Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

47results about How to "Rich reference information" patented technology

Online cognitive assessment system and assessment method

The invention discloses an online cognitive assessment system and an assessment method, and belongs to the field of assessment systems. The online cognitive assessment system comprises a terminal platform, wherein the terminal platform comprises a processor module, a power supply module, a man-machine interaction module, a communication module, a recording module, an assessment module, a storage module, a calculation module and an output module; the power supply module, the man-machine interaction module, the communication module, the recording module, the assessment module, the storage module, the calculation module and the output module are connected with the processor module respectively. Online cognitive diagnosis is carried out through reading and processing information of each module. By adopting the online cognitive assessment system and the assessment method, rapid and accurate assessment and good accuracy can be realized, and information is updated in real time.
Owner:BEIJING WISPIRIT TECH CO LTD

Surgical planning method and system for percutaneous puncture

The invention is suitable for the mechanical technology field, and provides a surgical planning method and system for the percutaneous puncture. In order to realize the above purpose, the invention provides a surgical planning method for the percutaneous puncture. The method comprises the following steps of: A) obtaining the mechanical image data of a patient; B) according to the mechanical image data, reconstructing the three-dimensional model of the relevant organ and / or tissue and / or focus of the patient; and C) determining the surgical operation process of the percutaneous puncture on the three-dimensional model by a virtual puncture device. Therefore, according to the invention, a user can repeatedly carry out the skin puncture operation by the virtual puncture device so as to accurately obtain the skin puncture point, the angle and the puncture path of the patient.
Owner:SHENZHEN YORATAL DMIT

Dual view-field dynamic-trajectory reverse image system

The invention relates to a dual view-field dynamic-trajectory reverse image system, which is characterized by comprising a wide angle reverse camera, a steering wheel turning angle sensor, a reverse image control system and a display, wherein the reverse image control system is used for acquiring vehicle gears, the steering wheel turning angle and driver reverse image view-field selection information; the reverse image control system is used for controlling the wide angle camera to acquire vehicle rear images and to respectively send the images to a reverse trajectory projection unit and a reverse image overlook conversion unit; a reverse trajectory calculation unit is used for acquiring the steel wheel turning angle, calculating a reverse trajectory and a distance mark line, and sending them to the reverse trajectory projection unit; the reverse trajectory projection unit is used for projecting the reverse trajectory line and the distance mark line to the images, and sending the images overlapped with the reverse trajectory line and the distance mark line to the display; and the reverse image overlook conversion unit is used for converting the vehicle rear images into overlook images, projecting the reverse trajectory and the distance mark line to the overlook images, and sending to the display. The dual view-field dynamic-trajectory reverse image system provided by the invention can be widely applied to providing more accurate reference information for drivers in the vehicle reverse process.
Owner:BEIJING ZHIXINGZHE TECH CO LTD

Medical treatment data processing system and processing method

The invention discloses a medical data processing system, which comprises a self-operation movable storage device, a terminal calculator, a medical data processing server and at least one case history information database. The invention also provides a medical data processing method, which comprises: when the terminal calculator detects that there is self-operation movable storage device is inserted into the data communication interface, starting the user program of self-operation movable storage device; the terminal calculator sends the data synchronous request to the medical data processing sever; the medical data processing server processes the synchronization of health information data. The health information can be viewed by many methods, via movable terminal or WEB, and it can automatically diagnose via the user health information. With said invention, user can easily browse the health information to solve the imbalance distribution of medical resource.
Owner:德源益康健康科技(北京)有限公司

Threat estimation method based on dynamic bayesian network

ActiveCN107016464AReflect continuous change characteristicsEffectively reflect the threat situationForecastingResourcesControl systemEstimation methods
The invention discloses a threat estimation method based on a dynamic Bayes network, relating to the technical field of situation estimation. The method is realized by the following steps of 1. performing data collection and arrangement and extracting the situation elements; 2. integrating various situation elements, and establishing dynamic bayesian network topology; 3. performing network parameter learning and setting; 4. realizing fast approximation Bayesian inference based on Markov property; 5. combining each threat level probability into a continuous threat indexes and a discrete threat level; and 6. outputting the treat estimation result. The method can integrate the various situation elements, and perform reasonable and intelligent inference analysis, thereby realizing the blue group object threat dynamic quantitative and qualitative estimation and being applicable to a situation estimation and commanding control system.
Owner:NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP

