A ventilation optimization method and system

Abstract

The embodiment of the specification discloses a ventilation optimization method and system, the method comprises: obtaining multi-dimensional sensing data based on a sensor, the sensor is arranged in at least one preset position in a sub-region of a room; determining an air index threshold of the sub-region according to a region type corresponding to the sub-region; adjusting a control parameter of a ventilation equipment according to the multi-dimensional sensing data and the air index threshold, the ventilation equipment is arranged in the sub-region.

Description

Technical Field

[0001] This specification relates to the field of environmental engineering, and in particular to a ventilation optimization method and system. Background Technology

[0002] With rapid urbanization, people are paying increasing attention to the impact of indoor environmental quality on their health and quality of life. Ventilation systems can effectively regulate indoor temperature and humidity, providing a comfortable living and working environment, and therefore, their application is gradually expanding.

[0003] CN100447497C provides a ventilation device and its control method, which circulates and exchanges indoor air by releasing stale indoor air to the outside and introducing fresh air into the room. The ventilation device includes a sensing unit and a control unit. The sensing unit senses sensor values ​​generated by heat sources present in the room. The control unit identifies the heat sources present in the room based on the sensed sensor values ​​and estimates the carbon dioxide concentration in the room based on the detection results to control the ventilation operation.

[0004] The above methods only maintain the circulation of indoor and outdoor air and do not involve measures to ensure indoor air quality. Therefore, there is an urgent need to propose a ventilation optimization method and system. Summary of the Invention

[0005] One embodiment of this specification provides a ventilation optimization method. The ventilation optimization method includes: acquiring multi-dimensional sensing data based on sensors, the sensors being deployed at at least one preset location within a sub-region of an indoor space; determining an air quality threshold for the sub-region based on the region type corresponding to the sub-region; and adjusting control parameters of a ventilation device, the ventilation device being installed in the sub-region, based on the multi-dimensional sensing data and the air quality threshold.

[0006] One embodiment of this specification provides a ventilation optimization system, the ventilation optimization system comprising: an acquisition module configured to acquire multidimensional sensing data based on sensors, the sensors being deployed at at least one preset location in a sub-region of an indoor space; a determination module configured to determine an air quality index threshold for the sub-region based on the region type corresponding to the sub-region; and a control module configured to adjust control parameters of a ventilation device based on the multidimensional sensing data and the air quality index threshold, the ventilation device being installed in the sub-region.

[0007] One embodiment of this specification provides a ventilation optimization device, including a processor for executing a ventilation optimization method.

[0008] One embodiment of this specification provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes a ventilation optimization method. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 These are exemplary block diagrams of a ventilation optimization system according to some embodiments of this specification;

[0011] Figure 2 This is an exemplary flowchart of a ventilation optimization method according to some embodiments of this specification;

[0012] Figure 3 This is an exemplary schematic diagram illustrating the determination of air quality thresholds according to some embodiments of this specification;

[0013] Figure 4 This is an exemplary schematic diagram illustrating the adjustment of control parameters of a ventilation device according to some embodiments of this specification;

[0014] Figure 5 This is an exemplary schematic diagram illustrating the determination of target optimization parameters according to some embodiments of this specification. Detailed Implementation

[0015] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0016] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0017] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not specifically singular and may include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps, and these steps do not constitute an exclusive list; the method or apparatus may also include other steps.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0019] The ventilation optimization method and system illustrated in some embodiments of this specification can be applied to scenarios where ventilation equipment is present. For example, in a catering setting, the system can intelligently turn the ventilation equipment on and off based on indoor air quality, and adjust the power of the ventilation equipment by monitoring the fumes, smoke, and odors generated during cooking in the restaurant kitchen in real time.

[0020] Figure 1 This is an exemplary block diagram of a ventilation optimization system according to some embodiments of this specification.

[0021] In some embodiments, the ventilation optimization system 100 may include an acquisition module 110, a determination module 120, and a control module 130.

[0022] The acquisition module 110 can acquire multidimensional sensing data based on the sensor.

[0023] The determining module 120 can determine the air quality threshold of a sub-region based on the region type corresponding to the sub-region. In some embodiments, the sub-region is a dining area, and the air quality threshold of the sub-region is determined based on the spatial characteristics of the sub-region.

[0024] The control module 130 can adjust the control parameters of the ventilation equipment based on multi-dimensional sensor data and air quality thresholds. In some embodiments, the control module can generate candidate optimization parameters based on multi-dimensional sensor data, which are configured as parameters for controlling the ventilation equipment; predict the air quality forecast values ​​corresponding to the candidate optimization parameters at a preset future time; determine the target optimization parameters based on the candidate optimization parameters whose air quality forecast values ​​meet preset conditions; and adjust the control parameters of the ventilation equipment based on the target optimization parameters. In some embodiments, the control module can, in response to the sub-area being a dining area, predict the optimized perceived values ​​corresponding to the candidate optimization parameters at a preset future time; and determine the target optimization parameters based on the air quality forecast values ​​and the optimized perceived values.

