Object behavior alarm method and device, electronic equipment and medium

Abstract

The embodiment of the invention discloses an object behavior warning method and device, electronic equipment and a storage medium. The method comprises the steps that real-time behavior data and surrounding environment parameters of a target object are acquired; according to the object information of the target object, determining a historical behavior sample matched with the target object and a historical alarm record corresponding to the historical behavior sample; determining a behavior risk level of the target object according to the real-time behavior data, the surrounding environment parameters, a historical behavior sample and a historical alarm record; if the behavior risk level meets a preset condition, an alarm prompt corresponding to the behavior risk level is generated and triggered, and according to the scheme, the rationality and effectiveness of alarm can be improved.

Description

Technical Field

[0001] This application relates to the field of behavior monitoring technology, specifically to an object behavior alarm method, device, electronic device, and storage medium. Background Technology

[0002] In many scenarios of modern society, the monitoring and alerting of object behavior has significant practical implications. Here, "objects" can encompass various types, including humans, vehicles, industrial equipment, and wild animals, with corresponding application scenarios including park security, traffic control, industrial production supervision, and ecological monitoring. Taking park security as an example, it requires real-time monitoring of abnormal human behavior (such as climbing over fences or prolonged stays in restricted areas) and timely alerts; in traffic control scenarios, it requires identifying and triggering alerts for vehicle violations (such as running red lights, speeding, and driving against traffic); and in industrial production scenarios, it requires monitoring abnormal equipment operation (such as overload operation and abnormal vibration) to prevent safety accidents.

[0003] Existing object behavior alarm technologies are mostly based on single behavioral characteristics for judgment, which has problems such as low alarm accuracy and poor adaptability. Summary of the Invention

[0004] This application provides an object behavior alarm method, device, electronic device, and storage medium. By dynamically adjusting the alarm threshold and alarm method, adaptive alarm triggering is achieved, thereby improving the rationality and effectiveness of alarms.

[0005] In a first aspect, embodiments of this application provide an object behavior alarm method, including: Acquire real-time behavioral data of the target object and parameters of its surrounding environment; Based on the object information of the target object, determine the historical behavior samples that match the target object and the historical alarm records corresponding to the historical behavior samples; Based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples, and historical alarm records, the behavioral risk level of the target object is determined. If the behavioral risk level meets the preset conditions, an alarm prompt corresponding to the behavioral risk level will be generated and triggered.

[0006] Optionally, in some embodiments of this application, determining the historical behavior samples matching the target object and the historical alarm records corresponding to the historical behavior samples based on the object information of the target object includes: Identify the object information of the target object; Based on the object information, obtain similar objects that are similar to the target object; The historical behavior samples of the similar objects and the historical alarm records corresponding to the historical behavior samples are determined as the historical behavior samples and the historical alarm records corresponding to the historical behavior samples that match the target object.

[0007] Optionally, in some embodiments of this application, obtaining similar objects to the target object based on the object information includes: Extracting object features from the object information, and; Extract sample features corresponding to each sample object in the historical sample database; Calculate the similarity between the object features and the sample features; Based on the calculation results, similar objects that are similar to the target object are obtained from the historical sample library.

[0008] Optionally, in some embodiments of this application, determining the behavioral risk level of the target object based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples, and historical alarm records includes: Based on the historical behavior samples and historical alarm records, determine the basic risk value of the behavior type to which the target object belongs; The behavioral risk level of the target object is determined based on the surrounding environmental parameters, real-time behavioral data, and the basic risk value.

[0009] Optionally, in some embodiments of this application, determining the behavioral risk level of the target object based on the surrounding environmental parameters, real-time behavioral data, and the basic risk value includes: Determine the environmental coefficients corresponding to the surrounding environmental parameters, and; Determine the behavior coefficients corresponding to the real-time behavior data; The behavioral risk level of the target object is determined based on the environmental coefficient, behavioral coefficient, and basic risk value.

[0010] Optionally, in some embodiments of this application, the step of generating and triggering an alarm notification corresponding to the behavior risk level if the behavior risk level meets a preset condition includes: If the behavioral risk level meets the preset conditions, determine the alarm parameters corresponding to the risk level; Based on the alarm parameters, an alarm prompt corresponding to the risk level is generated and output.

[0011] Optionally, in some embodiments of this application, after generating and triggering an alarm notification corresponding to the behavior risk level if the behavior risk level meets preset conditions, the step may further include: Generate a risk control strategy corresponding to the risk level of the behavior, and transmit the risk control strategy to the target terminal.

[0012] Secondly, embodiments of this application provide an object behavior alarm device including: The acquisition module is used to acquire real-time behavioral data of the target object and its surrounding environmental parameters; The first determining module is used to determine, based on the object information of the target object, historical behavior samples matching the target object and historical alarm records corresponding to the historical behavior samples; The second determining module is used to determine the behavioral risk level of the target object based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples and historical alarm records. The generation module is used to generate and trigger an alarm prompt corresponding to the behavior risk level if the behavior risk level meets the preset conditions.

