CN116080847A

CN116080847A - Ship safety management method, system, device and storage medium

Info

Publication number: CN116080847A
Application number: CN202310079844.9A
Authority: CN
Inventors: 柏建新; 李彦瑾; 史孝玲; 柏宗翰; 史孝金; 胡艳梅
Original assignee: Hebei Donglai Engineering Technology Service Co ltd
Current assignee: Hebei Donglai Engineering Technology Service Co ltd
Priority date: 2022-09-27
Filing date: 2022-09-27
Publication date: 2023-05-09
Anticipated expiration: 2042-09-27
Also published as: CN116080847B; CN115258078A; CN115258078B

Abstract

The embodiment of the specification provides a method, a system, a device and a storage medium for ship safety management. The method comprises the following steps: acquiring severe weather information based on weather forecast information of a sea area through which a ship passes; acquiring the outdoor position of a passenger in a ship; based on severe weather information and outdoor positions, predicting bump predictions corresponding to the outdoor positions, and taking the bump predictions corresponding to the outdoor positions as outdoor activity risks; based on the outdoor activity risk, outdoor activity alert information is sent to the passenger.

Description

Ship safety management method, system, device and storage medium

Description of the division

The application is a divisional application filed in China with the application date of 2022, 09 and 27 and the application number of 202211177733.3, and the invention is named as a method, a system, a device and a storage medium for ship emergency management.

Technical Field

The present disclosure relates to the field of ship management, and in particular, to a method, system, device, and storage medium for ship safety management.

Background

With the development of economy and the improvement of the living standard of people, ships such as cargo ships, cruise ships and the like are increasingly used. During sailing of a ship, passengers or crews located outdoors may be at risk of being dropped, bumped or even falling into water due to jolt of the ship.

Accordingly, it is desirable to provide a method, system, apparatus, and storage medium for ship safety management that enables prediction of ship jolts, gives early warning to outdoor active passengers, reduces the probability of injury to passengers due to ship jolts, and ensures the safety of ship passengers.

Disclosure of Invention

One of the embodiments of the present specification provides a method of ship safety management. The ship safety management method comprises the following steps: acquiring severe weather information based on weather forecast information of a sea area through which a ship passes; acquiring the outdoor position of a passenger in a ship; based on severe weather information and outdoor positions, predicting bump predictions corresponding to the outdoor positions, and taking the bump predictions corresponding to the outdoor positions as outdoor activity risks; based on the outdoor activity risk, outdoor activity alert information is sent to the passenger.

One of the embodiments of the present specification provides a system for ship safety management. The system for ship safety management comprises: the acquisition module is used for acquiring severe weather information and acquiring the outdoor position of a passenger in the ship based on weather forecast information of the sea area where the ship passes; the prediction module is used for predicting bump prediction corresponding to the outdoor position based on severe weather information and the outdoor position, and taking the bump prediction corresponding to the outdoor position as outdoor activity risk; and the determining module is used for sending outdoor activity alarm information to passengers based on the outdoor activity risk.

One of the embodiments of the present specification provides an apparatus for emergency management of a vessel, the apparatus comprising at least one processor and at least one memory; the at least one memory is configured to store computer instructions; the at least one processor executes at least some of the computer instructions to implement a method of vessel safety management.

One of the embodiments of the present specification provides a computer-readable storage medium storing computer instructions that, when read by a computer in the storage medium, perform a method of ship security management.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is a schematic illustration of an application scenario of a system for emergency management of a vessel according to some embodiments of the present description;

FIG. 2 is an exemplary block diagram of a system for emergency management of a vessel according to some embodiments of the present description;

FIG. 3 is an exemplary flow chart of a method of emergency management of a vessel according to some embodiments of the present description;

FIG. 4 is an exemplary schematic diagram of a hull pitch prediction model and a personal pitch prediction model according to some embodiments of the present disclosure;

fig. 5 is an exemplary flow chart for transmitting outdoor activity alert information based on ship's risk of outdoor activity according to some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

The terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly indicates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

Fig. 1 is a schematic view of an application scenario of a system for emergency management of a ship according to some embodiments of the present description.

As shown in fig. 1, a processor 110, a network 120, a storage device 130, a ship 140, a user terminal 150, and passengers 160 may be included in an application scenario 100 of a system for ship emergency management.

Processor 110 may be used to perform one or more functions disclosed in one or more embodiments herein. For example, the processor 110 may be configured to predict a ship risk based on ship state information. For another example, the processor 110 may be configured to send alert information to the passenger based on the risk of the vessel.

In some embodiments, processor 110 may include one or more processing engines (e.g., a single chip processing engine or a multi-chip processing engine). By way of example only, the processor 110 may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Processor (ASIP), a Graphics Processor (GPU), a Physical Processor (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), an editable logic circuit (PLD), a controller, a microcontroller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

The network 120 may connect components of the system and/or connect the system with external resource components. Network 120 enables communication between components and other parts of the system to facilitate the exchange of data and/or information. For example, processor 110 may obtain vessel status information from storage device 130 via network 120. For another example, the processor 110 may obtain passenger location information from the user terminal 150 via the network 120.