[0025] It should be noted that the above description of the ventilation optimization system and its modules is for convenience only and should not be construed as limiting this specification to the embodiments described. It is understood that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles. In some embodiments, Figure 1 The acquisition module, determination module, and control module disclosed herein can be different modules within a single system, or a single module can implement the functions of two or more of the aforementioned modules. For example, the modules can share a single storage module, or each module can have its own separate storage module. Such variations are all within the scope of protection of this specification.

[0026] Figure 2 This is an exemplary flowchart illustrating a ventilation optimization method according to some embodiments of this specification. Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 may be executed by a processor.

[0027] Step 210: Acquire multidimensional sensing data based on sensors, with the sensors deployed at at least one preset location in a sub-area of ​​the room.

[0028] A sensor is a device used to sense information. Sensors can include temperature sensors, humidity sensors, particulate matter (PM2.5 / PM10) sensors, smoke sensors, and volatile organic compound (VOC) sensors.

[0029] Preset locations refer to suitable installation sites for sensors within a sub-area. For example, temperature sensors, used to measure air temperature, can be preset in the center of the room or away from direct heat sources; humidity sensors, used to measure the moisture content in the air, can be preset in locations similar to temperature sensors, avoiding direct moisture interference; particulate matter sensors, used to detect fine particulate matter suspended in the air, can be preset near breathing areas or away from doors, windows, or vents; smoke sensors, used to detect smoke particles in the indoor environment, can provide early warning of potential fires, and can be preset near open flames; volatile organic compound (VOC) sensors, used to detect harmful chemical gases in the air, such as formaldehyde and benzene, can be preset in the center of the room or near potential VOC sources.

[0030] A sub-area refers to a larger area that has been divided into smaller areas based on historical experience. In some embodiments, an indoor area can be divided into multiple sub-areas. For example, in a restaurant, the indoor area can be divided into dining area, food preparation area, kitchen area (cooking area), cashier area, and other sub-areas.

[0031] Multidimensional sensing data refers to the aggregated data collected from different sensors. For example, multidimensional sensing data can include smoke sensing data, volatile organic compound sensing data, and PM2.5 sensing data.

[0032] Step 220: Determine the air quality threshold for the sub-region based on the region type corresponding to the sub-region.

[0033] Zone types can represent different functions, uses, characteristics, or management needs of a zone. In some embodiments, zone types may include at least one of a food preparation zone, a cooking zone, and a dining zone.

[0034] Air quality thresholds are numerical standards set for assessing and managing air quality. In some embodiments, if the current multidimensional sensor data does not meet an air quality threshold, ventilation equipment will respond to improve indoor air quality. For example, if the current multidimensional sensor data exceeds an air quality threshold, ventilation equipment will be activated to improve indoor air quality.

[0035] In some embodiments, air quality thresholds can be set based on the region type of different sub-regions. For example, the processor sets a preset value for the corresponding air quality threshold based on the type of the sub-region, and the preset value can be set based on past data and experience.

[0036] In some embodiments, the indoor sub-area is a cooking area, and the processor can determine the air quality threshold of the indoor sub-area based on the number of cooking stoves in operation within the sub-area. In some embodiments, the indoor sub-area is a dining area, and the processor determines the air quality threshold of the indoor sub-area based on the spatial characteristics of the sub-area. For further explanation on how to determine the air quality threshold, please refer to [link to relevant documentation]. Figure 3 Related descriptions.

[0037] Step 230: Adjust the control parameters of the ventilation equipment based on multidimensional sensor data and air quality thresholds. The ventilation equipment is set in the sub-area.

[0038] Ventilation equipment refers to various devices used to move air and improve indoor air quality. Examples include exhaust fans, air conditioners, and air purifiers.

[0039] In some embodiments, ventilation equipment can be distributed and can be located in different sub-areas of the room, with each device operating independently to achieve air circulation and exhaust.

[0040] Control parameters refer to the index parameters that can control ventilation equipment. For example, control parameters may include air volume, speed, power, etc.

[0041] In some embodiments, control parameters can be adjusted based on multidimensional sensor data and air quality threshold values ​​for each indoor sub-zone, according to preset rules. These preset rules can be set based on historical experience. For example, a preset rule could be that the closer the smoke concentration detected by the smoke detector is to a smoke concentration threshold, the greater the ventilation power of the ventilation equipment should be.

