Method for flow prediction of a gas meter and related device

Abstract

The application provides a flow prediction method and related device of a gas meter, which is used for combining the actual signal feedback of the gas meter to realize the prediction of the gas flow. In the method, in response to a flow prediction instruction, the current gas flow is determined based on the current voltage of a target gas meter; the gas feature data representing the flow change trend is determined based on the current gas flow and the historical voltage of the target gas meter in a historical period; and the gas predicted flow in a preset period is determined based on the current gas flow and the gas feature data.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and device for predicting the flow rate of a gas meter. Background Technology

[0002] With the increasing demand for safety and service experience in intelligent gas systems, simply detecting past gas flow is no longer sufficient to meet higher-level intelligent requirements. Intelligent functions such as abnormal gas usage detection and gas leak warning require advance estimation of future gas flow changes to enable risk prediction or proactive intervention.

[0003] Current smart gas meters generally use microelectromechanical systems (MEMS) sensors as flow detection units. They collect the voltage signal generated when gas flows through the sensing element and analyze the user's gas flow in real time based on the pre-calibrated voltage-flow conversion relationship.

[0004] While this method of calculating gas flow based on the current voltage signal can accurately capture real-time flow changes during gas usage, it cannot predict future changes in gas flow. Therefore, how to predict gas flow is a pressing issue that needs to be addressed. Summary of the Invention

[0005] This application provides a gas meter flow prediction method and related device, which is used to predict gas flow by combining the actual signal feedback of the gas meter.

[0006] In a first aspect, this application provides a method for predicting the flow rate of a gas meter, comprising: in response to a flow prediction instruction, determining the current gas flow rate based on the current voltage of a target gas meter; determining gas characteristic data characterizing the flow rate change trend based on the current gas flow rate and the historical voltage of the target gas meter in a historical period; and determining the predicted gas flow rate within a preset period based on the current gas flow rate and the gas characteristic data.

[0007] In some embodiments, the target gas meter has a first conversion relationship between voltage and gas flow rate; determining the current gas flow rate based on the current voltage of the target gas meter includes: determining the initial gas flow rate corresponding to the current voltage based on the first conversion relationship; and determining the current gas flow rate based on the current temperature and the initial gas flow rate.

[0008] In some embodiments, the first conversion relationship is calibrated at a preset temperature; determining the current gas flow rate based on the current temperature and the initial gas flow rate includes: determining the temperature deviation between the current temperature and the preset temperature; and correcting the initial gas flow rate based on a pre-calibrated temperature influence factor and the temperature deviation to obtain the current gas flow rate.

[0009] In some embodiments, determining gas characteristic data characterizing the flow rate change trend based on the current gas flow rate and the historical voltage of the target gas meter within a historical period includes: determining the historical voltage change rate based on the acquisition time corresponding to each historical voltage; determining the historical voltage fluctuation amplitude based on the standard deviation of each historical voltage; determining the target voltage corresponding to the current gas flow rate based on the first conversion relationship; and determining the gas characteristic data based on the historical voltage change rate, the historical voltage fluctuation amplitude, and the ratio of the target voltage to the current gas flow rate.

[0010] In some embodiments, determining the predicted gas flow rate within a preset time period based on the current gas flow rate and the gas characteristic data includes: dividing the preset time period into multiple sub-time periods; wherein each sub-time period has a corresponding time influence factor; for each sub-time period, determining the initial predicted flow rate corresponding to the sub-time period based on the time influence factor corresponding to the sub-time period, the current gas flow rate, and the gas characteristic data; and determining the predicted gas flow rate within the preset time period based on the initial predicted flow rate corresponding to each sub-time period.

[0011] In some embodiments, the method further includes: determining the target gas flow rate corresponding to each sub-time period based on the voltage generated by the target gas meter during each sub-time period; determining the flow prediction deviation corresponding to each sub-time period based on the target gas flow rate and the initial predicted flow rate; and updating the time influence factor based on the flow prediction deviation.

[0012] In some embodiments, before updating the time influence factor based on the flow prediction deviation, the method further includes: determining preset parameter update conditions; wherein the parameter update conditions include any or a combination of the following conditions: the total prediction deviation of the flow prediction deviation corresponding to each sub-time period exceeds a first deviation threshold; the number of abnormal sub-time periods exceeds a quantity threshold; the abnormal sub-time period is the sub-time period in each sub-time period where the flow prediction deviation exceeds a second deviation threshold; the flow change rate deviation between the predicted flow change rate and the target flow change rate exceeds a change rate threshold; the predicted flow change rate is determined based on the initial predicted flow and the number of sub-time periods for each sub-time period; the target flow change rate is determined based on the target gas flow for each sub-time period and the number of sub-time periods.

[0013] Secondly, this application provides a flow prediction device for a gas meter, comprising: a data acquisition unit configured to: determine the current gas flow rate based on the current voltage of a target gas meter in response to a flow prediction instruction; a feature acquisition unit configured to: determine gas feature data characterizing the flow rate change trend based on the current gas flow rate and the historical voltage of the target gas meter in a historical period; and a flow prediction unit configured to: determine the predicted gas flow rate within a preset period based on the current gas flow rate and the gas feature data.

[0014] In some embodiments, the target gas meter has a first conversion relationship between voltage and gas flow rate; the data acquisition unit is specifically configured to: determine the initial gas flow rate corresponding to the current voltage based on the first conversion relationship; and determine the current gas flow rate based on the current temperature and the initial gas flow rate.

[0015] In some embodiments, the first conversion relationship is calibrated at a preset temperature; the data acquisition unit is specifically configured to: determine the temperature deviation between the current temperature and the preset temperature; and correct the initial gas flow rate based on a pre-calibrated temperature influence factor and the temperature deviation to obtain the current gas flow rate.