Calling request processing method and device

The embodiment of the invention relates to the field of communication, and especially relates to a calling request processing method and device, wherein the method and device are used for solving a problem that a terminal cannot display information completely when a conventional terminal receives a calling request. The method comprises the steps that the terminal obtains a user ID and transmits a query request to a network side after receiving a calling request; and the network side queries ordering information corresponding to the user ID and / or logistics information corresponding to the ordering information according to the user ID, and enables the ordering information and / or logistics information to be transmitted to the terminal through a query response, so as to enable the terminal to display the received ordering information and / or logistics information at a display interface. The terminal enables the received ordering information and / or logistics information, which is related to the user ID, to be displayed at the display interface after receiving the calling request, thereby enabling a user to know more related information after the user receives the calling request, and providing more complete reference information to the next operation of the user.
Owner:BANMA ZHIXING NETWORK HONGKONG CO LTD

Kit and method for testing hypotype of virogene of hepatitis B and drug fast mutation

This invention provides method and test kit for synchronously detecting sub-genotypes and drug-resistant mutation of hepatitis B virus (HBV). The test kit comprises: two specific primers for amplifying gene or transcript of HBV, three specific oligonucleotide probes for detecting sub-genotypes of HBV, and thirteen specific oligonucleotide probes. The primers and the probes can also be replaced with the complementary sequences. The test kit can synchronously differentiate three sub-genotypes (B, C and D) of HBV, and detect lamivudine- and adefovir dipivoxil-resistant mutations. The test kit can reduce the detection cost.
Owner:亚能生物技术(深圳)有限公司

InSAR deformation monitoring result interpretation method for landslide

The invention discloses an InSAR deformation monitoring result interpretation method for landslide, and the method comprises the steps: delineating an initial boundary of a landslide body through an optical remote sensing image, correcting the boundary through combining with an InSAR deformation rate monitoring result, and obtaining a boundary range of the landslide body through integration; within the boundary range, carrying out regional grading division on the landslide mass deformation degree by using an InSAR deformation rate result; obtaining a spatial evolution rule of the landslide mass based on the digital elevation data and the deformation quantity result of each stage; and determining key monitoring points of the landslide mass based on a deformation area grading result and spatial evolution rule information. The method can effectively extract information such as evolution rules of landslide boundaries and landslide disaster earth surface deformation in a monitoring area. Through grading the apparent deformation of the landslide disaster and analyzing the spatial evolution rule, the application of the traditional InSAR deformation monitoring technology in the landslide disaster evaluation work is promoted, and meanwhile, richer InSAR reference information is provided for the analysis of the evolution rule of the landslide disaster.
Owner:RAILWAY ENG RES INST CHINA ACADEMY OF RAILWAY SCI +2

Video identification method and device and storage medium

The invention provides a video identification method and device and a storage medium, relates to the technical field of artificial intelligence and computers, and is used for improving the accuracy of identifying video tags. The method includes: inputting the to-be-processed video into the label classification model, and respectively obtaining a matching probability value corresponding to each preset label; inputting the to-be-processed video into a label retrieval model, obtaining candidate labeling labels successfully matched with the to-be-processed video and corresponding target similarities, wherein the target similarity corresponding to each candidate labeling label is determined based on the video data matching similarity between each historical video associated with the candidate labeling label and the to-be-processed video; screening out preset labels with matching probability values reaching a probability threshold value to form a first label set, and screening out candidate labeling labels with target similarity reaching a similarity threshold value to form a second label set; and performing fusion processing on the first label set and the second label set, and determining a target label corresponding to the to-be-processed video. The label recall and accuracy are improved, and the recognition accuracy is improved.
Owner:TENCENT TECH (SHENZHEN) CO LTD