[0042] In some embodiments, based on multidimensional sensing data, several sets of candidate optimization parameters are generated, each set of candidate optimization parameters being configured to control the operation of ventilation equipment; the estimated value of air quality indicators at a preset future time corresponding to each set of candidate optimization parameters is predicted; based on the estimated value of air quality indicators at the preset future time, target optimization parameters are determined; and based on the target optimization parameters, the control parameters of the ventilation equipment are adjusted. In some embodiments, the processor can predict the optimized perception estimate of each dining location at a preset future time corresponding to each set of candidate optimization parameters / candidate optimization sub-parameters, based on the area type of the indoor sub-region; based on the estimated value of air quality indicators at the preset future time and the optimized perception estimate, target optimization parameters are determined; and based on the target optimization parameters, the control parameters of the ventilation equipment are adjusted. For more explanation on how to adjust the control parameters, please refer to [link to relevant documentation]. Figure 5 Related descriptions.

[0043] By dividing the indoor area into several zones and installing different sensors in each zone, more accurate sensor data can be obtained, allowing for real-time monitoring of indoor air conditions and ensuring that the air quality indicators of each zone meet its specific functions and requirements. Determining the air quality indicator thresholds for each zone and adjusting the control parameters of the ventilation equipment accordingly allows for precise control of air quality, preventing over-ventilation while ensuring indoor air quality.

[0044] It should be noted that the above description of process 200 is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to process 200 under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0045] Figure 3 This is an exemplary schematic diagram illustrating the determination of air quality thresholds according to some embodiments of this specification.

[0046] In some embodiments, the air quality index threshold 360 is related to the region type 310, and different region types can correspond to different methods of determining the air quality index threshold.

[0047] In some embodiments, zone type 310 includes cooking zone 311. In some embodiments, in response to a sub-zone being a cooking zone 311, the processor can determine an air quality threshold 360 for the sub-zone based on the number 330 of cooktops in the sub-zone that meet preset conditions.

[0048] For details regarding region types, sub-regions, and air quality index thresholds, please refer to [link / reference]. Figure 2 Corresponding description.

[0049] A cooking area refers to an area used for cooking. For example, a cooking area can be a back kitchen or a kitchen.

[0050] In some embodiments, the preset conditions may include whether the stove is in working condition. When the stove is in working condition, the processor counts the number of stoves. For example, the processor may determine the working condition of the stoves in the cooking area, counting once when a stove is in working condition, until the condition of all stoves in the cooking area has been determined. The processor then determines the number of stoves in working condition based on the total count.

[0051] In some embodiments, the processor can determine the air quality threshold for a sub-region based on preset rules, according to the number of stoves meeting preset conditions within that sub-region. For example, since a larger number of operating cooking stoves may result in a higher rate of harmful gas production and a faster decline in air quality, the air quality threshold can be set more strictly to allow for timely ventilation intervention before the air quality in the area deteriorates, thus ensuring air quality. Therefore, the preset rules may include: the larger the number of stoves meeting the preset conditions, the smaller the air quality threshold.

[0052] Some embodiments in this specification, by establishing preset conditions and preset rules, can combine the characteristics of the cooking area, and based on the number of stoves that meet the preset conditions and preset rules, determine more realistic air quality thresholds, so that ventilation equipment can be more effectively controlled in the future.

[0053] In some embodiments, region type 310 includes dining region 312. In some embodiments, in response to a sub-region being dining region 312, the processor can determine an air quality threshold 360 for the sub-region based on the spatial characteristics 340 of the sub-region.

[0054] The dining area refers to the area where users eat. For example, the dining area can be a restaurant or a dining area.

[0055] Spatial features are data that reflect the spatial characteristics of a sub-region. For example, spatial features may include the spatial volume of the sub-region.

[0056] In some embodiments, the processor can determine the air quality threshold based on the spatial features of a sub-region using various methods. For example, the processor can retrieve and determine a matching first reference vector from a first vector database based on a first feature vector, thereby determining the air quality threshold for the corresponding subspace. The first feature vector can be composed of spatial features (such as the spatial volume of the subspace) of the subspace whose air quality threshold is to be determined. The first vector database is composed of first reference vectors, which can be based on the spatial features of the dining area in historical data. Each first reference vector corresponds to a reference index threshold. When the first feature vector matches a first reference vector in the first vector database, the reference index threshold corresponding to that vector can be used as the air quality threshold for the subspace corresponding to the first feature vector. The reference index threshold is determined based on prior knowledge and historical data; the larger the spatial volume, the more lenient the reference index threshold can be set, i.e., it can be set larger. In some embodiments, matching can be based on cosine similarity, Euclidean distance, etc., between vectors, selecting the vector with the highest similarity (shortest distance) as the matching vector.