In some embodiments, network 120 may be any one or more of a wired network or a wireless network. For example, the network 120 may include a cable network, a fiber optic network, a telecommunications network, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth network, a ZigBee network, a Near Field Communication (NFC), an intra-device bus, an intra-device line, a cable connection, and the like, or any combination thereof. The network connection between the parts can be in one of the above-mentioned ways or in a plurality of ways. In some embodiments, the network may be a point-to-point, shared, centralized, etc. variety of topologies or a combination of topologies.

The storage device 130 may be used to store data and/or instructions related to the application scenario 100 of the system for marine emergency management. In some embodiments, storage device 130 may store data and/or information obtained from processor 110, vessel 140, and the like. For example, the storage device 130 may store ship state information, passenger cabin information, historical outdoor activity records of passengers, and the like.

Storage device 130 may include one or more storage components, each of which may be a separate device or may be part of another device. In some embodiments, the storage device 130 may include Random Access Memory (RAM), read Only Memory (ROM), mass storage, removable memory, volatile read-write memory, and the like, or any combination thereof. By way of example, mass storage may include magnetic disks, optical disks, solid state disks, and the like. In some embodiments, storage device 130 may be implemented on a cloud platform.

The vessel 140 may comprise a variety of types of vessels. For example, the vessel 140 may be a passenger cargo vessel, a general cargo vessel, a cruise vessel, or the like. As shown in fig. 1, the vessel may be a multi-layered structure (e.g., 10 layers, etc.). The number of layers may be named up below. Such as layer 1, layer 2, … …, layer 10, etc. Different passengers may be located in different levels and at different locations of the watercraft. The vessel 140 may include an electronic control system equipped with various functional systems of the vessel itself. The electrical control system of the vessel may be part of a system for emergency management of the vessel. The processor 110 may acquire ship status information and the like through an electronic control system of the ship.

User terminal 150 may refer to one or more terminal devices or software used by a passenger. In some embodiments, the user terminal 150 may include a mobile device 150-1, a tablet computer 150-2, a notebook computer 150-3, or the like, or any combination thereof. In some embodiments, the processor 110 may interact with the passenger through the user terminal 150. The above examples are only intended to illustrate the broad scope of the user terminal and not to limit its scope.

In some embodiments, the user terminal 150 may be one or more passengers 160. Passengers 160 may refer to people on the vessel. For example, the passengers may be passengers, crews, captain, etc. on the vessel.

It should be noted that the application scenario 100 of the system for marine emergency management is provided for illustrative purposes only and is not intended to limit the scope of the present description. Many modifications and variations will be apparent to those of ordinary skill in the art in light of the present description. However, such changes and modifications do not depart from the scope of the present specification.

FIG. 2 is an exemplary block diagram of a system for marine emergency management according to some embodiments of the present description. In some embodiments, the system 200 for marine emergency management may include an acquisition module 210, a prediction module 220, and a determination module 230.

In some embodiments, the acquisition module 210 may be used to acquire vessel status information.

In some embodiments, the prediction module 220 may be configured to predict a ship risk based on ship state information.

In some embodiments, the determination module 230 may be configured to send alert information to the passenger based on the risk of the vessel.

In some embodiments, the alert information may include bump alert information, and the determination module 230 may also be used to obtain passenger cabin information and passenger positioning information; determining a passenger position of the passenger based on the passenger cabin information and the passenger positioning information; determining a bump prediction corresponding to the passenger position based on the passenger position and the ship risk; based on the jolt prediction, jolt alert information is sent to the passenger.

In some embodiments, the determination module 230 may also be configured to predict vessel pitch information based on vessel risk by a hull pitch prediction model, wherein the hull pitch prediction model is a machine learning model; based on ship bump information and passenger positions, bump prediction is predicted by a personal bump degree prediction model, wherein the personal bump degree prediction model is a machine learning model.

In some embodiments, the input to the hull pitch prediction model includes hull information, wherein the hull information includes at least one of displacement, hull size, and speed.

In some embodiments, the training mode of the hull pitch prediction model and the personal pitch prediction model includes joint training.

In some embodiments, the alert information includes outdoor activity alert information, and the determination module 230 may also be used to predict severe weather information based on weather forecast information; predicting outdoor activity risk based on severe weather information; an outdoor activity alert message is sent to an outdoor activity passenger based on the outdoor activity risk, wherein the outdoor activity passenger is determined from the passenger's current location information and/or historical outdoor activity records.

In some embodiments, the determination module 230 may also be used to obtain the outdoor location of the passenger; and determining bump prediction corresponding to the outdoor position based on the severe weather information and the outdoor position.

In some embodiments, the determination module 230 may also be used to obtain historical outdoor activity records of the passenger; based on the historical outdoor activity records, outdoor locations are determined by a clustering algorithm.

It should be appreciated that the system of marine emergency management shown in fig. 2 and its modules may be implemented in a variety of ways. For example, in some embodiments the system and its modules may be implemented in hardware, software, or a combination of software and hardware.

It should be noted that the above description of the system for emergency management of a ship and its modules is for convenience of description only and is not intended to limit the present description to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. In some embodiments, the acquisition module 210, the prediction module 220, and the determination module 230 disclosed in fig. 1 may be different modules in one system, or may be one module to implement the functions of two or more modules described above. For example, each module may share one memory module, or each module may have a respective memory module. Such variations are within the scope of the present description.

