322results about How to "Consider comprehensively" patented technology

The invention discloses an anti-seepage and leak-blocking construction method for excavation of a subway foundation pit in a soft soil area, which comprises the following steps: 1) joint pre-reinforcement construction of an underground continuous wall: constructing a pre-reinforcement structure of a high-pressure rotary jet grouting pile, guiding holes, grouting by a sleeve valve pipe, sealing the holes, guiding the holes again and pre-burying the sleeve valve pipe for standby; and 2) the excavation of the foundation pit and the anti-seepage and leak-blocking construction: using surface floating earth for clearing and using the encased steel plate reinforcement method for anti-leak treatment for the situations that joints of the underground continuous wall have defects definitely and risk points are positioned below the excavation surface of the foundation pit, adopting the hole-guiding cyanogen injection condensing method for blocking of leak points with slight water leakage situation, adopting the horizontal hole grouting method for blocking for the water leak points with serious water leakage situation, and carrying out filling, grouting and reinforcement through the pre-buried sleeve valve pipe after completing the blocking. The method has reasonable design, convenient construction, comprehensive consideration, good anti-leak and leak-blocking effect, fast leak-blocking speed and can solve the problems of pipe blocking, poor anti-leak and leak-blocking effect, slow construction progress and the like in the existing anti-leak and leak-blocking construction.

The invention discloses an electric energy metering device fault analysis method based on big data mining and scene pre-judgment, belonging to the monitoring field. The electric energy metering device fault analysis method comprises steps of calculating out a fault type of a secondary circuit of a watt hour meter, inferring relation coefficients between display electric quantities of the watt hour meter after various types of faults and the display electric quantity of the watt hour meter under a normal condition by targeting watt hour meters of two connection modes which include a three-phase four-wire mode and a three-phase three-wire mode, respectively calculating electric quantity imbalance rates corresponding to buses of a transformer station and performing determination according to electric quantity data of a bus balance daily statement, finding out a bus j corresponding to a failed watt hour meter, performing fault pre-judgment before going to side for checking, finding out potential faults and sorting the faults according to priorities, performing on site checking according to a pre-judgment result and finding out a final fault. The electric energy metering device fault analysis method of the invention carries out fault analysis of an electric energy metering device under a big data background, effectively solves a problem of influence on line loss statistics which is caused by electric energy metering device and improves efficiency and accuracy of fault analysis and checking of the electric energy metering device.

The invention discloses a peaty soft soil stratum subway station construction technology. A main structure of a constructed subway station comprises base plates, side walls, top plates and middle plates distributed between the top plates and the base plates. Underground consecutive walls are arranged on outer sides of the two side walls. The base plates, the side walls, the middle plates and the top plates are all of a rebar concrete structure formed by pouring waterproof concrete. The subway station construction technology comprises the following steps: (1) underground consecutive wall construction, (2) foundation reinforcement, namely, three-shaft stirring piles are used for reinforcing the foundation of excavated foundation pits, (3) vacuum water falling, namely conducting vacuum well point water falling construction on the foundation pits needing excavating, (4) foundation pit excavation, namely, an open excavation method is used for conducting earthwork excavation on the foundation pits needing excavating with a plurality of excavating layers from top to bottom, (5) subway station main structure construction. The method is simple, convenient to realize, quick in construction speed, capable of being ensured in construction quality easily, and good in construction effect, and enables the subway station construction process of peaty soft soil stratum to be completed simply, quickly and with high quality.

The invention discloses an urban natural gas pipeline failure multi-factor multi-mode probability analysis method and application thereof. The method emphasizes at modification research for failure states due to main factors such as corrosion, design, operation management, environments and third-party damage causing pipeline failure, a Bayesian network probability calculation model for a natural gas pipeline is established, single-factor multi-mode, two-factor multi-mode and multi-factor multi-mode situations of pipeline failure are respectively and quantitatively calculated, and pipeline failure tip event probability and structural importance of basic factors are obtained. By the method, the unique reasoning capability of a Bayesian network in complicated risk treatment system analysis is made full use of, comprehensiveness, predictability and systematicness of quantitative analysis of safety failure of an urban natural gas pipeline are improved, and a certain referential meaning for risk management and failure handling of the natural gas pipeline is achieved.