[0057] In some embodiments, spatial features may also include natural ventilation area.

[0058] Natural ventilation area refers to the area that allows for natural air exchange with the external environment. For example, natural ventilation area can be the total area of ​​windows that can be opened in a sub-area.

[0059] In some embodiments, when the spatial features include spatial volume and natural ventilation area, the processor can add the natural ventilation area from historical data to a reference vector in the first vector database constructed above, and then determine the air quality index threshold by matching the reference vector in the first vector database. The specific matching method can be found in the previous description. The reference index threshold of the reference vector can be further adjusted based on the natural ventilation area as described above; for example, the larger the natural ventilation area, the larger the air quality index threshold can be set.

[0060] In some embodiments of this specification, the natural ventilation area is taken as a factor of spatial characteristics. By determining the air index threshold through vector matching based on spatial characteristics, the influence of natural ventilation on air index in addition to space volume can be taken into account, so as to formulate a more reasonable air index threshold and make the control parameters of subsequent ventilation equipment more in line with the actual situation.

[0061] In some embodiments, the processor can determine the dish characteristics 350 of a sub-region and determine an air quality index threshold 360 based on the spatial characteristics 340 and the dish characteristics 350.

[0062] Dishes characteristics refer to features related to the dishes served in a dining area. In some embodiments, dishes characteristics can be the type of dish for each dish at each dining location; for example, dishes characteristics could be Cantonese cuisine, barbecue, hot pot, etc. A dining location refers to a concentrated area where users dine within the dining area; for example, each table can correspond to one dining location.

[0063] In some embodiments, the processor can determine the characteristics of the dish through user input or image recognition.

[0064] Because hot dishes contain a large amount of moisture, they evaporate into water vapor. This water vapor liquefies upon encountering cold air and releases heat. This process can affect air circulation speed, temperature, and humidity, thus influencing the setting of reference index thresholds. Therefore, in some embodiments, the processor can add the dish features of each dining location from historical data to a first reference vector in the first vector database constructed above. Then, by matching the first reference vector in the first vector database, the air quality index threshold is determined. The specific matching method can be found in the preceding description. The reference index threshold of the first reference vector can be further adjusted based on the dish features of each dining location, building upon the preceding description.

[0065] Different types of dishes in a dining area can affect the airflow within that area. Some embodiments in this specification demonstrate that by taking into account the characteristics of the dishes when determining air quality thresholds, the accuracy of the air quality thresholds can be improved, making the subsequent ventilation optimization process more based on evidence and more targeted.

[0066] When the sub-area type is a dining area, some embodiments of this specification determine air quality thresholds based on the spatial characteristics of the sub-area, making the determined air quality thresholds more applicable to the corresponding area, so that subsequent adjustments to the control parameters of the ventilation equipment can be more accurate.

[0067] Figure 4 This is an exemplary schematic diagram illustrating the adjustment of control parameters of a ventilation device according to some embodiments of this specification.

[0068] In some embodiments, the processor can generate candidate optimization parameters 420 based on multidimensional sensing data 410; predict the air quality index estimate 430 corresponding to the candidate optimization parameters 420 at a preset future time; determine the target optimization parameter 450 based on the candidate optimization parameters that meet the preset optimization conditions 440 of the air quality index estimate 430; and adjust the control parameters of the ventilation equipment based on the target optimization parameter 450.

[0069] For details regarding multidimensional sensor data, ventilation equipment, and control parameters, please refer to [link / reference]. Figure 2 The corresponding explanation.

[0070] Candidate optimization parameters refer to the control parameters of alternative ventilation equipment. In some embodiments, each set of candidate optimization parameters may include multiple optimized operating values. For example, a set of candidate optimization parameters may include optimized operating values ​​of the ventilation equipment (including optimized operating values ​​of the ventilation control system). The aforementioned optimized operating values ​​of the ventilation control system can be represented by ventilation power.

[0071] In some embodiments, the processor can randomly generate candidate optimization parameters in various ways based on multidimensional sensing data. For example, the processor can determine at least one candidate optimization parameter based on the historical operating parameters of the ventilation equipment. As another example, the processor can retrieve and determine a matching second reference vector from a two-vector database based on a second feature vector, determine historical optimization parameters, and generate candidate optimization parameters based on these historical optimization parameters. The second feature vector can be composed of multidimensional sensing data of the subspace to be matched; the second vector database is composed of a second reference vector, which can be based on multidimensional sensing data of sub-regions in historical data and the corresponding historical optimization parameters. By matching the second feature vector in the second vector database, and based on the historical optimization parameters corresponding to the matched second reference vector, multiple sets of candidate optimization parameters are generated by randomly increasing or decreasing the values ​​of each parameter using a preset algorithm. The algorithm can include linear congruence methods, etc. Matching can be based on cosine similarity, Euclidean distance, etc., for example, the processor can select the vector with the highest similarity (shortest distance) as the matching vector.

