Fire approach warning method, device, storage medium and program product

Abstract

This application provides a method, device, storage medium, and program product for warning of unauthorized hot work, relating to the field of kitchen safety and fire early warning technology. The method includes: acquiring personnel information within the warning range and a first temperature change time series of the warning object; if there are points in the first temperature change time series exceeding the warning temperature threshold, no personnel are within the warning range, and the temperature of the warning object shows a decreasing trend, determining, based on the first temperature change time series, whether the temperature decrease rate of the warning object is less than the temperature decrease rate after the stove is turned off; if the temperature decrease rate of the warning object is less than the temperature decrease rate after the stove is turned off, issuing a warning for unauthorized hot work. This application can improve the accuracy of warnings for unauthorized hot work.

Description

Technical Field

[0001] This application relates to the field of kitchen safety and fire early warning technology, and in particular to a method, device, storage medium and program product for early warning of hot work and unattended personnel. Background Technology

[0002] "Hot work unattended" refers to the dangerous act of leaving a kitchen unattended while equipment generating high-temperature heat sources is in use or operational. Kitchens are prone to fires and other hazards when "hot work unattended" is in this state, making effective detection and timely warnings crucial.

[0003] In related technologies, human figures are detected by visible light or microwaves, and temperature is measured by thermal imaging temperature measurement equipment. An alarm is triggered when no human figure is detected and the temperature exceeds a threshold. However, this method is prone to false alarms. Summary of the Invention

[0004] This application provides a method, device, storage medium, and program product for early warning of hot work leaving personnel unattended, in order to improve the accuracy of early warning of hot work leaving personnel unattended.

[0005] In a first aspect, embodiments of this application provide a method for early warning of hot work leaving personnel unattended, including:

[0006] Obtain information on personnel within the warning area and the first temperature change time series of the warning targets;

[0007] If there are points in the first temperature change time series that exceed the warning temperature threshold, there are no people within the warning range, and the temperature of the warning object is decreasing, determine whether the temperature decrease rate of the warning object is less than the temperature decrease rate of the warning object after the fire is turned off, based on the first temperature change time series.

[0008] If the rate of temperature drop of the warning object is less than the rate of temperature drop after the fire is turned off, a warning for leaving personnel unattended while in use will be issued.

[0009] In one possible implementation, determining whether the temperature drop rate of the warning target is less than the temperature drop rate of the warning target after it is turned off, based on a first temperature change time series, includes:

[0010] Based on the linear regression estimation algorithm, the slope of the first temperature change time series is determined to be the first temperature change rate;

[0011] If the absolute value of the first temperature change rate is less than the temperature change rate threshold, then it is determined whether the temperature drop rate of the warning object is less than the temperature drop rate of the warning object after it is turned off. The temperature change rate threshold is dynamically determined based on the temperature drop rate of the warning object after it is turned off.

[0012] In one possible implementation, the temperature change rate threshold is determined in the following manner:

[0013] Based on the first temperature change time series, the absolute value of the ratio of the temperature change value of the warning object to the temperature change time is determined as the second temperature change rate;

[0014] Determine the second rate of temperature change and The product of these is the temperature change rate threshold, where... This indicates the rate of temperature change of the warning target after it is turned off, over time. (Parameter) It is modeled using the natural exponential function and calibrated based on the temperature change process of the warning object after the fire is turned off.

[0015] In one possible implementation, it also includes:

[0016] In response to the calibration conditions that meet the changing law of temperature change rate, the second temperature change time series of the warning object is collected;

[0017] Using the natural exponential function as a model, parameters were obtained by fitting the data based on the second temperature change time series. .

[0018] In one possible implementation, the linear regression estimation algorithm includes a least-squares estimation algorithm for the linear regression slope, wherein the first rate of temperature change is determined according to the following formula:

[0019]

[0020] in, Within the warning range The first temperature change rate corresponding to each warning target The length of the first temperature change time series. For the first The first temperature change time series of the warning target Data points.

[0021] In one possible implementation, obtaining the first temperature change time series of the warning object within the warning range includes:

[0022] The temperature of the warning target is sampled at a preset sampling interval to obtain a third temperature change time series;

[0023] The third temperature change time series is preprocessed to obtain the first temperature change time series. The preprocessing includes repairing the jump values ​​in the third temperature change time series.

