Odor detection method and system, program product and equipment

Abstract

The embodiment of the invention discloses a peculiar smell detection method and system, a program product and equipment. The method comprises the following steps: acquiring peculiar smell gas data in a current scene collected by a sensor assembly; calculating current peculiar smell index data in the current scene by utilizing a peculiar smell calculation strategy based on the peculiar smell gas data; acquiring actual peculiar smell index data in the current scene; adjusting the peculiar smell calculation strategy based on the current peculiar smell index data and the actual peculiar smell index data, and calculating peculiar smell index data in the current scene based on the adjusted peculiar smell calculation strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of software detection, and in particular to an odor detection method, an odor detection system, a computer program product and an odor detection device. Background Art

[0002] As people's living standards continue to improve, the demand for odor control in public places is also increasing. In odor detection environments (such as public toilets), the concentrations of the main odor gases such as ammonia, hydrogen sulfide, methyl mercaptan, and methyl sulfide are very low. Most semiconductor / electrochemical sensors on the market cannot accurately detect their concentrations, resulting in a large deviation between the odor index output by the instrument and the actual value. In addition, the odor index is a subjective feeling of people, and the current odor index cannot be accurately inferred by the concentration of individual gases.

[0003] In the process of implementing the present invention, the inventors found that there are at least the following technical problems in the prior art:

[0004] Since people in different regions and environments have different perceptions of odor, the odor gas detection method in the existing technology is fixed. Once the odor gas detection equipment is installed in a certain location, the parameters cannot be adjusted to adapt to environmental changes, and thus the effect of the odor cannot be accurately measured. Summary of the invention

[0005] In order to improve the existing technical problems, the embodiments of the present invention provide an odor detection method, an odor detection system, a computer program product and an odor detection device, which can at least dynamically adjust the odor calculation strategy, are more suitable for odor monitoring under different environmental climates, and can more accurately monitor the odor conditions in the scene.

[0006] The technical solution of the embodiment of the present invention is achieved as follows:

[0007] In a first aspect, a method for detecting an odor is provided, comprising: obtaining odor gas data in a current scene collected by a sensor component; calculating current odor index data in the current scene based on the odor gas data and using an odor calculation strategy; obtaining actual odor index data in the current scene; adjusting the odor calculation strategy based on the current odor index data and the actual odor index data, and calculating the odor index data in the current scene based on the adjusted odor calculation strategy.

[0008] In a second aspect, a system for detecting an odor is provided, comprising an odor detection device and a server, wherein the odor detection device communicates with the server, the odor detection device is used to execute the odor detection method described in the embodiment of the present application, wherein the server is used to train and update the odor calculation strategy, wherein the odor calculation strategy is a pre-trained odor detection model.

[0009] In a third aspect, a computer program product is provided, including a computer program, wherein the computer program is executed by a processor to implement the odor detection method provided in any embodiment of the present application.

[0010] In a fourth aspect, an odor detection device is provided, comprising a memory for storing a computer program; and a processor for executing the computer program to implement the odor detection method provided in any embodiment of the present application.

[0011] In a fifth aspect, an odor detection device is provided, comprising a sensor component, a controller and an odor feedback component; the sensor component collects odor gas data in a current scene; the odor feedback component obtains actual odor index data in the current scene; the controller calculates current odor index data in the current scene based on the odor gas data and using an odor calculation strategy; based on the current odor index data and the actual odor index data, the odor calculation strategy is adjusted, and based on the adjusted odor calculation strategy, the odor index data in the current scene is calculated.

[0012] The odor detection method and system, odor detection method, odor detection system, computer program product and odor detection device provided in the embodiments of the present application have at least the following beneficial effects:

[0013] In the embodiment of the present application, the sensor component collects odor gas data in the current scene, calculates the current odor index data in the current scene based on the odor gas data and using the odor calculation strategy, compares the current odor index data with the actual odor index data obtained, and adjusts the odor calculation strategy based on the comparison result between the current odor index data and the actual odor index data, so that the odor calculation strategy can be dynamically adjusted to be more suitable for odor monitoring in different environmental climates. Based on the adjusted odor calculation strategy, the odor index data in the current scene is calculated, which can more accurately monitor the odor situation in the scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A schematic diagram of an application scenario of an odor detection method in an embodiment;

[0015] Figure 2 is a schematic diagram of another application scenario of the odor detection method in one embodiment;

[0016] Figure 3 is a flow chart of a method for detecting odor in one embodiment;

[0017] Figure 4 is a flow chart of a method for detecting odor in another embodiment;

[0018] Figure 5is a schematic diagram of an odor detection device in one embodiment;

[0019] Figure 6 Schematic diagram of the structure of an odor detection device in one embodiment. DETAILED DESCRIPTION

