An object early warning method, device, electronic equipment and storage medium

Abstract

The application discloses an object early warning method and device, electronic equipment and storage medium. The specific implementation scheme comprises the following steps: determining an object to be warned and early warning information corresponding to the object to be warned; determining a target group to which the object to be warned belongs based on a distributed data lake; and determining an early warning situation corresponding to the object to be warned according to the early warning information and the target group. The early warning information corresponding to the object to be warned and the distributed data lake are determined, early warning is realized through multi-dimensional data, the object to be warned is determined to belong to the target group, more refined early warning is realized, the misjudgment rate is reduced, the early warning situation corresponding to the object to be warned is determined according to the early warning information and the target group, early warning content is customized for the object to be warned, and the matching degree of the early warning content and the object to be warned is improved.

Description

Technical Field

[0001] This invention relates to the field of big data technology, and in particular to an object early warning method, device, electronic device, and storage medium. Background Technology

[0002] Currently, meteorological early warning systems in coastal areas primarily rely on independent monitoring and forecasting systems, characterized by single data sources or simple data overlay. These systems mainly include the following implementation paths: First, a single-monitor-driven approach: This involves collecting meteorological data such as temperature and wind speed through satellite remote sensing, offshore buoy stations, and coastal land observation stations. Based on weather forecasting models, combined with physical equations and historical data, the system predicts disaster development trends, generates early warnings, and then disseminates them to coastal areas via radio, television, and official platforms. Second, an administratively-based static group approach: This involves dividing the early warning area according to coastal administrative regions. Using an established static group database, a standardized format of early warning SMS messages or notifications is sent in batches to registered users within the warning area when a meteorological disaster is warned. Third, a manual-assisted reporting approach: This relies on grassroots personnel and offshore workers to report real-time weather and disaster conditions via telephone and instant messaging, combining macro-meteorological forecasts to refine the early warning content before dissemination.

[0003] However, most existing solutions rely solely on single meteorological data or simple overlays of communication data, resulting in limited data dimensions and difficulty in supporting refined early warning implementation. Furthermore, classifying early warning targets based on administrative divisions or static group databases fails to track the status of these targets in real time, leading to inaccurate warnings. Additionally, using standardized templates for mass dissemination of early warning information without tailoring content to the type of target (e.g., tourists, farmers, anglers) results in a low degree of matching between the warning information and the target's needs. Summary of the Invention

[0004] This invention provides an object early warning method, device, electronic device, and storage medium to achieve early warning through multi-dimensional data and improve the matching degree between early warning information and users.

[0005] According to one aspect of the present invention, an object early warning method is provided, comprising: Identify the target object to be warned and the warning information corresponding to the target object, wherein the warning information is related to the information of the environment in which the target object is located; Based on a distributed data lake, the target group to which the object to be warned belongs is determined. The target group corresponds to the target activity performed by the object to be warned. The distributed data lake includes data related to the activity of at least one object in the environment where the object to be warned is located. Based on the warning information and the target group, the warning situation corresponding to the target to be warned is determined. The warning situation is related to the type of the target activity. The warning situation includes warning content and warning channel. The warning channel includes a channel for sending the warning content to the target to be warned.

[0006] According to another aspect of the present invention, an object early warning device is provided, comprising: The first determining module is used to determine the object to be warned and the warning information corresponding to the object to be warned, wherein the warning information is related to the information of the environment where the object to be warned is located; The second determining module is used to determine the target group to which the object to be warned belongs based on a distributed data lake. The target group corresponds to the target activity performed by the object to be warned. The distributed data lake includes data related to the activities of at least one object in the environment where the object to be warned is located. The third determining module is used to determine the warning situation corresponding to the target object based on the warning information and the target group. The warning situation is related to the type of the target activity. The warning situation includes warning content and warning channel. The warning channel includes a channel for sending the warning content to the target object.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the object warning method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the object warning method according to any embodiment of the present invention.

[0009] The technical solution of this invention involves determining the object to be warned and the warning information corresponding to the object; determining the target group to which the object belongs based on a distributed data lake; and determining the warning status corresponding to the object based on the warning information and the target group. Determining the warning information and the distributed data lake enables warnings through multi-dimensional data. Identifying the target group to which the object belongs provides more granular warnings and reduces the false positive rate. Determining the warning status corresponding to the object based on the warning information and the target group allows for customized warning content, improving the matching degree between the warning content and the object.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of an object early warning method provided according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of a target group determination method provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of an object early warning device according to Embodiment 3 of the present invention; Figure 4 This is a block diagram of an electronic device provided according to Embodiment 4 of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] It is understood that before using the technical methods disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0016] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to autonomously choose whether to provide personal information to the software or hardware, such as the electronic device, application program, server, or storage medium performing the operations of this invention, based on the prompt message.

[0017] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0018] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0019] Example 1 Figure 1 This is a flowchart of an object early warning method according to Embodiment 1 of the present invention. This embodiment is applicable to situations where early warning is given for objects to be warned. The method can be executed by an object early warning device, which can be implemented in hardware and / or software. The object early warning device can be configured in an electronic device, such as a PC or a server. Figure 1 As shown, the method includes: S110. Determine the object to be warned and the warning information corresponding to the object to be warned.

[0020] The warning information is related to the information of the environment where the object to be warned is located.

[0021] In this embodiment, the object to be warned can be understood as the object to be warned, which can be an object active in a coastal area, and the environment in which the object is located can be a coastal area. The warning information can be understood as information about the environment in which the object is located, and the warning information can include existing meteorological warning levels, wind speed, population density, tidal current speed, etc. in the environment in which the object is located.

