49results about How to "Generate intelligence" patented technology

The invention discloses a meeting record generation method, comprising the following steps: receiving a meeting record generation request and obtaining meeting information in the meeting record generation request; And collecting audio information of the meeting through the audio collecting device; Performing speech recognition on the conference audio information to obtain voice print features andspeech text information corresponding to the conference audio information; Determining a speaker identification corresponding to the conference audio information according to the voiceprint characteristics; inputting The speech text information is to a preset processing model to obtain meeting text information, and associating the speaker identification with the meeting text information to generate meeting records. The invention also discloses a meeting record generation device, an apparatus and a computer storage medium. that the speech text information is obtained by the speech recognitionis used in the invention, the speech text information is input into a preset processing model obtained by the preset machine learn training, and the meeting records are automatically generated by theautomatic processing, so that the meeting records generation is more intelligent.

The invention relates to a geofence generating method which comprises the following steps of: a step a of calculating densities of points in a certain range around one by one by using longitude and latitude information of an interest point as the characteristic and using the interest point as the center and marking points of which the densities are greater than a certain threshold value into core points; a step b of calculating connectivity among the core points, processing each core point and integrating all the communicated core points and other non-core points in a local region into one point set; and a step c of carrying out rasterization and expansion processing on the point set, carrying out serializable searching on an expansion boundary point and automatically generating a smooth closed geographic boundary for the point set, wherein the geographic boundary comprises all the points in the point set and accords with the overall shape characteristic of the point set. According to the invention, relevance of geographic information can be automatically mined; the irregular geofence boundary which has obvious significance and accords with subjective geographic cognition of people is generated; and the aim of automatically and intelligently generating the geofence is fulfilled.

The invention provides an urban disaster thematic map real-time generating method based on network information. The method comprises the following steps that S1, the urban disaster information is obtained from networks in real time; S2, the urban disaster information is subjected to automatic place name recognition and is then subjected to spatial orientation; S3, the semantic mapping technology based on space time correlation rules is applied, and the urban disaster information subjected to the spatial orientation is subjected to semantic parsing; S4, the urban disaster information subjected to the semantic parsing is subjected to spatial data mining with graphic correlation, and the urban disaster thematic data with graphic spatial correlation is generated; S5, the urban disaster thematic data are subjected to visual representation, and an urban disaster thematic map is generated. The urban disaster thematic map real-time generating method has the advantages that the urban disaster information can be obtained in real time, the obtained urban disaster information is subjected to intelligent mining, the urban disaster thematic map is quickly generated and dynamically issued, and the quick generation and dynamical issuing level of the urban disaster thematic map is improved, and service is provided for urban management and emergency relief.

The invention relates to an intelligent video monitoring system based on a distributed wireless sensor network. The wireless sensor network is effectively combined with an video image monitoring system, and the system is mainly composed of an intelligent video monitoring device, transmission nodes, sink nodes, a video data cloud service center and a user access terminal. Early-warning information is transmitted to the sink nodes by the intelligent video monitoring device through the wireless sensor network, the information is transmitted to the video data cloud service center or the user access terminal by the sink nodes through an Internet or a mobile communication network, and the video data cloud service center is used for storing historical data and allows the user access terminal to have real-time access. The intelligent video monitoring system based on the distributed wireless sensor network fully combines the advantages of the video monitoring system and the advantages of the wireless sensor network and thus has the advantages of being intelligent in early warning, sensitive in reaction, easy for a user to operate, convenient to deploy and maintain and the like.

The invention discloses a double-flow video generation method based on different feature spaces of a text. The double-flow video generation method comprises a text feature extraction process, a double-flow video generation process and an adversarial resistance training process. According to the method, the input text content is analyzed, the feature information obtained by using the attention mechanism is separated, and the information of the appearance feature space and the information of the motion feature space are extracted respectively; a double-flow video generation mode is adopted, so that the learning capability of a single model on specified features is utilized to the maximum extent. According to the method, the adversarial resistance training process is used, the model is guidedand trained from the two aspects of the quality of each frame and the coherence of overall motion, and meanwhile text features are added to strengthen the training process, so that the generated video can conform to input text description, and the generation accuracy is achieved. The method provided by the invention can realize intelligent generation, and has wide market demands and application prospects in the aspects of material accumulation and data set automatic generation.