[0016] In some embodiments, the gas characteristic data characterizing the flow rate change trend is determined based on the current gas flow rate and the historical voltage of the target gas meter within a historical period. Specifically, the characteristic acquisition unit is configured to: determine the historical voltage change rate based on the acquisition time corresponding to each historical voltage; determine the historical voltage fluctuation amplitude based on the standard deviation of each historical voltage; determine the target voltage corresponding to the current gas flow rate based on the first conversion relationship; and determine the gas characteristic data based on the historical voltage change rate, the historical voltage fluctuation amplitude, and the ratio of the target voltage to the current gas flow rate.

[0017] In some embodiments, the process of determining the predicted gas flow rate within a preset time period based on the current gas flow rate and the gas characteristic data is performed. Specifically, the flow prediction unit is configured to: divide the preset time period into multiple sub-time periods; wherein each sub-time period has a corresponding time influence factor; for each sub-time period, determine the initial predicted flow rate corresponding to the sub-time period based on the time influence factor corresponding to the sub-time period, the current gas flow rate, and the gas characteristic data; and determine the predicted gas flow rate within the preset time period based on the initial predicted flow rate corresponding to each sub-time period.

[0018] In some embodiments, the flow prediction unit is further configured to: determine the target gas flow rate corresponding to each sub-period based on the voltage generated by the target gas meter in each sub-period; determine the flow prediction deviation corresponding to each sub-period based on the target gas flow rate and the initial predicted flow rate; and update the time influence factor based on the flow prediction deviation.

[0019] In some embodiments, before performing the update of the time influence factor based on the flow prediction deviation, the flow prediction unit is further configured to: determine a preset parameter update condition; wherein the parameter update condition includes any or a combination of the following conditions: the total prediction deviation of the flow prediction deviation corresponding to each sub-time period exceeds a first deviation threshold; the number of abnormal sub-time periods exceeds a quantity threshold; the abnormal sub-time period is the sub-time period in each sub-time period where the flow prediction deviation exceeds a second deviation threshold; the flow change rate deviation between the predicted flow change rate and the target flow change rate exceeds a change rate threshold; the predicted flow change rate is determined based on the initial predicted flow and the number of sub-time periods for each sub-time period; the target flow change rate is determined based on the target gas flow for each sub-time period and the number of sub-time periods.

[0020] Thirdly, this application provides an electronic device, comprising: a memory for storing program instructions; and a processor for calling the program instructions stored in the memory and executing the steps of the method described in any one of the first aspects according to the obtained program instructions.

[0021] Fourthly, this application provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a computer, cause the computer to perform the method described in any one of the first aspects.

[0022] Fifthly, this application provides a computer program product comprising: computer program code, which, when run on a computer, causes the computer to perform the method described in any of the first aspects.

[0023] In this embodiment, in response to a flow prediction instruction, the current gas flow rate is determined based on the current voltage of the target gas meter. Subsequently, gas characteristic data is determined by combining the current gas flow rate with the historical voltage of the target gas meter over a historical period. Since this gas characteristic data is constructed based on the current gas flow rate and the historical voltage signal of the target gas meter, it reflects the recent trend in gas flow rate. Based on this, the gas flow rate for a preset period can be predicted using the current gas flow rate and the gas characteristic data, resulting in a predicted gas flow rate. This prediction process does not require additional detection devices; it achieves accurate gas flow rate prediction solely based on the actual signal feedback from the target gas meter, offering advantages such as low deployment cost and high versatility. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. The 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.

[0025] Figure 1 The overall flowchart of the gas meter flow prediction method provided in the embodiments of this application is shown.

[0026] Figure 2 A flowchart illustrating the process of obtaining predicted gas flow rate as provided in an embodiment of this application.

[0027] Figure 3 This is a schematic diagram of the parameter update process provided in the embodiments of this application.

[0028] Figure 4 This is a structural block diagram of a gas meter flow prediction device provided in an embodiment of this application.

[0029] Figure 5 A structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0030] The technical solutions in the embodiments of this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " will mean "or", for example, A / B can mean A or B; "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0031] In the description of the embodiments of this application, unless otherwise stated, the term "multiple" refers to two or more, and other quantifiers are similarly understood. The preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0032] To further illustrate the technical solutions provided in the embodiments of this application, a detailed description is provided below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of this application provide method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on conventional or non-inventive effort. For steps that do not logically have a necessary causal relationship, the execution order of these steps is not limited to the execution order provided in the embodiments of this application. In actual processing or when the control device executes the method, it may be executed sequentially or in parallel according to the method shown in the embodiments or drawings.

[0033] As mentioned earlier, with the increasing demand for safety protection and service experience of intelligent gas systems, intelligent functions such as abnormal gas usage identification and gas leak warning need to estimate the changes in gas flow in the future and make risk prediction or proactive intervention accordingly.

[0034] Current MEMS gas meters primarily collect the voltage signal generated when gas flows through a sensing element and then analyze the user's gas flow rate in real time based on a pre-calibrated voltage-flow conversion relationship. While this method can accurately capture real-time flow changes during gas usage, it cannot predict future changes in gas flow rate.

[0035] In related technologies, gas flow is often predicted by adding additional detection devices such as pressure sensors inside the gas meter or on the pipeline, combined with fluid dynamics models. However, this method not only requires the introduction of additional detection devices, but also the establishment of customized mechanical models for different pipeline materials, sizes, and installation conditions, resulting in high deployment costs and complexity.

[0036] Some manufacturers have attempted to use data-driven machine learning methods to build predictive models of gas flow based on historical gas usage data from users under different weather conditions and times of day. However, the inference performance of these models is strongly correlated with sample quality, resulting in high sample acquisition costs and long processing times. Moreover, different users may have significantly different gas usage habits and use different gas appliances, making it difficult to reuse the models across different users and resulting in poor universality.