[0072] A preset future time refers to a point in time after a predetermined period of time. For example, a preset future time could be two hours later.

[0073] Air quality index forecast refers to the estimated air quality index corresponding to the optimized parameters at a preset future time.

[0074] In some embodiments, the processor can predict the air quality index estimate in multiple ways. For example, the processor can match a third feature vector in a third vector database, and take one or more third reference vectors with a similarity greater than a preset threshold as target vectors; based on the reference air quality index values ​​corresponding to the one or more matched target vectors, the processor can obtain the air quality index estimate corresponding to each set of candidate optimization parameters through weighted calculation.

[0075] The third feature vector comprises candidate operating parameters and spatial characteristics of the ventilation equipment in the sub-region to be matched. The third database includes a third reference vector and its corresponding reference air quality index value. The third reference vector consists of actual optimized parameters and historical spatial characteristics from historical records, and its corresponding reference air quality index value can be determined based on the actual air quality index value after applying the aforementioned optimized parameters. The weighted average can be determined based on the similarity between each set of candidate optimized parameters and one or more matched target vectors. The similarity can be calculated based on cosine distance, Euclidean distance, etc. The actual optimized parameters in the aforementioned historical records can include optimized ventilation operating values.

[0076] As an example, suppose we need to determine the estimated value of the air quality index at a preset future time corresponding to a set of candidate optimization parameters A. Using candidate optimization parameters A as the matching vector, we match in a third vector database, assuming we match three target vectors B, C, and D; the actual value of the air quality index corresponding to target vector B is b1, the actual value of the air quality index corresponding to target vector C is c1, and the actual value of the air quality index corresponding to target vector D is d1; at this time, the estimated value of the air quality index corresponding to candidate optimization parameter A can be determined by formula (1):

[0077] P = k1*b1 + k2*c1 + k3*d1, (1)

[0078] Where P is the predicted air quality index, k1 is related to the matching similarity between candidate optimization parameter A and target vector B, k2 is related to the matching similarity between candidate optimization parameter A and target vector C, and k3 is related to the matching similarity between candidate optimization parameter A and target vector D.

[0079] Preset optimization conditions are used to determine whether candidate optimization parameters are optimal. For example, a preset optimization condition could be: the average value of each predicted indicator in the air quality index prediction value corresponding to the candidate optimization parameter is lower than a preset threshold.

[0080] The target optimization parameter refers to the final optimized parameter of the ventilation equipment. In some embodiments, the processor can select the candidate optimization parameter that meets the preset optimization conditions and has the smallest average value of the predicted air quality indicators as the target optimization parameter.

[0081] In some embodiments, the processor can generate corresponding optimization instructions based on the target optimization parameters; and send the optimization instructions to the ventilation equipment to adjust the control parameters of the ventilation equipment.

[0082] In some embodiments, the control parameters for regulating the ventilation equipment may also include control parameters for temperature and humidity. In this case, the candidate optimization parameters may also include the operating values ​​after temperature control optimization and the operating values ​​after humidity control optimization, which can be represented by heating / cooling power and humidification power, respectively.

[0083] The optimized operating values ​​for temperature and humidity control refer to the optimized operating values ​​for the ventilation equipment. In some embodiments, the optimized operating values ​​for temperature and humidity control can be represented by heating / cooling power and humidification power, respectively.

[0084] In some embodiments, when the candidate optimization parameters include the optimized operating values ​​for temperature control and humidity control, the third feature vector also includes the optimized operating values ​​for temperature control and humidity control. The third reference vector in the third database may also include the actual optimized operating values ​​for temperature control and humidity control from historical records. In some embodiments, the processor can determine the target optimization parameters by matching the third feature vector in the third vector database, and then adjust the control parameters of the ventilation equipment. Specific matching methods and methods for determining the target optimization parameters can be found in the corresponding descriptions above.

[0085] Some embodiments in this specification, by taking into account the optimized operating values ​​of temperature / humidity control, can make the predicted values ​​of determined air indicators more accurate, thereby making the target optimization parameters more comprehensive, so as to combine temperature and humidity to regulate the ventilation equipment, and make the setting of the control parameters of the ventilation equipment more reasonable.

[0086] In some embodiments, in response to a sub-region including a dining area, the estimated air quality value for a future time can also be correlated with the characteristics of the dishes.