[0024] In one possible implementation, obtaining personnel information within the warning range includes:

[0025] A series of single-stage real-time target detection algorithms are used to detect visible light data within the warning range in real time, thereby obtaining information on personnel within the warning range.

[0026] Secondly, embodiments of this application provide a hot work and unattended personnel warning device, comprising:

[0027] The acquisition module is used to acquire information on personnel within the warning range and the first temperature change time series of the warning objects;

[0028] The processing module is used to determine whether the temperature drop rate of the warning object is less than the temperature drop rate of the warning object after the fire is turned off, if there is a point in the first temperature change time series that exceeds the warning temperature threshold, there are no people in the warning range, and the temperature of the warning object is decreasing.

[0029] The early warning module is used to issue an early warning if the temperature drop rate of the object being warned is less than the temperature drop rate after the flame is turned off.

[0030] Thirdly, embodiments of this application provide a hot work and unattended personnel early warning device, including: a memory and a processor;

[0031] The memory stores instructions that the computer executes;

[0032] The processor executes computer execution instructions stored in memory, causing the processor to perform the methods described in the various possible implementations of the first aspect above.

[0033] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the methods described in the various possible implementations of the first aspect above.

[0034] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed, implements the methods described in the various possible implementations of the first aspect above.

[0035] The hot work evacuation warning method, device, storage medium, and program product provided in this application obtain personnel information within the warning range and the first temperature change time series of the warning object. In cases where there are points exceeding the warning temperature threshold, no personnel within the warning range, and the temperature of the warning object is showing a downward trend, the method determines whether the temperature drop rate of the warning object is less than the temperature drop rate of the warning object after the fire is turned off, based on the first temperature change time series. This can distinguish whether the warning object is in a state of natural cooling after the fire is turned off or still has a continuous risk of hot work when personnel leave, thereby improving the accuracy of the hot work evacuation warning and reducing false alarms and missed alarms. Attached Figure Description

[0036] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0037] Figure 1 A schematic flowchart illustrating the hot work and unattended personnel early warning method provided in this application embodiment;

[0038] Figure 2 This is a schematic diagram of the structure of the hot work and unattended personnel warning device provided in the embodiments of this application;

[0039] Figure 3 This is a schematic diagram of the structure of the hot work and personnel leaving early warning device provided in the embodiments of this application.

[0040] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0041] 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.

[0042] Hot work unattended warning falls under the field of kitchen safety and fire early warning technology, primarily targeting environments such as home kitchens and restaurant kitchens where there is a risk of continuous heating on stoves. In these scenarios, it is typically necessary to establish an early warning range around the stove, cookware, and areas where people are active, and continuously acquire temperature information and personnel presence information of the warned objects to monitor situations where the stove is left on while cooking is in progress.

[0043] Related hot work and unattended personnel warning technologies typically combine temperature monitoring with personnel identification, continuously observing stoves or cookware within the warning range. When personnel are detected leaving and the temperature of a certain warning object reaches or exceeds a set threshold, a risk is determined and an alarm is issued. The basic idea is to use whether the current temperature exceeds the limit as the primary basis, supplemented by a joint judgment based on whether personnel are present.

[0044] However, this method relies on a fixed temperature threshold, and its judgment logic is biased towards static temperature values, making it difficult to reflect the temperature change process of the pot under different heating states. Especially in actual kitchens, different types of stoves, pot materials, and heat dissipation conditions vary significantly, and the natural cooling rate after the heat is turned off is not uniform. Relying solely on whether the current temperature is too high often fails to effectively distinguish whether the object being warned is in a normal cooling state after the heat is turned off or is still in a state of continuous heating. This can easily trigger false alarms when the residual temperature is still high after the heat has been turned off, affecting normal use by the user.

[0045] In view of this, there is an urgent need for a method for early warning of hot work leaving personnel unattended, which can combine personnel status and temperature change process for judgment. In this embodiment, after obtaining personnel information and a first temperature change time series of the warning object, if there is a point in the first temperature change time series that exceeds the warning temperature threshold, there are no personnel within the warning range, and the temperature of the warning object shows a downward trend, then the method determines whether the temperature drop rate of the warning object is less than the temperature drop rate after the fire is turned off, and issues an early warning of hot work leaving personnel unattended when the temperature drop rate is relatively small, thereby improving the accuracy of identifying situations where personnel leave without turning off the fire.