The invention discloses an industrial big data driven total completion time prediction method and relates to the field of engineering application. The method includes: establishing an industrial big data analysis platform; applying an association rule mining algorithm to analyze and mine total completion time influence factors; establishing a neural network model BP; dynamically improving a weight and a threshold of the neural network model BP to acquire a dynamical neural network model DBP; applying an AIGA (adaptive immune genetic algorithm) to optimize the dynamical neural network model DBP so as to acquire a prediction model AIGA-DBP, and computing a total completion time prediction value according to the prediction model AIGA-DBP; when an error of the total completion time prediction value and a total completion time expectation value meets preset conditions, outputting the total completion time prediction value. By the method, the total completion time can be predicated accurately, the work flow of enterprises is optimized, the production efficiency of the enterprises can be improved, and the method is adaptable to various changes of the enterprise due to time lapse.

The invention provides a method for reliability modeling and evaluation of a dynamic cascade coupling electromechanical system. The method is based on a physical background of a complex electromechanical system and is capable of carrying out research on reliability of the electromechanical system based on a dynamics response model, and an established reliability network model of the electromechanical system is capable of more accurately describing the characteristics of dynamic, cascading and coupling of the complex electromechanical system, so that reliability of the electromechanical system, which is obtained based on the network model, is more accurate and credible; meanwhile, by utilizing a method of combining dynamics analysis and uncertainty analysis, transfer of uncertain information from a bottom layer to a top layer of the network model is described, and the difficulties that an aerospace mechanism system has a response uncertainty character and system reliability information cannot be obtained through experiment measures due to large experimental expenses, long period, large technical difficulty and expensive product cost are solved.

The invention discloses a data processing method and a data processing device. In the method and the device, the obtained asset vulnerability index is related to an asset polling vulnerability index, a bug vulnerability index and a configuration irregularity vulnerability index, and the obtained asset threat index is related to an asset security event threat value, a security alarm threat value and a security event threat value. Moreover, the asset security event threat value, the security alarm threat value and the security event threat value are obtained by processing logs of assets. Thus, when network security situation assessment data is processed, the method and the device consider the result of an asset polling inspection service, a bug inspection service, a configuration irregularity inspection service and integrated log and traffic analysis. Therefore, the data considered and counted by the method and the device is more comprehensive, the asset security situation assessment result obtained by the method and the device is more accurate, and the credibility of the asset security situation assessment result is improved.

The invention belongs to the technical field of social network modeling and analysis and particularly relates to a microblog rumor spreading analysis method. On the basis of a microblog rumor spreading model, an inducement mechanism of microblog rumor spreading is analyzed, the UASR microblog rumor spreading model conducts state division on the basis of field influences of users, characteristics of rumor microblogs and the action of external social factors on rumoring mind of the users in the rumor spreading process, a proper threshold function is built, and a node state conversion rule is defined so as to depict actions of different factors on actual rumor spreading routes and effects in the rumor spreading process as accurately as possible. The method can simulate the microblog rumor spreading process in real world completely and truly.

The invention discloses a method for evaluating the economic operation of an active distribution network based on an economic operation domain, which includes: defining 14 secondary evaluation indicators in the context of an energy Internet-oriented active distribution network, and comparing them with existing indicators Combined, according to the classification and processing of the characteristics of the new secondary indicators, four new first-level indicators are established, and an evaluation index system for the economic operation of the active distribution network oriented to the energy Internet is constructed, and some existing indicators are improved; the entropy weight method is used to correct , using the combination of subjective and objective weighting methods to improve the interval analytic hierarchy process, and as the weight calculation method of the present invention, using the methodology of "domain" in the distribution network security analysis to define the economic operation function and the economic operation domain; based on the economic operation domain Establish a model of each economic operation level of the active distribution network; judge whether the sample to be evaluated belongs to the corresponding level according to whether the economic operation function exceeds the limit.

The invention relates to a comprehensive determination method for a coefficient of the roughness of a rock mass structure surface. The comprehensive determination method is suitable for the comprehensive determination on the coefficient of the roughness of the multiple forms of rock mass structure surface. Topography data of the integral rock mass structure surface can be obtained at a time through a three-dimensional laser scanner or a rock mass structure surface topography instrument and accordingly the condition that the measurement result of one line segment cannot represent the roughness of the integral rock mass structure surface previously is changed and the measurement result is objective and real. A typical curve is straightened in the space, an X coordinate and a Y coordinate of every point are changed, a Z coordinate of every point remains unchanged, the representation is performed on the roughness of the three-dimensional rock mass structure surface by a two-dimensional method, the comprehensive analysis is performed by four calculation methods, and accordingly a finally determined coefficient value of the roughness of the rock mass structure surface is accurate. The comprehensive determination method is comprehensive in consideration, simple in calculation and accurate in result.

