO LTD

Voice processing method and device, electronic equipment and storage medium

The invention relates to a voice processing method and device, electronic equipment and a storage medium. The method comprises the following steps: extracting voice features of a damaged voice signal to obtain damaged voice features; inputting the damaged voice features into a repaired voice generation network of a voice damage repair model to obtain generated repaired voice features; dividing the repaired voice features according to a plurality of preset sub-bands to obtain sub-repaired voice features corresponding to the sub-bands; inputting the sub-repaired speech features corresponding to the sub-bands into a multi-band speech enhancement network of a speech damage repair model, and performing speech enhancement processing on the corresponding sub-repaired speech features through speech enhancement sub-networks corresponding to the sub-bands in the multi-band speech enhancement network to obtain enhanced speech features of the sub-bands; and generating a deep repair voice signal corresponding to the damaged voice signal based on the enhanced voice feature of each sub-band. According to the invention, the voice quality and intelligibility can be remarkably improved in a scene in which multiple distortions exist at the same time.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD

Helium voice correction method based on generative adversarial network

The invention provides a helium voice correction method based on a generative adversarial network, and belongs to the technical field of voice processing and artificial intelligence. The technical problem of helium voice distortion caused by pitch period distortion and formant offset in a helium-oxygen environment is solved. According to the technical scheme, the method comprises the following steps of S1, preprocessing helium voice data; s2, constructing a special helium voice conversion model; and S3, inputting the preprocessed helium voice data into a voice recognition and semantic similarity evaluation system for processing. The beneficial effects of the invention are that the GAN is adopted as an advanced deep learning model, and the GAN can effectively capture the spectrum details in the voice signals through the multi-layer structure and the excellent unsupervised learning mechanism, thereby remarkably improving the voice correction performance.
Owner:NANTONG UNIV

Question and answer reply generation method and device, computer equipment and storage medium

The invention belongs to the field of artificial intelligence and financial science and technology, and relates to a question and answer reply generation method which comprises the steps that a query text is input into a reply generation model, and the reply generation model comprises an input analysis network, a style recognition network, a retrieval enhancement generation network and a reply selection network; processing the query text through the input analysis network to obtain a text input vector; inputting the user historical dialogue data and the text input vector into a style recognition network to generate a style recognition result; inputting the text input vector and the style recognition result into a retrieval enhancement generation network, and generating a plurality of candidate replies in combination with related document fragments retrieved by a preset knowledge base; a final reply is selected from the plurality of candidate replies through the reply selection network. The invention further provides a question and answer reply generation device, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and the final reply can be stored in the block chain. According to the method, the content meeting the long-term preference and personalized requirements of the user can be generated.
Owner:PING AN TECH (SHENZHEN) CO LTD

Voice restoration method and device, equipment and storage medium

The invention provides a voice restoration method and device, equipment and a storage medium, and the method comprises the steps: enabling a coding feature of a to-be-restored voice obtained at a current moment to be aligned with a target text feature, and obtaining a target feature; the target text feature is a text feature corresponding to a voice at a previous moment output by a decoder of a voice recognition model; based on the target feature, determining a posterior probability of each text corresponding to the to-be-restored voice; based on each posterior probability, determining a text recognition result of the to-be-restored voice; target information is input into a text repairing module of a voice repairing model, a first potential feature output by the text repairing module is obtained, the first potential feature comprises text potential features, and the target information comprises the posterior probabilities and the text recognition result; and repairing the to-be-repaired voice based on the text potential features. According to the embodiment of the invention, the intelligibility of the restored voice can be improved.
Owner:ANHUI IFLYTEK UNIVERSAL LANGUAGE TECH CO LTD

Visualization method for analysis of ex-warehouse goods of e-commerce warehouse

The invention provides a visualization method for analysis of ex-warehouse goods of an e-commerce warehouse, and relates to the technical field of information visualization and visual analysis. The method comprises the following steps: obtaining warehouse-out order data and warehouse-out goods data from a warehouse management system of a warehouse service provider, and storing the data to a database after data processing; based on the warehouse-out order data and the warehouse-out goods data, visual mapping is carried out; and performing visual layout based on a visual mapping result. According to the method, individual and group multi-dimensional comprehensive analysis can be carried out on warehouse-out goods characteristics, joint analysis is carried out on relevance among goods groups and the spatial distribution rule of the goods, high interactivity is achieved, the requirement for initiative analysis of warehouse managers can be met, and the displayed result has high intuition and understandability. Furthermore, good data support can be provided for optimizing goods management decisions, and it is guaranteed that the e-commerce warehouse has high overall operation efficiency.
Owner:SICHUAN UNIV