FIG. 3 is an exemplary flow chart of a method of marine emergency management according to some embodiments of the present description. In some embodiments, the process 300 may be performed by the processor 110. As shown in fig. 3, the process 300 may include the steps of:

step 310, acquiring ship state information. In some embodiments, step 310 may be performed by the acquisition module 210.

The ship status information may refer to related information that may have an influence on the ship. For example, the ship status information may include the status of the ship itself, the external environment information in which the ship is located, a ship sailing plan, and the like. The state of the vessel itself may include the operational state of the various functional systems of the vessel itself. For example, the operational status may include operational status information for bilge systems, ballast systems, fire protection systems, ventilation systems, cargo oil systems, electromechanical systems, and the like. The external environment information of the ship can comprise information such as navigational speed, weather forecast information, bow direction, track direction and the like.

In some embodiments, the acquisition module 210 may acquire the vessel status information in a variety of ways. For example, the acquiring module 210 may acquire the ship status information from a data interface of an electronic control system equipped with each of the functional systems of the ship itself. For another example, the acquisition module 210 may acquire information about the external environment in which the vessel is located (e.g., information about speed, bow direction, track direction, etc.) via a sensor or a GPS positioning device mounted on the vessel. For another example, the acquisition module 210 may acquire weather forecast information or the like through the network 120. For another example, the acquisition module 210 may acquire a ship voyage plan or the like in the storage device 130 through the network 120. In some embodiments, the acquisition module 210 may acquire the vessel status information in real-time.

Step 320, predicting the ship risk based on the ship status information. In some embodiments, step 320 may be performed by prediction module 220.

Ship risk may refer to information related to the risk that a ship may be at. The ship risk may include ship risk related information, risk that a ship may occur, and the like. The vessel risk related information may characterize the information related to vessel risk. For example, the ship risk related information may include information of sea areas where the ship passes at different points in time, wave heights corresponding to different sea areas, wind power, wind direction, and the like. By means of the above-mentioned ship risk related information, the risk that may occur at a future point in time/section of the ship can be predicted. The risk that may occur at future points in time/segments of the vessel may include bump, risk of outdoor activity, risk of the vessel itself, etc. See the relevant description of fig. 4 and 5 for bumps, risk of outdoor activity, etc. The ship risk is a risk related to abnormality of the ship state (such as ship running out of control, power failure, etc. caused by the failure of the ship electromechanical system). In some embodiments, the ship risk may include information about the risk that the ship may be at, a current point/segment, a future point/segment, etc. In some embodiments, the ship risk may be represented by a vector. The different elements in the vector may represent characteristics of information related to the risk that the ship may be at. For example, the different elements represent information of wave height characteristics, wind power characteristics, wind direction characteristics, and the like, respectively. Wherein the wind direction characteristic can be represented by the angle between the wind direction and the sailing direction of the hull.

In some embodiments, the prediction module 220 may predict the ship risk in a variety of ways based on the ship state information. For example, the prediction module 220 may determine the sea area (longitude, latitude, etc.) through which the ship passes at different points in time based on the ship's voyage plan in the ship state information. The prediction module 220 may predict ship risk related information (e.g., wave height, wind power, wind direction, etc. information corresponding to different sea areas) based on weather forecast information, etc. The prediction module 220 may represent the vessel risk related information by a vector, thereby determining information that may characterize the vessel risk related information. For another example, the prediction module 220 may predict that a portion of the ship's functions may not be operational based on the operational status of the ship itself, etc. An information comparison table exists between the failure of the ship part function to operate and the risk of the ship itself. The prediction module 220 may determine a ship self risk among the corresponding ship risks that the ship part function cannot operate based on the information comparison table.

Step 330, based on the ship risk, an alert message is sent to the passenger. In some embodiments, step 330 may be performed by determination module 230.

The alarm information refers to related information that can alert passengers to notice or pay attention to. For example, the warning message is a warning about a bump of a ship, and the passenger is alerted. For another example, the alert information is to disable outdoor activity based on outdoor activity risk assessment. As another example, the warning message is a warning that some areas of the ship may be powered down, asking passengers to leave as soon as possible, and not to panic. In some embodiments, the alert information may include a risk type and a risk level. Risk types may include bump risk, risk of outdoor activities, and so on. The risk level may be primary, secondary, tertiary, etc. The higher the rank, the greater the corresponding risk.

In some embodiments, the determination module 230 may determine different alert information based on different ship risks. For example, the determination module 230 determines when the vessel is likely to jolt based on the vessel risk. The warning information may be information about the risk of jolt, the level of the risk of jolt being 4, etc., which reminds passengers to pay attention to jolt of the ship and keep the respective articles. For another example, when the determining module 230 determines that there is a risk in the outdoor activity of the passenger based on the ship risk, the determining module 230 may determine that the alarm information is information about the risk of the outdoor activity, the risk level of the outdoor activity is three-level, and the like, to remind the passenger to avoid the outdoor activity. For another example, when the ship risk is a sudden power outage, the determination module 230 may determine the alert information as information regarding how long to alert the passengers to resume power supply as little as possible.

In some embodiments, the determination module 230 may send the alert information to the passenger in a variety of ways based on the alert information. For example, the determination module 230 may send alert information to the passenger by way of a broadcast. For another example, the determination module 230 may continuously scroll display the red bolded alert information to the passengers via one or more display screens on the watercraft (e.g., television screens in the lobby or each cabin, etc.). For another example, the determination module 230 may send alert information to the user terminal 150 used by the passenger through the network 120.