Adaptive AGV robot and adaptive navigation method

The invention belongs to the technical field of robots, and discloses an adaptive AGV robot and an adaptive navigation method. The adaptive AGV robot comprises a vehicle body, a navigation device arranged on the vehicle body, and an executing device arranged on the vehicle body. The navigation device comprises a detection radar, a detection camera and a processor and is used for planning the travelling path of the robot to enable the robot to actively avoid obstacles on the path. The executing mechanism comprises a base, a cooperative mechanical arm, and an executing steering engine. The cooperative mechanical arm comprises a first driving box, a four-bar linkage mechanism, a second driving box, a sleeve shaft engine arm, a tail end transmission head and a tail end executing head, and thusthe six-degree-of-freedom executing structure is formed. Under guidance of a bearing device and the navigation device of the vehicle body, the robot can freely travel in the indoor environment and drives the executing mechanism to carry out tasks. The adaptive AGV robot is small in self-weight and low in cost, and can realize more flexible path planning than similar cooperative robots, and the cooperative mechanical arm can have longer arm spread and larger load bearing, and has good expandability.
Owner:上海秘塔网络科技有限公司

Online measuring device for size and morphology of particle

The invention discloses an online measuring device for size and morphology of a particle. The device comprises a full-automatic sampling system, a diluting system, an online observation system, an image processing system and the like, wherein the sampling system comprises a peristaltic pump and a feeding tube and is used for conveying an obtained sample to the diluting system; the diluting systemcomprises a liquid storage tank and a diluting tank and is used for diluting the sample to a concentration suitable for the observation of the online observation system; the online observation systemcomprises a high-definition camera or a microscope, an observation table and a computer; the sample conveyed to the observation table is photographed in real time by the high-definition camera or themicroscope and stored on the computer; the morphology and the size of the particle can be observed in detail through a computer program; the image processing system is an image processing program withindependent intellectual property rights; and the program is used for processing pictures taken by the high-definition camera or the microscope in real time and obtaining the size distribution and the specific morphology features of the particle through data statistics.
Owner:QINGDAO INST OF BIOENERGY & BIOPROCESS TECH CHINESE ACADEMY OF SCI +1

Construction method of single cell RNA sequencing library

The invention relates to the field of biotechnology and provides a construction method of a single-cell RNA sequencing library. The method includes the following steps that 1, carrier RNA is added ina single cell lysis system to ensure the RNA quantity required by library construction without pre-amplification of full-length cDNA; 2, the library is constructed by using a commercial kit or RNA sequencing library construction method; 3, DNA formed through carrier RNA transcription is removed from the library; 4, high-throughput sequencing is performed. The pre-amplification step of the full-length cDNA in an existing method is omitted, in the library construction process, the added RNA with the known sequence is subjected to digestion removal and prevented from causing interference to sequencing, and the sequencing cost is greatly reduced.
Owner:ZHEJIANG UNIV

Application identifying method, application identifying device and server

The invention discloses an application identifying method, an application identifying device and a server. The method comprises the following steps of obtaining application downloading information on a terminal; and adding identification information on downloaded applications in an application store installed in the terminal on the basis of the application downloading information. When the embodiment of the invention is used, the server can obtain the application downloading information and can add the identification information in display information of the application store on the basis of the application downloading information by aiming at the downloaded applications, so that when a user browses the application store and selects the application, which application is the downloaded application or even the deleted application can be known through the identification information; and the effect of effectively reminding the user to prevent the user from downloading the downloaded application by mistake is achieved.
Owner:XIAOMI INC

Transaction two-party relationship information identification method and device

The embodiment of the invention provides a transaction two-party relationship information identification method and device. The method comprises the steps of obtaining a knowledge graph constructed based on multiple relationships among multiple users; wherein the knowledge graph comprises a plurality of nodes corresponding to a plurality of users and a plurality of categories of connection edges constructed corresponding to a plurality of relationships, and the plurality of users comprise natural person users and / or enterprise users; performing graph embedding processing on the knowledge graphby utilizing a pre-trained graph embedding model to obtain a node embedding vector corresponding to each node; respectively forming triples by the two node embedding vectors corresponding to the twousers involved in the target transaction and the edge embedding vectors of the connection edges of each category, inputting the triples into a pre-trained prediction model, and predicting evaluation scores corresponding to the triples through the prediction model; identifying the relationship category information between the users based on the evaluation score so as to assist in determining whether the transaction is safe or not.
Owner:ALIPAY (HANGZHOU) INFORMATION TECH CO LTD