[0022] Specifically, for entities subject to early warning operating in coastal areas, early warnings need to be issued based on their surrounding environment to ensure their safety during operations. Information about the environment in which the entity is located can be obtained as early warning information.

[0023] For example, the early warning information may include the weather warning level, wind force level, population density, and tidal current speed. L is the weather warning level (1-4), which can be the information that has been issued; W is the wind force level, Wmax is the maximum wind force (default is level 12); D is the population density, Dmax is the maximum carrying capacity of the area; V is the tidal current speed, Vmax is the upper limit of extreme tidal currents along the coast (default is 5m / s).

[0024] S120. Based on the distributed data lake, determine the target group to which the object to be warned belongs.

[0025] The target group corresponds to the target activity performed by the object to be warned, and the distributed data lake includes data related to the activities of at least one object in the environment where the object to be warned is located.

[0026] In this embodiment, a distributed data lake can be understood as a collection of data on the activities of at least one object in the environment where the object to be warned resides. The data in the distributed data lake may include data related to the communication, weather, and activity types of objects in the environment where the object to be warned resides. A target group can be understood as the group to which the object to be warned belongs, where objects in the target group perform the same activities as the object to be warned. The target group can be one of aquaculture, tourism, or fishing groups. A target activity can be understood as the activity performed by objects in the target group to which the object to be warned belongs. The target activity can be one of aquaculture, tourism, or fishing activities.

[0027] Specifically, the system identifies multi-source data, including communication data, meteorological data, and type data, generated during the activities of at least one object in the environment containing the target of the early warning. Communication data includes data generated during communication activities of at least one object; meteorological data is related to the state of the environment in which each object resides; and type data includes type information corresponding to the activities performed by each object. The collected communication, meteorological, and type data are then stored in a data lake to construct a distributed data lake. Next, features corresponding to the target of the early warning are extracted from the distributed data lake, and based on these features, the target group to which the target of the early warning belongs is determined. This target group indicates the type of target activity performed by the target of the early warning.

[0028] S130. Based on the warning information and the target group, determine the warning situation corresponding to the object to be warned.

[0029] The warning situation is related to the type of the target activity. The warning situation includes warning content and warning channel. The warning channel includes a channel for sending the warning content to the target to be warned.

[0030] In this embodiment, the warning situation can be understood as the warning content formulated for the object to be warned, and the warning channel through which the warning content is sent to the object to be warned. The warning situation may be content related to the type of target activity performed by the object to be warned. The warning content may include warning content formulated for the object to be warned, and may include information such as the risk level of the environment in which the object to be warned is located, and risk avoidance plans. The warning channel may include one or more of the following: message, video message, or SMS message.

[0031] Specifically, based on the target group to which the entity to be warned belongs, the target activities being warned can be determined. Different warning content can then be specified for different types of target activities. Based on the warning information, the warning level of the entity to be warned can be determined, which can include high-risk, medium-risk, and low-risk levels. Different warning content and different warning channels can be specified for different warning levels. Among these, the warning information for the high-risk level is the most detailed.

[0032] For example, different warning content can be specified for the target group to which the target object belongs. If the target object belongs to an aquaculture group, the warning content could include information related to aquaculture activities, such as the window period for cage reinforcement; if the target object belongs to a tourism group, the warning content could include information related to tourism activities, such as evacuation routes; if the target object belongs to a fishing group, the warning content could include information related to fishing activities, such as evacuation locations.

[0033] The technical solution of this invention involves determining the object to be warned and the warning information corresponding to the object; determining the target group to which the object belongs based on a distributed data lake; and determining the warning status corresponding to the object based on the warning information and the target group. Determining the warning information and the distributed data lake enables warnings through multi-dimensional data. Identifying the target group to which the object belongs provides more granular warnings and reduces the false positive rate. Determining the warning status corresponding to the object based on the warning information and the target group allows for customized warning content, improving the matching degree between the warning content and the object.

[0034] Based on the above embodiments, modified embodiments of the above embodiments are proposed. It should be noted that, in order to keep the description brief, only the differences from the above embodiments are described in the modified embodiments.

[0035] In one embodiment, determining the warning status corresponding to the target object based on the warning information and the target group includes: The warning information is quantified to obtain the warning index corresponding to the object to be warned, and the warning index is used to indicate the warning level of the environment where the object to be warned is located; Based on the target group to which the object to be warned belongs, an information threshold corresponding to the target warning information in the warning information is set. The information threshold includes a first information threshold, a second information threshold, and a third information threshold. The target warning information is related to the type of target activity corresponding to the target group. The value of the first information threshold is greater than the value of the second information threshold, and the value of the second information threshold is greater than the value of the third information threshold. Based on the warning index, the target warning information, and the information threshold, the warning situation corresponding to the object to be warned is determined.

[0036] In this embodiment, the early warning index can indicate the early warning level of the environment where the object to be warned is located. The early warning index can be a quantitative information of the environment where the object to be warned is located, and the early warning level can include high-risk level, medium-risk level, and low-risk level. Target early warning information can be understood as early warning information related to the target group to which the object to be warned belongs. Information threshold can be understood as a threshold set for the target early warning information. The information threshold can include a first information threshold, a second information threshold, and a third information threshold, which are used to determine the early warning status of the object to be warned.