[0037] In view of this, the inventive concept of this application is as follows: In response to a flow prediction instruction, the current gas flow rate is determined based on the current voltage of the target gas meter. Subsequently, gas characteristic data is determined by combining the current gas flow rate with the historical voltage of the target gas meter within a historical period. Since this gas characteristic data is constructed based on the current gas flow rate and the historical voltage signal of the target gas meter, it can reflect the recent trend of gas flow rate changes. Based on this, the gas flow rate for a preset period can be predicted based on the current gas flow rate and the gas characteristic data to obtain the predicted gas flow rate. The above prediction process does not require the introduction of additional detection devices; it can achieve accurate prediction of gas flow rate solely based on the actual signal feedback result of the target gas meter, and has the advantages of low deployment cost and high versatility.

[0038] After introducing the inventive concept of the embodiments of this application, the flow prediction method for a gas meter provided by the embodiments of this application will be described in detail below. Figure 1 As shown, the method includes the following steps: S11, in response to the flow prediction indication, determine the current gas flow rate based on the current voltage of the target gas meter; The traffic prediction indicator in this application can be set based on actual business needs. For example, it can be triggered actively by users or automatically triggered periodically. This application does not limit this.

[0039] The target gas meter in this application embodiment is a gas meter with a built-in MEMS sensor, also known as a MEMS gas meter.

[0040] As mentioned earlier, MEMS gas meters collect the voltage signal generated when gas flows through the sensing element and analyze the user's gas flow in real time based on the pre-calibrated voltage-flow conversion relationship.

[0041] Specifically, before leaving the factory, MEMS gas meters need to be calibrated using a standard flow meter to establish the correspondence between voltage signals and actual volumetric flow rates under different flow conditions, and the pre-calibrated voltage-flow curve is stored in the meter. During use, MEMS gas meters typically acquire voltage signals at a calibrated frequency (e.g., 10~15Hz) and convert the voltage signals into corresponding gas flow rates based on the voltage-flow conversion relationship.

[0042] When performing step S11, the current voltage can be determined based on the instantaneous voltage signal collected by the target gas meter when it receives the flow prediction instruction. Subsequently, according to the pre-calibrated first conversion relationship between voltage and gas flow (i.e., the voltage-flow relationship curve), the current voltage is converted into the corresponding gas flow to obtain the current gas flow of the target gas meter.

[0043] Furthermore, considering that changes in ambient temperature may affect the thermal conductivity of MEMS sensors, thereby interfering with the voltage-flow conversion results, the gas flow rate obtained from the above conversion can be used as the initial gas flow rate. Subsequently, based on the current temperature and the initial gas flow rate, the current gas flow rate of the target gas meter can be determined.

[0044] Specifically, the voltage-flow relationship curve is usually calibrated at a standard temperature (e.g., 20°C). When the actual ambient temperature deviates from this preset temperature, changes in gas density and thermal conductivity will cause a shift in the output voltage signal at the same flow rate, thus affecting the accuracy of gas flow rate analysis.

[0045] To improve the accuracy of gas flow rate acquisition, in some embodiments, the temperature deviation between the current temperature and a preset temperature of the curve can be predetermined. Subsequently, the initial gas flow rate is corrected based on this temperature deviation and a pre-calibrated temperature influence factor to obtain the current gas flow rate of the target gas meter.

[0046] Specifically, in the factory calibration stage of the target gas meter, in addition to establishing the aforementioned voltage-flow relationship curve, the target gas meter can also be placed in a constant temperature environment, and multiple preset temperature points can be set sequentially (e.g., in increments of 10°C, 15°C, 20°C, 25°C, etc.). The same standard volumetric flow rate (e.g., 2 m³ / h) is introduced at each temperature point. After each temperature point stabilizes, the voltage signal output by the MEMS sensor is recorded, and the corresponding gas flow rate is analyzed based on the pre-calibrated voltage-flow relationship curve.

[0047] Since the actual inflow rate is constant, the relative deviation between the analyzed flow rate and the standard flow rate is caused by temperature changes. Based on this, for each preset temperature point, the ratio of this relative deviation to the temperature difference between that temperature point and the preset temperature (e.g., 20℃) is calculated to obtain the local temperature influence coefficient at that temperature point. Then, linear fitting or averaging of the local temperature influence coefficients of multiple temperature points is performed to finally determine a unified temperature influence factor.

[0048] Based on this, the current gas flow rate of the target gas meter can be determined using the following formula (1): Q T =Q0×(1+KT×△T)(1) Among them, Q T Q0 is the current gas flow rate, Q0 is the initial gas flow rate, ΔT is the temperature deviation, and KT is the calibrated temperature influence factor, for example, KT=0.003 / ℃.

[0049] It should be noted that the target gas meter typically has a built-in temperature sensor, and the current temperature is the instantaneous ambient temperature signal collected by the target gas meter when it receives the flow prediction instruction. To improve signal reliability, in this embodiment, after acquiring the current voltage and temperature, wavelet denoising processing is performed on the voltage signal output by the MEMS sensor to suppress high-frequency noise, and a 3D model is employed. The criteria involve outlier detection and rejection of the temperature signal to eliminate temperature jumps caused by transient interference. The voltage signal, after the above processing, is used to calculate the initial gas flow rate, while the processed temperature signal is used to determine the temperature deviation and perform temperature compensation correction.

[0050] In the above process, the temperature deviation is obtained by comparing the current temperature with the preset temperature of the voltage-flow relationship curve, and the initial gas flow is compensated and corrected by combining the predetermined temperature influence factor, thereby effectively offsetting the sensor output drift caused by changes in ambient temperature, and accurately obtaining the current gas flow of the target gas meter.

[0051] S12, Based on the current gas flow rate and the historical voltage of the target gas meter during the historical period, determine the gas characteristic data that characterizes the flow rate change trend; To improve the accuracy of gas flow prediction, this application introduces multi-dimensional features based on historical voltage to more comprehensively depict the flow change trend of users' short-term gas consumption.