[0013] Accordingly, this application also provides an electronic device, including a memory, a processor, and a processor program stored in the memory and executable on the processor, wherein the processor executes the program as described in any of the methods above.

[0014] This application also provides a storage medium storing a processor program that, when executed by a processor, implements any of the methods described above.

[0015] This application provides an object behavior alarm method, device, electronic device, and storage medium. After acquiring real-time behavior data and surrounding environmental parameters of a target object, it determines historical behavior samples matching the target object and corresponding historical alarm records based on the target object's object information. Then, based on the real-time behavior data, surrounding environmental parameters, historical behavior samples, and historical alarm records, it determines the target object's behavior risk level. If the behavior risk level meets preset conditions, an alarm notification corresponding to the behavior risk level is generated and triggered. In the object behavior alarm scheme provided in this application embodiment, a comprehensive risk assessment system is constructed by integrating the target object's object information, real-time behavior data, surrounding environmental parameters, historical behavior samples, and historical alarm records. This achieves accurate determination of behavior risk levels and differentiated alarms. Simultaneously, a risk control strategy linkage function is added, solving problems such as low alarm accuracy, poor scenario adaptability, and lack of closed-loop post-alarm processing in existing technologies. This enables adaptive alarm triggering, improving the rationality and effectiveness of alarms. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the object behavior alarm method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of the object behavior alarm device provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0019] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0020] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0021] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0022] The following describes in detail the embodiments involved in this application. It should be noted that the order of description of the embodiments in this application is not intended to limit the priority of the embodiments.

[0023] This application provides an object behavior alarm method, apparatus, storage medium, and smart terminal. Specifically, the object behavior alarm method of this application can be executed by a smart terminal or a server, wherein the smart terminal can be a terminal. The terminal can be a smartphone, tablet computer, laptop touchscreen, game console, personal computer (PC), personal digital assistant (PDA), or other smart terminal. The terminal may also include a client, which can be a media playback client or a real-time object behavior alarm client, etc.

[0024] This application provides an object behavior alarm method, which can be executed by an electronic device or a server. This application example illustrates the method executed by an electronic device. The electronic device includes a touchscreen display and a processor. The touchscreen display is used to present a graphical user interface (GUI) and receive operation commands generated by the user interacting with the GUI. When the user operates the GUI through the touchscreen display, the GUI can control the local content of the electronic device or the content on the server side in response to the received operation commands.

[0025] In the object behavior alarm scheme provided in this application embodiment, adaptive alarm triggering is achieved by dynamically adjusting the alarm threshold and alarm method, thereby improving the rationality and effectiveness of alarms.

[0026] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the priority of the embodiments.

[0027] A method for object behavior alarm includes: acquiring real-time behavior data and surrounding environmental parameters of a target object; determining historical behavior samples matching the target object and historical alarm records corresponding to the historical behavior samples based on the object information of the target object; determining the behavior risk level of the target object based on the real-time behavior data, surrounding environmental parameters, historical behavior samples, and historical alarm records; and generating and triggering an alarm prompt corresponding to the behavior risk level if the behavior risk level meets preset conditions.

[0028] Please see Figure 1 , Figure 1 This application provides a flowchart illustrating the object behavior alarm method. The specific flow of this object behavior alarm method is as follows: S101: Obtain real-time behavioral data of the target object and parameters of its surrounding environment.

[0029] This system can collect real-time behavioral data by combining target object type monitoring devices. The collection frequency can be dynamically adjusted according to scenario requirements (e.g., 1 time / second for high-risk areas, 1 time / 5 seconds for low-risk areas). The real-time behavioral data collection range and corresponding devices for different types of target objects are as follows: (1) Human objects: Data such as movement speed, dwell time, limb movements (such as climbing, waving limbs), location trajectory, number of people gathered, number of people in the same group, and frequency of behavior (such as frequently going back and forth to a certain area) can be collected through devices such as high-definition cameras, infrared sensors, personnel positioning base stations, and smart bracelets. For special scenarios (such as financial venues and confidential areas), additional data such as facial expressions, eye direction, and type of items carried can be collected.

[0030] (2) Vehicle objects: Data such as driving speed, driving trajectory, lane change frequency, braking frequency, following distance, tire pressure status, engine speed, and driving time are collected through traffic cameras, speed radar, vehicle-mounted terminals (OBD), GPS / Beidou positioning equipment, tire pressure sensors, etc. For commercial vehicles, additional data such as passenger capacity, cargo weight, and driving time can be collected.

[0031] (3) Industrial equipment objects: Through vibration sensors, speed sensors, temperature sensors, humidity sensors, current sensors, pressure sensors and other equipment, data such as operating speed, vibration amplitude, surface temperature, ambient humidity, operating current, operating pressure, cutting force, running time, and number of start-stop times are collected; for special equipment (such as cranes and pressure vessels), additional data such as load weight, running angle, and pressure value can be collected.

[0032] (4) Wild animals: Data such as activity trajectory, movement speed, resting time, population size and activity range are collected through infrared cameras, sonar sensors, drones, GPS trackers and other equipment, which are suitable for ecological environment monitoring scenarios.