[0046] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0047] Figure 1 This is a flowchart illustrating the hot work and unattended personnel early warning method provided in this application embodiment, as shown below. Figure 1 As shown, the method includes:

[0048] S101. Obtain information on personnel within the warning range and the first temperature change time series of the warning targets.

[0049] Specifically, the warning range is the spatial area where personnel status and temperature status are jointly detected. This spatial area covers stoves, pots, or other high-temperature areas that need to be monitored, and is set up corresponding to personnel activity areas, so that the personnel status within the same detection area can be correlated with the temperature changes of each warning object. Personnel information includes status data on whether personnel exist within the warning range and whether personnel have left the area.

[0050] The warning targets are specific objects that need to be assessed for the risk of being left unattended while cooking. These can be the pot body corresponding to a single burner, the heating area of ​​the stove, or a high-temperature detection area that corresponds one-to-one with the spatial location of the burner. When multiple warning targets exist within the warning range, a separate object identifier is created for each target, and temperature change data corresponding to that target is acquired for each target.

[0051] The first temperature change time series is a data set of temperature changes over time formed during the continuous sampling process of the early warning object. It is the basic data for subsequent identification of temperature trends and calculation of the rate of temperature decrease.

[0052] In one implementation, the execution entity of this application embodiment may be an edge controller deployed in a kitchen terminal. The edge controller first initializes and calibrates the warning range, and delineates at least one warning target area based on the stove location. Subsequently, it acquires the temperature data of each warning target at continuous time intervals, forming a first temperature change time series for each warning target.

[0053] In one implementation, during the personnel information acquisition process, the status of personnel within the warning range is detected. When no personnel are detected, a status marker indicating no personnel are within the warning range is output; when personnel are detected entering or remaining within the warning range, a status marker indicating presence is output. This status marker is time-aligned with the temperature sampling values ​​of each warning object at the same time to form joint input data. For scenarios with multiple warning objects, such as kitchens with two stoves or multiple burners, personnel information can be shared within the same warning range, but each object maintains its own first temperature change time series, and the personnel departure status is associated with the temperature status of each warning object one by one.

[0054] S102. If there are points in the first temperature change time series that exceed the warning temperature threshold, there are no people within the warning range, and the temperature of the warning object is decreasing, determine whether the temperature decrease rate of the warning object is less than the temperature decrease rate of the warning object after the fire is turned off, based on the first temperature change time series.

[0055] The warning temperature threshold is a temperature judgment value used to determine whether a warning object has entered the risk analysis range. This threshold can be pre-written into the system parameter table based on the type of stove, the material of the cookware, or the scene calibration results. When there are multiple warning objects within the warning range, different warning temperature thresholds can be set according to the temperature characteristics of the warning objects. For example, in a home kitchen scenario, corresponding thresholds can be configured for gas stoves, induction cookers, or other types of stoves, and the threshold matching the type of warning object can be called at runtime.

[0056] The presence of points exceeding the warning temperature threshold in the first temperature change time series indicates that at least one sampling point has a temperature value greater than this threshold during the current observation period. This confirms that the warning target is in a relatively high temperature state, meeting the prerequisite for further analysis. A decreasing temperature trend indicates that the first temperature change time series is generally trending downwards during the current analysis. The temperature decrease rate is a parameter characterizing how quickly the temperature of the warning target decreases. The temperature decrease rate of the warning target after the stove is turned off is the reference decrease rate of the warning target under natural heat dissipation after the stove is turned off. This reference value can be obtained through pre-calibration, a historical learning model, or an object type mapping table.

[0057] For example, after updating the first temperature change time series, it is determined whether there are any points in the series that exceed the warning temperature threshold. If no points exceed the threshold, monitoring continues, and the temperature decrease rate comparison process is not initiated. If points exceed the threshold, the personnel information status corresponding to that series is read to confirm whether there are no personnel within the warning range. Subsequently, trend identification is performed on the temperature series to determine whether the temperature of the warning target is showing a downward trend.

[0058] After meeting the three conditions of having an over-threshold point, having no personnel within the warning range, and having a decreasing temperature trend, the current temperature decrease rate is determined based on the first temperature change time series, and the temperature decrease rate of the warning object after being turned off is obtained as a reference value for comparison. If the current temperature decrease rate is less than the reference value, it is determined that the current temperature decrease rate is lower than the natural cooling rate after being turned off, indicating that although the warning object shows a decreasing trend on the surface, its heat input state may still have continuous heating or residual heating compensation.