[0052] The historical time period in this application embodiment can be set based on actual needs. For example, 7 to 10 seconds before the target gas meter receives the flow prediction instruction can be used as the historical time period.

[0053] The gas characteristic data in this application embodiment includes: historical voltage change rate V, historical voltage fluctuation amplitude. And the slope K of the curve corresponding to the current gas flow rate.

[0054] To facilitate understanding, the following explains how to obtain the gas characteristic data of the embodiments of this application: In some embodiments, the historical voltage change rate V can be determined based on the acquisition time corresponding to each historical voltage.

[0055] Taking a sampling frequency of 10 Hz as an example, the sampling time interval of each historical voltage is 0.1 seconds. By calculating the difference between adjacent historical voltages and dividing it by the time interval, multiple instantaneous voltage changes are obtained. Then, by averaging or weighted averaging all instantaneous voltage changes within the historical period, the historical voltage change rate V can be obtained.

[0056] Since the voltage signal of a MEMS gas meter has a monotonic relationship with gas flow, a rise or fall in voltage directly corresponds to an increase or decrease in flow. Therefore, the historical voltage change rate V can reflect the overall direction and rate of change in gas flow in the recent period. Thus, including this parameter as a component of gas characteristic data helps identify the user's current dynamic behavior stages, such as starting, stopping, increasing, or decreasing gas usage, providing a basis for subsequent flow forecasting of gas consumption trends.

[0057] In some embodiments, the historical voltage fluctuation amplitude can be determined based on the standard deviation of each historical voltage. .

[0058] In practice, the standard deviation of each historical voltage can be calculated and used as the historical voltage fluctuation range. .

[0059] Because there is a conversion relationship between the voltage signal and gas flow rate in MEMS gas meters, when a user uses gas at a relatively constant flow rate, the voltage signal output by the sensing element changes only slightly, and its standard deviation is small. However, when the user engages in intermittent start-stop or frequent adjustments during gas usage (such as stove ignition or alternating operation of multiple gas-using appliances), the voltage signal will fluctuate significantly, and its standard deviation will increase substantially. Therefore, the historical voltage fluctuation amplitude... It can reflect the intensity and dynamic complexity of recent gas flow fluctuations. Therefore, incorporating this parameter as a component of gas characteristic data can effectively characterize the non-steady-state characteristics of gas consumption behavior, providing a basis for subsequent flow forecasting on the stability of gas consumption.

[0060] In some embodiments, the target voltage corresponding to the current gas flow rate can be determined based on the voltage-flow rate curve. The ratio of the target voltage to the current gas flow rate is the slope K of the curve corresponding to the current gas flow rate.

[0061] Because the voltage-flow relationship curve of a MEMS gas meter is typically non-linear, the voltage change caused by the same flow rate change varies across different gas flow rate ranges. This voltage response capability is known as the sensor's sensitivity. For example, in a low flow rate range, a unit flow rate change may cause a large voltage change (high sensitivity); while in a high flow rate range, the same flow rate change causes a smaller voltage change (low sensitivity). The slope K of the curve is a quantitative representation of this sensitivity at the current gas flow rate.

[0062] Therefore, incorporating this parameter as a component of gas characteristic data can accurately reflect the response capability of the voltage signal to changes in flow rate within the current flow range during the prediction process, providing a basis for subsequent flow rate prediction on the sensitivity of gas consumption changes at the current flow rate level.

[0063] S13, Based on the current gas flow rate and the gas characteristic data, determine the predicted gas flow rate within a preset time period.

[0064] The preset time period in this application embodiment can be set based on actual business needs. For example, in tasks such as abnormal gas consumption identification and gas leak early warning, a rapid response to the gas consumption status is required. Therefore, the preset time period can be set to a shorter time window to capture sudden changes in flow or unexpected gas consumption behavior in a timely manner. In other cases, in tasks such as daily gas consumption estimation, peak and valley gas consumption analysis, or user profile construction, the focus is on the user's gas consumption patterns over a longer period of time. Therefore, the preset time period can be set to a longer time window to more accurately reflect the user's continuous gas consumption trend.

[0065] In this embodiment, a preset time period can be divided into multiple sub-time periods, and the predicted gas flow rate within the preset time period can be determined based on the time influence factor, current gas flow rate, and gas characteristic data corresponding to each sub-time period. Specifically, as follows... Figure 2 As shown, it includes the following steps: S131, the preset time period is divided into multiple sub-time periods; each sub-time period has a corresponding time influence factor; the time influence factor corresponding to each sub-time period is negatively correlated with the time interval between each sub-time period and the current time. To improve prediction accuracy, this application embodiment pre-configures various preset time periods of different lengths for different business needs before leaving the factory, and calibrates the time influence factor for each preset time period.

[0066] Specifically, in scenarios requiring rapid response, such as abnormal gas consumption identification and gas leak warning, the preset time period is set to a relatively short time window (e.g., 10 seconds). In scenarios focusing on long-term trends, such as daily gas consumption estimation, peak-valley gas consumption analysis, or user profile construction, a longer preset time period (e.g., tens of minutes) is used. For each preset time period length, it is divided into a fixed number of sub-time periods (e.g., 10 sub-time periods) to support structured modeling of the time dimension within the prediction window.

[0067] Based on this, for each preset time period, a corresponding time influence factor is set for each of its sub-time periods. This time influence factor represents the contribution weight of each sub-time period to future traffic forecasting, reflecting that the traffic status of the sub-time period closer to the current time is more affected by the current operating conditions, while the weight should decrease accordingly as uncertainty increases over time.

[0068] In practice, in a standard laboratory environment, mainstream gas appliances such as built-in stoves, countertop stoves, forced draft water heaters, and wall-hung boilers are used to simulate typical dynamic gas usage conditions such as rapid ignition, stable low flame combustion, firepower adjustment, and sudden shutdown. Simultaneously, the voltage signal output by the MEMS sensor and the actual gas flow measured by the standard flow device are collected to form a calibration dataset with multiple scenarios and time alignment.

