Method and device for predicting indoor carbon dioxide concentration, processing equipment, fresh air air conditioning system and storage medium

Abstract

The application relates to the technical field of carbon dioxide concentration prediction, and provides a method and device for predicting indoor carbon dioxide concentration, a processing equipment, a fresh air air conditioning system and a storage medium, which can reduce the dependence of indoor carbon dioxide concentration detection on a CO2 sensor. According to volatile organic compound concentration measurement values of a target room at multiple sampling moments, a volatile organic compound concentration measurement value sequence is obtained; a time period to which each sampling moment belongs and a fresh air opening and closing state of each sampling moment are determined; input data is obtained according to the volatile organic compound concentration measurement value sequence, the time period to which each sampling moment belongs, the fresh air opening and closing state of each sampling moment and a room type of the target room; and a carbon dioxide prediction model is used to obtain a predicted value of indoor carbon dioxide concentration corresponding to the target room according to the input data.

Description

Technical Field

[0001] This application relates to the field of carbon dioxide concentration prediction technology, and in particular to a method, apparatus, processing equipment, fresh air conditioning system, storage medium and computer program product for predicting indoor carbon dioxide concentration. Background Technology

[0002] The application of fresh air conditioning systems is becoming increasingly common, with the main purpose of improving indoor air quality by introducing fresh air. Fresh air conditioning systems are equipped with various sensors indoors, such as temperature and humidity sensors to detect indoor temperature and humidity, sensors to detect indoor volatile organic compound concentrations, CO2 sensors to detect indoor CO2 (carbon dioxide) concentrations, and sensors to detect indoor PM2.5 concentrations.

[0003] Indoor CO2 concentration detection relies on CO2 sensors, which are expensive. Summary of the Invention

[0004] This application provides a method, apparatus, processing equipment, fresh air conditioning system, storage medium, and computer program product for predicting indoor carbon dioxide concentration, in order to solve the technical problem that indoor carbon dioxide concentration detection relies on CO2 sensors.

[0005] In a first aspect, some embodiments provide a method for predicting indoor carbon dioxide concentration, the method comprising:

[0006] Based on the volatile organic compound (VOC) concentration measurements of the target room at multiple sampling times, a sequence of VOC concentration measurements was obtained.

[0007] Determine the time period to which each sampling moment belongs and the fresh air opening / closing status at each sampling moment;

[0008] The input data is obtained based on the sequence of volatile organic compound concentration measurements, the time period to which each sampling time belongs, the fresh air opening and closing status at each sampling time, and the room type of the target room;

[0009] Based on the input data and the carbon dioxide prediction model, the predicted indoor carbon dioxide concentration for the target room is obtained.

[0010] In one embodiment, input data is obtained based on the sequence of volatile organic compound concentration measurements, the time period to which each sampling time belongs, the fresh air opening / closing status at each sampling time, and the room type of the target room. This input data includes:

[0011] Each sampling time is sequentially used as the target sampling time;

[0012] Based on the volatile organic compound concentration measurement value at the target sampling time, the time period to which the target sampling time belongs, the fresh air opening / closing status at the sampling time, and the room type of the target room in the volatile organic compound concentration measurement value sequence, the vector corresponding to the target sampling time is obtained;

[0013] The input data is obtained from the vectors corresponding to each of the multiple sampling times.

[0014] In one embodiment, the method further includes:

[0015] A dataset of volatile organic compound (VOC) concentrations is obtained based on the measured VOC concentrations in the target room over a unit of time.

[0016] Based on the volatile organic compound concentration dataset, determine the active periods of the target room within multiple time intervals per unit duration;

[0017] Based on the volatile organic compound concentration dataset, determine the peak-valley concentration difference of volatile organic compounds in the target room;

[0018] Based on the volatile organic compound concentration dataset, determine the rate of change of volatile organic compound concentration in the target room;

[0019] The room type of the target room is determined based on the active period, peak-to-valley concentration difference, and concentration change rate.

[0020] In one embodiment, based on the volatile organic compound concentration dataset, determining the active periods of the target room within multiple time intervals per unit duration includes:

[0021] Based on the relative magnitudes between the data, a target dataset is determined within the volatile organic compound concentration dataset;

[0022] Based on the time period to which the sampling time corresponds to the data, the data in the target dataset is classified to obtain the datasets corresponding to multiple time periods of unit duration;

[0023] The active time periods of the target room are determined based on the amount of data included in the dataset corresponding to each time period.

[0024] In one embodiment, the room type of the target room is determined based on the active period, peak-to-valley concentration difference, and concentration change rate, including:

[0025] The first matching degree is obtained based on the degree of matching between the active time period and the standard active time period of the target room type;

[0026] The second matching degree is obtained based on the degree of matching between the peak-valley concentration difference and the standard peak-valley concentration difference of the target room type;

[0027] A third degree of matching is obtained based on the degree of matching between the concentration change rate and the standard concentration change rate of the target room type;

[0028] Based on the first matching degree, the second matching degree, and the third matching degree, determine whether to determine the target room type as the room type of the target room.

[0029] In one embodiment, the method further includes:

[0030] The predicted indoor carbon dioxide concentration for the target room is standardized to obtain the standard indoor carbon dioxide concentration.

[0031] The measured values ​​of volatile organic compound (VOC) concentration in the target room were standardized to obtain standard values ​​for VOC concentration.

[0032] Based on the room type of the target room, determine the corresponding weight pairs;

[0033] Based on the weighted pairs, the standard values ​​of indoor carbon dioxide concentration and volatile organic compound concentration are weighted and summed to obtain the corresponding comfort index of the target room.

[0034] Secondly, some embodiments also provide an indoor carbon dioxide concentration prediction device, the device comprising:

[0035] The measurement acquisition module is used to obtain a sequence of volatile organic compound (VOC) concentration measurements based on the VOC concentration measurements of the target room at multiple sampling times.

[0036] The time period and opening / closing determination module is used to determine the time period to which each sampling moment belongs and the fresh air opening / closing status at each sampling moment;

[0037] The input data acquisition module is used to obtain input data based on the sequence of volatile organic compound concentration measurements, the time period to which each sampling time belongs, the fresh air opening and closing status at each sampling time, and the room type of the target room;

[0038] The prediction value acquisition module is used to obtain the predicted value of indoor carbon dioxide concentration for the target room based on the input data and the carbon dioxide prediction model.

[0039] Thirdly, some embodiments also provide a processing device including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of any of the methods described in the above embodiments.

[0040] Fourthly, some embodiments also provide a fresh air conditioning system, which includes a plurality of indoor air detection modules; each indoor air detection module is arranged in a corresponding room; the indoor air detection module includes a concentration detection sensor and the processing equipment described in the above embodiments; the concentration detection sensor is used to detect the concentration of volatile organic compounds.