In some embodiments, the determination module 230 may obtain passenger cabin information and passenger positioning information, and determine a passenger position of the passenger based on the passenger cabin information and the passenger positioning information. The determination module 230 may determine a bump prediction corresponding to the passenger location based on the passenger location and the ship risk, and send bump alert information to the passenger based on the bump prediction.

In some embodiments, the alert information may include bump alert information. The bump alarm information is ship bump information that can alert passengers to the attention or focus. The bump alarm information corresponding to different positions of the hull may be different. For example, the hull is a multi-layer structure (e.g., 10 layers), and the higher the bump risk level in the bump alarm information of the passenger position corresponding to the upper layer in the hull (the bump risk level corresponding to the 10 th layer is 5 levels, for example). The lower the bump risk level in the bump alarm information of the passenger position corresponding to the lower layer in the hull (the bump risk level corresponding to the passenger position of layer 3 is, illustratively, level 2).

In some embodiments, the determination module 230 may obtain passenger cabin information and passenger positioning information. The determination module 230 may determine the passenger position of the passenger based on the passenger cabin information and the passenger positioning information. The determination module 230 may determine a bump prediction corresponding to the passenger location based on the passenger location and the ship risk, and send bump alert information to the passenger based on the bump prediction.

The passenger compartment information may refer to position information of the passengers in the cabin of the ship. For example, the passengers are crews, and the passenger cabin information is the cabin in which the crews live or work. For example, the passenger is an occupant, and the passenger compartment information is a compartment corresponding to the time the occupant purchased the ticket. The passenger positioning information may be a position on the vessel where the passenger is located for a period of time. For example, the positioning information indicates that the passenger is in a cabin within 5 minutes. For another example, the positioning information shows a viewing area on the deck of the vessel where the passenger is located within 30 minutes.

In some embodiments, the determination module 230 may obtain the passenger cabin information and the passenger positioning information in a variety of ways. For example, the determination module 230 may obtain ticket information of the occupant via the network 120, thereby determining passenger cabin information of the occupant, and the like. For another example, the determination module 230 may obtain crew information in the storage device 130 via the network 120 to determine cabins or the like in which the crew lives or works. For another example, the determination module 230 may determine the passenger location information by detecting the identity of the passenger in the cabin via a sensor or camera mounted on the watercraft, or the like. For another example, the determination module 230 may determine the passenger location information through the location information of the user terminal. In some embodiments, the determination module 230 may obtain passenger location information in real-time.

The passenger position may refer to an area position where the passenger may be located within a certain range on the ship at the present time.

In some embodiments, the determination module 230 may determine the location corresponding to the passenger cabin information or the location corresponding to the passenger positioning information as the passenger location of the passenger.

Jolt prediction may refer to relevant information about jolt corresponding to the passenger location. The pitch predictions for different positions of the hull are different. When the passengers are located at different positions of the hull, the bump predictions corresponding to the passenger positions are also different. In some embodiments, the bump predictions may include a shake amplitude, a shake frequency, etc. corresponding to the passenger position. In some embodiments, the bump prediction may include a bump risk level of the passenger's location, etc.

In some embodiments, the determination module 230 determines a bump prediction corresponding to the passenger location based on the passenger location and the ship risk. For example, the greater the corresponding wave height, wind force, etc. in the ship risk, the higher the corresponding bump risk level in the bump prediction determined by the determination module 230. The higher the passenger position is at an upper level in the hull, the higher the corresponding bump risk level for the passenger position determined by the determination module 230.

In some embodiments, the determination module 230 may predict the vessel pitch information via a hull pitch degree prediction model based on the vessel risk. Based on the ship pitch information and the passenger position, a pitch prediction is predicted by a personal pitch degree prediction model. For a specific description of the prediction of the pitching prediction based on the hull pitching degree prediction model and the individual pitching degree prediction model, reference is made to the relevant description of fig. 4.

In some embodiments, the determination module 230 may determine bump alert information based on the bump prediction, and send the bump alert information to the corresponding passenger. For example, the determination module 230 determines that the bump prediction corresponding to the passenger location (e.g., layer 7 of the hull) is a bump risk level of 4. The determining module 230 may determine that the bump alarm information corresponding to the passenger position is "bump risk level 4", please the passenger notice that the ship bumps, keep the respective articles, and avoid damaging the articles. For another example, the determination module 230 determines that the bump prediction corresponding to the passenger location (e.g., layer 3 of the hull) is a bump risk level 2. The determining module 230 may determine that the bump alarm information corresponding to the passenger position is "bump risk level 2", and please the passenger pay attention to hull bump ".

In some embodiments of the present disclosure, by predicting bump prediction of a passenger position in advance and sending a prompt and advice about bump to a passenger, unnecessary loss of the passenger caused by bump can be well avoided, and timely and efficient communication and organization management in an emergency process can be further realized, so that safety of the passenger is ensured.

In some embodiments, the alert information may include outdoor activity alert information. The determination module 230 may predict severe weather information based on weather forecast information; based on the severe weather information, the outdoor activity risk is predicted. The determination module 230 may send outdoor activity alert information to the outdoor activity passenger based on the outdoor activity risk. For more on the transmission of outdoor activity alert information to outdoor activity passengers based on outdoor activity risk, see the associated description of fig. 5.