[0033] Surrounding environmental parameters are environmental data directly or indirectly related to the behavioral risks of the target object. They are acquired through environmental sensors, meteorological monitoring equipment, video image analysis, and Geographic Information Systems (GIS), providing data for subsequent environmental coefficient calculations. The collection range of surrounding environmental parameters for different scenarios is as follows: (1) Security scenarios (parks, financial venues): light intensity, ambient temperature, humidity, precipitation (sunny / cloudy / rainy / snowy), personnel density, distribution of obstacles (fences, green plants, buildings), working status of lighting equipment, coverage of monitoring equipment, etc.

[0034] (2) Traffic control scenarios: road type (highway / national highway / city road), road surface condition (dry / slippery / icy / damaged), light intensity, precipitation, traffic flow, traffic light status, distribution of surrounding buildings, location of construction area, etc.

[0035] (3) Industrial production scenarios: workshop temperature, humidity, dust concentration, voltage stability, air quality, noise intensity, equipment layout, material stacking location, number of operators, etc.

[0036] (4) Ecological and environmental monitoring scenarios: temperature, precipitation, wind force, vegetation coverage, water source location, topography, traces of human activities, etc.

[0037] It should be noted that preprocessing operations are required during the data acquisition process, including data cleaning, deduplication, standardization, and data completion, to ensure the accuracy of subsequent data processing and analysis. Specific preprocessing may include: Data cleaning: removing outliers caused by sensor malfunctions (e.g., human movement speed > 10m / s, equipment temperature > 1000℃), missing values ​​due to data transmission interruptions, and maliciously tampered data; using the 3σ criterion and box plot method to identify and remove outliers; Data deduplication: removing duplicate data collected from the same device at the same time, retaining only one valid data point; Data standardization: standardizing data formats and units, such as standardizing light intensity to 0-100 lux, movement speed to 0-5m / s, and temperature to -20℃-100℃, ensuring data comparability across different devices; and Data completion: for a small number of missing data points, using linear interpolation, mean imputation, or median imputation to complete the data and prevent missing data from affecting subsequent analysis.

[0038] S102: Based on the object information of the target object, determine the historical behavior samples that match the target object and the historical alarm records corresponding to the historical behavior samples.

[0039] The object information can include identity information, type attributes, and permission / inherent attributes. The scope of object information for different types of target objects is as follows: ① Human Subject: Identity Information (Personnel ID, Name, ID Card Number, Visitor Registration Number), Type Attributes (Internal Employee / External Visitor / Construction Worker / Student / Security Personnel), Access Attributes (Accessible Areas, Activity Time Range), Inherent Attributes (Age Range, Gender, Department / Unit), Historical Behavior Tags (Whether there are any records of misconduct). For example, the object information of a human subject may include "External Visitor, 25-30 years old, No access to restricted areas, Visitor ID: FK20260126, Visit Time: January 26, 2026, 20:30-22:00, No history of misconduct".

[0040] ② Vehicle object: identity information (license plate number, vehicle identification number VIN, owner information), type attributes (compact car / large truck / commercial vehicle / private car / emergency vehicle), permission attributes (allowed driving area, passing time), inherent attributes (vehicle model, service life, engine displacement, maintenance records), historical behavior tags (whether there are violations, traffic accident records). For example, the object information of a vehicle object may include "compact car, private car, 3 years of service life, license plate: Beijing A12345, allowed to pass on urban roads, no violation records in the past year".

[0041] ③ Industrial equipment object: identity information (equipment number, factory number), type attributes (CNC machine tool / assembly line equipment / crane / pressure vessel), permission attributes (operation permission, operator qualification requirements), inherent attributes (equipment model, service life, factory date, maintenance cycle, historical failure records), operation attributes (current working condition: production / standby / maintenance). For example, the object information of an industrial equipment object may include "CNC machine tool, model CK6150, belonging to the processing workshop, 5 years of service life, maintenance cycle of 3 months, no failure records in the past year, current working condition: production".

[0042] Among them, for human objects, they can be obtained through the visitor registration system, employee clock-in system, face recognition system, and ID card reading device; for vehicle objects, they can be obtained through the license plate recognition system, vehicle-mounted terminal, and traffic management platform; for industrial equipment objects, they can be obtained through the equipment management system (MES), Internet of Things platform, and maintenance record ledger.

[0043] Furthermore, convert the identified unstructured object information into computable feature vectors, and at the same time extract the sample features of each sample object from the historical sample library. Then, based on the target object feature vector and the historical sample feature vector, select an appropriate method to quantify the similarity in combination with the type of feature vector. Cosine similarity, Euclidean distance, Manhattan distance, etc. can be used. Among them, cosine similarity is applicable to high-dimensional sparse vectors (human body, vehicle), Euclidean distance is applicable to low-dimensional dense vectors (industrial equipment), and Manhattan distance is applicable to vectors with outliers.