[0059] Based on the above analysis, this step incorporates a multi-condition triggering and rate comparison mechanism. First, a low-temperature state is screened out using a warning temperature threshold. Then, the risk scenario is limited by considering the personnel's departure status. Next, even when the temperature is already trending downwards, the current rate of temperature decrease is compared with the rate of temperature decrease after the warning object is turned off. This distinguishes between normal residual heat cooling after the fire is turned off and the abnormally slow cooling process when the fire is still burning after people have left. Because cookware materials, stove power, and environmental heat dissipation conditions vary in actual kitchens, simply relying on whether the current temperature exceeds the limit is insufficient to accurately identify the true risk. By introducing a temperature decrease rate parameter from the time series and using the rate of temperature decrease after the warning object is turned off as the criterion, a more refined identification of the continuous heating state can be achieved even when the temperature is still high and personnel have left.

[0060] S103. If the rate of temperature drop of the warning object is less than the rate of temperature drop of the warning object after the fire is turned off, a warning for leaving personnel without fire shall be issued.

[0061] When the rate of temperature drop is less than the rate of temperature drop after the fire is turned off, it indicates that the cooling process of the current warning object is slower than the cooling process that the warning object should have when it is naturally dissipating heat after the fire is turned off. Assuming that there are no personnel within the warning range, this state is identified as a risk state of hot work away from people that requires intervention, and a hot work away from people warning is issued.

[0062] In one implementation, a comparison result marker is generated after the comparison is completed in step S102. When the comparison result shows that the current temperature drop rate is less than the temperature drop rate after the warning object is turned off, the processor calls the warning output module to generate a hot work and personnel departure warning event, and writes the event content, including at least the warning object identifier, warning trigger time, current temperature value, current temperature drop rate, temperature drop rate after the warning object is turned off, and personnel departure status, into the event record area.

[0063] The warning method can be either local or remote. For example, a local warning can drive a buzzer to sound at a preset rhythm and illuminate the indicator light associated with the corresponding stove burner; if the terminal has a display interface, it can also display the location and risk status of the corresponding warning object. A remote warning can send an alarm message to the user's mobile terminal, home gateway, or kitchen management platform via a wireless communication module. The message content includes the object number and the triggering reason, prompting the user to return to the scene to confirm the stove's status.

[0064] In another possible implementation, after the first warning is triggered, subsequent monitoring can continue. If the comparison results in several consecutive sampling processes still show that the current temperature drop rate is less than the temperature drop rate after the warning object is turned off, then the warning output is maintained. If personnel are subsequently detected to re-enter the warning range, or the current temperature drop rate recovers to a level not less than the temperature drop rate after the warning object is turned off, then the repeated sending of the warning is canceled or stopped.

[0065] For scenarios with multiple warning objects, the above judgment and warning output are performed independently for each warning object, and the specific object is specified in the warning message to ensure that the operator can locate the corresponding stove or pot. If multiple warning objects simultaneously meet the warning conditions, they can be merged into a composite warning message containing multiple object identifiers, or multiple object-level alarm records can be generated separately. If the current temperature drop rate is not less than the temperature drop rate after the warning object is turned off, the "warmth removal warning" is not executed. Instead, the current historical data is retained and the first temperature change time series is continued to be sampled and updated, entering the next round of monitoring.

[0066] The hot work evacuation warning method provided in this application executes the following processes in series: personnel status identification, temperature threshold judgment, temperature trend identification, and comparison of the current temperature drop rate with the temperature drop rate after the fire is turned off. It determines whether continuous heating characteristics still exist based on the temperature change process of the warning object. For warning objects that have been turned off but are still in the high-temperature residual heat stage, the temperature drop rate corresponding to their natural heat dissipation process is consistent with or close to the temperature drop rate after the fire is turned off, and continuous monitoring is maintained without triggering a hot work evacuation warning. For warning objects where personnel have left but heat input has not disappeared, even if the temperature curve shows a local decrease, its temperature drop rate is still less than the temperature drop rate after the fire is turned off, and a warning is output accordingly. This achieves the identification of the risk of leaving the kitchen unattended and improves the accuracy of the hot work evacuation warning.