[0041] Fifthly, some embodiments also provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor of the steps described above.

[0042] The above technical solution has the following beneficial effects: Indoor carbon dioxide concentration is estimated by measuring volatile organic compound (VOC) concentration. This VOC concentration can be obtained using sensors that detect indoor VOC concentration, eliminating the need for CO2 sensors and reducing reliance on them, thus lowering hardware costs. Furthermore, the input data includes VOC concentration measurements of the target room at multiple sampling times, the time period of each sampling time, the ventilation status at each sampling time, and the room type. Predicting based on this multi-dimensional input data yields more accurate indoor carbon dioxide concentration predictions, improving prediction accuracy. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is an application environment diagram of an indoor carbon dioxide concentration prediction method in one embodiment;

[0045] Figure 2 This is a flowchart illustrating a method for predicting indoor carbon dioxide concentration in one embodiment.

[0046] Figure 3 This is a schematic diagram of an indoor and outdoor air detection module deployment scheme in one embodiment;

[0047] Figure 4 This is a schematic diagram of the hardware architecture and system communication scheme of an indoor and outdoor air detection module in one embodiment;

[0048] Figure 5 Here is a flowchart of the room type prediction process in one embodiment;

[0049] Figure 6 This is a flowchart illustrating the prediction of indoor carbon dioxide concentration in one embodiment.

[0050] Figure 7 This is a flowchart illustrating how to determine whether to turn on the fresh air system in a target room, as shown in one embodiment.

[0051] Figure 8 This is a flowchart illustrating the interaction between the processing device and the sensor in one embodiment;

[0052] Figure 9 This is a structural block diagram of an indoor carbon dioxide concentration prediction device in one embodiment;

[0053] Figure 10 This is an internal structural diagram of the processing device in one embodiment. Detailed Implementation

[0054] The 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 represent the same or similar elements. The embodiments described below do not represent all embodiments consistent with this application. They are merely examples of systems and methods consistent with some aspects of this application as detailed in the claims.

[0055] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0056] The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms are interchangeable where appropriate.

[0057] The terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device that includes a range of components is not necessarily limited to all of the components that are clearly listed, but may include other components that are not clearly listed or that are inherent to such product or device.

[0058] The term "module" refers to any known or subsequently developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] Indoor carbon dioxide is mainly produced by human activities, and the amount of carbon dioxide produced by human respiration is strongly correlated with the number of volatile organic compound (VOC) gas molecules. Therefore, the method provided in this application can predict indoor carbon dioxide concentration by means of VOC concentration measurement, without the need for a CO2 sensor, thus reducing the dependence on CO2 sensors.

[0061] The method provided in this application can be applied to fresh air conditioning systems to intelligently regulate indoor air quality. It is understood that the method provided in this application can also be applied to other systems that require prediction of indoor carbon dioxide concentration.

[0062] The method provided in this application involves Figure 1 The diagram illustrates a processing device and a concentration sensor for detecting the concentration of volatile organic compounds. The processing device may include, but is not limited to, an MCU (Microcontroller Unit), some of which may be deployed with AI (Artificial Intelligence) models. The steps performed by the processing device include... Figure 2 Steps S201 to S204 are shown.

[0063] Step S201: Based on the volatile organic compound concentration measurements of the target room at multiple sampling times, obtain the volatile organic compound concentration measurement sequence.

[0064] Volatile organic compounds can be VOCs, and correspondingly, concentration detection sensors can be called VOC sensors. VOC stands for Volatile Organic Compounds. Volatile organic compounds can also be TVOCs, and correspondingly, concentration detection sensors can be called TVOC sensors. TVOC stands for Total Volatile Organic Compounds. The following examples use VOCs as an example.

[0065] The target room can be equipped with VOC sensors, which are used to detect the concentration of volatile organic compounds in the target room.

[0066] When the VOC sensor is in operation, it can collect the concentration value of volatile organic compounds in the target room in real time. This concentration value is observed by the VOC sensor, so it can be called the volatile organic compound concentration measurement value.

[0067] To predict the indoor carbon dioxide concentration of a target room at time t, we start from time t and backtrack according to a set time step m to determine N sampling times, where N is a positive integer greater than or equal to 1. The N sampling times can be denoted in chronological order as: tm, t-2m, t-3m, ..., tN×m.

[0068] The volatile organic compound concentration measurements collected by the VOC sensor have corresponding sampling times. After determining N sampling times, the volatile organic compound concentration measurements at each of the N sampling times can be determined from the volatile organic compound concentration measurements collected by the VOC sensor using the N sampling times as an index.

[0069] The volatile organic compound (VOC) concentration measurements at N sampling times are sorted in chronological order to obtain a sequence of VOC concentration measurements.

[0070] Step S202: Determine the time period to which each sampling time belongs and the fresh air opening / closing status of each sampling time.

[0071] A unit of time (such as a day) can be pre-divided into multiple time periods, such as cooking and dining time, sleep time, wake-up time, play time, and bathing time. Each time period has a corresponding time range. For example, the cooking and dining time period corresponds to the time range of 6 pm to 8 pm, and the sleep time period corresponds to the time range of 10 pm to 7 am.

[0072] After determining N sampling times, for any given sampling time, the time range in which the sampling time is located can be determined from the time ranges corresponding to the multiple time periods, and the time period corresponding to the time range is taken as the time period to which the sampling time belongs.

[0073] For any of the N sampling times, the processing device can also determine the fresh air opening and closing status of the target room at that sampling time based on the data fed back by the fresh air conditioning system.

[0074] Step S203: Input data is obtained based on the sequence of volatile organic compound concentration measurements, the time period to which each sampling time belongs, the fresh air opening / closing status at each sampling time, and the room type of the target room.

[0075] In some scenarios, the room type of the target room can be pre-set in the processing device, allowing the device to directly determine the room type when predicting the indoor carbon dioxide concentration. In other scenarios, if the room type is not pre-set, the processing device can identify the room type using a specific algorithm. Room types include, but are not limited to, living room, bedroom, bathroom, and kitchen.

[0076] The processing equipment can generate input data from the volatile organic compound concentration measurements at N sampling times, the time periods to which each of the N sampling times belongs, the fresh air opening and closing status at each of the N sampling times, and the room type of the target room.

[0077] Step S204: Based on the input data and the carbon dioxide prediction model, obtain the predicted value of the indoor carbon dioxide concentration for the target room.