[0044] Optionally, in some embodiments of the present application, the step of "determining the historical behavior sample matching the target object and the corresponding historical alarm record of the historical behavior sample according to the object information of the target object" may specifically include: Identify the object information of the target object; Based on the object information, obtain a similar object similar to the target object; The historical behavior samples of the similar objects and the historical alarm records corresponding to the historical behavior samples are determined as the historical behavior samples and the historical alarm records corresponding to the historical behavior samples that match the target object.

[0045] Feature extraction employs a coding method for quantification, with a pre-set coding table to ensure that different values ​​of the same attribute correspond to a unique code. For example, personnel identity type coding: external visitor = 01, internal employee = 02, construction worker = 03; vehicle type coding: small car = 01, large truck = 02, emergency vehicle = 03; equipment access permission attribute coding: no restricted area access = 00, limited restricted area access = 01, full area access = 02. ② Continuous attributes (such as age, years of use, maintenance cycle): are converted into discrete values ​​using a segmented quantization method, with the segment intervals adjustable according to scenario requirements. For example, age range coding: 25-30 years old = 03, 31-40 years old = 04, 41-50 years old = 05; vehicle years of use coding: 1-3 years = 01, 4-6 years = 02, 7 years and above = 03; equipment maintenance cycle coding: 1-3 months = 01, 4-6 months = 02, 7 months and above = 03. ③ Historical behavior tags: coding for any negative records: none = 0, yes = 1.

[0046] The dimension of the feature vector needs to be determined according to the object type to ensure coverage of core attributes. For example, the feature vector dimension of a human object is [identity type code, age range code, permission attribute code, historical behavior tag code]; the feature vector dimension of a vehicle object is [vehicle type code, service life code, permission attribute code, historical behavior tag code]; and the feature vector dimension of an industrial equipment object is [equipment model code, service life code, operating condition code, historical fault tag code].

[0047] The historical sample library needs to be built in advance. For example, it should store historical behavior samples and corresponding historical alarm records from the past 6 months to 3 years. The sample library should be stored according to object type.

[0048] Optionally, in some embodiments of this application, the step "based on the object information, obtain similar objects that are similar to the target object" may specifically include: Extracting object features from the object information, and; Extract sample features corresponding to each sample object in the historical sample database; Calculate the similarity between the object features and the sample features; Based on the calculation results, similar objects that are similar to the target object are obtained from the historical sample library.

[0049] Specifically, the similarity between the object features and sample features can be calculated using cosine similarity or Euclidean distance. For example, for high-dimensional sparse feature vectors, such as feature vectors of human objects or vehicle objects, cosine similarity can be used to calculate the similarity between object features and sample features. Cosine similarity measures the cosine of the angle between two vectors, with a value range of [-1, 1]. The closer the value is to 1, the higher the similarity. The formula is: cosθ = (A·B) / (|A| × |B|), where A is the feature vector of the target object, B is the feature vector of the sample object, and A·B is the... The vector dot product, |A| and |B| are the magnitudes of vectors A and B, respectively. For low-dimensional dense feature vectors, such as feature vectors of industrial equipment objects, the Euclidean distance method is used for calculation. Euclidean distance measures the straight-line distance between two vectors in space. The smaller the distance, the higher the similarity. The formula is: d=√[Σ(ai-bi)²], where ai and bi are the values ​​of the i-th dimension of vectors A and B, respectively. To facilitate comparison with other similarity indicators, the Euclidean distance can be normalized to similarity. The formula is: sim=1 / (1+d), with a value range of (0,1).

[0050] To improve the accuracy of similarity calculation, differentiated weights can be assigned to features of different dimensions, highlighting the influence of core attributes (such as identity type, vehicle model, and device model, with a weight ratio of no less than 40%). The sum of the weights is 1, and the weighted similarity formula is: Weighted Similarity = Σ(Single-Dimension Similarity × Corresponding Weight). For example, in the human object feature vector, identity type has a weight of 0.4, age range has a weight of 0.2, permission attribute has a weight of 0.2, and historical behavior tag has a weight of 0.2. After calculating the similarity of each dimension separately, the weighted sum is used to obtain the final similarity.

[0051] Sample objects with similarity scores higher than the threshold are identified as similar objects. If the similarity threshold is too high, resulting in too few similar objects (less than 3), the threshold can be appropriately lowered (by a maximum of 0.1) to supplement similar objects. If there are still fewer than 3 similar objects after lowering the threshold, it is determined that there are no matching similar objects. In this case, industry benchmark data of similar behaviors are used as a substitute, and the behavioral data of the target object is temporarily stored in the sample library. The sample library will be updated after the data is accumulated.

[0052] If multiple similar objects exist, sort them from highest to lowest similarity and select the top N (N can be adjusted according to the scenario), such as 5-10, as core similar objects to reduce sample redundancy and improve the efficiency of subsequent data processing. Extract all historical behavior samples and corresponding historical alarm records of the core similar objects to form a matching dataset. It should be noted that during extraction, only historical behavior samples that are consistent with the current behavior type of the target object are extracted, and irrelevant behavior samples are excluded. In addition, the extracted historical alarm records must contain complete information, namely alarm trigger time, alarm type, risk level, trigger conditions, handling result, whether adverse consequences occurred (such as illegal intrusion, equipment failure, traffic accident), handling person, and handling completion time. False alarms, incomplete records, and tampered invalid data are removed.