In some embodiments of the present disclosure, by predicting the ship risk by using the ship status information, and sending the alarm information to the passengers, timely and efficient communication and organization management in the emergency process can be achieved, timely and effective reactions can be made to various emergency situations of the ship, and the safety of the ship and the passengers is ensured.

FIG. 4 is an exemplary schematic diagram of a hull pitch prediction model and a personal pitch prediction model according to some embodiments of the present description.

In some embodiments, the determination module 230 may predict the vessel pitch information 431 based on the vessel risk 411 through the hull pitch degree prediction model 420.

The vessel pitch information 431 may refer to information reflecting the degree of hull pitch of the vessel at a plurality of time points/segments in the future. In some embodiments, the degree of hull pitch may be represented by a pitch risk level. The higher the grade, the greater the degree of hull pitching.

In some embodiments, the degree of hull pitch may be characterized by predicting the roll amplitude, roll frequency, etc. of the hull in different directions. The vessel pitch information may be represented by a feature vector. For example, the feature vectors (a, b, c, … …) may represent vessel pitch information, and different elements in the feature vectors may represent roll amplitudes, roll frequencies, etc. of the hull in different directions at a plurality of points/segments in the future.

In some embodiments, the hull pitch prediction model 420 may be a machine learning model. In some embodiments, the type of hull pitch prediction model 420 may include a neural network model, a deep neural network model, etc., with the choice of model type being contingent on the particular situation.

In some embodiments, the input 410 of the hull pitch prediction model may include a ship risk 411 or the like. For more explanation of the risk of a ship, see fig. 3 and the associated description. The output of the hull pitch prediction model 420 may include vessel pitch information 431.

In some embodiments, the input 410 of the hull pitch prediction model may include hull information 412. The hull information 412 may refer to parameter information related to the hull. For example, the hull information may include at least one of a displacement of the ship, a hull size, a voyage speed of the ship, and the like. For example, hull information may be "10 ten thousand tons of water displaced, 150 meters long, 25 meters wide, 20 meters high, 12 knots of speed of the ship, etc.

In some embodiments of the present disclosure, based on the displacement, the hull size, the speed, etc. in the hull information, the prediction efficiency and accuracy of the ship bump information may be further improved by predicting the ship bump information through a model, and the risk of ship bump may be further responded to timely and effectively, so as to ensure the safety of the ship and passengers.

In some embodiments, the determination module 230 may input the ship risk and hull information, etc. of the ship at a plurality of points in the future into the hull pitch prediction model 420. The hull pitch degree prediction model 420 may output the ship pitch information 431.

In some embodiments, the hull pitch prediction model may be trained from a plurality of tagged first training samples. For example, a plurality of first training samples with labels may be input into an initial hull pitch prediction model, a loss function is constructed from the labels and the results of the initial hull pitch prediction model, and parameters of the initial hull pitch prediction model are iteratively updated based on the loss function. And when the loss function of the initial hull bumping degree prediction model meets the preset condition, model training is completed, and a trained hull bumping degree prediction model is obtained. The preset condition may be that the loss function converges, the number of iterations reaches a threshold value, etc.

In some embodiments, the first training sample may include sample vessel risk, sample hull information, and the like. The tag may be sample vessel bump information corresponding to sample vessel risk, sample hull information, and the like. The first training sample may be obtained based on historical data. For example, the determination module 230 may take the ship risk and hull information in the historical data as sample ship risk and sample hull information, and the like. The labels of the first training samples may be obtained based on manual labeling or automatic labeling. For example, the determining module 230 may obtain, based on ship risk and hull information at different time points, sway amplitudes, sway frequencies, and the like of the hulls corresponding to the different time points in different directions through the sway sensing device. The determining module 230 may represent the sway amplitude, sway frequency, etc. of the hull in different directions by the feature vector, and generate sample ship bump information of the hull corresponding to different time points. The determining module 230 may use sample ship bump information corresponding to sample ship risk and sample hull information at different time points as a tag of the first training sample.

In some embodiments, the determination module 230 may predict the bump prediction by a personal bump degree prediction model based on the ship bump information, the passenger position, and the like. For more explanation on passenger position and jounce predictions, see the associated description of FIG. 3.

In some embodiments, the personal jolt degree prediction model 440 may be a machine learning model. In some embodiments, the type of personal jolt degree prediction model 440 may include a neural network model, a deep neural network model, etc., with the selection of the model type being contingent on the particular situation.

In some embodiments, the input 430 of the personal jounce degree prediction model may include passenger position 432, vessel jounce information 431, and the like. In some embodiments, the passenger position may be represented by the amount of deviation of the passenger's position in three directions relative to the center of the hull. The three directions may include a length direction, a width direction, and a height direction of the hull. For example, the hull center is set to the center point of the three-dimensional coordinate XYZ. The length direction, width direction and height direction of the ship body are respectively X-axis, Y-axis and Z-axis directions. The positive directions of the X axis, the Y axis and the Z axis can be preset in advance. For example, the direction from the center of the hull to the bow is the positive X-axis direction; one side, which points to the width of the ship body from the center of the ship body, is a Y-axis positive direction, and the other side, which points to the width of the ship body from the center of the ship body, is a Y-axis negative direction; the direction from the center of the ship body to the ship top is the positive direction of the Z axis, and the direction from the center of the ship body to the ship bottom is the negative direction of the Z axis. Illustratively, a passenger position is (5, 2, -1), where 5 may represent a deviation of the passenger position in the length direction from the center of the hull toward the bow direction by 5 meters; 2 may indicate that the passenger position deviates from the center of the hull by 2 meters in the width direction to one side of the hull width; -1 may denote that the passenger position deviates 1 meter in height from the centre of the hull towards the bottom of the ship. The output of the personal jerk prediction model 440 may include a jerk prediction 450.