[0078] Carbon dioxide prediction models can be deployed on processing devices. These models can be classified as AI models and can employ an LSTM (Long Short-Term Memory) architecture. After receiving input data, the processing device can input this data into the carbon dioxide prediction model. Based on the model's output, the indoor carbon dioxide concentration value for the target room is obtained. This predicted indoor carbon dioxide concentration value can therefore be called the indoor carbon dioxide concentration prediction value.

[0079] In the aforementioned method for predicting indoor carbon dioxide concentration, the indoor carbon dioxide concentration is estimated by measuring the concentration of volatile organic compounds (VOCs). These VOC concentration measurements can be obtained using sensors that detect indoor VOC concentrations, eliminating the need for CO2 sensors and reducing reliance on them. Furthermore, the input data in this application includes VOC concentration measurements of the target room at multiple sampling times, the time period of each sampling time, the ventilation status at each sampling time, and the room type. Predicting based on this multi-dimensional input data yields a more accurate indoor carbon dioxide concentration prediction, improving prediction accuracy.

[0080] In one embodiment, input data is obtained based on the sequence of volatile organic compound concentration measurements, the time period to which each sampling time belongs, the fresh air opening / closing status at each sampling time, and the room type of the target room. This input data includes:

[0081] Each sampling time is sequentially taken as the target sampling time; based on the volatile organic compound concentration measurement value of the target sampling time in the volatile organic compound concentration measurement value sequence, the time period to which the target sampling time belongs, the fresh air opening and closing status of the sampling time, and the room type of the target room, the vector corresponding to the target sampling time is obtained; based on the vectors corresponding to multiple sampling times, the input data is obtained.

[0082] Let's take the first sampling time out of N sampling times as an example. Starting from time t, we backtrack according to a set time step m to determine the first sampling time in the scenario with N sampling times, which can be denoted as tm.

[0083] The processing equipment can determine the volatile organic compound concentration measurement value (denoted as VOC_t-m) at the first sampling time tm in the volatile organic compound concentration measurement value sequence. Assuming that the time period to which the first sampling time tm belongs is the sleep period, the fresh air is on at the first sampling time tm, and the target room type is bedroom, then the vector corresponding to the first sampling time tm can be formed as [VOC_t-m, room type_bedroom, fresh air_on, sleep period].

[0084] Following the above method, we can also obtain the vector corresponding to the second sampling time t-2m, for example, [VOC_t-2m, room type_bedroom, fresh air_on, sleep period]; we can also obtain the vector corresponding to the third sampling time t-3m, for example, [VOC_t-3m, room type_bedroom, fresh air_on, sleep period].

[0085] After obtaining the vectors for each of the N sampling times, these vectors can be concatenated to form a matrix, which can then be used as input data.

[0086] In this embodiment, a vector is formed based on relevant data at the same sampling time to ensure that time-related data are aligned in time, thereby improving the accuracy of indoor carbon dioxide concentration prediction.

[0087] In one embodiment, the method provided in this application further includes:

[0088] Based on the measured volatile organic compound (VOC) concentrations in the target room within a unit of time, a VOC concentration dataset is obtained. Based on this dataset, active periods in the target room are determined across multiple time intervals within the unit of time. Based on the VOC concentration dataset, the peak-to-valley concentration difference of VOCs in the target room is determined. Based on the VOC concentration dataset, the concentration change rate of VOCs in the target room is determined. Based on the active periods, peak-to-valley concentration difference, and concentration change rate, the room type of the target room is determined.

[0089] Before predicting the indoor carbon dioxide concentration in a target room, a specific algorithm can be used to identify the room type. This will be illustrated using a one-day timeframe as an example.

[0090] The processing device can acquire VOC concentration measurements of a target room throughout the day, forming a VOC concentration dataset. After obtaining the VOC concentration dataset, the device can perform feature recognition to determine the active periods of the target room across multiple time slots throughout the day. The device can also perform feature recognition to determine the peak-to-valley concentration difference of VOCs in the target room; specifically, it can identify the maximum and minimum VOC concentration measurements in the dataset and obtain the peak-to-valley concentration difference of VOCs in the target room based on the difference between these measurements.

[0091] The processing equipment can also perform feature recognition based on the VOC concentration dataset to determine the fastest rate of change in VOC concentration in the target room within a day, thereby obtaining the rate of change of VOC concentration in the target room.

[0092] The processing device can acquire standard data for multiple room types and determine the room type of the target room based on the degree of matching between the standard data and the relevant data of the target room (active time period, peak-to-valley concentration difference of VOCs, and concentration change rate).

[0093] This embodiment can identify the room type of the target room even when the room type is not preset; moreover, it uses the concentration measurement of volatile organic compounds to identify features and obtain the relevant features of the target room, thereby obtaining a more accurate room type identification result.

[0094] The processing device can identify the room type of the target room multiple times, thereby obtaining multiple room type identification results. The results of multiple room type identification are statistically analyzed to obtain the cumulative number of times each room type is identified. The room type with the highest cumulative number of times is taken as the room type of the target room.

[0095] In one embodiment, based on a dataset of volatile organic compound concentrations, the active periods of the target room within multiple time intervals per unit duration are determined, including:

[0096] Based on the relative magnitudes of the data, the target dataset is determined within the volatile organic compound concentration dataset. The data in the target dataset is then categorized according to the time period corresponding to the sampling time, resulting in multiple time periods per unit duration. Finally, the active time periods of the target room are determined based on the amount of data included in each time period's dataset.

[0097] For example, the data in the VOC concentration dataset can be sorted from largest to smallest to determine the top Y data points, and the target dataset can be formed based on the top Y data points. Y is a positive integer greater than or equal to 1.

[0098] The target dataset contains several VOC concentration measurements, each with a corresponding sampling time. The time period to which each VOC concentration measurement belongs is determined, forming datasets for each time period. For example, if a VOC concentration measurement's sampling time belongs to the sleep period, then that VOC concentration measurement can be assigned to the sleep period dataset; similarly, if another VOC concentration measurement's sampling time belongs to the cooking and dining period, then that VOC concentration measurement can be assigned to the cooking and dining period dataset.

[0099] Obtain the amount of data in the dataset corresponding to each time period, determine the dataset with the most data, and use the time period corresponding to that dataset as the active time period of the target room.

[0100] In this embodiment, when determining the active time period of the target room, a target dataset is formed based on the larger data in the volatile organic compound concentration dataset. Some interfering data is removed to improve the accuracy of identifying the active time period. Furthermore, the data in the target dataset is classified according to the time period to which the data belongs. Based on the amount of data included in the dataset corresponding to each time period, the active time period of the target room can be determined more accurately through this statistical method.