[0067] In one possible implementation, determining whether the temperature drop rate of the warning object is less than the temperature drop rate of the warning object after it is turned off, based on a first temperature change time series, includes: determining the slope of the first temperature change time series as a first temperature change rate based on a linear regression estimation algorithm; if the absolute value of the first temperature change rate is less than a temperature change rate threshold, then determining whether the temperature drop rate of the warning object is less than the temperature drop rate of the warning object after it is turned off, wherein the temperature change rate threshold is dynamically determined based on the temperature drop rate of the warning object after it is turned off.

[0068] Specifically, the temperature sampling points in the first temperature change time series are first aligned in time and outliers are removed. Then, the sampling time is used as the independent variable and the temperature value as the dependent variable, which are input into a linear regression estimation algorithm. The slope is obtained by fitting the data using the linear regression estimation algorithm, and the slope is the first temperature change rate. A negative slope indicates an overall temperature decrease, and the smaller the absolute value, the slower the temperature decrease. The temperature change rate threshold can be obtained by statistically analyzing the temperature decay data of the warning object in historical heat-off scenarios, and dynamically corrected by combining the current cookware material, contact environment, or ventilation conditions, thus forming a temperature change rate threshold that matches the current object. If the absolute value of the first temperature change rate is less than the temperature change rate threshold, it indicates that the temperature decay characteristics are inconsistent with the natural cooling process after heat-off, and this can be used as a basis for subsequent warning judgments.

[0069] The hot work and unattended personnel warning method provided in this application quantifies the temperature change trend of the warning object into a calculable regression slope, and uses a dynamic threshold that is more consistent with the temperature drop rate characteristics of the warning object after the fire is turned off as the judgment benchmark, thereby improving the recognition accuracy of situations where personnel leave without turning off the fire.

[0070] In one possible implementation, the temperature change rate threshold is determined as follows: based on a first temperature change time series, the absolute value of the ratio of the temperature change value of the warning target to the temperature change time is determined as the second temperature change rate; the second temperature change rate is then compared with... The product of these is the temperature change rate threshold, where... This indicates the rate of temperature change of the warning target after it is turned off, over time. (Parameter) It is modeled using the natural exponential function and calibrated based on the temperature change process of the warning object after the fire is turned off.

[0071] Specifically, the temperature change rate threshold can be determined using the following formula:

[0072]

[0073] in, for Temperature change rate threshold at any given time The temperature change value of the target object under warning. is the length of the first temperature change time series.

[0074] Understandable The temperature change value within the observation period corresponding to the first temperature change time series can be determined by the difference between the first and last temperature sampling data. For temperature change sampling data with a fixed sampling interval, the sequence length can represent its temperature change time, that is... It is the ratio of the temperature change value of the warning object to the temperature change time.

[0075] The inventors of this application have discovered that when the stove or other warning device is completely shut off from the heat source and stops continuous heating, the overall temperature change rate of the stove exhibits a clear evolution pattern of being fast at first and then slowing down. In the initial stage after the heat is turned off, the temperature difference between the stove and the indoor environment is large, and heat is rapidly dissipated outward through three pathways: heat conduction, heat convection, and heat radiation. The temperature drop per unit time is significant, and the temperature change rate is at a high level. As the temperature of the stove itself continues to decrease, the temperature difference between it and the surrounding air and the countertop continues to narrow. The driving force for heat transfer outward gradually weakens, and the amount of heat lost per unit time decreases accordingly. The temperature drop narrows continuously, and the temperature change rate slows down until the stove temperature approaches the ambient temperature, and the temperature change rate eventually approaches zero.

[0076] This pattern of change conforms to the pattern of an exponential function; therefore, it can be used... This indicates the rate of temperature change of the warning target after it is turned off, over time. (Parameter) It is modeled using the natural exponential function and calibrated based on the temperature change process of the target object after it is turned off. The second temperature change rate can be regarded as a rough estimate of the temperature change rate over the observation period. Multiplying it by the second temperature change rate can be seen as a correction to the second temperature change rate, dynamically determining the theoretical temperature change rate threshold.

[0077] This method ensures that the temperature change rate threshold not only reflects the intensity of local changes in the current temperature sequence, but also incorporates the time-varying pattern of natural cooling after shutdown. Therefore, it can dynamically adjust the comparison benchmark as the heat dissipation process progresses, making the judgment of the temperature drop rate consistent with the actual thermal decay process after shutdown.