In some embodiments, the determination module 230 may input the vessel jolt information 431 and the passenger position 432, etc. into the trained personal jolt degree prediction model 440. The individual pitch prediction model 440 may output a pitch prediction 450 corresponding to the passenger position.

In some embodiments, the personal jolt degree prediction model may be trained by a plurality of labeled second training samples. For example, a plurality of second training samples with labels may be input into the initial personal jounce degree prediction model, a loss function is constructed from the labels and the results of the initial personal jounce degree prediction model, and parameters of the initial personal jounce degree prediction model are iteratively updated based on the loss function. And when the loss function of the initial personal bumping degree prediction model meets the preset condition, model training is completed, and a trained personal bumping degree prediction model is obtained. The preset condition may be that the loss function converges, the number of iterations reaches a threshold value, etc.

In some embodiments, the second training samples may include sample vessel bump information, sample passenger position, and the like. The tag may be sample passenger bump information corresponding to the sample passenger position and sample ship bump information. The second training sample may be obtained based on historical data. For example, the determination module 230 may take the vessel jolt information, the passenger position, etc. in the history data as the sample vessel jolt information, the sample passenger position, etc. The labels of the second training samples may be obtained based on manual labeling or automatic labeling. For example, the determining module 230 may obtain, based on the ship bump information and the passenger position at different time points, the sway amplitude, the sway frequency, etc. of the hull at the passenger position in different directions corresponding to the different time points through the sway sensing device. The determining module 230 may represent the sway amplitude, sway frequency, etc. of the hull at the passenger position in different directions by the feature vector, and generate sample passenger pitch information of the hull at the passenger position corresponding to different time points. The determination module 230 may use the sample ship jolt information and the sample passenger jolt information corresponding to the sample passenger position, etc. at different points in time as a tag of the second training sample.

In some embodiments, the output of the hull pitch prediction model may be an input of the individual pitch prediction model, and the training of the hull pitch prediction model and the individual pitch prediction model may be joint training.

In some embodiments, the sample data of the joint training includes sample ship risk, sample hull information, sample passenger position, etc., and the tag is sample passenger jolt information corresponding to the sample data. The determining module 230 may input the sample ship risk and the sample ship information into the ship bump degree prediction model, so as to obtain the ship bump information output by the ship bump degree prediction model. And taking the ship bump information as training sample data, and inputting the sample passenger position into a personal bump degree prediction model to obtain the passenger bump information output by the personal bump degree prediction model. And constructing a loss function based on the passenger bump information output by the sample passenger bump information and the personal bump degree prediction model, and synchronously updating parameters of the ship bump degree prediction model and the personal bump degree prediction model based on the loss function. And obtaining a trained ship body bumping degree prediction model and a trained individual bumping degree prediction model through parameter updating.

In some embodiments of the present disclosure, parameters of the hull pitch prediction model and the individual pitch prediction model are determined by means of joint training. In some cases, the problem that labels are difficult to obtain when the hull bumping degree prediction model and the personal bumping degree prediction model are independently trained is solved, the number of required samples can be reduced, and the training efficiency can be improved.

In some embodiments of the present disclosure, the prediction efficiency and accuracy of the bump prediction corresponding to the bump information and the passenger position of the ship are effectively improved by predicting the bump prediction corresponding to the bump information and the passenger position of the ship through the model, so that timely and efficient communication and organization management in an emergency process can be further realized, timely and effective reactions can be made to various emergency situations of the ship, and the safety of the ship and the passenger is ensured.

Fig. 5 is an exemplary flow chart for transmitting outdoor activity alert information based on ship's risk of outdoor activity according to some embodiments of the present description. In some embodiments, the process 500 may be performed by the determination module 230.

Step 510, predicting severe weather information based on the weather forecast information.

The severe weather information may include information of a start time, a duration, a degree of severity, and the like of the severe weather. Bad weather may refer to weather corresponding to the type of weather that may cause injury to personnel in outdoor activities, such as, for example, heavy winds, heavy rain, hail, etc. The severity of severe weather can be characterized by weather parameters. For example, the wind power rating may be indicative of the severity of windy weather. As another example, the level of rainfall may be indicative of the severity of heavy rain weather.

In some embodiments, the determination module 230 may determine the severe weather information based on weather forecast information predictions for the sea area over which the vessel passes at a plurality of future points in time. The future time points of the ship can be selected manually, and the time interval between every two adjacent time points can be the same. The sea area location through which the vessel passes at a plurality of time points in the future may be determined based on the vessel's voyage plan.

Step 520, predicting outdoor activity risk based on the severe weather information.