The invention discloses a bend safe speed calculation method based on vehicle and road collaboration. The method comprises the steps as follows: firstly, the cut-in speed of a vehicle at a bend, the geometrical characteristic of the bend and other information are acquired by use of an OBU (on-board unit) and an RSU (roadside unit) in a vehicle and road collaboration system, driving styles of different drivers are reflected by replacing the bend radius with the driver running radius, and a bend speed model self-adaptive to the driving styles of the drivers is established; then, accident forms such as sideslip, rollover, rear-end collision and the like of the vehicle are considered, the optimal bend speed of an autonomous vehicle is decided in the aspects of yaw stability, sideslip stability, car following safety, driving comfort and the like, and finally, expected speed planning is provided for an active control system of the vehicle. Compared with existing bend safe speed calculation methods, the bend speed calculation method has the advantages that multiple accident forms such as sideslip, rollover, rear-end collision and the like are considered comprehensively, considered factorsare more comprehensive, and the speed planning of the autonomous vehicle can be supported.

The invention relates to a prevention, control and fault handling method and system for a power distribution network. The prevention, control and fault handling system for the power distribution network comprises a uniform-control platform, an information acquisition unit and a prevention and control unit, wherein one end of the uniform-control platform is connected with the information acquisition unit, the other end of the uniform-control platform is connected with the prevention and control unit, the prevention and control unit is used for predicting the abnormal operating state of devices in the power distribution network in a short period of time in future, and the prevention and control unit comprises a second index calculation module used for setting an index in advance according to the information of the devices in the power distribution network and the information of a network topology and storing the information of the topology so that data support can be provided for a fault handling unit. The prevention, control and fault handling method and system for the power distribution network have the advantages that the practicability is high, threshold crossing can not occur easily in a short period of time, time of prevention and control handing is effectively saved, energy is saved, and the probability of occurrence of faults is lowered.

The invention discloses a pedestrian re-identification monitoring system based on a depth convolution neural network. The system comprises a video acquisition device, an identification monitoring device and a pedestrian database. The video acquisition device is used for acquiring a pedestrian image to be measured; the pedestrian database is used for storing a target pedestrian image; the identification monitoring device is used for acquiring a measured pedestrian image from the video acquisition device, acquiring the target pedestrian image from the pedestrian database, learning the target pedestrian feature by using the target pedestrian image using a depth convolution neural network, and judging whether the measured pedestrian image is a target pedestrian according to the target pedestrian feature matching. The technical scheme can effectively reduce a plurality of adverse influence factors on identification robustness, thereby improving the matching accuracy of pedestrian target similarity.

The invention discloses a system and a method for switching a long term evolution (LTE)-advanced mobile relay (MR) and an eNode B. The system comprises a timing measurement module, a switching policy module, a reliable switching module and a group switching module, wherein the timing measurement module measures the channel quality of a current eNode B cell and a neighbor eNode B cell at fixed time; the switching policy module is used for judging whether a source eNode B is required to be switched and determining a target eNode B which is switched from the source eNode B; the reliable switching module is used for switching a relay from the source eNode B to the target eNode B; during switching of the MR, an MR_user equipment (UE) 1 establishes synchronization with the target eNode B, applies for resource reservation, establishes connection with the target eNode B at fixed time, and then forwards information which is required by establishment of connection between the MR_UE1 and the target eNode B to an MR_UE2; after receiving related information, the MR_UE2 is immediately disconnected from the source eNode B and quickly switched into the target eNode B; and by using the group switching module, an MR_eNode B unit re-allocates resources which are required by accepted UE and reports a result to a mobility management entity (MME), and the MR_eNode B unit allocates the resources which are provided by the target eNode B to the UE which is accepted by the MR, and reports an allocation result to the MME through the MR_UE1.

The invention discloses a method for predicting the risk of chronic obstructive pulmonary disease. The method includes the steps that the range of user information needing to be acquired is set; relevant sample data is acquired according to the range of the user information; multiple models are established according to the sample data, and training and testing are conducted to screen out the optimal model combination; a combined classifier model is established according to the optimal model combination; the risk of chronic obstructive pulmonary disease is predicted according to the combined classifier model and the user personal information. The invention further provides a server and a computer-readable storage medium. The method for predicting the risk of chronic obstructive pulmonary disease, the server and the computer-readable storage medium can realize the prediction of the risk of chronic obstructive pulmonary disease in the coming year for individuals.