[0053] S103: Determine the behavioral risk level of the target object based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples, and historical alarm records.

[0054] Specifically, a base risk value is calculated based on matched historical behavior samples and historical alarm records to anchor the inherent risk level of the target object's current behavior type. The core is to statistically determine the probability of adverse consequences occurring for this type of behavior in historical data, while also taking into account implicit risks and scenario corrections for insufficient sample size to ensure the reliability of the base risk value.

[0055] Optionally, in some embodiments of this application, the step of "determining the behavioral risk level of the target object based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples, and historical alarm records" may specifically include: Based on the historical behavior samples and historical alarm records, determine the basic risk value of the behavior type to which the target object belongs; The behavioral risk level of the target object is determined based on the surrounding environmental parameters, real-time behavioral data, and the basic risk value.

[0056] Specifically, first, the total number of historical behavior samples of core similar objects is counted. Then, the number of samples that triggered alarms and had adverse consequences is distinguished from the number of latent risk samples that did not trigger alarms but had adverse consequences. A latent risk coefficient is introduced to weaken the impact of low-probability latent events. The basic risk value can be calculated by the formula (M + K×λ) / N, where M is the number of adverse consequences samples after the alarm, K is the number of latent risk samples, λ is the latent risk coefficient with a value of 0.3-0.5, and N is the total number of samples.

[0057] Next, environmental coefficients are calculated based on surrounding environmental parameters to quantify the amplification or mitigation effect of the scene environment on inherent risks. Environmental parameters are divided into core parameters (directly related to risk, weight ≥70%) and auxiliary parameters (indirectly related, weight ≤30%). The environmental coefficient is obtained by weighted summation, considering the pre-defined influence of different states of each parameter in the scene (values ​​0-2, >1 amplifies risk, <1 weakens risk). For example, in a park security scenario, light intensity and personnel density are core parameters, while temperature and humidity are auxiliary parameters. A low-light environment with few people at night will result in an environmental coefficient greater than 1, amplifying behavioral risks; while a well-lit environment with many people will result in a coefficient less than 1, weakening risks. This achieves dynamic adaptation of risk assessment to the real-time environment.

[0058] Furthermore, behavioral coefficients are calculated based on real-time behavioral data to calibrate the degree of deviation between the target object's current behavior and its historical normal behavior. One to three core feature parameters (such as human movement speed, vehicle following distance, and equipment vibration amplitude) are extracted for the current behavior type. The average and standard deviation of these parameters in historical samples of similar objects are statistically analyzed to determine the range of normal behavior. The relative deviation rate between the real-time parameters and the historical mean is calculated, and a deviation amplification factor (valued at 0.5-1.2 based on behavioral sensitivity) is introduced. The behavioral coefficient is calculated using the formula 1 + k × δ (where δ is the relative deviation rate). If the real-time parameters are within the normal range, the deviation amplification factor can be reduced to weaken the impact of normal deviations, ensuring that the behavioral coefficient accurately reflects the degree of behavioral abnormality. That is, the greater the deviation, the higher the coefficient, and the more significant the amplification effect on inherent risks.

[0059] Optionally, in some embodiments of this application, the step "determining the behavioral risk level of the target object based on the surrounding environmental parameters, real-time behavioral data, and the basic risk value" may specifically include: Determine the environmental coefficients corresponding to the surrounding environmental parameters, and; Determine the behavior coefficients corresponding to the real-time behavior data; The behavioral risk level of the target object is determined based on the environmental coefficient, behavioral coefficient, and basic risk value.

[0060] Furthermore, the risk quantification value is calculated by integrating the basic risk value, environmental coefficient, and behavioral coefficient, and mapped to the final behavioral risk level. The formula is: Risk Quantification Value = Corrected Basic Risk Value × Environmental Coefficient × Behavioral Coefficient, to obtain a comprehensive quantification result (range 0-4.4). This result is then combined with preset grading rules to classify the risk level. The general grading standards are: Low Risk (R_quant < 0.5, no alarm required, continuous monitoring), Medium Risk (0.5 ≤ R_quant < 1.0, low-intensity alarm, routine inspection), High Risk (1.0 ≤ R_quant < 2.0, medium-intensity alarm, intervention initiated), and Extremely High Risk (R_quant ≥ 2.0, high-intensity alarm, emergency response). For high-risk scenarios (such as financial institutions and hazardous materials warehouses), a special risk level can be added; for ordinary scenarios, the grading can be simplified to ensure that the level classification adapts to the safety requirements of the scenario.

[0061] S104: If the behavioral risk level meets the preset conditions, an alarm prompt corresponding to the behavioral risk level is generated and triggered.