Outdoor activity risk may refer to the potential risk of passengers on a vessel performing outdoor activities suffering from accidental dangerous injuries. The outdoor activity risk may be characterized by a form of outdoor activity risk rating or outdoor activity risk score, or the like. Types of accidental hazards may include, but are not limited to, falling injury, bruising, scratching, falling water, etc. due to inclement weather. The risk of outdoor activity corresponding to different time periods may be different.

In some embodiments, the determination module 230 may determine the outdoor activity risk based on a correspondence of historical severe weather information and historical outdoor activity risk.

In some embodiments, the determination module 230 may obtain the outdoor location of the passenger, determine a bump prediction corresponding to the outdoor location based on the severe weather information and the outdoor location of the passenger.

The outdoor location may refer to an area location on the ship where an outdoor passenger may move, for example, a balcony, a deck, a swimming pool, etc.

In some embodiments, the determination module 230 may determine the outdoor location of the passenger based on the location information of the passenger's user terminal. In some embodiments, the determination module 230 may determine the identity of the passenger based on the image of the passenger captured by the monitoring device of the outdoor area, and take the corresponding outdoor area as the outdoor location of the passenger.

In some embodiments, the determination module 230 may obtain historical outdoor activity records of the passenger and determine the outdoor location by a clustering algorithm based on the historical outdoor activity records.

Historical outdoor activity records may refer to text information recorded with the time and location of the outdoor activity of the passenger. Illustratively, the content of the historical outdoor activity record of a passenger (e.g., zhang Sanj) may include historical outdoor activity information 1"5 months, 6 days, 10 hours to 11 hours on deck"; historical outdoor activity information 2"5 months 7 days 16 to 17 on balcony" and the like.

In some embodiments, the determination module 230 may obtain the historical outdoor activity record of the passenger in a variety of ways. For example, the determination module 230 may determine the identity of the passenger based on the passenger image captured by the monitoring device in the outdoor area and store information about the outdoor activities for different periods of time to the storage device 130 as a historical outdoor activity record. When a historical outdoor activity record is desired, the determination module 230 may obtain the historical outdoor activity record via the storage device 130.

In some embodiments, the clustering algorithm may include the steps of: the historical outdoor activity is recorded as a set of historical outdoor activity information, each piece of historical outdoor activity information being an element of the set. And clustering the historical outdoor activity information set to determine a clustering center set. A set of historical outdoor activity information vectors may be constructed based on the set of historical outdoor activity information, the set of historical outdoor activity information vectors including a plurality of historical outdoor activity information vectors, wherein each historical outdoor activity information vector corresponds to a piece of historical outdoor activity information.

The set of cluster centers may include one or more cluster centers. The cluster center may represent an area in which the passenger outdoor activity is located. In some embodiments, the determination module 230 may cluster the set of historical outdoor activity information vectors by a clustering algorithm to determine a cluster center set. Clustering algorithms may include, but are not limited to, K-Means clustering and/or density-based clustering methods (DBSCAN), and the like.

In some embodiments, the determination module 230 may construct the outdoor activity risk vector based on information corresponding to the outdoor activity risk. The determination module 230 may determine a cluster center of the set of cluster centers that is closest to the outdoor activity risk vector. Methods of calculating the distance may include, but are not limited to, euclidean distance, cosine distance, mahalanobis distance, chebyshev distance, and/or Manhattan distance, among others. In some embodiments, the determination module 230 may determine a location corresponding to a cluster center closest to the outdoor activity risk vector as the outdoor location of the passenger.

In some embodiments of the present disclosure, the accuracy of determining the outdoor location of the passenger may be improved by determining the outdoor location of the passenger through a clustering algorithm.

In some embodiments, the prediction of the risk of outdoor activity may also include a prediction of a corresponding bump of the outdoor location. Different outdoor locations may correspond to different bump predictions. For more on bump prediction see fig. 3. The bump prediction corresponding to the outdoor location can be represented by a bump risk. The bump risk may refer to the degree of bump in the outdoor location where the passenger is located. The bump risk may be characterized by a bump risk level or a bump risk score, etc.

In some embodiments, the determination module 230 may determine the bump predictions corresponding to the outdoor locations based on severe weather information, the outdoor locations of the passengers, and the like. For example, the determination module 230 may input severe weather information or the like into the hull pitch degree prediction model to predict the vessel pitch information. The determination module 230 may input the ship pitch information, the outdoor position of the passenger, and the like into the personal pitch degree prediction model to predict a pitch prediction corresponding to the outdoor position. For more explanation on the hull pitch prediction model and the individual pitch prediction model, see fig. 4.

In some embodiments, the determination module 230 may comprehensively predict the bump risk corresponding to the outdoor location based on ship bump information, bad weather information, the outdoor location of the passenger, and the like. For example, the bump risk corresponding to the outdoor position is determined by weighting and summing ship bump information, bad weather information, the outdoor position of the passenger, and the like. The corresponding relation between the ship bump information, bad weather information, the outdoor position of the passenger and the like and the bump risk can be preset. The weight values of the ship pitch information, the bad weather information, and the outdoor position of the passenger may also be preset.

In some embodiments of the present disclosure, determining the bump prediction corresponding to the outdoor location based on the severe weather information and the outdoor location of the passenger may effectively improve accuracy of predicting risk of outdoor activities, thereby better alerting the passenger.