[0087] For details regarding the dining area and the characteristics of the dishes, please refer to [link / reference]. Figure 3 The corresponding description.

[0088] In some embodiments, when the sub-region includes a dining area, the third feature vector may also include dish features, and the third reference vector in the third database may also include actual dish features from historical records. By matching the third feature vector in the third vector database, the target optimization parameters are determined, and then the control parameters of the ventilation equipment are adjusted. For specific matching methods and methods for determining the target optimization parameters, please refer to the corresponding descriptions above.

[0089] In some embodiments of this specification, when the sub-region includes a dining area, taking the characteristics of the dishes into account can yield more realistic air quality forecasts, making the subsequently determined target optimization parameters more reasonable and helping to improve the ventilation optimization effect of the dining area.

[0090] Some embodiments in this specification generate candidate optimization parameters based on multi-dimensional sensor data, predict the air quality index estimates corresponding to each group of candidate optimization parameters, determine the target optimization parameters based on the air quality index estimates, and thereby adjust the control parameters of the ventilation equipment. This can generate reasonable and effective optimization parameters for the ventilation equipment in a targeted manner, thereby improving the user experience in various indoor areas.

[0091] Figure 5 This is an exemplary schematic diagram illustrating the determination of target optimization parameters according to some embodiments of this specification.

[0092] In some embodiments, in response to the region type 310 of the sub-region being a dining area, the processor can predict the optimization perception estimate 510 corresponding to the candidate optimization parameter 420 at a preset future time; and determine the target optimization parameter 450 based on the air quality indicator estimate 430 and the optimization perception estimate 510.

[0093] For definitions related to subregions, please refer to [link / reference]. Figure 2 For related explanations and definitions regarding dining areas, please refer to [link / reference]. Figure 3 For related explanations, please refer to the definitions of candidate optimization parameters preset for future times, air quality index estimates, and target optimization parameters. Figure 4 Related explanations.

[0094] The optimized perception prediction value refers to the estimated value of the environmental characteristics sensed in a given area after the ventilation equipment is adjusted and operated with a certain candidate optimized parameter / candidate optimized sub-parameter. In some embodiments, the optimized perception prediction value may include noise perception prediction value, wind speed perception prediction value, temperature perception prediction value, etc. In some embodiments, the optimized perception prediction value may include the estimated value of the environmental characteristics sensed at each dining point in the dining area. Here, the candidate optimized sub-parameter refers to the optimized operating value of one of the parameters included in the candidate optimized parameters.

[0095] In some embodiments, the processor can predict the expected value of optimization perception at a preset future time based on candidate optimization parameters / candidate optimization sub-parameters in various ways. For example, the processor can perform matching in a fourth vector database based on a fourth feature vector, and determine the actual optimization perception value corresponding to the matched fourth reference vector as the expected value of optimization perception for the corresponding candidate optimization parameter / candidate optimization sub-parameter; the fourth feature vector can be composed of candidate optimization parameters / candidate optimization sub-parameters corresponding to the sub-region to be matched, spatial features, the position of each dining point in the sub-region, and the fourth vector database is composed of fourth reference vectors. The fourth reference vector can be composed of candidate optimization parameters / candidate optimization sub-parameters of the sub-region in historical data, spatial features, the position of each dining point in the sub-region, and the corresponding actual optimization perception value. The specific matching process and... Figure 4The method of matching a third feature vector in a third vector database is similar to that used in [the previous method], see [reference]. Figure 4 The corresponding description.

[0096] In some embodiments, the actual optimized perception values ​​in the fourth vector database can be obtained in the following way: for each historical scenario corresponding to a feature vector, sensors (e.g., sensors that can detect sound, wind speed, and temperature) are deployed in advance near each dining location, and the data collected by the sensors is used as the actual optimized perception values ​​of each dining location in that historical scenario; after collecting enough data, the sensors can be removed from each location to save resources.

[0097] In some embodiments, the processor can determine the target optimization parameters based on air quality index predictions and optimized perception predictions through various methods. For example, the processor can score each group of candidate optimization parameters or each candidate optimization sub-parameter using a weighted average. As an example only, for each sub-region, the processor can preset an optimal optimized perception value (such as optimal noise level, optimal wind speed, or optimal temperature). It can then take a weighted average of the average value of each item in the air quality index prediction and the absolute value of the difference between the optimized perception prediction and the optimal optimized perception value to obtain a score for the candidate optimization parameter / sub-parameter. The candidate optimization parameter or combination of candidate optimization sub-parameters with the highest score is then used as the target optimization parameter. The weights can be set by technical personnel based on historical experience.

[0098] In some embodiments, the processor may first filter out candidate optimization parameters that do not meet the threshold conditions from several sets of candidate optimization parameters based on the optimized perception threshold range; and then determine the target optimization parameters based on the preset future air quality index estimates corresponding to the filtered candidate optimization parameters.