[0069] Subsequently, based on the current gas flow rate and gas characteristic data, a weighted superposition prediction expression is constructed: the local predicted values ​​for each sub-period are generated by a unified mapping relationship, multiplied by their corresponding time influence factors, and then summed to obtain the overall prediction result. Using the cumulative deviation (e.g., mean square error) between this prediction result and the actual gas flow rate as the optimization objective, and combining physical constraints such as non-negative weights, monotonically decreasing over time, and normalized summation, offline numerical optimization methods (e.g., grid search or gradient descent) are employed to configure the time influence factors for each sub-period. The factor combination determined through this process naturally exhibits a decay characteristic of high near-term and low far-term, and can effectively suppress prediction overshoot or lag under various dynamic operating conditions.

[0070] The target gas meter has this set of time influence factors as default parameters fixed in the firmware at the factory. When executing step S131, it directly calls the time influence factors corresponding to each sub-period for weighted processing, thereby improving the accuracy and adaptability of gas flow prediction.

[0071] S132, For each sub-period, determine the initial predicted flow rate corresponding to that sub-period based on the time influence factor, current gas flow rate, and gas characteristic data corresponding to that sub-period; As mentioned above, the gas characteristic data in this application embodiment includes: historical voltage change rate V, historical voltage fluctuation amplitude. And the slope K of the curve corresponding to the current gas flow rate.

[0072] In practice, the three characteristics mentioned above can be normalized and then weighted and fused to generate a comprehensive index that reflects the dynamic characteristics of gas consumption. Normalization is used to eliminate dimensional differences and make features with different physical meanings comparable. The weighting coefficients can be set based on actual business needs, and this application does not impose any restrictions on them.

[0073] Indicators obtained through the above processing It can reflect the comprehensive state of current gas consumption behavior in three dimensions: direction of change, intensity of fluctuation, and sensor sensitivity, that is, the recent gas flow trend of users. Based on this, the initial predicted flow rate for the sub-period can be determined by the following formula (2): Q i =Q T ×(1+α i × (2) Among them, Q i The initial predicted flow rate corresponding to sub-time period i, α i This represents the time influence factor corresponding to sub-time period i.

[0074] S133, based on the initial predicted flow rate corresponding to each sub-period, determine the predicted gas flow rate within the preset period.

[0075] In practice, the duration of each sub-period can be correlated with the corresponding initial predicted flow Q. i The products of these factors are summed to obtain the total predicted flow rate within the preset time period. Simultaneously, the initial predicted flows Q can also be... i The gas flow rate is arranged into a sequence according to its time order within a preset time period, and then fitted with a low-order polynomial (e.g., using a first-order or quadratic function) to generate a continuous curve reflecting the future evolution of gas flow. This fitted curve can indicate whether the target gas meter is in the gas usage on-phase (flow rate continuously increases from the current value), stable phase (flow rate fluctuates within a small range), or gas usage off-phase (flow rate rapidly decreases and approaches zero) in the future time period. Thus, while outputting the total predicted flow rate, it provides dynamic characteristic information that can be used to determine the type of gas usage behavior of users.

[0076] The resulting predictions can then provide analytical and decision-making support for various intelligent tasks. For example, in a gas leak warning scenario, if the total predicted flow rate is significantly higher than the historical baseline within a short preset time period, and the fitted curve shows a monotonically increasing trend, then abnormal activation behavior can be identified and an alarm can be triggered. As another example, in a user gas consumption profile construction scenario, if the prediction results for multiple long preset time periods during the day consistently show two high flow rate intervals in the morning and evening, with a stable and low flow rate in the middle period, then a typical household bi-peak gas consumption pattern can be identified, which can be used to support refined energy consumption analysis or gas supply resource scheduling.

[0077] In the above process, a preset time period is divided into multiple sub-time periods, and a time influence factor calibrated based on typical gas consumption conditions before delivery is configured for each sub-time period. This results in a higher weighting for recent sub-time periods in the prediction, while the weight of longer-term sub-time periods naturally decreases. Based on this, multi-dimensional gas characteristic data is combined to dynamically characterize the current operating conditions, generating initial predicted flow rates for each sub-time period. Finally, the total flow rate and evolution pattern are output synchronously through accumulation and curve fitting. This method avoids oversimplification of complex gas consumption behavior by a single model, effectively balancing response speed and prediction stability, and significantly improving the accuracy and versatility of gas flow rate prediction.

[0078] Furthermore, considering the time influence factor α iThe initial factors were calibrated before leaving the factory based on typical gas appliances and general gas usage conditions. However, the types of gas appliances used by actual users, their operating habits, and gas usage patterns vary. For example, some users frequently use small flames for stable combustion, while others use large flow rates for rapid start-stop, making it difficult for the initial factors of the general calibration to fully match the dynamic characteristics of specific users.

[0079] Based on this, the embodiments of this application also introduce an adaptive correction mechanism based on actual feedback, which uses real observation data to optimize the key parameters in the prediction model online, thereby gradually improving the prediction accuracy in daily use.

[0080] In some embodiments, the target gas flow rate for each sub-period can be determined based on the voltage generated by the target gas meter within each sub-period. Subsequently, based on the target gas flow rate and the initial predicted flow rate, the flow prediction deviation corresponding to each sub-period is determined. Finally, the time influence factor and / or temperature influence factor are updated based on the flow prediction deviation.

[0081] Specifically, for each sub-time period, when the actual time arrives at that sub-time period, the average value of all voltage signals collected by the target gas meter during that sub-time period is calculated to obtain the target gas flow rate for that sub-time period. For example, if sub-time period 1 is from 10:00:00 to 10:00:01, then the average value of all voltage signals collected by the target gas meter during the period from 10:00:01 to 10:00:01 is obtained as the target gas flow rate for sub-time period 1.