[0078] The hot work and unattended personnel warning method provided in this application embodiment can change the temperature change rate threshold exponentially over time. The threshold benchmark is no longer fixed at a static value, but matches the actual heat dissipation characteristics of the warning object after the fire is turned off, thereby improving the adaptability and recognition accuracy of the temperature drop rate judgment.

[0079] In one possible implementation, the method further includes: in response to calibration conditions that satisfy the rate of temperature change pattern, acquiring a second temperature change time series of the warning target; and using a natural exponential function as a model, fitting parameters based on the second temperature change time series. .

[0080] Specifically, calibration conditions may include: the detected object has been turned off and there are no obstructions or other factors interfering with the cooling and heat dissipation of the object within the detection range.

[0081] After meeting the calibration conditions, the temperature of the warning target is continuously sampled using a temperature measurement device. The sampled data is then denoised and time-series aligned to obtain a second temperature change time series. Subsequently, the natural exponential function is used as the fitting model to characterize the temperature change process as a function that decays exponentially with time. The parameters are then solved using least squares fitting or nonlinear regression. This ensures that the error between the fitted curve and the second temperature change time series meets a set threshold. Parameters This parameter is used to characterize the temperature decay of the object after the heat is turned off. A larger parameter value indicates a faster temperature decay, while a smaller parameter value indicates a slower cooling process. In practical applications, this parameter can also be updated based on different cookware materials, stove types, and environmental heat dissipation conditions; this application does not limit this.

[0082] When issuing a hot work hazard warning, first obtain parameters that reflect the temperature decay characteristics after the flame is turned off. This information is then used as the basis for dynamically determining the subsequent temperature change rate threshold. By parameterizing the historical cooling process, the temperature change rate threshold can be matched with the actual heat dissipation characteristics of the target object.

[0083] The hot work and unattended personnel warning method provided in this application embodiment has the following parameters. Instead of relying on fixed empirical values, it is obtained by fitting the temperature change process of the warning object after the fire is turned off. Therefore, it can more accurately characterize the natural cooling law after the fire is turned off in different scenarios and provide dynamic threshold support for subsequent judgment of leaving people without turning off the fire.

[0084] In one possible implementation, the linear regression estimation algorithm includes a least-squares estimation algorithm for the linear regression slope, wherein the first rate of temperature change is determined according to the following formula:

[0085]

[0086] in, Within the warning range The first temperature change rate corresponding to each warning target The length of the first temperature change time series. For the first The first temperature change time series of the warning target Data points.

[0087] In the calculation of the linear regression slope, the least squares estimation algorithm is used to fit the first temperature change time series, so that the slope result does not depend on the instantaneous fluctuation of a single temperature point, but rather integrates the change characteristics of multiple sampling points. For different warning targets, corresponding first temperature change time series can be established separately, and solved independently using the same formula. This ensures that the temperature change trends of all warning targets can be consistently represented. If the number of sampling points for a warning target changes, then... With the update, the calculation module only needs to substitute the new sequence length into the formula to complete the update, without changing the overall solution logic.

[0088] The hot work evacuation warning method provided in this application employs a least-squares estimation algorithm based on the slope of a linear regression. This algorithm quantifies the temperature change process of the warning target as a first temperature change rate. Furthermore, when personnel have left the area and the temperature is trending downwards, the system can further distinguish between actual cooling and continuous heating based on this change rate. Therefore, the judgment of the temperature change trend no longer relies solely on the instantaneous temperature value but on the regression results of the entire time series, thereby improving the accuracy of identifying the risk of leaving a hot work evacuated.

[0089] In one possible implementation, obtaining a first temperature change time series of a warning object within the warning range includes: sampling the temperature of the warning object at a preset sampling interval to obtain a third temperature change time series; preprocessing the third temperature change time series to obtain a first temperature change time series, wherein the preprocessing includes repairing jump values ​​in the third temperature change time series.

[0090] In practical implementation, temperature sensors can be deployed on or near the surface of the object to be warned. Temperature values ​​are continuously read at preset sampling intervals, and each reading result is written to a cache or storage unit in chronological order to form a third temperature change time series. The sampling interval needs to be set to ensure that the temperature change trajectory is reflected even when the temperature changes slowly, while avoiding excessively dense sampling that would cause redundant data. First, the third temperature change time series is time-aligned and missing data is compensated. Then, outlier identification is performed on the continuous data. After identifying points where the temperature change is inconsistent with the adjacent temperature changes, the outlier point is replaced with the interpolation result or local smoothing result of the adjacent normal point, thereby completing the repair of abrupt values ​​and obtaining the first temperature change time series. The repaired series can reduce the impact of single sampling jitter on the temperature trend judgment and provide a stable input for subsequent hot work and evacuation warnings based on the temperature drop rate.