[0099] The optimized perception threshold range refers to the range of environmental characteristics that a user can accept while dining. In some embodiments, the optimized perception threshold range may include a noise perception range, a wind speed perception threshold range, and a temperature perception threshold range.

[0100] The noise perception threshold range refers to the range of noise levels that a user can tolerate while dining.

[0101] The wind speed perception threshold range refers to the range of wind speeds that users can accept while dining.

[0102] The temperature perception threshold range refers to the range of temperatures that users can accept while eating.

[0103] Threshold conditions refer to the conditions used to filter candidate optimization parameters. In some embodiments, the threshold condition can be that the proportion of poor experience points is less than or equal to a preset proportion threshold. Specifically, poor experience points are dining locations with poor perceived ventilation optimization, and the preset proportion threshold is used to characterize the highest acceptable proportion of poor experience points; this threshold can be preset manually.

[0104] In some embodiments, the processor can filter out candidate optimization parameters that do not meet the threshold condition from several groups of candidate optimization parameters. For example, the processor can predict the optimized perception estimate for each dining location corresponding to each group of candidate optimization parameters; compare the optimized perception estimate for each dining location corresponding to each group of candidate optimization parameters with the optimized perception threshold range; determine any dining location whose optimized perception estimate does not fall within the threshold range as a poor experience location; calculate the proportion of poor experience locations, i.e., the number of poor experience locations divided by the total number of dining locations in the area; and remove candidate optimization parameters whose proportion of poor experience locations is greater than a preset proportion threshold from several groups of candidate optimization parameters.

[0105] In some embodiments, the processor can determine the target optimization parameters based on the predicted air quality indicators at preset future times corresponding to the eliminated candidate optimization parameters. For example, the processor can utilize... Figure 5 The method for determining air quality index estimates involves identifying the predicted air quality index values ​​for preset future times corresponding to the eliminated candidate optimization parameters, and then determining the target optimization parameters based on these predicted air quality index values. For more information on determining air quality index estimates and determining target optimization parameters based on these estimates, please refer to [link to relevant documentation]. Figure 4 The corresponding description.

[0106] In some embodiments of this specification, candidate optimization parameters that do not meet the threshold conditions are filtered out based on the optimized perception threshold range, and more reasonable candidate optimization parameters are retained for subsequent processes. In these subsequent processes, the optimized perception prediction value no longer needs to be considered, which can improve the processing efficiency of the processor. This makes the air index prediction value corresponding to the determined candidate optimization parameters at the preset future time more reasonable, thereby determining more reasonable target optimization parameters.

[0107] In some embodiments, different dining locations may have different optimized perception threshold ranges, which may also be related to the spatial characteristics of the sub-region and the characteristics of the dishes at the current dining location.

[0108] In some embodiments, the spatial characteristics of a sub-region may include spatial volume and natural ventilation area. The relevant definitions of spatial volume and natural ventilation area can be found in [reference needed]. Figure 3 The corresponding description.

[0109] In some embodiments, the processor can determine the optimized perception threshold interval corresponding to a dining location based on the dish features and spatial features of the corresponding sub-region, using various methods. For example, the processor can match a fifth feature vector in a fifth vector database, and determine the optimized perception threshold interval corresponding to the dining location through the reference perception threshold interval corresponding to the matched fifth reference vector. The fifth feature vector can be composed of the dish features and spatial features (such as spatial volume and natural ventilation area) of the corresponding sub-region in the current fifth vector database. The fifth vector database is composed of fifth reference vectors. The fifth reference vectors include the dish features, spatial volume, and natural ventilation area of ​​a dining location at a certain historical moment in historical data, and each fifth reference vector also corresponds to a reference perception threshold interval. The matching can be based on cosine similarity, Euclidean distance, etc. For example, the processor can select the fifth reference vector with the highest similarity (shortest distance) to the fifth feature vector as the matching vector, and use the reference perception threshold interval corresponding to the matching vector as the optimized perception threshold interval corresponding to the dining location in the fifth feature vector.

[0110] In some embodiments, the reference perception threshold range of the fifth reference vector can be determined as follows: at the dining location corresponding to the fifth reference vector and at a historical moment, if a customer at that dining location calls a waiter and requests adjustments to the indoor temperature / humidity / wind speed / sound, then it is considered that the indoor temperature / humidity / wind speed / sound at this time (i.e., before adjustment) exceeds the threshold range. The indoor temperature / humidity / wind speed / sound at this time can be used as an endpoint value of a threshold range. For example, if the customer requests a temperature reduction, the current temperature can be used as the upper limit of the temperature perception threshold range. In some embodiments, for similar environments at the same dining location, such as differences in dish characteristics, space volume, and natural ventilation area not exceeding a preset range, if there are multiple historical samples, i.e., multiple endpoint values, the average value can be taken to obtain the endpoint value of the final optimized perception threshold range corresponding to that dining location.