[0037] Specifically, each warning message is quantified to obtain the warning index corresponding to the target object, thus determining the warning level to which the target object belongs. Based on the target group to which the target object belongs, the target warning information is determined. For example, if the target group is aquaculture, the target warning information is wind force; if the target group is tourism, the target warning information is crowd density; and if the target group is fishing, the target warning information is tidal current speed. Next, multiple information thresholds are set for the target warning information, including a first information threshold, a second information threshold, and a third information threshold. By combining the warning index with the first, second, and third information thresholds, it can be determined whether the target object has triggered the corresponding warning level. If the warning level has been triggered, a warning condition is specified for the target object.

[0038] For example, the early warning index is Where L is the weather warning level (1-4), W is the wind force level, Wmax is the maximum wind force (default is level 12), D is the population density, Dmax is the maximum carrying capacity of the area, V is the tidal current velocity, Vmax is the upper limit of extreme tidal currents along the coast (default is 5m / s).

[0039] Based on the target group to which the object to be warned belongs, information thresholds are set for the target warning information. If the target group is an aquaculture group, the target warning information is wind force level, with the first information threshold set to 10, the second information threshold set to 8, and the third information threshold set to 6; if the target group is a tourist group, the target warning information is crowd density, with the first information threshold set to 80, the second information threshold set to 50, and the third information threshold set to 30; if the target group is a fishing group, the target warning information is tidal current speed, with the first information threshold set to 3, the second information threshold set to 2, and the third information threshold set to 1.5.

[0040] Optionally, determining the warning status corresponding to the object to be warned based on the warning index, the target warning information, and the information threshold includes: When the warning index is greater than the first warning threshold and the target warning information is greater than the first information threshold, the warning situation corresponding to the object to be warned is determined as the first warning situation; If the warning index is less than the first warning threshold and greater than the second warning threshold, and the target warning information is greater than the second information threshold, then the warning situation corresponding to the object to be warned is determined to be the second warning situation. If the warning index is less than the second warning threshold and greater than the third warning threshold, and the target warning information is greater than the third information threshold, then the warning situation corresponding to the object to be warned is determined to be the third warning situation. Wherein, the value of the first warning threshold is greater than the value of the second warning threshold, the value of the second warning threshold is greater than the value of the third warning threshold, the number of warning channels and the number of warning contents indicated by the first warning situation are greater than the number of warning channels and the number of warning contents indicated by the second warning situation are greater than the number of warning channels and the number of warning contents indicated by the second warning situation are greater than the number of warning channels and the number of warning contents indicated by the third warning situation.

[0041] In this embodiment, the first warning threshold, the second warning threshold, and the third warning threshold are all warning thresholds set for the warning index. These thresholds are used to determine the warning level of the object to be warned. The value of the first warning threshold is greater than the value of the second warning threshold, and the value of the second warning threshold is greater than the value of the third warning threshold. The first warning situation can be understood as the warning situation when a high-risk level is triggered, the second warning situation can be understood as the warning situation when a medium-risk level is triggered, and the third warning situation can be understood as the warning situation when a low-risk level is triggered.

[0042] For example, based on the early warning index (Value range 0-1), the first warning threshold is set to 0.8, the second warning threshold is set to 0.6, and the third warning threshold is set to 0.5, dividing the warning levels into three levels: High-risk level: This corresponds to a red / orange weather warning, accompanied by extreme winds (≥10 on the Beaufort scale) or strong tides (current speed ≥3m / s); medium risk level: This corresponds to a yellow weather warning, with winds of force 8-10 or tidal currents of 2-3 m / s; low risk level: This corresponds to a blue weather warning, with wind force of 6-8 or tidal current speed of 1.5-2 m / s. Table 1 is a warning level triggering condition table provided according to Embodiment 1 of the present invention.

[0043] Table 1. Warning Level Triggering Conditions As shown in Table 1, if the target group is a livestock farming group, then when the warning index is greater than 0.8 and the wind force is greater than 10, the target group is determined to trigger a high-risk level, and the warning situation is the first warning situation. When the warning index is greater than 0.6 and less than 0.8, and the wind force is greater than 8, the target group is determined to trigger a medium-risk level, and the warning situation is the second warning situation. When the warning index is greater than 0.5 and less than 0.6, and the wind force is greater than 6, the target group is determined to trigger a low-risk level, and the warning situation is the third warning situation. If the target group is a tourist group, then when the warning index is greater than 0.8 and the population density is greater than 80, the target group is determined to trigger a high-risk level, and the warning situation is the first warning situation. When the warning index is greater than 0.6 and less than 0.8, and the population density is greater than 80, the target group is determined to trigger a high-risk level, and the warning situation is the first warning situation. When the warning index is greater than 50, the target group is determined to be at medium risk, and the warning situation is the second warning situation. When the warning index is greater than 0.5 and less than 0.6, and the crowd density is greater than 30, the target group is determined to be at low risk, and the warning situation is the third warning situation. If the target group is a fishing group, when the warning index is greater than 0.8 and the tidal current speed is greater than 3, the target group is determined to be at high risk, and the warning situation is the first warning situation. When the warning index is greater than 0.6 and less than 0.8, and the tidal current speed is greater than 2, the target group is determined to be at medium risk, and the warning situation is the second warning situation. When the warning index is greater than 0.5 and less than 0.6, and the tidal current speed is greater than 1.5, the target group is determined to be at low risk, and the warning situation is the third warning situation.