Product design risk analysis method and system based on multi-system integration

The invention discloses a design risk analysis method and system based on multi-system integration. The method comprises the following steps: obtaining experience information from experiment entrustment information, experiment report information, trial-manufacture problems, production problems and after-sales problems; establishing a product design failure mode and consequence analysis structure tree according to the bill of material data, and giving a product design failure mode and consequence analysis report by taking the product design failure mode and consequence analysis structure tree as a basis and referring to technical standard information and experience information; establishing a process design failure mode and consequence analysis structure tree according to the technological process list data, and giving a process design failure mode and consequence analysis report based on the process design failure mode and consequence analysis structure tree by referring to technological resource library data and experience information; and obtaining a product design risk analysis result according to the product design failure mode and consequence analysis report and the process design failure mode and consequence analysis report. According to the method, the risk analysis is more comprehensive, and the design and manufacturing misunderstanding is reduced.
Owner:XIAN FASHITE AUTOMOBILE TRANSMISSION CO LTD

Time history display method and system for radar primary information A-scope display

ActiveCN107966685AReasonable and accurate operationRich reference informationWave based measurement systemsTarget analysisRadar
The invention relates to a time history display method for radar primary information A-scope display. The method comprises steps: radar primary information of radar echo signals is acquired, the radarprimary information is subjected to target comprehensive analysis and processing, and a target analysis result is obtained; a three-dimensional drawing scene is built, and the three-dimensional map with amplitude, distance and time as coordinate axes is used for displaying the radar primary information of the target analysis result within a preset range, wherein the radar primary information comprises the distance and amplitude information of the radar echo signals. The three-dimensional map with amplitude, distance and time as coordinate axes is used for displaying the radar primary information of the target analysis result within the preset range, a radar operator can intuitively understand the echo signal condition in a period of time based on the three-dimensional map, comprehensive consideration is carried out according to the echo signals, the reference information provided in the invention is richer, and operation by the operator is more reasonable and accurate. The invention also provides a time history display system for the radar primary information A-scope display.
Owner:BEIJING INST OF RADIO MEASUREMENT

Training method and system for improving function of each cognition domain

The invention relates to the field of brain health cognition rehabilitation training, particularly to a training method and system for improving the function of each cognition domain. The cognition training method comprises the following steps: inputting personal basic information of a user for account registration; performing mental evaluation; automatically recommending a cognitive training scheme from a system training library according to the mental evaluation result of the user, and performing cognitive function training in combination with a training tool; and storing the data generatedin the training process in the personal information database of the user, and generating a training report. The training system for improving the functions of the cognition domains comprises an account registration module, an evaluation module training module, a storage module, a training report module, an evaluation module, a training updating module and an evaluation report module.
Owner:李阳

Method and device for recommending users

The invention provides a method and a device for recommending users. The method comprises steps: after the current user logs in to a financing platform, a to-be-recommended user corresponding to the current user is determined; and on the financing platform, the to-be-recommended user is provided for the current user. The method can recommend a financing expert for the user on the financing platform and more reference information is provided for the user.
Owner:ADVANCED NEW TECH CO LTD

Parameter estimation model training method and device, equipment and storage medium

The invention discloses a parameter estimation model training method and device, equipment and a storage medium. The method comprises the following steps: inputting a face image training set into a pre-constructed neural network model, estimating reconstruction parameters specified by three-dimensional face reconstruction, inputting the reconstruction parameters into a pre-constructed three-dimensional deformation model, and reconstructing a three-dimensional face corresponding to a training sample; calculating loss functions between the three-dimensional face and the training sample under multiple items of two-dimensional supervision information, and adjusting the weight corresponding to each loss function; and generating a corresponding fitting loss function based on each loss function and the corresponding weight, and performing reverse correction on the neural network model by using the fitting loss function to obtain a trained parameter estimation model. According to the technicalscheme provided by the invention, the parameter estimation model is trained through the loss function under multiple items of two-dimensional supervision information, so that the reference information in the training process is more comprehensive, and the estimation accuracy of the reconstruction parameters adopted during three-dimensional face reconstruction is improved.
Owner:BIGO TECH PTE LTD