Rule engine driven power distribution network planning problem library construction method

The invention relates to the technical field of power grid planning, in particular to a rule engine driven power distribution network planning problem library construction method. The method comprises the following steps: acquiring environment information data of the power distribution network; performing data preprocessing on the power distribution network environment information data to generate standard power distribution network environment information data; performing substation site selection on the power distribution network environment information data to obtain power distribution network substation site selection data; carrying out transformer substation capacity distribution on the power distribution network transformer substation site selection data to generate transformer substation capacity distribution data; performing transformer substation layout according to the transformer substation capacity distribution data and the power distribution network transformer substation site selection data so as to generate transformer substation layout data; and carrying out power transmission line path selection on the standard power distribution network environment information data based on the substation layout data to generate power transmission line route data. Through systematic data integration, flexible rule extraction, dynamic decision monitoring and knowledge management, the accuracy and adaptability of power distribution network planning are improved.
Owner:ECONOMIC & TECH RES INST OF STATE GRID HEILONGJIANG ELECTRIC POWER CO LTD

Data monitoring early warning method and system, computer equipment and storage medium

The invention provides a data monitoring early warning method and system, computer equipment and a storage medium, and the method comprises the steps: obtaining a dotting message, transmitting the dotting message to a gateway controller through a controller domain network protocol, and when the gateway controller recognizes that a received message identifier belongs to a controller domain network message of the dotting message, sending the dotting message to the controller domain network protocol; analyzing the dotting data of the controller domain network message, and calling an application programming interface in a server database to perform dotting on the data of the target electronic control unit; and displaying data of the target electronic control unit on a preset display panel based on the dotting result, and performing monitoring and early warning on the data of the target electronic control unit through index data configured in advance or in real time. By displaying the data of the electronic control unit on the preset display panel, the target personnel can be assisted to monitor and analyze the data of the electronic control unit in real time, so that the manual inspection time is shortened, and the efficiency and quality of the whole vehicle test are greatly improved.
Owner:CHONGQING SELIS PHOENIX INTELLIGENT INNOVATION TECH CO LTD

Classroom intelligent terminal integrated with micro host, network access and audio acquisition

The invention relates to the technical field of classroom intelligent terminals, in particular to a classroom intelligent terminal integrating a micro host, network access and audio acquisition. According to the technical scheme, the classroom intelligent terminal integrating a micro host, network access and audio acquisition is provided. Comprising a main control unit, an acoustic array device, a network interface device, a deep learning audio processing unit, a multi-mode interaction device, an adaptive network technology component, an edge computing unit, a virtual reality and augmented reality device, a block chain module and a voice synthesis and emotion recognition module. The system provides more advanced, intelligent and interactive rich education experience, is expected to improve the learning effect and teaching efficiency, has potential revolutionary influence in the education field, and provides a more flexible, personalized and efficient learning environment.
Owner:NANJING JINSHENG YURUN SCI & EDUCATION EQUIP CO LTD

Communication method and device of marine very high frequency equipment, electronic equipment and storage medium

The invention discloses a communication method and device for marine very high frequency equipment, electronic equipment and a storage medium. The method comprises the following steps: determining an original voice signal, performing signal processing on the original voice signal, and determining semantic text data; performing data processing on the semantic text data, and determining effective text data in the semantic text data; generating an effective text signal corresponding to the effective text data, and transmitting the effective text signal to a voice receiving end through a target communication channel; and the voice receiving end determines a target communication voice based on the effective text signal. Based on the technical scheme of the invention, the communication quality of the marine very high frequency equipment can be effectively improved.
Owner:SHANGHAI MERCHANT SHIP DESIGN & RES INST

Carbonization depth detection method, system and device

The invention relates to the technical field of depth measurement, and discloses a carbonization depth detection method, system and device, and the method comprises the steps: starting drilling equipment with impact and rotation functions, and carrying out the automatic drilling according to preset parameters, the preset parameters comprise the drilling depth, the rotation speed, the impact frequency and the like; when a hole is drilled to a certain depth, a concrete powder sample is automatically collected; then the built-in fan is started, and concrete powder in the drilled hole is automatically blown away; the computer system controls the alcohol phenolphthalein solution to be automatically added into the container, and the color change of the solution is monitored in real time through a built-in camera; the average value of the two drilling depths is calculated to serve as a carbonization depth detection result; and automatically generating a detection report. The system comprises a parameter setting module, a depth acquisition module and a result output module. According to the invention, automation, precision and intelligence of carbonization depth detection are realized; the detection accuracy and efficiency are improved, and the standardization of the detection process and the visualization of data are also realized.
Owner:POWER CHINA KUNMING ENG CORP LTD