[0044] When the warning status of the target object is the first warning status, the warning channels can include a triple approach of "message + video + SMS", with the following weight allocation for the three warning channels: (Message, including real-time tide animation and evacuation route map) (Visual demonstration of risk avoidance steps) (SMS). The warning content includes risk level, threat parameters, evacuation plan, time reminder, etc. For example: Aquaculture group: "[High Risk Warning] Current wind force n, tidal current speed x in area A, cage reinforcement window y minutes, immediately go to area B for shelter, contact fishing port dispatch: xxx"; Tourist group: "[High Risk Warning] Real-time population flow n people / square kilometer in area A, gale force y + tide z will occur within x minutes, immediately evacuate from entrance C, evacuation route: xxx"; Angler group: "[High Risk Warning] Tidal current speed n, wind force x at fishing spot A, current area overlaps with dangerous tide period y, please evacuate to the nearest safe harbor within q minutes, maritime rescue: xxx".

[0045] When the warning status of the target object is the second warning status, the warning channels can include a dual approach of "message + SMS". The weight allocation of the two warning channels is as follows: (Message, including static tide charts and prevention guidelines) (SMS, core information). The warning content includes risk alerts, prevention suggestions, and warning timeliness. For example: Aquaculture group: "[Medium Risk Warning] Area A has wind force n and tidal current speed x. It is recommended to reinforce the net cages within y hours and closely monitor subsequent tidal updates"; Tourist group: "[Medium Risk Warning] Area A currently has a population flow of n people / square kilometer. In the next x hours, there will be y-level wind + z-tidal current. It is recommended to adjust the itinerary to inland attractions. For scenic spot inquiries: xxx"; Angler group: "[Medium Risk Warning] Fishing spot A has wind force n and tidal current speed x. The risk rating of the fishing spot is x stars. It is recommended to suspend fishing or move to a sheltered fishing spot."

[0046] When the warning status of the target group is the third level, the warning channel is a single SMS message. The warning content includes a concise risk warning and basic prevention suggestions. For example: Aquaculture group: "[Low Risk Warning] Area A: Wind force n, tidal current speed x. Take precautions against wind during daily operations and pay attention to today's tide update"; Tourist group: "[Low Risk Warning] Area A: Wind force n, tidal current speed x. The coastal walkway is open as usual. It is recommended to bring windproof equipment"; Angler group: "[Low Risk Warning] Fishing spot A: Wind force n, tidal current speed x. The risk rating of the fishing spot is x stars. Pay attention to safety during low tide."

[0047] Furthermore, the weighting of each early warning channel can be optimized based on real-time feedback data. ,in, The actual readership of warning channel c. The average read rate is used. When the read rate of a certain early warning channel is consistently below 30% of the average, its weight is automatically reduced and the resource allocation to alternative early warning channels is increased.

[0048] In one embodiment, the method for determining the distributed data lake includes: Identify a target group for early warning, wherein the target group consists of at least one object in the environment where the target object is located; Collect raw data corresponding to the group to be warned. The raw data includes communication data, meteorological data and type data corresponding to the group to be warned. The communication data includes data generated by the group to be warned when communicating. The meteorological data is related to the state of the environment in which the group to be warned is located. The type data includes information corresponding to the activities performed by at least one object in the group to be warned. The original data is preprocessed to obtain preprocessed data, which includes preprocessed communication data, preprocessed meteorological data, and preprocessed type data. Based on the preprocessed data, a distributed data lake corresponding to the group to be warned is constructed.

[0049] In this embodiment, the target group for early warning can be understood as a group consisting of at least one object in the environment where the target object is located. This target group may include aquaculture groups, tourism groups, or fishing groups. Raw data can be understood as data collected when objects in the target group perform activities. Raw data may include communication data, meteorological data, and type data. Communication data can be data generated by communication within the target group, and may include location data and communication characteristics of each object in the group. Meteorological data is related to the state of the environment where each object in the target group is located. Meteorological data can be obtained from an emergency warning platform and may include fields such as the affected area, warning level, and effective time. Type data includes type information corresponding to the activities performed by each object in the target group, such as data related to aquaculture, tourism, or fishing activities. Preprocessed data can be understood as data obtained after preprocessing the raw data. It can be preprocessed communication data, preprocessed meteorological data, and preprocessed type data obtained by preprocessing the communication data, meteorological data, and type data respectively.

[0050] Specifically, a target group for early warning is identified, consisting of at least one object within the environment of the target target, and the corresponding raw data is collected. This raw data includes communication data, meteorological data, and type data. Object location data (including base station location, latitude and longitude, etc.) with a set grid precision can be collected via interactive signaling at a frequency of "real-time streaming + batch update," simultaneously extracting object communication characteristics (including call frequency, data usage, SMS sending volume, etc.). The object location data and object communication characteristics are then used as communication data. Meteorological data can be obtained from the emergency warning platform. This meteorological data can include disaster data, containing fields such as affected area, warning level, and effective time (e.g., typhoon path, wind force level, tidal current velocity, storm surge prediction, etc.). The timestamps of the meteorological data are aligned with the timestamps of the communication data. Industry data can be obtained by acquiring aquaculture area coordinates, software usage records, and tourism platform logs. The communication data, meteorological data, and type data contained in the raw data are preprocessed to obtain preprocessed data, including preprocessed communication data, preprocessed meteorological data, and preprocessed type data. Preprocessed communication data, preprocessed meteorological data, and preprocessed type data are stored in a data lake to build a distributed data lake corresponding to the groups requiring early warning. Optionally, the step of preprocessing the original data to obtain preprocessed data includes: Filter out abnormal signaling in the communication data contained in the original data to obtain preprocessed communication data. The abnormal signaling includes communication data that exceeds a preset range in the communication data. The meteorological data contained in the original data are aligned to obtain preprocessed meteorological data; The type data contained in the original data is tagged to obtain preprocessed type data; The preprocessed communication data, the preprocessed meteorological data, and the preprocessed type data are identified as preprocessed data.