Speech synthesis method and device, equipment and storage medium

The invention discloses a speech synthesis method and device, equipment and a storage medium. In the process of performing speech synthesis on a to-be-synthesized original text, auxiliary synthesis features corresponding to a matching text of a text fragment matched with the original text are referred; the auxiliary synthesis features are features which are determined based on a pronunciation audio corresponding to the matching text and are used for assisting speech synthesis; by referring to the auxiliary synthesis features corresponding to the matching text, the pronunciation information in the pronunciation audio corresponding to the matching text can be used for assisting speech synthesis of the original text, so that the reference information during the speech synthesis of the original text is enriched, and the speech synthesis quality of the original text is improved. The speech synthesis method of the invention can be suitable for speech synthesis systems with front-end preprocessing and speech synthesis systems without front-end preprocessing; the auxiliary synthesis features can be used as front-end text analysis results and can also directly assist the speech synthesis systems in speech synthesis, and can improve the quality of synthesized speech.
Owner:IFLYTEK CO LTD

Dual view-field dynamic-trajectory reverse image system

The invention relates to a dual view-field dynamic-trajectory reverse image system, which is characterized by comprising a wide angle reverse camera, a steering wheel turning angle sensor, a reverse image control system and a display, wherein the reverse image control system is used for acquiring vehicle gears, the steering wheel turning angle and driver reverse image view-field selection information; the reverse image control system is used for controlling the wide angle camera to acquire vehicle rear images and to respectively send the images to a reverse trajectory projection unit and a reverse image overlook conversion unit; a reverse trajectory calculation unit is used for acquiring the steel wheel turning angle, calculating a reverse trajectory and a distance mark line, and sending them to the reverse trajectory projection unit; the reverse trajectory projection unit is used for projecting the reverse trajectory line and the distance mark line to the images, and sending the images overlapped with the reverse trajectory line and the distance mark line to the display; and the reverse image overlook conversion unit is used for converting the vehicle rear images into overlook images, projecting the reverse trajectory and the distance mark line to the overlook images, and sending to the display. The dual view-field dynamic-trajectory reverse image system provided by the invention can be widely applied to providing more accurate reference information for drivers in the vehicle reverse process.
Owner:BEIJING ZHIXINGZHE TECH CO LTD

Bill information extraction method and device, equipment, medium and product

The invention discloses a bill information extraction method and device, equipment, a medium and a product, and the method comprises the steps: carrying out the text recognition of a bill image, and obtaining the coordinate information of a textbox of each text region and the text information in the textbox; graph structure data are constructed, each node represents the coordinate information of the single textbox and the feature information of the text information, and the edge between any two nodes represents the feature information of the relative distance information between the textboxes of the two nodes; adopting a preset graph convolutional neural network to carry out multiple times of iterative updating on the feature information of the nodes and the edges in the graph structure data to obtain updated graph structure data; and inputting the feature information of the nodes in the updated graph structure data into a classification network for classification, and determining a classification label corresponding to the text information of each textbox. According to the method and the device, the text information required by the order data can be accurately extracted from the bill image.
Owner:广州欢聚时代信息科技有限公司

Malicious domain name detection method and device based on deep reinforcement learning

The invention relates to a malicious domain name detection method and device based on deep reinforcement learning. The method comprises the following steps: acquiring the real DNS flow of a domain name to be detected; inquiring and recording whois information of the domain name to be detected in the real DNS flow; according to the domain name to be detected and the whois information, carrying out feature extraction on the domain name to be detected, and generating a feature vector of the domain name to be detected; and inputting the feature vector of the to-be-detected domain name into the deep reinforcement learning model, and judging whether the to-be-detected domain name has a malicious behavior or not. The method based on deep reinforcement learning is used for solving the classification problem of unbalanced benign and malicious sample data in the real DNS traffic, low-proportion malicious samples in the real DNS traffic can be quickly and effectively found, and a good effect is still kept at a low balance rate.
Owner:INST OF INFORMATION ENG CHINESE ACAD OF SCI