The invention discloses a multi-tug cooperative open caisson floating transportation manipulation simulation control method. The method is in allusion to that scale parameters of a pipe section are very special, the floating transportation process is affected by multiple factors such as channel conditions, the floating transportation distance, the hydrology, the meteorology and the like, and difficulties of heavy water transportation and cooperative towing of multiple tugs are required to be overcome at the same time. According to the invention, the whole process of immersed pipe floating transportation manipulated and towed in a cooperative mode by six tugs under different wind, wave and flow sea conditions is simulated through continuously changing the towing power and the position of the tugs, stress analysis is carried out on the towing force for the immersed pipe every time when the position of the immersed pipe is changed, the manipulating modes of different tugs are adjusted, the single and total tug stresses and a resultant force received by the immersed pipe are calculated, moving postures of the immersed pipe are displayed in an immersed pipe floating transportation towing system, and curves of the cycle time, the track belt width, the tug service power and the like are acquired. The method disclosed by the invention can realize selection and tests for channels, steering areas, foundation trench towing modes and turning modes of each tug, evaluates the controllability, gives an advice on the size of a steering water area and the towing cable length, and judges whether configuration of the tugs is reasonable or not.

The invention discloses a wind turbine self-adaptive torque control method taking the changeable turbulent wind condition into consideration. According to the wind turbine self-adaptive torque control method, by introducing the dynamic power loss index, the self-adaptive searching process of the self-adaptive torque control method is completed, the phenomenon of algorithm failures caused by changes of the turbulent wind condition is eliminated, and accordingly the wind turbine self-adaptive torque control method taking the changeable turbulent wind condition into consideration is provided. The self-adaptive searching algorithm of the wind turbine self-adaptive torque control method is completed, good adaptability can be achieved under the changeable turbulent wind condition, and the wind energy capturing efficiency of a wind turbine is further improved.

The invention relates to a social network based multi-dimension comprehensive recommending method. The recommending method includes: establishing a social network model and a community model; S2: defining the user compactness, the user entity interest degree, and the entity similarity, wherein the user compactness reflects the compactness of a relation between two users, the user entity interest degree reflects the interest degree of a user in an entity, and the entity similarity reflects the consistent degree of attributes of two entities; and S3: performing multi-dimension entity comprehensive recommending on users in a social network according to the user compactness, the user entity interest degree, and the entity similarity. Compared with the prior art, the method can evaluate the influence of commerce websites of the social network from the user relation dimension, the entity similarity dimension, and the user interest dimension, and can perform relative entity recommending, and has wide actual application prospect.

The invention discloses a self-adaptive setting method and a self-adaptive setting device of a network-access searching time interval of a multi-mode multi-standby handheld mobile terminal device, which aims at solving the problems of the prior art that shortage of self-adaptive setting time of the network searching waiting time interval for different types of wireless access technologies leads to the bad user experience. The self-adaptive setting device of the network-access searching time interval of the multi-mode multi-standby handheld mobile terminal device comprises a searching waiting time calculator, a speed measuring module, a coverage density parameter calculator which is provided with a service parameter database, an access remote access Trojan (RAT) searching execution module and an RAT analysis module, wherein the output end of the speed measuring module and the output end of the coverage density parameter calculator are connected with the searching waiting time calculator, the input end of the access RAT searching execution module is connected with the searching waiting time calculator, and the output end of the RAT analysis module is connected with the coverage density parameter calculator. The self-adaptive setting device is simple in structure, complete in functions and high in practical value and popularization value.

The invention relates to an energy system reliability evaluation method considering thermal inertia and energy network constraints. The energy system reliability evaluation method comprises the following steps: determining a reliability index of a user-level comprehensive energy system; acquiring power, thermal and natural gas supply networks and coupling association data thereof, and establishinga user-level comprehensive energy system model; and evaluating the reliability of the user-level comprehensive energy system model based on the reliability index, wherein the user-level comprehensiveenergy system model considers thermal inertia, and the reliability of the user-level comprehensive energy system is calculated based on constraints of different energy networks, and the constraints of the different energy networks comprise power network power flow equation constraints, natural gas network energy flow equation constraints and heat network energy flow equation constraints. Comparedwith the prior art, the user-level comprehensive energy system model disclosed by the invention considers the thermal inertia, and the evaluation of the reliability of the model considers the constraints of different energy networks, and the consideration is more comprehensive, and the accuracy of reliability evaluation is improved.