[0082] By performing the above processing on each sub-time period, the target gas flow rate for each sub-time period can be obtained. Subsequently, for each sub-time period, the difference between the initial gas flow rate and the target gas flow rate for that sub-time period can be obtained to obtain the flow prediction deviation for that sub-time period. This deviation can reflect the adaptation error of the currently used time influence factor or temperature compensation parameter in the user's specific gas usage mode. If the deviation is consistently large or shows a systematic trend, it indicates that the general calibration initial parameters have failed to accurately characterize the user's dynamic characteristics, and adjustments are necessary.

[0083] To avoid parameter misadjustment due to accidental noise or transient interference, embodiments of this application include parameter update conditions, including any or a combination of the following conditions: Condition 1: The total deviation of the traffic forecast for each sub-period exceeds the first deviation threshold. In practice, the sum of the absolute values ​​of the prediction deviations for each sub-period can be calculated. If the value exceeds the preset first deviation threshold, it indicates that there is an overall deviation between the current prediction result and the actual gas usage status. This may be caused by environmental temperature drift, long-term sensor drift, or significant differences between the user's gas usage mode and the general calibration scenario. Therefore, parameter updates are required.

[0084] Condition 2: The number of abnormal sub-time periods exceeds the quantity threshold; The abnormal sub-period in this application embodiment is the sub-period where the traffic prediction deviation exceeds the second deviation threshold.

[0085] If the number of abnormal sub-time periods exceeds the preset threshold, it indicates that the prediction error is not caused by random noise, but rather by a persistent and significant inaccuracy at multiple time points. This reflects that the current parameter configuration is difficult to match the user's actual gas usage dynamics (such as frequent start-stop, atypical firepower adjustment, etc.), and therefore parameter updates are required.

[0086] Condition 3: The deviation between the predicted flow rate change rate and the target flow rate change rate exceeds the change rate threshold; The predicted flow rate change rate in this application embodiment is determined based on the initial predicted flow rate and the number of sub-time periods for each sub-time period, and the target flow rate change rate is determined based on the target gas flow rate and the number of sub-time periods for each sub-time period.

[0087] The predicted rate of change and the target rate of change of flow can be calculated as shown in the following formula (3): △ k = (Q last - Q first ) / [(N - 1)× Δt] (3) Where N is the number of sub-time periods; Δt is the duration of a single sub-time period; △K represents the predicted flow rate of change or the target flow rate of change. When △k is the predicted flow rate of change, Q last and Q first These represent the initial predicted flow rates for the last and first sub-periods, respectively; when Δk is the target flow rate of change, Q... last and Q first These are the target gas flow rates for the last sub-period and the first sub-period, respectively. If the deviation of the flow rate change rate exceeds the preset change rate threshold, it indicates that the prediction model's judgment on the overall trend of gas consumption behavior (such as rising, falling, or remaining stable) is inconsistent with the actual observation results in terms of direction or magnitude. This means that the current distribution of time-influencing factors fails to accurately reflect the temporal evolution of user gas consumption, and therefore parameter updates are required.

[0088] Furthermore, considering that the above judgment conditions reflect the inaccuracy characteristics of the prediction results in different dimensions, the parameters that need to be corrected can be selected in a targeted manner based on different parameter update conditions, thereby improving the prediction accuracy.

[0089] In specific implementation, it can be as follows: Figure 3As shown, after obtaining the initial predicted flow rate and target gas flow rate corresponding to each sub-period, the total prediction deviation, the number of abnormal sub-periods, and the flow rate change deviation of each sub-period 1 to N can be statistically analyzed.

[0090] When the total deviation exceeds the first deviation threshold (i.e., condition 1 above is met), the deviation reflects a significant difference between the predicted result and the actual gas consumption data. This phenomenon is usually caused by overall parameter inaccuracy. Therefore, the influence of flow prediction deviation on temperature influence factor KT and time influence factor can be considered. Updated simultaneously.

[0091] Correspondingly, when the number of abnormal sub-periods exceeds the threshold (i.e., condition 2 above is met), it indicates that the prediction results consistently and significantly deviate from the measured values ​​at multiple time points. In other words, the current time-related factors are difficult to accurately reflect users' actual gas usage habits. Therefore, the time-related factors can be adjusted in conjunction with the flow prediction deviation. Update.

[0092] Correspondingly, when the deviation between the predicted flow rate change rate and the target flow rate change rate exceeds the change rate threshold (i.e., condition 3 above is met), it indicates that the flow rate increase or decrease presented by the prediction results is significantly inconsistent with the actual observation, reflecting that the decay law of the current time-influence factor does not match the flow rate change during the user's actual gas consumption. Therefore, the time-influence factor can be analyzed in conjunction with the flow prediction deviation. Update.

[0093] In the above process, the total prediction deviation, the number of abnormal sub-periods, and the deviation of the flow rate change rate are calculated based on the initial predicted flow rate and the target gas flow rate of each sub-period within a preset time period. The temperature influence factor and / or time influence factor are updated in a targeted manner according to the currently met parameter update conditions, so that the prediction results continuously approach the user's actual gas usage habits in both the overall level and the temporal evolution dimensions, thereby improving the prediction accuracy of gas flow rate.

[0094] In some embodiments, the temperature influence factor can be updated using the following formula (4): =KT old +e / (Q) avg ×△T avg (4) in, The updated temperature influence factor; KT old The temperature influence factor before the update; Q avg denoted as , where is the average of the target gas flow rate for each sub-period; e is the total prediction deviation, i.e., the sum of the flow prediction deviations for each sub-period; ΔT avgThe mean temperature deviation between the temperature signal collected by the target gas meter in each sub-period and the preset temperature corresponding to the voltage-flow relationship curve.