User experience assessment system based on hotel rating

The invention relates to a user experience evaluation system based on hotel ratings, which includes a cloud platform, a user experience rating module, a query module, a hotel rating database and a client; Connected to the cloud platform; the user experience scoring module is located on the cloud platform, the user experience scoring module is connected to the information query client, the query module is located on the cloud platform, and the query module is connected to the information query client. The itinerary is optimized, and query and check-in scoring services are provided to further improve the supervision of hotels and the quality of people's travel.
Owner:HUNAN INSTITUTE OF ENGINEERING

Medium-large automobile driver assistance equipment and working method thereof

The invention relates to medium-large automobile driver assistance equipment, which comprises sound pickups, an audio processing device and sound equipment, wherein the output ends of the sound pickups are connected with the input end of the audio processing device, the output end of the audio processing device is connected with the input end of the sound equipment, the sound pickups are arrangedon the left side and the right side of the middle of the vehicle and used for collecting audio information of the surrounding environment of the vehicle when the vehicle changes lanes or turns a corner and transmitting the collected audio information to the audio processing device; the audio processing device is used for receiving audio signals collected by the pickups and performing audio signalprocessing operation; and the sound equipment is arranged on the left side and the right side of a driving position and used for playing output audio signals of the audio processing device, and the audio processing device transmits processed audio into a cab through the sound equipment. According to the invention, when a driver drives a medium-large vehicle to change lanes or turn, the real-time audio information of the external surrounding environment can be collected and fed back to the driver in real time, so that the purpose of safe driving or timely loss stopping is achieved.
Owner:HUNAN INSTITUTE OF ENGINEERING

Plug-in method, device and system, storage medium and equipment

The invention relates to a plug-in method, device and system, a storage medium and equipment. The plug-in method comprises the following steps: acquiring a side view of an element; the element is the element which is grabbed by an actuator; identifying a pin position of a pin based on the side view; the pin is the pin of the element; obtaining a jack position of the jack; and generating a control instruction based on the pin position and the jack position, and controlling an actuator to drive the pin to be inserted into the jack through the control instruction. According to the technical scheme, the pin position is identified based on the side view, so that the pin position identification precision is improved.
Owner:ROBOTICS ROBOTICS LTD

Control method and device, computer equipment and storage medium

The invention discloses a control method and device, computer equipment and a storage medium. The control method and device are used for improving the control decision accuracy of a suspension controlsystem. The method comprises the following steps: determining a current driving mode; acquiring first sensor information and second sensor information, wherein the first sensor information is information acquired by sensors of a suspension system in the vehicle, and the second sensor information is information acquired by sensors of other intelligent systems except the suspension system in the vehicle; fusing the first sensor information and the second sensor information to obtain fused information; acquiring external environment information of the vehicle from a cloud server; inputting the fusion information and the external environment information into a first neural network model corresponding to the current driving mode to determine a first decision instruction for controlling the suspension; and sending the first decision instruction to a suspension system executing mechanism so that the suspension system executing mechanism can control the suspension according to the first decision instruction.
Owner:GUANGZHOU AUTOMOBILE GROUP CO LTD

Order data processing method and device, equipment, medium and product

The invention discloses an order data processing method and device, equipment, a medium and a product. The method comprises the following steps: acquiring a to-be-detected image; identifying a line text corresponding to each line text image existing in the to-be-detected image; a knowledge graph representing the line texts and the relative position relation between the line texts is constructed, the knowledge graph establishes nodes corresponding to the line texts, and the data distance between the position information of the line text images of every two nodes in the image to be detected serves as the edge weight of the two nodes; order data are constructed according to the knowledge graph, the order data comprise data items correspondingly obtained according to the line text, and the data items comprise attribute fields used for describing the order and attribute data corresponding to the attribute fields. According to the invention, the structured order data can be identified from the to-be-detected image and can be directly called by an order business process of a power supplier, so that the processing efficiency of the order business process of the e-commerce is improved.
Owner:广州欢聚时代信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products