[0051] In this embodiment, abnormal signaling can be understood as communication data that exceeds a preset range, and abnormal signaling can be noise data.

[0052] For example, abnormal signaling filtering is performed on communication data using... The principle is to remove abnormal signaling exceeding a preset range (e.g., removing data with location drift > 5 km or dwell time < 5 minutes) to obtain preprocessed communication data. Let the communication data be... ( (where the location coordinates are for the i-th signaling message), the samples are filtered using the following formula: Calculate the sample mean. Calculate the sample standard deviation , retain satisfaction The data is used as preprocessed communication data. The meteorological data is aligned to obtain preprocessed meteorological data, and the coordinate system of the meteorological data is converted to be consistent with the coordinate system of the communication base station. Let the original coordinates of the meteorological data be... The coordinates of the communication base station are Coordinate unification is achieved through a linear transformation formula, the formula is as follows: ,in, , This is the coordinate scaling factor (calculated from the deviation between the meteorological data coordinate system and the communication base station coordinate system). , This represents the coordinate offset. The type data is labeled to obtain preprocessed type data, generating a four-dimensional feature vector of "object ID + time + location + meteorological element".

[0053] Example 2 Figure 2 This is a flowchart of a target group determination method according to Embodiment 2 of the present invention. This embodiment focuses on the target group determination method described in the above embodiment. Figure 2 As shown, the method includes: S210. Determine the object to be warned and the warning information corresponding to the object to be warned.

[0054] S220. Determine at least one candidate group contained in the environment where the object to be warned is located.

[0055] The objects in the candidate group perform the same type of activity.

[0056] In this embodiment, the candidate group can be understood as the group to which the object to be warned may belong. The candidate group may include aquaculture groups, tourist groups, or fishing groups.

[0057] Specifically, a target warning group is identified, consisting of at least one object in the environment where the target object resides. This target warning group includes at least one candidate group, where objects in each candidate group perform the same type of activity. For example, objects in an aquaculture group all perform aquaculture activities, objects in a tourism group all perform tourism activities, and objects in a fishing group all perform fishing activities.

[0058] S230. For each candidate group, determine the candidate feature identifier corresponding to the candidate group, and determine the belonging probability corresponding to the candidate group based on the candidate feature identifier and the distributed data lake.

[0059] The attribution probability includes the probability that the target group to which the object to be warned belongs is the candidate group.

[0060] In this embodiment, candidate feature identifiers can indicate the features corresponding to candidate groups, and different candidate groups have different features. The attribution probability indicates the probability that the target group to which the object to be warned belongs is a candidate group. The attribution probability can be calculated by extracting the feature data corresponding to the candidate feature identifiers from the distributed data lake.

[0061] Specifically, for each candidate group, candidate feature identifiers are determined. For aquaculture groups, candidate feature identifiers may include: dwell time at base stations in the aquaculture area, frequency of use of sports apps, correlation with aquaculture license identifiers, concentration during work periods, and the number of base stations surrounding the aquaculture area. For tourists, candidate feature identifiers may include: cumulative dwell time at scenic area base stations, frequency of visits to scenic area base stations, proportion of non-local phone numbers, frequency of use of social media apps, and visit coefficient during holidays. For anglers, candidate feature identifiers may include: dwell time during specific periods, frequency of visits to the same base station, duration of signal interruption during a single fishing trip, historical fishing spot matching degree, and frequency P of use of fishing apps. Based on each candidate feature identifier, feature data is extracted from the distributed data lake, and the probability of a candidate group belonging to the target group is calculated.

[0062] Optionally, determining the affiliation probability of the candidate group based on the candidate feature identifier and the distributed data lake includes: Extract the differential features corresponding to the objects to be warned in the distributed data lake, and determine the target differential features indicated by the candidate feature identifiers among the differential features; Construct candidate feature vectors corresponding to the target differentiated features; Based on the candidate feature vectors, the belonging probability corresponding to the candidate group is calculated.

[0063] In this embodiment, differentiated features can be understood as the features corresponding to the objects to be warned in the distributed data lake, such as communication data, meteorological data, and type data of the objects to be warned when performing target activities. Target differentiated features can be understood as features selected from differentiated features according to candidate feature identifiers. Candidate feature vectors can be understood as vectors corresponding to target differentiated features, and candidate feature vectors can be used to quantify target differentiated features.

[0064] For example, the differential features corresponding to the objects to be warned in the distributed data lake are extracted. Assuming the candidate group is a livestock farming group, the extracted target differential features include: base station dwell time T in the farming area (unit: hours / day, average over the past 7 days), number of times sports apps are used C (unit: times / day, excluding exercise users), correlation degree R of farming license identification (0-1 normalized, 1 indicates a perfect match with the registration information of the farming group), concentration of work hours D (0-1 normalized, 1 indicates a dwell time ≥90% between 5-20 AM daily), and number of base stations around the farming area S (units / day, low handover rate indicates stable operation). A candidate feature vector is formed. A random forest model with 100 decision trees is used, where the classification function of a single tree is... (Output 1 = farmed population, 0 = non-farmed population). Output the probability of attribution. ,in Let be the weight of the t-th tree (determined by the tree's classification accuracy). ), This is an indicator function.