[0111] Some embodiments in this specification, by determining different optimized perception threshold ranges for different dining locations in the dining area based on the spatial characteristics and dish characteristics of the sub-area, can make the determination of target optimization parameters more accurate, realize targeted ventilation optimization strategies, and improve the user's dining experience.

[0112] In some embodiments of this specification, when the sub-area is a dining area, by predicting the preset future time-based optimization perception estimate corresponding to each set of candidate optimization parameters / candidate optimization sub-parameters, and then determining the target optimization parameters based on the air index estimate and optimization perception estimate corresponding to each set of candidate optimization parameters / candidate optimization sub-parameters, the determined target optimization parameters can be more evidence-based and accurate, making the control parameters determined based on the target optimization parameters more reasonable and effective in regulating the ventilation equipment.

[0113] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0114] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0115] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0116] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0117] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0118] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0119] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A ventilation optimization method, characterized in that, Executed by the processor, including: The sensor acquires multidimensional sensing data based on the sensor, which is deployed at at least one preset location in a sub-area of ​​the room. The air quality threshold of the sub-region is determined based on the region type corresponding to the sub-region; Based on the multidimensional sensor data and the air quality threshold, the control parameters of the ventilation equipment are adjusted, and the ventilation equipment is set in the sub-area; The area type includes a dining area, and determining the air quality threshold of the sub-area based on its corresponding area type includes: In response to the sub-region being the dining area, the air quality index threshold of the sub-region is determined based on the spatial characteristics and food type of the sub-region; The step of adjusting the control parameters of the ventilation equipment based on the multidimensional sensing data and the air quality index threshold includes: Based on the multidimensional sensing data, candidate optimization parameters are generated, and these candidate optimization parameters are configured as parameters for controlling the ventilation equipment. In response to the sub-region being the dining area, predict the air quality index estimate of the candidate optimization parameters at a preset future time. Based on the candidate optimization parameters that meet the preset optimization conditions, the target optimization parameters are determined. The preset optimization conditions are that the average value of each predicted index value in the predicted air index value corresponding to the candidate optimization parameters is lower than the preset value of the air index threshold. Based on the target optimization parameters, the control parameters of the ventilation equipment are adjusted.

2. The method as described in claim 1, characterized in that, The process of determining the target optimization parameters based on candidate optimization parameters that meet preset optimization conditions, according to the air quality index prediction values, includes: In response to the sub-region being the dining area, the optimization perception estimate of the candidate optimization parameters at the preset future time is predicted. Based on the air quality index prediction and the optimized perception prediction, the target optimization parameters are determined.

3. A ventilation optimization system, characterized in that, include: The acquisition module is configured to acquire multidimensional sensing data based on sensors, which are deployed at at least one preset location in a sub-area of ​​the room. The determination module is configured to determine the air quality threshold of the sub-region based on the region type corresponding to the sub-region; The control module is configured to adjust the control parameters of the ventilation equipment based on the multidimensional sensing data and the air quality index threshold, wherein the ventilation equipment is located in the sub-region. The area type includes a dining area, and the determining module is further configured to: In response to the sub-region being the dining area, the air quality index threshold of the sub-region is determined based on the spatial characteristics and food type of the sub-region; The control module is further configured as follows: Based on the multidimensional sensing data, candidate optimization parameters are generated, and these candidate optimization parameters are configured as parameters for controlling the ventilation equipment. In response to the sub-region being the dining area, predict the air quality index estimate of the candidate optimization parameters at a preset future time. Based on the candidate optimization parameters that meet the preset optimization conditions, the target optimization parameters are determined. The preset optimization conditions are that the average value of each predicted index value in the predicted air index value corresponding to the candidate optimization parameters is lower than the preset value of the air index threshold. Based on the target optimization parameters, the control parameters of the ventilation equipment are adjusted.

4. The system according to claim 3, characterized in that, The control module is further configured as follows: In response to the sub-region being the dining area, the optimization perception estimate of the candidate optimization parameters at the preset future time is predicted. Based on the air quality index prediction and the optimized perception prediction, the target optimization parameters are determined.

5. A ventilation optimization device, characterized in that, The device includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is configured to execute at least a portion of the computer instructions to implement the method as described in any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions. When the computer reads the computer instructions in the computer-readable storage medium, the computer executes the method as described in any one of claims 1 to 2.

Images