The invention discloses an accounting report generation method and device, electronic equipment and a computer readable storage medium, and the accounting report generation method comprises the steps:carrying out the management and control of an assignment process through employing a beforehand control strategy, and generating a completely controlled accounting informatization bill; mapping the receipt information into an account book; adding errors, adjustment and normal items to the report, so that the report has a normalized detection error reporting function, and receipts in an account book and accumulated information are detected and corrected again by using a post-event control strategy; and receiving a report generation transfer command, obtaining a corresponding report template, calling a corresponding index from the corrected account book according to the report generation command, mapping the index into the template, obtaining a calculation relationship of a template taskbar, and performing calculation to generate a target accounting report. According to the accounting report generation method, the system data is subjected to beforehand and afterwards management and control by a logic method, and the system data is detected in real time in a normalized report form manner, so that the correctness of the data is ensured, and the accounting report forms have normalized,timely and intelligent detection and error reporting functions.

The invention relates to the technical field of computers, in particular to a standard statistical format data generation method and device, equipment and a storage medium. The method comprises the steps of receiving a field selection instruction carrying clinical test data fields in a conventional field library through a form generation interface; generating a data receiving table according to the selected clinical test data field; based on the incidence relation between clinical test data fields and medical research data standard fields in a standard field library, obtaining a medical research data standard field corresponding to the clinical test data field from a standard field library, generating a statistical data table according to a statistical format requirement of a statistical terminal, and storing the statistical data table into a statistical database; and receiving diagnosis data corresponding to each clinical test data field through the data receiving table, and storing the received diagnosis data into a statistical data table in a statistical database to obtain statistical format data. By adopting the method, the data processing efficiency can be improved.

The invention discloses a purchase order generation and management method which aims to divide and calculate orders and generate purchase orders through a computer management system and comprises thefollowing steps: 101, acquiring orders; 102, performing material calculation according to the orders; 103, performing material parameter calculation; and 104, producing purchase orders, and automatically generating purchase orders according to order and material calculation results and material parameter checking results. By adopting the method disclosed by the invention, purchase orders are automatically generated according to orders of clients on the basis of generation rules, the purchase orders do not depend on manual control and input, accurate control of material purchase can be achieved, and waste can be avoided.

Embodiments of the invention disclose an intersection path automation generation method and a device thereof. The method comprises the following steps of acquiring all path units and determining an optimum weight value of each path unit; according to the optimum weight value of each path unit, generating a sparse matrix; acquiring a source element and a target element corresponding to a source node and a target node in the sparse matrix respectively; and calculating and acquiring all available paths between the source element and the target elements, and according to each available path, correspondingly generating each intersection path between the source node and the target node. Through determining the optimum weight value of each path unit, the sparse matrix is generated. And through calculating the sparse matrix, all the available paths between the source element and the target elements are acquired. An operation intersection path is automatically generated so that the intersection path is intelligent and rationalized. Simultaneously, a work flow is simplified, work intensity is reduced, manpower and material resource investments are decreased and a train full load factor is effectively increased. Train turnover is accelerated, a service train number is reduced, and a passenger service level and train application economical efficiency are increased.

The invention relates to a video processing method and device and a storage medium. The method is applied to a terminal, and comprises the steps of determining a main body region where a target objectis located in a video frame in a video and a background region outside the main body region; and covering the main body region in the at least one first video frame with the target object in at leastone second video frame with the target object, and generating a special effect frame simultaneously containing at least two main body regions where the target object is located. Through the technicalscheme in the embodiment of the invention, a plurality of main bodies can be displayed in the picture at the same time in a mode of segmenting the video picture and covering different segmented imageregions, so that a display effect of a cloned special effect is realized.

The invention relates to a video processing method and device and a storage medium. The method is applied to a terminal, and comprises the steps of determining a background frame of a time static special effect from video frames of a to-be-processed video; obtaining an image area where a target object in a video frame of the video is located; and fusing the image area into the background frame togenerate a special effect frame of the time static special effect. Through the technical scheme of the embodiment of the invention, the effect of the time static special effect is realized through thefusion of the partial regions of the different video frame images, the target object can be conveniently and automatically identified and the image fusion is carried out at the terminal, and a complex video processing tool and a post-production skill are not needed.

The embodiment of the invention provides an information distributing method and device based on the internet of things and an object platform. The method includes the steps of obtaining sensing information transmitted by the object platform through an operator management server, wherein the object platform comprises a first sensing unit, a second sensing unit and a control unit, and the control unit is electrically connected with the first sensing unit and the second sensing unit; analyzing the sensing information through the operator management server to obtain a sensing result; extracting classification judging information from the sensing information through the operator management server; transmitting the sensing result to at least one of an operator service platform server, a government server and a social public network server according to the classification judging information through the operator management server. The classification management capacity of the sensing information in the internet of things is improved, information flowing direction is more targeted, the home experience of a user can be easily improved, and the home environment of the user can be conveniently known by the user and an operator.