[0065] Assuming the candidate group is a tourist group, the extracted target differentiated features include: cumulative dwell time S (hours, total of the past 3 days) at scenic area base stations, frequency of visits to scenic area base stations D (times / day), proportion of non-local phone numbers L (0-1 normalized, 1 indicates the location is not a coastal city), frequency of social media usage A (unit: times / day), and holiday visit coefficient H (weekend / public holiday visits are recorded as 1, weekday visits as 0.3). This forms the candidate feature vector. A random forest model with 80 decision trees is used, and the classification function of a single tree is: (Output 1 = tourist group, 0 = non-tourist group), output the probability of belonging. .

[0066] Assuming the candidate group is a fishing group, the extracted target differential features include: dwell time S (hours, 4-9 am and 4-12 am), access frequency D (times / 180 days) to the same base station, single out-of-sea signaling loss duration T (hours, signaling loss / recovery location within 200 meters of the coastline), historical fishing point matching degree K (0-1 normalized, probability of overlap with known fishing point base stations), and usage frequency P (times / day) of fishing-related software. This forms the candidate feature vector. A random forest model with 90 decision trees is used, and the classification function of a single tree is: (Output 1 = fishing group, 0 = non-fishing group), output the probability of belonging. .

[0067] S240. If the probability of belonging is greater than a set probability threshold, the candidate group is determined as the target group to which the object to be warned belongs.

[0068] In this embodiment, the set probability threshold can be understood as a threshold set for each candidate group, which can be used to determine whether the target group is a candidate group.

[0069] For example, assuming the candidate population is a farming population, then when The target group to which the warning target belongs is determined to be a livestock farming group. Assuming the candidate group is a livestock farming group, then when... The target group to which the warning target belongs is determined to be a tourist group. Assuming the candidate group is a livestock farming group, then when... The target group to which the warning target belongs is determined to be a fishing group.

[0070] S250. Based on the warning information and the target group, determine the warning situation corresponding to the object to be warned.

[0071] For example, assuming a typhoon yellow warning scenario (wind force 8-10, tidal current speed 2.2-2.5 m / s), determine the warning status for the objects to be warned in this scenario: (1) Distributed data lake Communication data: 5km grid signaling (collection cycle 30 minutes / time); Meteorological data: minute-level data (wind speed every 10 minutes, tide speed every 30 minutes); Industry data: Coordinates of 23 aquaculture areas, real-time visitor flow in scenic areas, and usage records of fishing software.

[0072] (2) Data processing Abnormal signaling filtering: in principle( , , , After removing noise, the data accuracy rate is 98%. Coordinate system alignment: The coordinate system of meteorological data is converted to the WGS84 coordinate system of the communication base station. , ), with a correlation error of <80 meters; Tagging process: Generate a four-dimensional feature vector consisting of "object ID + time + location + meteorological element", outputting a total of 92,000 valid vectors.

[0073] (3) Candidate Group Farming population: Feature vector , 280 people were identified; Tourist groups: Feature vector , 6200 people were identified; Fishing Groups: Feature Vectors , 950 people were identified.

[0074] (4) Early warning situation Early warning index calculation: (Medium risk), matched with "message + SMS" dual early warning channels; Customized outreach: Differentiated warning content including wind force, tide, and evacuation plans was pushed to three groups, and all 9,340 people received the warning (time < 5 minutes). Weight optimization: Message read rate 85%, SMS read rate 60%, based on... Adjusting weights (5G) ,Short message ).

[0075] The technical solution of this invention involves determining at least one candidate group within the environment of the object to be warned; for each candidate group, determining a candidate feature identifier corresponding to the candidate group, and determining the belonging probability of the candidate group based on the candidate feature identifier and a distributed data lake; if the belonging probability is greater than a set probability threshold, the candidate group is determined as the target group to which the object to be warned belongs. By determining at least one candidate group within the environment of the object to be warned, a refined candidate group segmentation is achieved, thereby determining the target group to which the object to be warned belongs, resulting in more refined warnings and a reduced false positive rate.

[0076] Example 3 Figure 3 This is a schematic diagram of the structure of an object early warning device according to Embodiment 3 of the present invention. Figure 3 As shown, the device includes: The first determining module 310 is used to determine the object to be warned and the warning information corresponding to the object to be warned, wherein the warning information is related to the information of the environment where the object to be warned is located; The second determining module 320 is used to determine the target group to which the object to be warned belongs based on a distributed data lake. The target group corresponds to the target activity performed by the object to be warned. The distributed data lake includes data related to the activities of at least one object in the environment where the object to be warned is located. The third determining module 330 is used to determine the warning situation corresponding to the target object based on the warning information and the target group. The warning situation is related to the type of the target activity. The warning situation includes warning content and warning channel. The warning channel includes a channel for sending the warning content to the target object.

[0077] The object early warning device provided in this embodiment of the invention determines the object to be warned and the corresponding early warning information through a first determining module; determines the target group to which the object to be warned belongs through a second determining module based on a distributed data lake; and determines the early warning status corresponding to the object to be warned through a third determining module based on the early warning information and the target group. Through the cooperation of these modules, the early warning information and the distributed data lake corresponding to the object to be warned are determined, enabling early warning through multi-dimensional data. Determining the target group to which the object to be warned belongs provides more granular early warning and reduces the false positive rate. Determining the early warning status corresponding to the object to be warned based on the early warning information and the target group allows for customized early warning content, improving the matching degree between the early warning content and the object to be warned.