[0101] In one embodiment, the room type of the target room is determined based on the active period, peak-to-valley concentration difference, and concentration change rate, including:

[0102] The first degree of matching is obtained based on the degree of matching between the active period and the standard active period of the target room type; the second degree of matching is obtained based on the degree of matching between the peak-valley concentration difference and the standard peak-valley concentration difference of the target room type; the third degree of matching is obtained based on the degree of matching between the concentration change rate and the standard concentration change rate of the target room type; based on the first degree of matching, the second degree of matching, and the third degree of matching, it is determined whether the target room type is identified as the target room type.

[0103] The standard active period, standard peak-valley concentration difference, and standard concentration change rate can be preset for each room type.

[0104] The processing device can determine whether the active time period of the target room is consistent with the standard active time period of the target room type. If they are consistent, it can be determined that the active time period of the target room and the standard active time period of the target room type are highly matched, thus forming the first degree of matching.

[0105] The processing equipment can determine whether the peak-valley concentration difference of VOC in the target room falls within the range of the standard peak-valley concentration difference for the target room type. If so, it can be determined that the peak-valley concentration difference of VOC in the target room is a high match with the standard peak-valley concentration difference for the target room type, thus forming a second degree of matching.

[0106] The processing equipment can determine whether the VOC concentration change rate of the target room falls within the range of the standard concentration change rate of the target room type. If so, it can be determined that the VOC concentration change rate of the target room is highly matched with the concentration change rate of the target room type, thus forming a third degree of matching.

[0107] After obtaining the first matching degree, the second matching degree, and the third matching degree, if all three matching degrees are high matching, the target room type can be determined as the target room type; if any matching degree is not high matching, the target room type is not determined as the target room type.

[0108] In this embodiment, after obtaining the active time period, peak-to-valley concentration difference, and concentration change rate of the target room, these data are compared with standard data of the target room type to obtain the feature matching degree in three dimensions, thereby obtaining a more accurate room type identification result.

[0109] In one embodiment, the method provided in this application further includes:

[0110] The predicted indoor carbon dioxide concentration for the target room is standardized to obtain the standard indoor carbon dioxide concentration value; the measured volatile organic compound (VOC) concentration for the target room is standardized to obtain the standard VOC concentration value; based on the room type of the target room, the corresponding weight pairs are determined; based on the weight pairs, the standard indoor carbon dioxide concentration value and the standard VOC concentration value are weighted and summed to obtain the corresponding comfort index for the target room.

[0111] The VOC concentration measurements output by the VOC sensor are relative values. Therefore, after the processing equipment obtains the measured VOC concentration at time t and the predicted indoor carbon dioxide concentration at time t, it can perform standardization processing. The measured VOC concentration at time t can be denoted as VOC_t, and the predicted indoor carbon dioxide concentration at time t can be denoted as CO2_t.

[0112] The processing equipment can determine a period of time tracing back from time t, and determine the maximum VOC concentration measurement value (denoted as VOC_t_max) and the minimum VOC concentration measurement value (denoted as VOC_t_min) within this period. The processing equipment can obtain the difference between the VOC concentration measurement value VOC_t at time t and the minimum VOC concentration measurement value VOC_t_min, which is called the first difference; the processing equipment can obtain the difference between the maximum VOC concentration measurement value VOC_t_max and the minimum VOC concentration measurement value VOC_t_min, which is called the second difference; the processing equipment divides the first difference by the second difference, and multiplies the result by 100% to obtain the standard VOC concentration value. This standardization process can be expressed by the following formula:

[0113] .

[0114] VOC_t represents the measured VOC concentration at time t, VOC_standard value represents the standard VOC concentration, VOC_t_max represents the maximum measured VOC concentration, and VOC_t_min represents the minimum measured VOC concentration.

[0115] The treatment equipment can obtain the upper limit (denoted as a) and lower limit (denoted as b) of the CO2 concentration. The predicted indoor carbon dioxide concentration at time t, CO2_t, is subtracted from the lower limit b, yielding the difference, which is called the third difference. The upper limit (a) of the CO2 concentration is subtracted from the lower limit (b), yielding the fourth difference. The treatment equipment divides the third difference by the fourth difference, and multiplies the result by 100% to obtain the standard CO2 concentration value. This standardization process can be expressed by the following formula:

[0116] CO2 standard value = (CO2_t-b) / (ab)×100%.

[0117] CO2_t represents the predicted indoor carbon dioxide concentration at time t, CO2_standard value represents the standard value of CO2 concentration, a represents the upper limit of CO2 concentration, and b represents the lower limit of CO2 concentration.

[0118] Weight pairs can be pre-set for different room types. Each weight pair includes a first weight and a second weight. The first weight is used to assign the standard value of VOC concentration, and the second weight is used to assign the standard value of CO2 concentration. The sum of the first weight and the second weight in the same weight pair can be 1.

[0119] In the weighting of different room types, the value of the first weight varies and can be set according to the actual situation. For example, the first weight value of a bedroom should be smaller, and the second weight value of a bedroom should be larger.

[0120] Table 1

[0121]

[0122] Table 1 shows the weighted pairs for the four room types: bedroom, living room, bathroom, and kitchen.

[0123] If the target room is a bedroom, then the weighted pair [K1, 1-K1] can be obtained. Multiply K1 by the standard value of VOC concentration (VOC_standard value), multiply 1-K1 by the standard value of CO2 concentration (CO2_standard value), and add the two multiplication results to obtain a weighted sum. Subtract the weighted sum from the set value (e.g., 100) to obtain the comfort index of the target room. Since the target room is a bedroom, the comfort index can also be called the sleepability index.

[0124] If the target room is a living room, then the weighted pair [K2, 1-K2] can be obtained. Multiply K2 by the VOC concentration standard value (VOC_standard value), multiply 1-K2 by the CO2 concentration standard value (CO2_standard value), and add the two multiplication results to obtain a weighted sum. Subtract the weighted sum from the set value (e.g., 100) to obtain the comfort index of the target room. Since the target room is a bedroom, the comfort index can also be called the playability index.

[0125] If the target room is a kitchen, then the weighted pair [K4, 1-K4] can be obtained. Multiply K4 by the VOC concentration standard value (VOC_standard value), multiply 1-K4 by the CO2 concentration standard value (CO2_standard value), and add the two multiplication results to obtain a weighted sum value; subtract the weighted sum value from the set value (e.g., 100) to obtain the comfort index of the target room; since the target room is a bedroom, the comfort index can also be called the cooking suitability index.

[0126] This embodiment standardizes the predicted indoor carbon dioxide concentration and measured volatile organic compound concentration for the target room to avoid inaccurate evaluation results due to non-standardized data. Furthermore, in this embodiment, different room types have corresponding weight pairs to avoid using uniform weight pairs, thereby improving the accuracy of the evaluation results and obtaining a more accurate comfort index.