[0095] In formula (4), "e / (Q)" avg ×△T avg ")" serves as a correction factor for the temperature influence factor, and the adjustment range of this correction factor will be based on the average value Q of the target gas flow rate. avg and the mean temperature deviation ΔT avg Scaling is applied. The correction amount generated for the same total prediction bias e will vary with Q. avg or △T avg The temperature influence factor is reduced as the flow rate increases to avoid excessive adjustment due to local disturbances under high flow rate or large temperature difference conditions.

[0096] By utilizing the above-mentioned update method, the prediction error naturally generated during daily gas consumption can be used to adaptively correct the temperature influence factor without relying on external calibration or historical data. This effectively suppresses systematic prediction offsets caused by changes in ambient temperature and improves the metering accuracy and prediction stability of gas meters under different temperature environments.

[0097] In some embodiments, the time influence factor can be updated using the following formula (5): = ×(1+e / ( ×Q T × ))(5) in, The updated time influence factor for sub-period i The time influence factor before the update of sub-period i. The time influence factor before the update of each sub-time period i The sum of .

[0098] In formula (5), "e / ( ×Q T × The adjustment amount, referred to as the time-related factor, will be based on the gas characteristic data collected before the forecast. Q T as well as Scaling is applied. The correction amount generated by the same total prediction deviation e will decrease as the three factors increase, in order to avoid over-adjustment of the time influence factor due to local deviations when gas consumption dynamics are drastic, flow rates are high, or the overall weight is large.

[0099] The above-described update method enables closed-loop feedback correction of the time-related factors based on the deviation between the predicted flow rate and the actual collected flow rate for each sub-period. This ensures that the weights of each sub-period in the segmented weighted prediction continuously adapt to the user's current gas consumption dynamics. This mechanism requires no external calibration intervention; it utilizes only the comparative data generated by the gas meter itself during normal operation to achieve adaptive optimization of the time-related factors, effectively improving the prediction accuracy of gas flow rate.

[0100] Based on the same inventive concept, this application also provides a flow prediction device 400 for a gas meter, specifically as follows: Figure 4 As shown, it includes: The data acquisition unit 401 is configured to: determine the current gas flow rate based on the current voltage of the target gas meter in response to a flow prediction indication; The feature acquisition unit 402 is configured to: determine gas feature data characterizing the flow rate change trend based on the current gas flow rate and the historical voltage of the target gas meter in the historical period. The flow prediction unit 403 is configured to determine the predicted gas flow rate within a preset time period based on the current gas flow rate and the gas characteristic data.

[0101] In some embodiments, the target gas meter has a first conversion relationship between voltage and gas flow rate; the data acquisition unit 401 is specifically configured to: determine the initial gas flow rate corresponding to the current voltage based on the first conversion relationship; and determine the current gas flow rate based on the current temperature and the initial gas flow rate.

[0102] In some embodiments, the first conversion relationship is calibrated at a preset temperature; the data acquisition unit 401 is specifically configured to: determine the temperature deviation between the current temperature and the preset temperature; and correct the initial gas flow rate based on a pre-calibrated temperature influence factor and the temperature deviation to obtain the current gas flow rate.

[0103] In some embodiments, the gas characteristic data characterizing the flow rate change trend is determined based on the current gas flow rate and the historical voltage of the target gas meter within a historical period. Specifically, the feature acquisition unit 402 is configured to: determine the historical voltage change rate based on the acquisition time corresponding to each historical voltage; determine the historical voltage fluctuation amplitude based on the standard deviation of each historical voltage; determine the target voltage corresponding to the current gas flow rate based on the first conversion relationship; and determine the gas characteristic data based on the historical voltage change rate, the historical voltage fluctuation amplitude, and the ratio of the target voltage to the current gas flow rate.

[0104] In some embodiments, the process of determining the predicted gas flow rate within a preset time period based on the current gas flow rate and the gas characteristic data is performed. Specifically, the flow prediction unit 403 is configured to: divide the preset time period into multiple sub-time periods; wherein each sub-time period has a corresponding time influence factor; for each sub-time period, determine the initial predicted flow rate corresponding to the sub-time period based on the time influence factor corresponding to the sub-time period, the current gas flow rate, and the gas characteristic data; and determine the predicted gas flow rate within the preset time period based on the initial predicted flow rate corresponding to each sub-time period.

[0105] In some embodiments, the flow prediction unit 403 is further configured to: determine the target gas flow rate corresponding to each sub-period based on the voltage generated by the target gas meter in each sub-period; determine the flow prediction deviation corresponding to each sub-period based on the target gas flow rate and the initial predicted flow rate; and update the time influence factor based on the flow prediction deviation.

[0106] In some embodiments, before performing the update of the time influence factor based on the flow prediction deviation, the flow prediction unit 403 is further configured to: determine a preset parameter update condition; wherein the parameter update condition includes any or a combination of the following conditions: the total prediction deviation of the flow prediction deviation corresponding to each sub-time period exceeds a first deviation threshold; the number of abnormal sub-time periods exceeds a quantity threshold; the abnormal sub-time period is the sub-time period in each sub-time period where the flow prediction deviation exceeds a second deviation threshold; the flow change rate deviation between the predicted flow change rate and the target flow change rate exceeds a change rate threshold; the predicted flow change rate is determined based on the initial predicted flow and the number of sub-time periods for each sub-time period; the target flow change rate is determined based on the target gas flow for each sub-time period and the number of sub-time periods.

[0107] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for apparatus or device embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The professional and apparatus embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0108] Based on the same inventive concept, embodiments of this application also provide an electronic device. See also Figure 5 As shown, the electronic device may include a memory 1000 and a processor 1010. The memory 1000 is connected to the processor 1010 and is used to store programs; the processor 1010 is used to implement a gas meter flow prediction method disclosed in any of the above embodiments by running the programs stored in the memory 1000.