[0078] In one embodiment, the second determining module 320 includes: The first determining unit is used to determine at least one candidate group contained in the environment where the object to be warned is located, wherein objects in the candidate group perform the same type of activity; The second determining unit is used to determine the candidate feature identifier corresponding to each candidate group, and to determine the belonging probability corresponding to the candidate group based on the candidate feature identifier and the distributed data lake. The belonging probability includes the probability that the target group to which the object to be warned belongs is the candidate group. The third determining unit is used to determine the candidate group as the target group to which the object to be warned belongs when the attribution probability is greater than a set probability threshold.

[0079] In one embodiment, the second determining unit is specifically used for: Extract the differential features corresponding to the objects to be warned in the distributed data lake, and determine the target differential features indicated by the candidate feature identifiers among the differential features; Construct candidate feature vectors corresponding to the target differentiated features; Based on the candidate feature vectors, the belonging probability corresponding to the candidate group is calculated.

[0080] In one embodiment, the third determining module 330 includes: A quantization unit is used to quantify the warning information to obtain the warning index corresponding to the object to be warned, and the warning index is used to indicate the warning level of the environment where the object to be warned is located; A setting unit is configured to set an information threshold corresponding to the target warning information in the warning information based on the target group to which the object to be warned belongs. The information threshold includes a first information threshold, a second information threshold, and a third information threshold. The target warning information is related to the type of target activity corresponding to the target group. The value of the first information threshold is greater than the value of the second information threshold, and the value of the second information threshold is greater than the value of the third information threshold. The fourth determining unit is used to determine the warning situation corresponding to the object to be warned based on the warning index, the target warning information and the information threshold.

[0081] In one embodiment, the fourth determining unit is specifically used for: When the warning index is greater than the first warning threshold and the target warning information is greater than the first information threshold, the warning situation corresponding to the object to be warned is determined as the first warning situation; If the warning index is less than the first warning threshold and greater than the second warning threshold, and the target warning information is greater than the second information threshold, then the warning situation corresponding to the object to be warned is determined to be the second warning situation. If the warning index is less than the second warning threshold and greater than the third warning threshold, and the target warning information is greater than the third information threshold, then the warning situation corresponding to the object to be warned is determined to be the third warning situation. Wherein, the value of the first warning threshold is greater than the value of the second warning threshold, the value of the second warning threshold is greater than the value of the third warning threshold, the number of warning channels and the number of warning contents indicated by the first warning situation are greater than the number of warning channels and the number of warning contents indicated by the second warning situation are greater than the number of warning channels and the number of warning contents indicated by the second warning situation are greater than the number of warning channels and the number of warning contents indicated by the third warning situation.

[0082] In one embodiment, the second determining module 320 includes: The fifth determining unit is used to determine the group to be warned, wherein the group to be warned consists of at least one object in the environment where the object to be warned is located; The data acquisition unit is used to acquire the raw data corresponding to the group to be warned. The raw data includes communication data, meteorological data and type data corresponding to the group to be warned. The communication data includes data generated by the group to be warned when communicating. The meteorological data is related to the state of the environment in which the group to be warned is located. The type data includes information corresponding to the activities performed by at least one object in the group to be warned. The preprocessing unit is used to preprocess the raw data to obtain preprocessed data, which includes preprocessed communication data, preprocessed meteorological data, and preprocessed type data. The building unit is used to build a distributed data lake corresponding to the group to be warned based on the preprocessed data.

[0083] In one embodiment, the preprocessing unit is specifically used for: Filter out abnormal signaling in the communication data contained in the original data to obtain preprocessed communication data. The abnormal signaling includes communication data that exceeds a preset range in the communication data. The meteorological data contained in the original data are aligned to obtain preprocessed meteorological data; The type data contained in the original data is tagged to obtain preprocessed type data; The preprocessed communication data, the preprocessed meteorological data, and the preprocessed type data are identified as preprocessed data.

[0084] The object warning device provided in this embodiment of the invention can execute the object warning method provided in any embodiment of the invention. Through the cooperation and coordination between the modules, the object warning is completed, and it has the corresponding functional modules and beneficial effects of the execution method.

[0085] Example 4 According to embodiments of the present invention, the present invention also provides an electronic device and a computer-readable storage medium.

[0086] Figure 4This is a block diagram of an electronic device according to Embodiment 4 of the present invention, which implements the object warning method described in the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0087] like Figure 4 As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0088] Multiple components in the electronic device are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, optical disk, etc.; and a communication unit 419, such as a network card, modem, wireless transceiver, etc. The communication unit 419 allows the electronic device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0089] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as object warning methods.

[0090] In some embodiments, the object warning method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the object warning method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the object warning method by any other suitable means (e.g., by means of firmware).

[0091] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0092] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0093] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0094] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0095] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0096] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0097] The technical solution of this invention provides an object early warning method, device, electronic device, and storage medium. It involves determining the object to be warned and the corresponding early warning information; determining the target group to which the object belongs based on a distributed data lake; and determining the early warning status corresponding to the object based on the early warning information and the target group. Determining the early warning information and the distributed data lake enables early warning through multi-dimensional data; determining the target group to which the object belongs provides more granular early warning and reduces the false positive rate; and determining the early warning status corresponding to the object based on the early warning information and the target group allows for customized early warning content, improving the matching degree between the early warning content and the object.