The invention discloses an expression processing method, a terminal and a storage medium. The expression processing method comprises the steps of obtaining target content in a content interaction interface; generating at least one expression according to the target content; displaying a target expression in the at least one expression on a content interaction interface; if a first selection instruction for the target expression is obtained, sending the target expression. Through the method, the target expression can be intelligently generated and sent according to the target content.

The invention relates to the technical field of computers, in particular to a vehicle frame number image generation method and device, computer equipment and a storage medium, and the method comprisesthe steps: obtaining a vehicle frame number depth image which comprises a color image and depth information; determining a plurality of initial acquisition points in the frame number area in the color image, and determining pixel coordinates of each initial acquisition point; obtaining camera coordinates of each initial acquisition point in a camera coordinate system based on the pixel coordinates and the depth information of each initial acquisition point; determining the pixel coordinates of the third acquisition point in the image coordinate system and the pixel size of the pixel point inthe frame number area; and determining reference coordinates according to the pixel sizes of the pixel points in the vehicle frame number area, and obtaining a vehicle frame number image correspondingto the actual size according to the reference coordinates, the pixel coordinates of the first initial acquisition point and the pixel coordinates of the third acquisition point. By adopting the method, the vehicle frame number image consistent with the actual size can be intelligently obtained.

A rock mass generalized RQD rapid intelligent solution drawing method belongs to the technical field of rock mass quality characterization, and comprises the following steps: (1) digital photogrammetry rapid acquisition on a rock mass structural surface; (2) research and development of an intelligent drawing system for a rock mass structural plane pole diagram and an occurrence rose diagram; (3) intelligent generation of a rock mass three-dimensional fracture network model and research and development of a sectioning system; and (4) research and development of a rock mass generalized RQD anisotropy diagram intelligent drawing system. According to the invention, a digital photogrammetry method is adopted to rapidly obtain parameter information of a rock mass structural plane, an intelligent drawing system of the rock mass structural plane pole diagram and the trend rose diagram is researched and developed, an intelligent generating and sectioning system of a rock mass three-dimensional fracture network model is researched and developed based on a Monte Carlo method, the intelligent drawing system for the generalized RQD anisotropic diagram of the rock mass is researched and developed on the basis of the generalized RQD theory, and rapid and intelligent solving and drawing of the structural plane pole diagram, the occurrence rose diagram, the fracture network model and the generalized RQD anisotropic diagram are achieved. The method is rapid and intelligent in means and convenient in engineering application.

The embodiment of the invention provides a method, a device and a system for information privacy transmission and object control based on Internet of Things. The method comprises steps: an operator service platform server acquires operator service awareness management information sent by an operator management server, wherein the operator management server obtains the operator service awareness management information through awareness information transmitted by an awareness unit; the operator service platform server analyzes the operator service awareness management information to obtain operator service awareness service information; and the operator service platform server transmits the operator service awareness service information to a user end via an operator privacy channel to enable the user end to analyze the operator service awareness service information, and user control information is transmitted to the operator service platform server via the operator privacy channel. The privacy of information transmission in the Internet of Things is improved, and the user and the operator can know the home environment of the user.

The invention discloses a coupon distribution method, a system and a computer-readable storage medium. The method comprises the following steps: when receiving the ticket information of a consumptionticket sent by a terminal, identifying the ticket information and obtaining the consumption information corresponding to the ticket information, wherein, the consumption information comprises a consumption amount; when receiving the ticket information of the consumption ticket sent by the terminal, identifying the ticket information; judging whether the consumption amount corresponding to the ticket information sent by the terminal reaches a preset amount; if yes, generating a coupon corresponding to the consumption amount; the license plate number sent by the terminal is received, and the coupon and the license plate number are sent to a preset parking control system. The invention generates the coupon by combining the consumption slip and distributes the coupon and the license plate number to the preset parking control system, which not only generates and distributes the coupon in a more intelligent manner, but also meets the needs of users, and promotes the vehicle owner to consumethe coupon in the mall or the shop near the parking lot.

The invention provides an information private distribution and object control method and apparatus of a private channel of Internet of Things. After receiving sensing information of a sensing unit, a service provider management server obtains a sensing result through analysis, extracts classified determination information, and distributes the sensing result to at least one of a service provider service platform server, a government server, and a social public network server according to the demand so that the information flow is more targeted. The service provider service platform server transmits business sensing service information of a service provider to a user terminal through the private channel of the service provider, the business sensing service information is analyzed through the user terminal, and user control information is sent to the service provider service platform server through the private channel of the service provider so that the effectiveness, the security, the privacy, and the openness of information transmission are improved. According to the method and apparatus, different information can be sensed through two different sensing units, whether a control command is sent is determined according to different information, the generation of the control command is more intelligent, and the home experience of the users is enhanced.