Step 530, based on the outdoor activity risk, sending outdoor activity alert information to the outdoor activity passenger.

An outdoor active passenger may refer to a passenger located outdoors. The outdoor activity passengers corresponding to different time periods may be different. In some embodiments, the determination module 230 may determine the outdoor activity passenger via the passenger's current location information and/or historical outdoor activity records. The current location information of the passenger may be determined by the user terminal. For example, the determination module 230 may determine the passenger as an outdoor activity passenger when the frequency of the passenger being outdoors is greater than a preset threshold for a period of time corresponding to the risk of outdoor activity. The frequency at which the passenger is located outdoors can be represented by a frequency. For example, the number of times a passenger is located outdoors during the passenger's boarding of the watercraft. The preset threshold may refer to a minimum frequency (e.g., 3 times) at which a passenger preset in advance is outdoors. The frequency at which the passenger is located outdoors may be determined by historical outdoor activity records. For example, through historical outdoor activity records, the determination module 230 may determine a time period corresponding to a risk of outdoor activity, a number of historical outdoor activity records for which the passenger is located outdoors. The determination module 230 may determine the number of historical outdoor activity records corresponding to the passenger as the frequency with which the passenger is located outdoors for the time period corresponding to the risk of outdoor activity. For more details regarding historical outdoor activity records, see the relevant description of step 520.

The outdoor activity alert information may refer to alert information issued to an outdoor activity passenger for danger alerting thereof. For example, the content of the outdoor activity alert message may be "mr/ms, you good, you can be in a deck area next with a higher security risk due to bad weather, please make a guard or return to an indoor area.

In some embodiments, the determination module 230 may determine outdoor activity alert information based on outdoor activity risk. The outdoor activity risk may preset a correspondence with the outdoor activity alert information, and determine the outdoor activity alert information through the correspondence. After the outdoor activity alert information is determined, the outdoor activity alert information may be transmitted to the outdoor activity passenger by transmitting to the user terminal of the corresponding passenger, broadcasting in the outdoor area, or the like.

In some embodiments of the present description, by predicting the risk of an outdoor active passenger and sending an alert thereto, the likelihood of a passenger on board a ship encountering an unexpected risk may be greatly reduced. Furthermore, timely and efficient communication and organization management in the emergency process can be realized, timely and effective response can be made to various emergency situations of the ship, and the safety of the ship and passengers is ensured.

It should be noted that the above description of the flow is only for the purpose of illustration and description, and does not limit the application scope of the present specification. Various modifications and changes to the flow may be made by those skilled in the art under the guidance of this specification. However, such modifications and variations are still within the scope of the present description.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims

1. A method of vessel safety management, the method comprising:

acquiring severe weather information based on weather forecast information of a sea area through which a ship passes;

acquiring the outdoor position of the passenger in the ship;

based on the severe weather information and the outdoor position, predicting bump prediction corresponding to the outdoor position, and taking the bump prediction corresponding to the outdoor position as outdoor activity risk;

and sending outdoor activity alarm information to the passenger based on the outdoor activity risk.

2. The method of claim 1, wherein the acquiring the outdoor location of the passenger in the vessel comprises:

and determining the outdoor position through a clustering algorithm based on the historical outdoor activity record of the passenger.

3. The method of claim 2, wherein the determining the outdoor location by a clustering algorithm based on the historical outdoor activity record of the passenger comprises:

constructing a set of historical outdoor activity information vectors based on the historical outdoor activity records, the set of historical outdoor activity information vectors comprising a plurality of historical outdoor activity information vectors, wherein each historical outdoor activity information vector corresponds to one piece of historical outdoor activity information in the historical outdoor activity records;

clustering the plurality of historical outdoor activity information vectors through the clustering algorithm to determine a clustering center set;

determining distances between a plurality of cluster centers in the cluster center set and an outdoor activity risk vector; the outdoor activity risk vector is constructed based on information corresponding to the outdoor activity risk;

and determining the outdoor position based on the position corresponding to the clustering center with the smallest distance of the outdoor activity risk vector.

4. The method of claim 1, wherein the predicting a bump prediction corresponding to the outdoor location based on the severe weather information and the outdoor location comprises:

And processing the bad weather information, the ship risk and the ship information based on a ship bump prediction model, and determining the ship bump information during outdoor activities, wherein the ship bump prediction model is a machine learning model, and the ship risk is predicted based on ship state information.

5. A system for vessel safety management, the system comprising:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring bad weather information and acquiring the outdoor position of a passenger in a ship based on weather forecast information of a sea area where the ship passes;

the prediction module is used for predicting bump prediction corresponding to the outdoor position based on the severe weather information and the outdoor position, and taking the bump prediction corresponding to the outdoor position as an outdoor activity risk;

and the determining module is used for sending outdoor activity alarm information to the passengers based on the outdoor activity risk.

6. The system of claim 5, wherein the acquisition module is further to:

7. The method of claim 5, wherein the acquisition module is further to:

8. The method of claim 7, wherein the prediction module is further to:

9. An apparatus for vessel safety management, the apparatus comprising at least one processor and at least one memory;

the at least one memory is configured to store computer instructions;

the at least one processor is configured to execute at least some of the computer instructions to implement the method of any one of claims 1 to 4.

10. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the method of any one of claims 1 to 4.