[0020] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art of the technical field of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the scope of protection of the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0022] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it should be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0023] See also Figure 1 , is a schematic diagram of an application scenario of the odor detection method provided in an embodiment of the present application, and the application scenario diagram includes an odor detection device 10, and the odor detection device 10 is installed in a scene where odor detection is required, and is used for odor monitoring in the scene. The odor detection device 10 includes a sensor component 101, a controller 102, and an odor feedback component 103, wherein the sensor component 101 is used to collect odor gas data, and the odor gas includes but is not limited to ammonia, hydrogen sulfide, methyl mercaptan, and methyl sulfide. One or more combinations of the sensor component 101 or more sensors. The controller 102 is used to execute the program corresponding to the odor detection method. The odor feedback component 103 includes an odor index input control, through which the feedback group can trigger the odor index input control, thereby obtaining the actual odor index data of the current scene fed back by the feedback group. The actual odor index data represents the real odor index level in the current scene, for example, the odor index level can be represented by a level, set to low, medium, high, etc., and more levels can also be set according to demand, wherein the higher the level, the more smelly the smell. The controller 102 and the sensor component 101 can be integrated together to form a sensor matrix, that is, the odor detection device 10 includes a sensor matrix and an odor feedback component 103. The controller 102 obtains actual odor index data through the odor feedback component 103, adjusts the odor calculation strategy in the scene, and thus accurately monitors the odor in the scene. The feedback population includes but is not limited to professional odorists, sanitation cleaning personnel, or ordinary users.

[0024] Please refer to Figure 2 , is a schematic diagram of another application scenario of the odor detection method provided in the embodiment of the present application, and the application scenario diagram includes an odor detection system, which includes an odor detection device 10 and a server 20. The odor detection device 10 includes the components described in the above embodiment, and also includes a gateway 104. The gateway 104 is used to establish communication between the odor detection device 10 and the server 20. For example, the data collected by the odor detection device 10 is uploaded to the server 20 through the gateway 104, and the instructions or data issued by the server 20 are transmitted to the odor detection device 10 through the gateway 104. The firmware in the odor detection device 10 can be upgraded, and the model parameters can be updated, etc. through the gateway 104. The odor detection device 10 can be one or more. For a region, since the environmental factors in the region vary similarly, the actual odor index data obtained by each odor detection device 10 in the region can be used as reference data to calculate the actual odor index data at the location of other odor detection devices 10. The server 20 can obtain the collected data under real-time environmental data from one or more odor detection devices 10 as samples, update and train the model, obtain updated model parameters, and then send the updated model parameters to the odor detection device 10.

[0025] See also Figure 3 , which is a method for detecting odor provided in an embodiment of the present application, can be applied to Figure 1 The odor detection device 100 shown includes the following steps:

[0026] S11. Obtain odorous gas data in the current scene collected by the sensor component.

[0027] In this embodiment, the current scene is the scene to be monitored by the odor detection device 100, such as a public toilet at a location, etc. The odor gas data includes but is not limited to one or more of the following combinations: concentration data of ammonia, hydrogen sulfide, methyl mercaptan, and methyl sulfide.

[0028] S12. Based on the odor gas data, current odor index data in the current scene is calculated using an odor calculation strategy.

[0029] In this embodiment, the odor calculation strategy can be a calculation formula or a pre-trained odor detection model. In the odor calculation strategy, the independent variable is the odor gas data, and the dependent variable is the current odor index data, wherein the current odor index data is the theoretical odor index data, that is, the data calculated by the odor calculation strategy. Due to changes in environmental factors, the current odor index data may not be accurate data. For example, in the rainy season of autumn and winter, the wind is not very good. It is very likely that the odor calculation strategy used by the odor detection device 10 is no longer applicable to this environment, so the current odor index data may be inaccurate.

[0030] S13, obtaining actual odor index data in the current scene.

[0031] In this embodiment, the actual odor index data represents the actual odor index level data in the current scene. The actual odor index data is obtained based on the data fed back by the feedback group.

[0032] S14. Based on the current odor index data and the actual odor index data, the odor calculation strategy is adjusted, and based on the adjusted odor calculation strategy, the odor index data in the current scenario is calculated.

[0033] In this embodiment, the current odor index data is compared with the actual odor index data. When the current odor index data is not within the index error range of the actual odor index data, it indicates that the current odor index data is inaccurate and the odor calculation strategy needs to be adjusted. When the current odor index data is within the index error range of the actual odor index data, it indicates that the current odor index data is relatively accurate and the odor calculation strategy does not need to be adjusted temporarily. In an optional implementation, each time the current odor index data is calculated, it is compared with the actual odor index data, and the odor calculation strategy can be adjusted in real time according to the comparison result.

[0034] In the above embodiment, the sensor component collects odor gas data in the current scene, calculates the current odor index data in the current scene based on the odor gas data and using the odor calculation strategy, compares the current odor index data with the actual odor index data obtained, and adjusts the odor calculation strategy based on the comparison result between the current odor index data and the actual odor index data, so that the odor calculation strategy can be dynamically adjusted to be more suitable for odor monitoring in different environmental climates. Based on the adjusted odor calculation strategy, the odor index data in the current scene is calculated, which can more accurately monitor the odor situation in the scene.