[0127] The method provided in this application can be applied to a fresh air conditioning system, which includes an outdoor air detection module and several indoor air detection modules; each indoor air detection module is arranged in a corresponding room.

[0128] The indoor air quality monitoring module includes a sensor for detecting the concentration of volatile organic compounds (VOCs), a processing device, and a temperature sensor. The outdoor air quality monitoring module includes a processing device, a temperature sensor, and a PM2.5 sensor (for detecting indoor PM2.5 concentration).

[0129] The indoor air quality detection module for the target room can be referred to as the target indoor air quality detection module. The processing equipment of the target indoor air quality detection module can obtain the indoor temperature measurement value of the target room based on the temperature sensor of the module. This processing equipment can also obtain the outdoor temperature measurement value from the temperature sensor of the outdoor air quality detection module. Based on the outdoor temperature measurement value and the indoor temperature measurement value of the target room, the processing equipment obtains the indoor-outdoor temperature difference value. The processing equipment can also obtain the outdoor air PM2.5 measurement value from the PM2.5 sensor of the outdoor air quality detection module.

[0130] like Figure 7 As shown, the processing equipment can determine whether the comfort index of the target room is lower than the comfort index threshold. If the comfort index of the target room is lower than the comfort index threshold, it can determine whether the PM2.5 measurement value of the outdoor air is lower than the PM2.5 threshold, and whether the indoor-outdoor temperature difference value is lower than the indoor-outdoor temperature difference threshold. If the PM2.5 measurement value of the outdoor air is lower than the PM2.5 threshold, and the indoor-outdoor temperature difference value is lower than the indoor-outdoor temperature difference threshold, the processing equipment can control the fresh air of the target room to be turned on and set the corresponding air volume. If the PM2.5 measurement value of the outdoor air is not lower than the PM2.5 threshold, or the indoor-outdoor temperature difference value is not lower than the indoor-outdoor temperature difference threshold, the fresh air of the target room will not be turned on temporarily.

[0131] In one embodiment, a processing device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps in the various method embodiments described above.

[0132] In one embodiment, a fresh air conditioning system is provided, which includes a plurality of indoor air detection modules; each indoor air detection module is arranged in a corresponding room; the indoor air detection module includes a concentration detection sensor and the processing device described in the above embodiment; the concentration detection sensor is used to detect the concentration of volatile organic compounds.

[0133] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the various method embodiments described above.

[0134] In one embodiment, a computer program product is provided having a computer program stored thereon, the computer program being executed by a processor of the steps described in the various method embodiments above.

[0135] To better understand this application, an application example is described in detail below. In this application example, the indoor carbon dioxide prediction method is applied to a fresh air conditioning system. The fresh air conditioning system can introduce fresh air to improve indoor air quality. The fresh air conditioning system may include an outdoor air detection module and several indoor air detection modules. Both the outdoor and indoor air detection modules belong to the category of air detection modules; the outdoor air detection module includes a temperature sensor, a humidity sensor, a processing device, and a wireless communication unit; the indoor air detection module includes a temperature sensor, a humidity sensor, a VOC sensor, a processing device, and a wireless communication unit.

[0136] The processing device includes a chip capable of deploying lightweight AI models, which are used to process and analyze data collected by sensors in real time, supporting localized intelligent decision-making. The AI ​​model deployed on the chip can be a carbon dioxide prediction model, used to equate indoor CO2 concentration from VOC concentration.

[0137] The wireless communication unit can be a WiFi (Wireless Fidelity) unit, used to realize wireless communication between air detection modules, or wireless communication between air detection modules and the central control system, and can also enable the fresh air conditioning system to support remote monitoring and control.

[0138] Regarding the overall sensor network construction and deployment, an indoor air quality monitoring module can be installed at the return air vent of the indoor unit of the fresh air conditioning system in each room to ensure comprehensive air quality monitoring. The monitoring modules communicate with each other via the home's wireless network (such as WiFi). (See reference...) Figure 3 , Figure 3 The deployment scheme for indoor and outdoor air quality monitoring modules is shown. (Refer to...) Figure 4 , Figure 4 The hardware architecture and system communication scheme of the indoor and outdoor air quality detection modules are shown. Each air quality detection module can be equipped with a WiFi unit. Sensors and processing devices within the same air quality detection module communicate with each other via I2C (Inter-Integrated Circuit). The indoor air quality detection module communicates with the indoor unit via UART (Universal Asynchronous Receiver / Transmitter). The outdoor air quality detection module communicates with the outdoor unit via UART. The indoor unit communicates with the outdoor unit via UART.

[0139] In some studies using traditional techniques, under normal physiological conditions in healthy individuals, the body's metabolism is relatively stable, and the levels of exhaled carbon dioxide and VOCs are also relatively stable. Generally, the amount of exhaled carbon dioxide is related to factors such as the rate and depth of breathing, while the VOC content is relatively low and stable, although there may be some differences between individuals, but it is usually within the normal reference range. There is a certain correlation between CO2 concentration and VOC concentration generated by human activity. Therefore, this application example uses VOC concentration measurements collected by a lower-cost VOC sensor, combined with a model, to estimate the equivalent CO2 concentration, thus avoiding the use of a more expensive CO2 sensor.

[0140] This application example can also identify the room type based on the VOC concentration characteristics of the room.

[0141] Each type of room has its own unique functional attributes and air quality characteristics. For example, CO2 concentrations are higher in bedrooms at night, and users are particularly concerned about bedroom CO2 levels because they affect sleep quality. Kitchens and bathrooms contain more organic gases, and users are more concerned about odor levels in these rooms (odors are mainly caused by VOCs). Based on this, this application example also provides customized air quality assessment solutions for different room types, evaluating the comfort index of different room types to improve the overall performance of the fresh air conditioning system and the user experience. When performing fresh air exchange, outdoor PM2.5 levels, temperature, and humidity can be considered.

[0142] This application example involves three algorithms that can be deployed on the chips of corresponding processing devices to achieve localized intelligent processing.

[0143] (1) Room classification algorithm:

[0144] Function: Automatically identify room type based on the room's active time period, the peak-to-valley concentration difference of VOCs in the room, and the concentration change rate of VOCs in the room. Room types include, but are not limited to, bedrooms, kitchens, living rooms, and bathrooms.

[0145] Implementation: When room type detection is triggered, room type detection is performed to ensure that the fresh air conditioning system can perform customized air quality management according to the room function.