Credit risk assessment and transmission method based on multi-source data and knowledge spectrogram

The invention discloses a credit risk assessment and transmission method based on multi-source data and a knowledge map, and the method comprises the steps: collecting credit event data from the multi-source data through an integrated crawler technology and a keyword-based event extraction technology, and carrying out the cleaning and conversion, so as to construct a credit knowledge map. The credit knowledge graph identifies each credit subject through a uniform resource identifier (URI), uses a credit evaluation index system as a data specification, and continuously updates through real-time data acquisition. In addition, the invention further provides a credit risk multi-path transmission composite influence probability calculation model, and credit risk management is optimized by analyzing influence factors of nodes in a credit subject association model.
Owner:NANJING AUDIT UNIV

Natural gas desulfurization device energy consumption optimization method based on deconstruction algorithm and electronic equipment

The invention discloses a natural gas desulfurization device energy consumption optimization method based on a deconstruction algorithm, optimization is carried out according to an energy consumption minimization optimization model to obtain optimal operation parameters and minimum energy consumption, and the model generation process comprises the following steps: S1, obtaining historical data of a desulfurization device, dividing the processing load of the desulfurization device, and obtaining a plurality of desulfurization load optimization areas; s2, performing energy consumption influence association degree filtering to obtain adjustable operation input data and energy consumption response output data; s3, establishing a desulfurization simulation model to obtain a mapping relation database of the adjustable operation input data and the energy consumption response output data; s4, calculating energy consumption key influence data; and S5, performing variance analysis and polynomial fitting on the energy consumption key influence data to obtain an energy consumption regression model, and performing nonlinear optimization to obtain an energy consumption minimization optimization model of natural gas desulfurization. Compared with the prior art, the method has the advantages that the desulfurization equipment runs in the optimal state, the performance and efficiency of the equipment are improved, and finer management is realized.
Owner:CHINA PETROLEUM & CHEMICAL CORP +1

Mobile phone auxiliary type intelligent interphone and implementation method thereof

The invention belongs to the field of interphones, and provides a mobile phone auxiliary type intelligent interphone and an implementation method thereof, and the mobile phone auxiliary type intelligent interphone comprises a mobile phone end assembly which comprises a central processing unit, an audio processing chip, a first connection module, a loudspeaker and a microphone; the interphone end assembly comprises a main control chip, a wireless communication module, a second connection module and a power management module; a radio frequency transceiver chip is arranged in the wireless communication module, data transmission is carried out between the second connection module and the first connection module, and the audio processing chip adopts a CNN noise reduction model to process digital audio signals; according to the method, the digital audio signals are processed through the CNN noise reduction model, various complex background noises can be accurately identified and removed, clear voice signals can be restored, the voice definition and intelligibility are greatly improved, it is ensured that both communication parties can accurately transmit information in a noisy environment, and the user experience is improved. The problem of poor voice quality caused by noise interference in a traditional matching mode is effectively solved.
Owner:LIAONING ERYA NETWORK INFORMATION TECH CO LTD

Tibetan language Anduodialect speech enhancement method suitable for specific noise and general noise

The invention discloses a Tibetan language Andole speech enhancement method suitable for specific noise and general noise, and relates to the technical field of low-resource language speech processing. The method specifically comprises the following steps: acquiring noisy voice information; preprocessing the noisy voice information, and dividing the processed data into a training set and a test set; a noise spectrum feature input by the noise classification module is optimized based on a weighted average method of a logarithmic power spectrum domain hard threshold; constructing a noise classification task and noise suppression task fused multi-target Tibetan speech enhancement model; training and testing the built speech enhancement model by using the training set and the test set to obtain a trained speech enhancement model; and inputting the actually collected noisy speech into the trained speech enhancement model to obtain an enhanced logarithmic power spectrum. Through effective fusion of the noise classification task and the suppression task, the quality and the intelligibility of the Tibetan language Andor dialect enhancement voice are improved, the human-computer interaction of the Tibetan language Andor dialect is more perfect, and the method has a positive effect on popularization of Tibetan language informatization.
Owner:LANZHOU CITY UNIV