[0062] The preset alarm conditions are based on risk level as the core threshold and dynamically configured according to the security requirements of the scenario to form a hierarchical triggering rule, ensuring the targeted nature of alarm triggering. The general verification logic is as follows: low risk (R_quant < 0.5) does not meet the alarm conditions, only a continuous monitoring mechanism is activated, updating the target object's behavior data and surrounding environment parameters every 2 minutes and recording the behavior trajectory to the system log, without triggering any alarm prompts; medium risk (0.5 ≤ R_quant < 1.0), high risk (1.0 ≤ R_quant < 2.0), and very high risk (R_quant ≥ 2.0) all meet the alarm conditions, triggering alarms of corresponding intensities respectively; for high-risk scenarios such as financial venues, hazardous materials warehouses, and confidential areas, an additional enhanced rule of "immediately triggering alarms for medium risk and above" can be configured, while for low-security scenarios such as small parks and ordinary shops, it can be simplified to "only triggering alarms for high risk and above". All rules can be manually adjusted through the system interface or automatically optimized based on historical alarm handling efficiency.

[0063] During the verification process, the system needs to synchronously associate the target object's historical alarm records with its current behavioral characteristics and perform secondary verification for special scenarios: if the target object has three or more similar high-risk historical records, the alarm intensity will be automatically upgraded even if the current risk level is medium risk; if the target object is a special subject such as an emergency vehicle or maintenance personnel, and the current behavior is to perform an emergency task (such as equipment repair or emergency rescue), the alarm can be exempted after manual confirmation to avoid interfering with normal work.

[0064] Optionally, in some embodiments of this application, the system has a built-in alarm parameter configuration library, which presets differentiated parameters according to risk level to ensure that the alarm method, intensity, push range, retry mechanism, duration and risk level are matched. The parameters can be adjusted in a personalized manner according to the scenario, as follows: Medium-risk alarm: Alarms are sent via system pop-ups and SMS notifications; alarm intensity is set to low level, pop-ups appear once and disappear automatically after 10 seconds, SMS messages are sent only once and there is no continuous notification; the push scope is limited to security personnel in the corresponding area and control room duty officers to ensure accountability; the retry mechanism is to retry twice if the push fails, with an interval of 1 minute, and failure records are fed back to the control room log in real time; there is no continuous alarm duration, and a secondary reminder is only triggered when the behavior escalates.

[0065] High-risk alarm: Alarm methods include system pop-ups, SMS, and voice broadcasts; alarm intensity is set to medium level, the pop-up is forced to remain until manually closed, and the voice broadcast repeats every 5 minutes for 15 minutes; the push scope is expanded to regional security personnel, central control room duty officers, and security supervisors, achieving simultaneous execution at the grassroots level and supervision at the management level; the retry mechanism is to retry 3 times if the push fails, with an interval of 1 minute, and simultaneously trigger the push of backup contact methods; the voice broadcast lasts for 5 minutes until manual confirmation of receipt.

[0066] Extremely high risk alarm: Alarm methods include system pop-ups, SMS, voice broadcasts, on-site audible and visual alarms, and emergency broadcasts, combining online reminders with on-site warnings; alarm intensity is set to high level, with continuous looping of voice broadcasts and audible and visual warnings until manual confirmation and handling are completed; push.

[0067] Optionally, in some embodiments of this application, the step "if the behavioral risk level meets the preset conditions, then generate and trigger an alarm prompt corresponding to the behavioral risk level" may specifically include: If the behavioral risk level meets the preset conditions, determine the alarm parameters corresponding to the risk level; Based on the alarm parameters, an alarm prompt corresponding to the risk level is generated and output.

[0068] For example, specifically, the type and identification of the target objects are determined, such as labeling human objects with visitor ID / employee number, vehicle objects with license plate number, and equipment objects with equipment number and current precise location. Then, combined with the risk level and historical handling experience, handling guidelines are output, such as: for medium risk, "confirm on-site inspection, no need to activate emergency procedures", for high risk, "immediately go to the scene to intervene and seal off the risk area", and for very high risk, "emergency evacuation of surrounding personnel, activation of emergency plan and contact of external rescue".

[0069] Optionally, in some embodiments of this application, after the step "if the behavioral risk level meets the preset conditions, then generate and trigger an alarm prompt corresponding to the behavioral risk level", it may further include: Generate a risk control strategy corresponding to the risk level of the behavior, and transmit the risk control strategy to the target terminal.

[0070] The risk control strategy is precisely matched with the risk level, behavior type, and scenario requirements. The content includes handling actions, responsible personnel, execution time limits, emergency measures, and review requirements. Optionally, in some embodiments of this application, the risk control strategies for different risk levels are as follows: Under low risk, behavioral data is updated every 2 minutes, recording behavioral trajectories; the responsible personnel are the control room duty officers; the execution time limit is until the target object leaves the risk area or the behavior returns to normal. If the behavior escalates to medium risk, the corresponding alarm is triggered immediately. Medium risk selection: On-site inspection, confirm the nature of the risk (normal behavior / potential risk / violation), and report the handling results. Under high risk: Initiate the intervention process, intercept and control the target object's behavior on-site, seal off the risk area, and report the handling progress; the execution time limit is to arrive at the scene within 5 minutes and complete the initial handling within 30 minutes; emergency measures = if the risk escalates, activate the emergency plan and allocate support forces; under extremely high risk: the handling actions are to urgently seal off the area, evacuate surrounding personnel, control the target object on-site, and activate the emergency response plan (such as alarm and rescue); the execution time limit is to arrive at the scene within 2 minutes and activate the emergency plan within 10 minutes.