[0146] (2) Carbon dioxide prediction model:

[0147] Function: Estimates indoor CO2 concentration in a room by using VOC concentration and other parameters, avoiding the use of expensive CO2 sensors.

[0148] Implementation: Provides reliable CO2 concentration predictions based on features such as VOC concentration and room type.

[0149] (3) Comprehensive air quality evaluation model:

[0150] Function: Based on different room types, a specific evaluation algorithm is determined to comprehensively assess the room's air quality, obtain the room's comfort index, and provide refined air management.

[0151] The process of this application example will be introduced using the target room as an example.

[0152] The processing equipment in the indoor air detection module of the target room can perform at least one room type prediction. Figure 5 The process for predicting room type is illustrated. Specifically, each time the room type is predicted, the processing device can perform the following steps:

[0153] The processing equipment can acquire VOC concentration measurements of the target room throughout the day, forming a VOC concentration dataset based on these measurements. The data in the VOC concentration dataset is then sorted from largest to smallest, and the top Y data points are determined. This top Y data points form the target dataset. The target dataset contains several VOC concentration measurements, each with a corresponding sampling time. The time period to which each VOC concentration measurement belongs is determined, forming datasets for each time period. The amount of data in each time period's dataset is then determined, and the dataset with the most data is identified. The time period corresponding to this dataset is considered the active time period for the target room.

[0154] The processing device can also perform feature recognition based on the VOC concentration dataset to determine the peak-valley concentration difference of VOC in the target room. Specifically, the processing device can determine the maximum and minimum VOC concentration measurements in the VOC concentration dataset, and obtain the peak-valley concentration difference of VOC in the target room based on the difference between the maximum and minimum VOC concentration measurements. The peak-valley concentration difference can include low peak-valley concentration difference, medium peak-valley concentration difference, and high peak-valley concentration difference.

[0155] The processing equipment can also perform feature recognition based on VOC concentration datasets to determine the fastest rate of change in VOC concentration in a target room within a day, thereby obtaining the VOC concentration change rate of the target room. The concentration change rate can include extremely fast concentration change rate, fast concentration change rate, medium concentration change rate, and slow concentration change rate.

[0156] The processing device can acquire standard data for multiple room types and determine the room type of the target room based on the degree of matching between the standard data and the relevant data of the target room (active time period, peak-to-valley concentration difference of VOCs, and concentration change rate).

[0157] If the processing device identifies the room type of the target room multiple times, it can obtain multiple room type identification results. The results of multiple room type identification are statistically analyzed to obtain the cumulative number of times each room type is identified. The room type with the highest cumulative number of times is taken as the room type of the target room.

[0158] After determining the room type of the target room, the indoor carbon dioxide concentration of the target room can be predicted. Figure 6 The process for predicting indoor carbon dioxide concentration is shown.

[0159] Specifically, to predict the indoor carbon dioxide concentration of a target room at time t, the processing equipment can start at time t and backtrack according to a set time step m to determine N sampling times, where N is a positive integer greater than or equal to 1. The N sampling times can be denoted in chronological order as: tm, t-2m, t-3m, ..., tN×m.

[0160] The volatile organic compound concentration measurements collected by the VOC sensor have corresponding sampling times. After determining N sampling times, the processing device can use the N sampling times as an index to determine the volatile organic compound concentration measurements for each of the N sampling times from the volatile organic compound concentration measurements collected by the VOC sensor.

[0161] The volatile organic compound (VOC) concentration measurements at N sampling times are sorted in chronological order to obtain a sequence of VOC concentration measurements.

[0162] After determining N sampling times, for any given sampling time, the processing device can determine the time range in which the sampling time is located within the time range corresponding to each of the multiple time periods, and take the time period corresponding to that time range as the time period to which the sampling time belongs.

[0163] For any of the N sampling times, the processing device can also determine the fresh air opening and closing status of the target room at that sampling time based on the data fed back by the fresh air conditioning system.

[0164] The processing equipment can determine the volatile organic compound concentration measurement value (denoted as VOC_t-m) at the first sampling time tm in the volatile organic compound concentration measurement value sequence. Assuming that the time period to which the first sampling time tm belongs is the sleep period, the fresh air is on at the first sampling time tm, and the target room type is bedroom, then the vector corresponding to the first sampling time tm can be formed as [VOC_t-m, room type_bedroom, fresh air_on, sleep period].

[0165] Following the above method, we can also obtain the vector corresponding to the second sampling time t-2m, for example, [VOC_t-2m, room type_bedroom, fresh air_on, sleep period]; we can also obtain the vector corresponding to the third sampling time t-3m, for example, [VOC_t-3m, room type_bedroom, fresh air_on, sleep period].

[0166] After obtaining the vectors for each of the N sampling times, these vectors can be concatenated to form a matrix, which can then be used as input data.

[0167] After receiving the input data, the processing equipment can input the input data into the carbon dioxide prediction model. Based on the output of the carbon dioxide prediction model, the indoor carbon dioxide concentration value corresponding to the target room is obtained. This indoor carbon dioxide concentration value is a prediction, so it can be called the indoor carbon dioxide concentration prediction value. The indoor carbon dioxide concentration prediction value is measured in ppm (parts per million). An indoor carbon dioxide concentration of X ppm means that there are X volumes of carbon dioxide in every million volumes of air.

[0168] The VOC concentration measurements output by the VOC sensor are relative values. Therefore, after the processing equipment obtains the measured VOC concentration at time t and the predicted indoor carbon dioxide concentration at time t, it can perform standardization processing. The measured VOC concentration at time t can be denoted as VOC_t, and the predicted indoor carbon dioxide concentration at time t can be denoted as CO2_t.

[0169] The processing equipment can determine a period of time tracing back from time t, and determine the maximum VOC concentration measurement value (denoted as VOC_t_max) and the minimum VOC concentration measurement value (denoted as VOC_t_min) within this period. The processing equipment can obtain the difference between the VOC concentration measurement value VOC_t at time t and the minimum VOC concentration measurement value VOC_t_min, which is called the first difference; the processing equipment can obtain the difference between the maximum VOC concentration measurement value VOC_t_max and the minimum VOC concentration measurement value VOC_t_min, which is called the second difference; the processing equipment divides the first difference by the second difference, and multiplies the result by 100% to obtain the standard VOC concentration value. This standardization process can be expressed by the following formula:

[0170] .

[0171] VOC_t represents the measured VOC concentration at time t, VOC_standard value represents the standard VOC concentration, VOC_t_max represents the maximum measured VOC concentration, and VOC_t_min represents the minimum measured VOC concentration.