The invention relates to a torque distribution control system for considering coordination of maneuverability and wheel stability, and a method. The method comprises the following steps that (1) the range constraint of wheel output torque is obtained; (2) generalized force demands for a motion control layer are pre-distributed; (3) the peak slip rate corresponding to a road surface adhesion coefficient and the reference wheel speed of each wheel are obtained, and the working mode of each wheel is determined; (4) an anti-saturation integral slip-mode variable-structure controller is built, anda difference value between the actual wheel speed and the reference wheel speed serves as input to obtain control torque; (5) the non-slip wheels serve as a control variable of secondary distribution,the weighted sum of the minimum generalized force tracking error and the minimum adhesion utilization rate serves as a target function, and optimization solution is conducted; and (6) finally, a torque instruction of a driving anti-slip control unit and a torque instruction of a four-wheel torque distribution control unit are combined to be output to a motor controller. Compared with the prior art, the torque distribution control system for considering coordination of maneuverability and wheel stability, and the method have the advantages of secondary distribution, effective slip preventing,comprehensive consideration, precise control and the like.

The invention belongs to the technology of determination of time between overhauls of an aero-engine and relates to the improvement of a method for determining the time between overhauls of an aero-engine, in particular to a method for determining the time between the overhauls of the aero-engine. The method for determining the time between the overhauls of the aero-engine is characterized by comprising the following steps of sampling estimation, performance degradation analysis, reliability analysis, analysis of the relation between the service life of each part with service life control and the service life of the aero-engine, analysis of the economical efficiency of maintenance, and determination of the time between the overhauls of the aero-engine. By the adoption of the improved method for determining the time between the overhauls of the aero-engine, the accuracy of determination of the time between the overhauls of the aero-engine is improved, the safe reliability of the aero-engine is guaranteed, and the economical efficiency of use and maintenance of the aero-engine is improved. The improved method for determining the time between the overhauls of the aero-engine is suitable for the Chinese management mode of the time between the overhauls of the aero-engine.

The invention discloses a software system performance modeling and optimization method based on a generating countermeasure network, which mainly solves the problems of high time cost, too much difficulty in training, easy collapse of training network and limited optimization space in the prior art. The implementation scheme is as follows: 1) acquiring the feature sample set of the software system; 2) fixing that hardware environment, configuring the software system, carry out performance testing according to the characteristic sample set, obtaining throughput or time delay, carry out pretreatment on the throughput or time delay, and sequentially carrying out single thermal coding and normalization to obtain structured data; 3) at that start of each iteration, randomly selecting half of the structured data from the step 1 as a training sample, iteratively train the generated antagonism network to obtain an optimized sample; 4) comparing the performance of the training sample and the optimization sample to verify the optimization effect. The invention reduces the time cost, improves the robustness and stability of the network, has obvious optimization effect, and can be used for theprocessing of the Internet and the big data.

A method for predicting attributes of webpage crowd includes steps of (1) obtaining basic attribute information of users according to registration information of the user or user IDs (identifications), and preprocessing the basic attribute information to remove unreasonable attribute information of the user; (2) tracking webpage accessed by the user by the aid of loaded Cookie when the users access webpage, and collecting the accessed webpage; (3) computing influence of the word-pair webpage on tendency of the attributes of the users; (3.1) selecting text vector feature words according to differential gain DG of the attributes of the crowd and information gain; (3.2) computing influences of the words on the tendency of the attributes of the webpage crowd; (4) computing the tendency of the attributes of the crowd of a webpage theme; and (5) predicting the tendency of the attributes of the webpage crowd from the respects of the theme and the words respectively and then obtaining integral tendency of the attributes of the webpage crowd. The method is a reliable method for effectively determining the attributes of the webpage crowd in a targeted delivery manner.

The invention discloses an analyzing and determining method for a bridge foundation slope stable slope-angle line. On the basis of the inversion of slope rock-soil physics and mechanics parameters, the action width, embedded depth and load effect modes of a foundation are considered, and the specific position of the stable slope-angle line is analyzed, so that arrangement and engineering design demands for the bridge foundation in a steep slope can be met. The method comprises following technical steps: S1, determining a critical slide surface for the slope parameter inversion; S2, working out the comprehensive cohesive force of a slope rock-soil mass through inverse calculation according to a limit equilibrium state; S3, setting the initial position of the stable slope-angle line; S4, recalculating the slope stability under a bridge foundation loading effect according to the obtained cohesive force of the slope rock-soil mass through inversion calculation; S5, determining whether a safety factor is larger than or equal to a designed safety factor; and S6, obtaining the stable slope-angle line through the analysis.