[0091] The hot work and personnel leaving the site early warning method provided in this application embodiment can promptly repair abnormal jumps in the third temperature change time series, enhance the continuity and consistency of the series, and make subsequent judgments on temperature change trends, temperature drop rates, and cooling characteristics after the fire is turned off more reliable, thereby improving the accuracy of temperature status identification of the early warning object.

[0092] In one possible implementation, obtaining personnel information within the warning range includes:

[0093] A series of single-stage real-time target detection algorithms are used to detect visible light data within the warning range in real time, thereby obtaining information on personnel within the warning range.

[0094] Specifically, visible light data within the warning range is first collected by a front-end camera device, then preprocessed before being input into a single-stage real-time target detection algorithm model for real-time detection. The model determines the presence of personnel based on the output target confidence and category results, and transmits the detected personnel information to the warning judgment module. This personnel information, linked with the temperature change information of the warning target, can be used to determine whether the warning range is uninhabited, and provides a basis for subsequent temperature decline trend analysis and open flame / unmanned movement warnings.

[0095] The hot work and personnel evacuation warning method provided in this application embodiment can acquire personnel information in real time through visible light images and output it stably in the form of target detection results. This enables the warning system to promptly identify whether there are personnel within the warning range, providing reliable input for judging temperature changes in evacuation scenarios, thereby improving the recognition accuracy of hot work and personnel evacuation warnings.

[0096] Figure 2 This is a schematic diagram of the structure of the hot work and unattended personnel warning device provided in the embodiments of this application, as shown below. Figure 2 As shown, the hot work and unattended personnel warning device 20 provided in this embodiment includes:

[0097] The acquisition module 201 is used to acquire personnel information within the warning range and the first temperature change time series of the warning objects;

[0098] Processing module 202 is used to determine whether the temperature drop rate of the warning object is less than the temperature drop rate of the warning object after the fire is turned off, if there is a point in the first temperature change time series that exceeds the warning temperature threshold, there are no people in the warning range, and the temperature of the warning object is decreasing.

[0099] The early warning module 203 is used to issue an early warning for leaving a person unattended while in use if the rate of temperature drop of the object being warned is less than the rate of temperature drop after the object is turned off.

[0100] In one possible implementation, the processing module 202 is specifically used for:

[0101] Based on the linear regression estimation algorithm, the slope of the first temperature change time series is determined to be the first temperature change rate;

[0102] If the absolute value of the first temperature change rate is less than the temperature change rate threshold, then it is determined whether the temperature drop rate of the warning object is less than the temperature drop rate of the warning object after it is turned off. The temperature change rate threshold is dynamically determined based on the temperature drop rate of the warning object after it is turned off.

[0103] In one possible implementation, the processing module 202 is further configured to:

[0104] Based on the first temperature change time series, the absolute value of the ratio of the temperature change value of the warning object to the temperature change time is determined as the second temperature change rate;

[0105] Determine the second rate of temperature change and The product of these is the temperature change rate threshold, where... This indicates the rate of temperature change of the warning target after it is turned off, over time. (Parameter) It is modeled using the natural exponential function and calibrated based on the temperature change process of the warning object after the fire is turned off.

[0106] In one possible implementation, the processing module 202 is further configured to:

[0107] In response to the calibration conditions that meet the changing law of temperature change rate, the second temperature change time series of the warning object is collected;

[0108] Using the natural exponential function as a model, parameters were obtained by fitting the data based on the second temperature change time series. .

[0109] In one possible implementation, the linear regression estimation algorithm includes a least-squares estimation algorithm for the linear regression slope, and the processing module 202 is further configured to determine the first temperature change rate according to the following formula:

[0110]

[0111] in, Within the warning range The first temperature change rate corresponding to each warning target The length of the first temperature change time series. For the first The first temperature change time series of the warning target Data points.