[0172] The treatment equipment can obtain the upper limit (denoted as a) and lower limit (denoted as b) of the CO2 concentration. The predicted indoor carbon dioxide concentration at time t, CO2_t, is subtracted from the lower limit b, yielding the difference, which is called the third difference. The upper limit (a) of the CO2 concentration is subtracted from the lower limit (b), yielding the fourth difference. The treatment equipment divides the third difference by the fourth difference, and multiplies the result by 100% to obtain the standard CO2 concentration value. This standardization process can be expressed by the following formula:

[0173] CO2 standard value = (CO2_t-b) / (ab)×100%.

[0174] CO2_t represents the predicted indoor carbon dioxide concentration at time t, CO2_standard value represents the standard value of CO2 concentration, a represents the upper limit of CO2 concentration, and b represents the lower limit of CO2 concentration.

[0175] Weight pairs can be pre-set for different room types. Each weight pair includes a first weight and a second weight. The first weight is used to assign the standard value of VOC concentration, and the second weight is used to assign the standard value of CO2 concentration. The sum of the first weight and the second weight in the same weight pair can be 1.

[0176] The weighting pairs for different room types have different values ​​for the first weight, which can be set according to the actual situation. For example, the first weight value for a bedroom should be smaller, and the second weight value for a bedroom should be larger.

[0177] Table 1

[0178]

[0179] Table 1 shows the weighted pairs for the four room types: bedroom, living room, bathroom, and kitchen.

[0180] If the target room is a bedroom, then the weighted pair [K1, 1-K1] can be obtained. Multiply K1 by the standard value of VOC concentration (VOC_standard value), multiply 1-K1 by the standard value of CO2 concentration (CO2_standard value), and add the two multiplication results to obtain a weighted sum. Subtract the weighted sum from the set value (e.g., 100) to obtain the comfort index of the target room. Since the target room is a bedroom, the comfort index can also be called the sleepability index.

[0181] If the target room is a living room, then the weighted pair [K2, 1-K2] can be obtained. Multiply K2 by the VOC concentration standard value (VOC_standard value), multiply 1-K2 by the CO2 concentration standard value (CO2_standard value), and add the two multiplication results to obtain a weighted sum. Subtract the weighted sum from the set value (e.g., 100) to obtain the comfort index of the target room. Since the target room is a bedroom, the comfort index can also be called the playability index.

[0182] If the target room is a kitchen, then the weighted pair [K4, 1-K4] can be obtained. Multiply K4 by the VOC concentration standard value (VOC_standard value), multiply 1-K4 by the CO2 concentration standard value (CO2_standard value), and add the two multiplication results to obtain a weighted sum value; subtract the weighted sum value from the set value (e.g., 100) to obtain the comfort index of the target room; since the target room is a bedroom, the comfort index can also be called the cooking suitability index.

[0183] After obtaining the comfort index of the target room, the processing equipment can determine whether to turn on the fresh air supply to the target room. Figure 7 The relevant process is illustrated. Specifically, the processing device can determine whether the comfort index of the target room is lower than a comfort index threshold; if the comfort index of the target room is lower than the comfort index threshold, such as... Figure 8 As shown, the processing device can perform the following steps to obtain relevant data: the processing device can obtain the indoor temperature measurement value of the target room from the temperature sensor of the target indoor air detection module, obtain the outdoor temperature measurement value from the temperature sensor of the outdoor air detection module, and obtain the indoor and outdoor temperature difference value based on the outdoor temperature measurement value and the indoor temperature measurement value of the target room; the processing device can obtain the PM2.5 measurement value of the outdoor air from the PM2.5 sensor of the outdoor air detection module.

[0184] The processing equipment can determine whether the measured value of PM2.5 in the outdoor air is lower than the PM2.5 threshold and whether the indoor-outdoor temperature difference is lower than the indoor-outdoor temperature difference threshold. If the measured value of PM2.5 in the outdoor air is lower than the PM2.5 threshold and the indoor-outdoor temperature difference is lower than the indoor-outdoor temperature difference threshold, the processing equipment can control the fresh air of the target room to be turned on and set the corresponding air volume. If the measured value of PM2.5 in the outdoor air is not lower than the PM2.5 threshold, or the indoor-outdoor temperature difference is not lower than the indoor-outdoor temperature difference threshold, the fresh air of the target room will not be turned on temporarily.

[0185] This application example can reduce the cost of a fresh air conditioning system, making it suitable for large-scale deployment throughout the house, covering more areas, and improving detection accuracy. Furthermore, the distributed deployment of air detection modules provides more comprehensive air quality data, avoiding the inaccuracies of a single sensor. The processing device's chip can be equipped with corresponding algorithms to achieve real-time adjustments to indoor air quality, reducing latency and improving system response speed.

[0186] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0187] Based on the same inventive concept, this application also provides an indoor carbon dioxide concentration prediction device for implementing the indoor carbon dioxide concentration prediction method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more indoor carbon dioxide concentration prediction device embodiments provided below can be found in the limitations of the indoor carbon dioxide concentration prediction method described above, and will not be repeated here.

[0188] In one embodiment, such as Figure 9 As shown, an indoor carbon dioxide concentration prediction device is provided, comprising:

[0189] The measurement value acquisition module 901 is used to obtain a sequence of volatile organic compound concentration measurements based on the volatile organic compound concentration measurements of the target room at multiple sampling times.

[0190] The time period and opening / closing determination module 902 is used to determine the time period to which each sampling moment belongs and the fresh air opening / closing status at each sampling moment;

[0191] The input data acquisition module 903 is used to obtain input data based on the sequence of volatile organic compound concentration measurements, the time period to which each sampling time belongs, the fresh air opening and closing status at each sampling time, and the room type of the target room;

[0192] The prediction value acquisition module 904 is used to obtain the predicted value of indoor carbon dioxide concentration for the target room based on the input data and the carbon dioxide prediction model.

[0193] In one embodiment, the input data acquisition module 903 is used for:

[0194] Each sampling time is sequentially taken as the target sampling time; based on the volatile organic compound concentration measurement value of the target sampling time in the volatile organic compound concentration measurement value sequence, the time period to which the target sampling time belongs, the fresh air opening and closing status of the sampling time, and the room type of the target room, the vector corresponding to the target sampling time is obtained; based on the vectors corresponding to multiple sampling times, the input data is obtained.

[0195] In one embodiment, the apparatus further includes a room type prediction module for:

[0196] Based on the measured volatile organic compound (VOC) concentration values ​​of the target room within a unit of time, a VOC concentration dataset is obtained; based on the VOC concentration dataset, the active periods of the target room within multiple time periods of the unit of time are determined; based on the VOC concentration dataset, the peak-to-valley concentration difference of the target room with respect to VOCs is determined; based on the VOC concentration dataset, the concentration change rate of the target room with respect to VOCs is determined; based on the active periods, peak-to-valley concentration difference, and concentration change rate, the room type of the target room is obtained.