[0109] Specifically, the aforementioned electronic device may further include: a bus, a communication interface 1020, an input device 1030, and an output device 1040. The processor 1010, memory 1000, communication interface 1020, input device 1030, and output device 1040 are interconnected via the bus. The bus may include a pathway for transmitting information between various components of the computer system.

[0110] Processor 1010 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. Processor 1010 may include a main processor, and may also include a baseband chip, a modem, etc.

[0111] The memory 1000 stores a program for executing the technical solution of this application, and may also store an operating system and other critical business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 1000 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0112] Input device 1030 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0113] Output device 1040 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0114] The communication interface 1020 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0115] The processor 1010 executes the program stored in the memory 1000 and calls other devices, which can be used to implement the various steps of any of the gas meter flow prediction methods provided in the above embodiments of this application.

[0116] Based on the same inventive concept, embodiments of this application also provide a computer program product, which includes computer program instructions that, when executed by a processor, cause the processor to perform the steps in a gas meter flow prediction method according to various embodiments of this application as described in any of the above embodiments of this specification.

[0117] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. These programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server; this application does not limit this.

[0118] Based on the same inventive concept, embodiments of this application also provide a storage medium storing a computer program thereon, the computer program being executed by a processor of the steps in a gas meter flow prediction method according to various embodiments of this application as described in any of the foregoing embodiments of this specification.

[0119] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0120] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0121] The steps in the methods of the various embodiments of this application can be adjusted, merged, or deleted in order according to actual needs, and the technical features described in each embodiment can be replaced or combined.

[0122] The functional modules or sub-modules in the various embodiments of this application can be integrated into a single processing module, or each module or sub-module can exist physically separately, or two or more modules or sub-modules can be integrated into a single module. The integrated modules or sub-modules described above can be implemented in hardware or as software functional modules or sub-modules. Those skilled in the art will further recognize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0123] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software unit executed by a processor, or a combination of both. The software unit can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0124] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, 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.

[0125] The above description of the embodiments disclosed in this application enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting the flow rate of a gas meter, characterized in that, include: In response to a flow forecast indication, the current gas flow rate is determined based on the current voltage of the target gas meter; Based on the current gas flow rate and the historical voltage of the target gas meter during the historical period, gas characteristic data characterizing the flow rate change trend are determined. Based on the current gas flow rate and the gas characteristic data, the predicted gas flow rate within a preset time period is determined.

2. The method according to claim 1, characterized in that, The target gas meter is equipped with a first conversion relationship between voltage and gas flow; Determining the current gas flow rate based on the current voltage of the target gas meter includes: Based on the first conversion relationship, the initial gas flow rate corresponding to the current voltage is determined; The current gas flow rate is determined based on the current temperature and the initial gas flow rate.

3. The method according to claim 2, characterized in that, The first conversion relationship is calibrated at a preset temperature; determining the current gas flow rate based on the current temperature and the initial gas flow rate includes: Determine the temperature deviation between the current temperature and the preset temperature; Based on the pre-calibrated temperature influence factor and the temperature deviation, the initial gas flow rate is corrected to obtain the current gas flow rate.

4. The method according to claim 2, characterized in that, The determination of gas characteristic data representing the flow rate change trend based on the current gas flow rate and the historical voltage of the target gas meter within a historical period includes: The historical voltage change rate is determined based on the acquisition time corresponding to each historical voltage. The historical voltage fluctuation amplitude is determined based on the standard deviation of each historical voltage. Based on the first conversion relationship, the target voltage corresponding to the current gas flow rate is determined; The gas characteristic data are determined based on the historical voltage change rate, the historical voltage fluctuation amplitude, and the ratio of the target voltage to the current gas flow rate.

5. The method according to any one of claims 1-4, characterized in that, The step of determining the predicted gas flow rate within a preset time period based on the current gas flow rate and the gas characteristic data includes: The preset time period is divided into multiple sub-time periods; each sub-time period is provided with a corresponding time influence factor; For each sub-time period, the initial predicted flow rate corresponding to the sub-time period is determined based on the time influence factor corresponding to the sub-time period, the current gas flow rate, and the gas characteristic data; Based on the initial predicted flow rate corresponding to each sub-time period, the predicted gas flow rate within the preset time period is determined.

6. The method according to claim 5, characterized in that, The method further includes: Based on the voltage generated by the target gas meter in each sub-time period, the target gas flow rate corresponding to each sub-time period is determined; Based on the target gas flow rate and the initial predicted flow rate, the flow prediction deviation corresponding to each sub-period is determined; The time influence factor is updated based on the traffic prediction deviation.

7. The method according to claim 6, characterized in that, Before updating the time influence factor based on the traffic prediction deviation, the method further includes: Determine if the preset parameter update conditions are met; The parameter update conditions include any or a combination of the following conditions: The total prediction deviation of the traffic prediction deviation corresponding to each sub-time period exceeds the first deviation threshold. The number of abnormal sub-periods exceeds a threshold; the abnormal sub-periods are those sub-periods in which the traffic prediction deviation exceeds a second deviation threshold. The deviation between the predicted flow rate change rate and the target flow rate change rate exceeds a change rate threshold; the predicted flow rate change rate is determined based on the initial predicted flow rate and the number of sub-periods for each sub-period; the target flow rate change rate is determined based on the target gas flow rate for each sub-period and the number of sub-periods.

8. A flow prediction device for a gas meter, characterized in that, include: The data acquisition unit is configured to: determine the current gas flow rate based on the current voltage of the target gas meter in response to a flow prediction indication; The feature acquisition unit is configured to: determine gas feature data characterizing the flow rate change trend based on the current gas flow rate and the historical voltage of the target gas meter in the historical period; The flow prediction unit is configured to determine the predicted gas flow rate within a preset time period based on the current gas flow rate and the gas characteristic data.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a computer, cause the computer to perform the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, The method includes a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, causing the electronic device to perform the steps of any one of the methods of claims 1-7.

Images