[0112] In one possible implementation, the acquisition module 201 is specifically used for:

[0113] The temperature of the warning target is sampled at a preset sampling interval to obtain a third temperature change time series;

[0114] The third temperature change time series is preprocessed to obtain the first temperature change time series. The preprocessing includes repairing the jump values ​​in the third temperature change time series.

[0115] In one possible implementation, the acquisition module 201 is specifically used for:

[0116] A series of single-stage real-time target detection algorithms are used to detect visible light data within the warning range in real time, thereby obtaining information on personnel within the warning range.

[0117] The hot work and unattended personnel warning device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0118] Figure 3 This is a schematic diagram of the structure of a hot work hazard warning device provided in an embodiment of this application. Figure 3As shown, the hot work evacuation warning device 30 provided in this embodiment includes at least one processor 301 and a memory 302. Optionally, the hot work evacuation warning device 30 also includes a communication interface 303. The processor 301, memory 302, and communication interface 303 are connected via a communication bus 304.

[0119] In a specific implementation, at least one processor 301 executes computer execution instructions stored in memory 302, causing at least one processor 301 to perform the above-described method.

[0120] The specific implementation process of processor 301 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0121] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0122] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0123] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0124] This application also provides a computer program product, including a computer program that, when executed, implements the above-described method.

[0125] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed, implement the above-described method.

[0126] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0127] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0128] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0129] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0131] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0132] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0133] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for fire ignition away from person early warning, characterized in that, include: Obtain information on personnel within the warning area and the first temperature change time series of the warning targets; If there is a point in the first temperature change time series that exceeds the warning temperature threshold, there are no people in the warning range, and the temperature of the warning object is decreasing, determine whether the temperature decrease rate of the warning object is less than the temperature decrease rate of the warning object after the fire is turned off, based on the first temperature change time series. If the rate of temperature drop of the warning object is less than the rate of temperature drop after the fire is turned off, a warning will be issued for leaving the person unattended while the fire is still burning.

2. The method of claim 1, wherein, The step of determining whether the temperature drop rate of the warning object is less than the temperature drop rate of the warning object after it is turned off, based on the first temperature change time series, includes: Based on the linear regression estimation algorithm, the slope of the first temperature change time series is determined to be the first temperature change rate; If the absolute value of the first temperature change rate is less than the temperature change rate threshold, then it is determined whether the temperature drop rate of the warning object is less than the temperature drop rate of the warning object after it is turned off, wherein the temperature change rate threshold is dynamically determined based on the temperature drop rate of the warning object after it is turned off.

3. The method of claim 2, wherein, The temperature change rate threshold is determined in the following way: Based on the first temperature change time series, the absolute value of the ratio of the temperature change value of the warning object to the temperature change time is determined as the second temperature change rate; determining a product of the second temperature change rate and is the temperature change rate threshold, wherein, represents a change rule of the temperature change rate of the pre-warning object after the fire is closed over time, and parameters is calibrated according to a temperature change process of the pre-warning object after the fire is closed, taking a natural exponential function as a model.

4. The method for early warning of hot work leaving personnel as described in claim 3, characterized in that, Also includes: In response to the calibration conditions that satisfy the change law of temperature change rate, the second temperature change time series of the warning object is collected; Using the natural exponential function as a model, parameters are obtained by fitting the second temperature change time series. .

5. The method for early warning of hot work leaving personnel unattended according to any one of claims 2 to 4, characterized in that, The linear regression estimation algorithm includes a least-squares estimation algorithm for the linear regression slope, and the first temperature change rate is determined according to the following formula: in, Within the warning range The first temperature change rate corresponding to each warning target The length of the first temperature change time series. For the first The first temperature change time series of the warning target Data points.

6. The method for early warning of hot work leaving personnel as described in any one of claims 1 to 4, characterized in that, Obtain the first temperature change time series of the warning objects within the warning range, including: The temperature of the warning object is sampled at a preset sampling interval to obtain a third temperature change time series; The third temperature change time series is preprocessed to obtain the first temperature change time series. The preprocessing includes repairing jump values ​​in the third temperature change time series.

7. The method for early warning of hot work leaving personnel as described in any one of claims 1 to 4, characterized in that, Obtain information on personnel within the warning area, including: A series of single-stage real-time target detection algorithms are used to detect visible light data within the warning range in real time, thereby obtaining personnel information within the warning range.

8. A hot work and unattended personnel early warning device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed, implements the method according to any one of claims 1 to 7.

Images