[0071] Furthermore, risk control strategies can be automatically optimized by combining historical handling data. For example, in the historical handling process of a certain type of high-risk behavior, the on-site interception link is inefficient. The strategy can be optimized to first block off the area and then gradually intercept the risk.

[0072] After the risk control strategy is generated, it is transmitted to the target terminals, including handheld terminals of security personnel, central control room systems, mobile phones of management personnel, and terminals of emergency response teams. The transmission method is consistent with the alarm notification push method to ensure that the personnel handling the situation receive alarm information and risk control strategies simultaneously.

[0073] If transmission fails, the same retry mechanism as the alarm notification is used, and the control room operator manually communicates the policy. After the policy is transmitted, the system records the transmission time, receiving terminal, receiving personnel, and confirmation status, forming a transmission log.

[0074] This application provides an object behavior alarm method. After acquiring real-time behavior data and surrounding environmental parameters of a target object, it determines historical behavior samples matching the target object and corresponding historical alarm records based on the object information of the target object. Then, based on the real-time behavior data, surrounding environmental parameters, historical behavior samples, and historical alarm records, it determines the behavior risk level of the target object. If the behavior risk level meets preset conditions, an alarm prompt corresponding to the behavior risk level is generated and triggered. In the object behavior alarm scheme provided in this application embodiment, a full-dimensional risk assessment system is constructed by integrating the object information of the target object, real-time behavior data, surrounding environmental parameters, historical behavior samples, and historical alarm records. This achieves accurate determination of behavior risk levels and differentiated alarms. Simultaneously, a risk control strategy linkage function is added, solving problems such as low alarm accuracy, poor scenario adaptability, and lack of closed-loop post-alarm processing in existing technologies. This achieves adaptive alarm triggering, improving the rationality and effectiveness of alarms.

[0075] To facilitate better implementation of the object behavior alarm method of this application embodiment, this application embodiment also provides an object behavior alarm device, wherein the meanings of the terms are the same as those in the object behavior alarm system described above, and specific implementation details can be found in the description of the system embodiment.

[0076] Please see Figure 2 , Figure 2 The diagram below illustrates the structure of an object behavior alarm device provided in this embodiment of the application. Specifically, the object behavior alarm device may be as follows: The acquisition module 201 is used to acquire real-time behavioral data of the target object and surrounding environmental parameters; The first determining module 202 is used to determine, based on the object information of the target object, historical behavior samples matching the target object and historical alarm records corresponding to the historical behavior samples; The second determining module 203 is used to determine the behavioral risk level of the target object based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples and historical alarm records. The generation module 204 is used to generate and trigger an alarm prompt corresponding to the behavior risk level if the behavior risk level meets the preset conditions.

[0077] This application provides an object behavior alarm device. After the acquisition module 201 acquires real-time behavior data and surrounding environmental parameters of the target object, the first determination module 202 determines historical behavior samples matching the target object and historical alarm records corresponding to the historical behavior samples based on the object information of the target object. Then, the second determination module 203 determines the behavior risk level of the target object based on the real-time behavior data, surrounding environmental parameters, historical behavior samples, and historical alarm records. If the behavior risk level meets preset conditions, the generation module 204 generates and triggers an alarm prompt corresponding to the behavior risk level. In the object behavior alarm scheme provided in this application embodiment, by integrating the object information of the target object, real-time behavior data, surrounding environmental parameters, historical behavior samples, and historical alarm records, a full-dimensional risk assessment system is constructed to achieve accurate determination of behavior risk level and differentiated alarms. At the same time, a risk control strategy linkage function is added to solve the problems of low alarm accuracy, poor scenario adaptability, and non-closed-loop post-alarm processing in the prior art, realizing adaptive alarm triggering and improving the rationality and effectiveness of alarms.

[0078] To facilitate better implementation of the object behavior alarm method in the embodiments of this application, the embodiments of this application also provide Furthermore, embodiments of this application also provide an electronic device, such as... Figure 3 As shown, it illustrates a structural schematic diagram of the electronic device involved in the embodiments of this application, specifically: The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more processor-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will understand that... Figure 3 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: Processor 301 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in memory 302, and by calling data stored in memory 302, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Optionally, processor 301 may include one or more processing cores; preferably, processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless object behavior alarms. It is understood that the modem processor may not be integrated into processor 301.

[0079] The memory 302 can be used to store software programs and modules. The process 301 executes various functional applications and object behavior alarm methods by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the process 301 with access to the memory 302.