The invention discloses an immune algorithm-based siting planning method of electric power communication network access points. The method is characterized in that the method comprises steps of 1: determining an access point siting network model; 2: establishing an access point siting mathematic model including cost, reliability, time delays and N-1 principle constraints; 3: defining related concepts of antibodies and antigens in the immune algorithm so as to allow the related concepts to satisfy requirements on access point siting; 4: setting parameters of the immune algorithm and initializing antibody populations; 5: cloning, varying and selecting the antibody populations so as to form a new generation population; 6: judging iteration finishing conditions, and if the iteration finishing conditions are met, finishing iteration, or else continuing the step; and 7: obtaining an optimal access point siting scheme. According to the invention, by comprehensively considering economic construction cost, network reliability, N-1 principles and network time delay constraints, reliable and effective communication of an electric power communication network can be ensured.

The invention relates to an anti-phishing method based on a multi-factor comprehensive assessment method. The method comprises the following steps: step a, establishing a blacklist and whitelist library of URL (uniform resource locator), and processing a target URL, judging whether the processed URL is in the blacklist / whitelist, if so, executing the step d, directly feeding back a result to the user; otherwise, executing the step b, subsequently detecting the website; step b, detecting four aspects of the website: URL angle recognition, website behavior and detail feature recognition, server angle recognition and crawler angle recognition; step c, summarizing and affirming the feedback result; and step d, displaying a result. The method provided by the invention can be used for assessing in many ways with strict procedure; the consideration is comprehensive and the accuracy is high; the hit suspects and corresponding weight value, searched webpage link, website file and judgment criterion are displayed in a graphical interface in a simple and clear mode , the result is available for related professional for examining while being fed back to the user.

The invention provides an exterior-covered waterproof construction method for subway station side walls with hanging plate girders. The method comprises the following particular steps that firstly, underground diaphragm walls, embedded bars, uplift piles and lattice columns are constructed; secondly, a first layer of an earthwork is excavated, and roofs of a subway station and a commercial real estate are constructed; thirdly, a second layer of the earthwork and a second last layer of the earthwork are continuously excavated, pouring of middle plates and the hanging plate girders of all layers of the subway station is completed, and waterproof treatment is performed before the middle plates and the hanging plate girders of all the layers are poured; fourthly, the bottommost layer of the earthwork is excavated, bottom plates of the subway station and the commercial real estate are constructed, waterproof structures at the bottom plates are constructed, and the station side wall at the bottommost layer is poured; fifthly, all layers of the hanging plate girders are sequentially removed in a chiseling mode from bottom to top, and the station side walls are sequentially poured after waterproof treatment is performed on the layers.

The invention discloses an SDN-based space-based information network multi-controller efficacy-losing backup method. The method comprises the following steps of constructing an SDN-based space-based information network multi-controller efficacy-losing backup framework; designing an efficacy-losing detecting mechanism; recovering a controller election algorithm based on faults of a Paxos algorithm.The SDN core technology is applied to a space-based information network, and therefore the structure of network equipment is simplified, a satellite just needs to achieve the simple forwarding and hardware configuring functions, and therefore the defect that satellite nodes are complex in design and high in manufacturing cost is overcome. The SDN-based space-based information network can achieveoverall resource distribution and overall optimization, and the resource utilization rate is increased. By adopting the multi-controller framework, the expansibility of the space-based information network can be improved, and therefore the flexible and efficient network configuration and management are achieved. In addition, centralized management has the overall view of all nodes in the whole network, the state of the satellite nodes can be grasped, and the network destroy resistance is improved.

The invention discloses an operation opportunity prediction model for a patient with acute necrotizing pancreatitis, and the model comprises the following steps: S100, collecting and cleaning case data which comprises admission data and hospitalization data of the patient; S200, sorting the case data to obtain preprocessed data, wherein the sequence form of the preprocessed data is {Variables, Time}; S300, carrying out one-hot coding on the category type variables in the preprocessed data by using an Embedding mechanism, and then mapping the category type variables into a real vector space; S400, normalizing the data obtained in the step S300, introducing an LSTM model which is a multi-task model, wherein the output layer of the LSTM model is provided with four outcome indexes: 48-hour death after the patient is hospitalized, the number of remaining hospitalized days, whether organ failure occurs or not and whether an operation is performed or not. The optimal operation opportunity ofeach patient with acute pancreatitis necrosis can be determined according to the characteristics of the patient, so the prognosis condition of the patient is improved.