[0098] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0099] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An object early warning method, characterized in that, include: Identify the target object to be warned and the warning information corresponding to the target object, wherein the warning information is related to the information of the environment in which the target object is located; Based on a distributed data lake, the target group to which the object to be warned belongs is determined. The target group corresponds to the target activity performed by the object to be warned. The distributed data lake includes data related to the activity of at least one object in the environment where the object to be warned is located. Based on the warning information and the target group, the warning situation corresponding to the target to be warned is determined. The warning situation is related to the type of the target activity. The warning situation includes warning content and warning channel. The warning channel includes a channel for sending the warning content to the target to be warned.

2. The method according to claim 1, characterized in that, The process of determining the target group to which the object to be warned belongs, based on a distributed data lake, includes: Identify at least one candidate group contained in the environment where the object to be warned is located, wherein objects in the candidate group perform the same type of activity; For each candidate group, a candidate feature identifier corresponding to the candidate group is determined, and based on the candidate feature identifier and the distributed data lake, the belonging probability corresponding to the candidate group is determined. The belonging probability includes the probability that the target group to which the object to be warned belongs is the candidate group. If the probability of belonging is greater than a set probability threshold, the candidate group is determined as the target group to which the object to be warned belongs.

3. The method according to claim 2, characterized in that, The step of determining the affiliation probability of the candidate group based on the candidate feature identifiers and the distributed data lake includes: Extract the differential features corresponding to the objects to be warned in the distributed data lake, and determine the target differential features indicated by the candidate feature identifiers among the differential features; Construct candidate feature vectors corresponding to the target differentiated features; Based on the candidate feature vectors, the belonging probability corresponding to the candidate group is calculated.

4. The method according to claim 1, characterized in that, The step of determining the warning status corresponding to the target object based on the warning information and the target group includes: The warning information is quantified to obtain the warning index corresponding to the object to be warned, and the warning index is used to indicate the warning level of the environment where the object to be warned is located; Based on the target group to which the object to be warned belongs, an information threshold corresponding to the target warning information in the warning information is set. The information threshold includes a first information threshold, a second information threshold, and a third information threshold. The target warning information is related to the type of target activity corresponding to the target group. The value of the first information threshold is greater than the value of the second information threshold, and the value of the second information threshold is greater than the value of the third information threshold. Based on the warning index, the target warning information, and the information threshold, the warning situation corresponding to the object to be warned is determined.

5. The method according to claim 4, characterized in that, The step of determining the warning status corresponding to the object to be warned based on the warning index, the target warning information, and the information threshold includes: When the warning index is greater than the first warning threshold and the target warning information is greater than the first information threshold, the warning situation corresponding to the object to be warned is determined as the first warning situation; If the warning index is less than the first warning threshold and greater than the second warning threshold, and the target warning information is greater than the second information threshold, then the warning situation corresponding to the object to be warned is determined to be the second warning situation. If the warning index is less than the second warning threshold and greater than the third warning threshold, and the target warning information is greater than the third information threshold, then the warning situation corresponding to the object to be warned is determined to be the third warning situation. Wherein, the value of the first warning threshold is greater than the value of the second warning threshold, the value of the second warning threshold is greater than the value of the third warning threshold, the number of warning channels and the number of warning contents indicated by the first warning situation are greater than the number of warning channels and the number of warning contents indicated by the second warning situation are greater than the number of warning channels and the number of warning contents indicated by the second warning situation are greater than the number of warning channels and the number of warning contents indicated by the third warning situation.

6. The method according to claim 1, characterized in that, The method for determining the distributed data lake includes: Identify a target group for early warning, wherein the target group consists of at least one object in the environment where the target object is located; Collect raw data corresponding to the group to be warned. The raw data includes communication data, meteorological data and type data corresponding to the group to be warned. The communication data includes data generated by the group to be warned when communicating. The meteorological data is related to the state of the environment in which the group to be warned is located. The type data includes information corresponding to the activities performed by at least one object in the group to be warned. The original data is preprocessed to obtain preprocessed data, which includes preprocessed communication data, preprocessed meteorological data, and preprocessed type data. Based on the preprocessed data, a distributed data lake corresponding to the group to be warned is constructed.

7. The method according to claim 6, characterized in that, The process of preprocessing the original data to obtain preprocessed data includes: Filter out abnormal signaling in the communication data contained in the original data to obtain preprocessed communication data. The abnormal signaling includes communication data that exceeds a preset range in the communication data. The meteorological data contained in the original data are aligned to obtain preprocessed meteorological data; The type data contained in the original data is tagged to obtain preprocessed type data; The preprocessed communication data, the preprocessed meteorological data, and the preprocessed type data are identified as preprocessed data.

8. An object early warning device, characterized in that, include: The first determining module is used to determine the object to be warned and the warning information corresponding to the object to be warned, wherein the warning information is related to the information of the environment where the object to be warned is located; The second determining module is used to determine the target group to which the object to be warned belongs based on a distributed data lake. The target group corresponds to the target activity performed by the object to be warned. The distributed data lake includes data related to the activities of at least one object in the environment where the object to be warned is located. The third determining module is used to determine the warning situation corresponding to the target object based on the warning information and the target group. The warning situation is related to the type of the target activity. The warning situation includes warning content and warning channel. The warning channel includes a channel for sending the warning content to the target object.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the object warning method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the object warning method according to any one of claims 1-7.

Images