[0080] The electronic device also includes a power supply 303 that supplies power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 303 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0081] The electronic device may also include an input unit 304, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0082] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in the embodiments of this application, the processing 301 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 302 according to the following instructions, and the processing 301 runs the applications stored in the memory 302 to realize various functions, as follows: The system acquires real-time behavioral data and surrounding environmental parameters of the target object; based on the object information of the target object, it determines historical behavioral samples matching the target object and historical alarm records corresponding to the historical behavioral samples; based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples, and historical alarm records, it determines the behavioral risk level of the target object; if the behavioral risk level meets preset conditions, it generates and triggers an alarm prompt corresponding to the behavioral risk level.

[0083] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0084] This application embodiment achieves adaptive alarm triggering by dynamically adjusting the alarm threshold and alarm method, thereby improving the rationality and effectiveness of alarms.

[0085] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a processor-readable storage medium and loaded and executed by a processor.

[0086] Therefore, embodiments of this application provide a storage medium storing multiple instructions that can be loaded by a processor to execute steps in any of the object behavior alarm methods provided in embodiments of this application. For example, the instructions can execute the following steps: The system acquires real-time behavioral data and surrounding environmental parameters of the target object; based on the object information of the target object, it determines historical behavioral samples matching the target object and historical alarm records corresponding to the historical behavioral samples; based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples, and historical alarm records, it determines the behavioral risk level of the target object; if the behavioral risk level meets preset conditions, it generates and triggers an alarm prompt corresponding to the behavioral risk level.

[0087] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0088] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0089] Since the instructions stored in the storage medium can execute the steps in any of the object behavior alarm methods provided in the embodiments of this application, the beneficial effects that any of the object behavior alarm methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0090] The foregoing has provided a detailed description of an object behavior alarm method, apparatus, electronic device, and storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for alerting object behavior, characterized in that, include: Acquire real-time behavioral data of the target object and parameters of its surrounding environment; Based on the object information of the target object, determine the historical behavior samples that match the target object and the historical alarm records corresponding to the historical behavior samples; Based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples, and historical alarm records, the behavioral risk level of the target object is determined. If the behavioral risk level meets the preset conditions, an alarm prompt corresponding to the behavioral risk level will be generated and triggered.

2. The object behavior alarm method according to claim 1, characterized in that, The step of determining historical behavior samples matching the target object and historical alarm records corresponding to the historical behavior samples based on the object information of the target object includes: Identify the object information of the target object; Based on the object information, obtain similar objects that are similar to the target object; The historical behavior samples of the similar objects and the historical alarm records corresponding to the historical behavior samples are determined as the historical behavior samples and the historical alarm records corresponding to the historical behavior samples that match the target object.

3. The object behavior alarm method according to claim 2, characterized in that, The step of obtaining similar objects to the target object based on the object information includes: Extracting object features from the object information, and; Extract sample features corresponding to each sample object in the historical sample database; Calculate the similarity between the object features and the sample features; Based on the calculation results, similar objects that are similar to the target object are obtained from the historical sample library.

4. The object behavior alarm method according to claim 1, characterized in that, The step of determining the behavioral risk level of the target object based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples, and historical alarm records includes: Based on the historical behavior samples and historical alarm records, determine the basic risk value of the behavior type to which the target object belongs; The behavioral risk level of the target object is determined based on the surrounding environmental parameters, real-time behavioral data, and the basic risk value.

5. The object behavior alarm method according to claim 4, characterized in that, The step of determining the behavioral risk level of the target object based on the surrounding environmental parameters, real-time behavioral data, and the basic risk value includes: Determine the environmental coefficients corresponding to the surrounding environmental parameters, and; Determine the behavior coefficients corresponding to the real-time behavior data; The behavioral risk level of the target object is determined based on the environmental coefficient, behavioral coefficient, and basic risk value.

6. The object behavior alarm method according to claim 1, characterized in that, If the behavioral risk level meets preset conditions, an alarm notification corresponding to the behavioral risk level is generated and triggered, including: If the behavioral risk level meets the preset conditions, determine the alarm parameters corresponding to the risk level; Based on the alarm parameters, an alarm prompt corresponding to the risk level is generated and output.

7. The object behavior alarm method according to any one of claims 1 to 6, characterized in that, If the behavioral risk level meets the preset conditions, then after generating and triggering an alarm corresponding to the behavioral risk level, the process may further include: Generate a risk control strategy corresponding to the risk level of the behavior, and transmit the risk control strategy to the target terminal.

8. An object behavior alarm device, characterized in that, include: The acquisition module is used to acquire real-time behavioral data of the target object and its surrounding environmental parameters; The first determining module is used to determine, based on the object information of the target object, historical behavior samples matching the target object and historical alarm records corresponding to the historical behavior samples; The second determining module is used to determine the behavioral risk level of the target object based on the real-time behavioral data, surrounding environmental parameters, historical behavioral samples and historical alarm records. The generation module is used to generate and trigger an alarm prompt corresponding to the behavior risk level if the behavior risk level meets the preset conditions.

9. An electronic device, characterized in that, include: A memory, a processor, and a processor program stored in the memory and executable on the processor, wherein the processor executes the program as steps of the object behavior alarm method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, A computer processing program that stores steps of the object behavior alerting method as described in any one of claims 1 to 7, which can be loaded by a processor.

Images