[0197] In one embodiment, the apparatus further includes a room type prediction module for:

[0198] Based on the relative magnitudes of the data, a target dataset is determined within the volatile organic compound concentration dataset; the data in the target dataset is classified according to the time period to which the sampling time corresponds, resulting in datasets corresponding to multiple time periods per unit duration; the active time period of the target room is determined based on the amount of data included in the datasets corresponding to each time period.

[0199] In one embodiment, the apparatus further includes a room type prediction module for:

[0200] A first degree of matching is obtained based on the degree of matching between the active period and the standard active period of the target room type; a second degree of matching is obtained based on the degree of matching between the peak-valley concentration difference and the standard peak-valley concentration difference of the target room type; a third degree of matching is obtained based on the degree of matching between the concentration change rate and the standard concentration change rate of the target room type; and a determination is made as to whether the target room type is determined as the room type of the target room based on the first degree of matching, the second degree of matching, and the third degree of matching.

[0201] In one embodiment, the device further includes a comfort index determination module, used for:

[0202] The predicted indoor carbon dioxide concentration of the target room is standardized to obtain the standard value of indoor carbon dioxide concentration; the measured value of volatile organic compound (VOC) concentration of the target room is standardized to obtain the standard value of VOC concentration; according to the room type of the target room, the corresponding weight pair is determined; according to the weight pair, the standard value of indoor carbon dioxide concentration and the standard value of VOC concentration are weighted and summed to obtain the corresponding comfort index of the target room.

[0203] The modules in the aforementioned indoor carbon dioxide concentration prediction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the processing device in hardware form or independent of it, or stored in the memory of the processing device in software form, so that the processor can call and execute the corresponding operations of each module.

[0204] In one exemplary embodiment, a processing device is provided, the internal structure of which can be as shown in the figure. Figure 10 As shown, the processing device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and data storage units. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The data storage units store the data involved in the aforementioned methods. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for predicting indoor carbon dioxide concentration.

[0205] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the processing device to which the present application is applied. The specific processing device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0206] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0207] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, data storage units, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited thereto.

[0208] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0209] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for predicting indoor carbon dioxide concentration, characterized in that, The method includes: Based on the volatile organic compound (VOC) concentration measurements of the target room at multiple sampling times, a sequence of VOC concentration measurements was obtained. Determine the time period to which each sampling moment belongs and the fresh air opening / closing status at each sampling moment; The input data is obtained based on the sequence of volatile organic compound concentration measurements, the time period to which each sampling time belongs, the fresh air opening and closing status at each sampling time, and the room type of the target room; Based on the input data and the carbon dioxide prediction model, the predicted indoor carbon dioxide concentration for the target room is obtained.

2. The method according to claim 1, characterized in that, Based on the sequence of volatile organic compound concentration measurements, the time period to which each sampling time belongs, the fresh air opening / closing status at each sampling time, and the room type of the target room, the input data is obtained, including: Each sampling time is sequentially used as the target sampling time; Based on the volatile organic compound concentration measurement value at the target sampling time, the time period to which the target sampling time belongs, the fresh air opening / closing status at the sampling time, and the room type of the target room in the volatile organic compound concentration measurement value sequence, the vector corresponding to the target sampling time is obtained; The input data is obtained from the vectors corresponding to each of the multiple sampling times.

3. The method according to claim 1, characterized in that, The method further includes: A dataset of volatile organic compound (VOC) concentrations is obtained based on the measured VOC concentrations in the target room over a unit of time. Based on the volatile organic compound concentration dataset, determine the active periods of the target room within multiple time intervals per unit duration; Based on the volatile organic compound concentration dataset, determine the peak-valley concentration difference of volatile organic compounds in the target room; Based on the volatile organic compound concentration dataset, determine the rate of change of volatile organic compound concentration in the target room; The room type of the target room is determined based on the active period, peak-to-valley concentration difference, and concentration change rate.

4. The method according to claim 3, characterized in that, Based on the volatile organic compound concentration dataset, the active periods of the target room within multiple time intervals per unit duration are determined, including: Based on the relative magnitudes between the data, a target dataset is determined within the volatile organic compound concentration dataset; Based on the time period to which the sampling time corresponds to the data, the data in the target dataset is classified to obtain the datasets corresponding to multiple time periods of unit duration; The active time periods of the target room are determined based on the amount of data included in the dataset corresponding to each time period.

5. The method according to claim 3, characterized in that, Based on the active period, peak-to-valley concentration difference, and concentration change rate, the room type of the target room is determined, including: The first matching degree is obtained based on the degree of matching between the active time period and the standard active time period of the target room type; The second matching degree is obtained based on the degree of matching between the peak-valley concentration difference and the standard peak-valley concentration difference of the target room type; A third degree of matching is obtained based on the degree of matching between the concentration change rate and the standard concentration change rate of the target room type; Based on the first matching degree, the second matching degree, and the third matching degree, determine whether to determine the target room type as the room type of the target room.

6. The method according to claim 1, characterized in that, The method further includes: The predicted indoor carbon dioxide concentration for the target room is standardized to obtain the standard indoor carbon dioxide concentration. The measured values ​​of volatile organic compound (VOC) concentration in the target room were standardized to obtain standard values ​​for VOC concentration. Based on the room type of the target room, determine the corresponding weight pairs; Based on the weighted pairs, the standard values ​​of indoor carbon dioxide concentration and volatile organic compound concentration are weighted and summed to obtain the corresponding comfort index of the target room.

7. A device for predicting indoor carbon dioxide concentration, characterized in that, The device includes: The measurement acquisition module is used to obtain a sequence of volatile organic compound (VOC) concentration measurements based on the VOC concentration measurements of the target room at multiple sampling times. The time period and opening / closing determination module is used to determine the time period to which each sampling moment belongs and the fresh air opening / closing status at each sampling moment; The input data acquisition module is used to obtain input data based on the sequence of volatile organic compound concentration measurements, the time period to which each sampling time belongs, the fresh air opening and closing status at each sampling time, and the room type of the target room; The prediction value acquisition module is used to obtain the predicted value of indoor carbon dioxide concentration for the target room based on the input data and the carbon dioxide prediction model.

8. A processing device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes a computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A fresh air conditioning system, characterized in that, The fresh air conditioning system includes: Several indoor air quality detection modules; each indoor air quality detection module is arranged in a corresponding room; the indoor air quality detection module includes: A concentration detection sensor for detecting the concentration of volatile organic compounds; and, The processing apparatus as described in claim 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images