[0035] In some embodiments, the obtaining of actual odor index data in the current scene includes at least one of the following:

[0036] Acquire current actual odor index data fed back by the odor feedback component in the current scene, and determine the actual odor index data based on the current actual odor index data; or

[0037] Requesting a server to send the actual odor index data, wherein the actual odor index data is calculated based on the target odor index data fed back by the target odor feedback component in the target area where the current scene is located; or

[0038] A request is made to the server to send the target odor index data fed back by the odor feedback component in the target area where the current scene is located, and the actual odor index data is determined according to the target odor index data.

[0039] In this embodiment, the odor detection device in the current scene can also request the server for odor index data fed back by odor feedback components in other odor detection devices in the target area where the current scene is located. The target odor feedback component is the odor feedback component in other odor detection devices in the target area, and the target odor index data is the odor index data fed back by the odor feedback components in other odor detection devices. Since the environmental factors in the same area change almost the same, for example, a city is divided into area A, area B and area C, and there are five odor detection devices in area A, represented by A1, A2, A3, A4 and A5 respectively, and these five odor detection devices are located at different positions in area A respectively. The odor detection device in the current scene is A1, then A1 can request the server for the target odor index data fed back by the other four odor feedback components, and obtain the actual odor index data corresponding to A1 based on the target odor index data fed back by these four odor feedback components.

[0040] In an optional embodiment, the current actual odor index data fed back by the odor feedback component in the current scene is obtained:

[0041] The odor index input operation corresponding to the odor index input control that triggers the odor index input control is obtained through the odor feedback component, and the odor index data corresponding to the obtained odor index input operation is used as the current actual odor index data, wherein the odor index input control includes at least one of the following: a physical button, an interface control on a user interface, wherein different physical buttons correspond to different odor indices, and different odor indices can be input through the interface control.

[0042] In this embodiment, the odor index input control can be a physical button, and each different physical button corresponds to a different odor index. For example, different physical buttons are represented by different colors, red represents high level, yellow represents medium level, and green represents low level. Different odor levels correspond to different odor index ranges. In this way, the feedback group can trigger the corresponding physical button according to their own taste perception. It is also possible to provide a user interface and configure the interface control on the user interface, so that the feedback group can enter the user interface, for example, by scanning the display code to enter the user interface, and then input the corresponding feedback content through the interface control. The interface control includes but is not limited to a drop-down box, an input box, a check box, and the like.

[0043] The feedback group can trigger the corresponding odor index input control according to their own taste perception, thereby obtaining the corresponding odor index input operation, and then obtain the current actual odor index data according to the level corresponding to the odor index input operation, that is, the odor index data corresponding to the level. The odor index data can be a odor index range, or a odor index value. For example, different levels can correspond to different odor index ranges, or different levels correspond to different odor index values. The current actual odor index data can be directly used as the actual odor index data. Since the taste of different feedback groups is different, multiple current actual odor index data can be obtained, and the actual odor index data can be calculated based on multiple current actual odor index data. For example, the odor index data corresponding to the level that accounts for a large proportion of the current actual odor index data is selected as the actual odor index data. For example, there are five levels corresponding to the current actual odor index data, which are high, high, high, high, and medium, respectively, and the odor index data corresponding to the high level is selected as the actual odor index data. In an optional implementation, according to the feedback time corresponding to each current actual odor index data, the current actual odor index data corresponding to the feedback time closest to the current time may be selected as the actual odor index data.

[0044] In an optional implementation, determining the actual odor index data according to the target odor index data includes one or more of the following:

[0045] Obtain the feedback time of each target odor index data, and take the target odor index data with the feedback time closest to the current time as the actual odor index data; or

[0046] Among the multiple target odor index data, the target odor index data corresponding to the level with a relatively large proportion is taken as the actual odor index data.

[0047] The target odor index data of the feedback time is used as the actual odor index data, which can better reflect the odor index in the current environment of the area. According to the target odor index data, the step of determining the actual odor index data can be implemented in the server, or in the odor detection device that sends a request to the server.

[0048] In the above embodiment, the actual odor index data in the current scene can be fed back through the odor feedback component in the own device, or the actual odor index data can be requested from the server, or the target odor index data fed back by the odor feedback components in other odor detection devices in the same area can be requested from the server, and the actual odor index data can be calculated based on the target odor index data, thereby obtaining more accurate actual odor index data, so as to more accurately adjust the odor calculation strategy dynamically and more accurately monitor the odor situation in the scene.

[0049] In some embodiments, the odor calculation strategy is an odor calculation formula, and adjusting the odor calculation strategy based on the current odor index data and the actual odor index data includes:

[0050] When the current odor index data is not within the index error range corresponding to the actual odor index data, multiple groups of sampling data are obtained, each group of sampling data includes the sampled odor gas data collected in the current scene, and the actual sampled odor index data corresponding to the obtained sampled odor gas data;

[0051] A group of sampling data is taken as a sampling point, and multiple sampling points are formed based on the multiple groups of sampling data. The multiple sampling points are fitted to obtain an adjusted odor calculation formula.

[0052] In this embodiment, the index error range can be a range determined according to the actual odor index data. For example, the actual odor index data is a value, and the index error range is within a range of 10% above and below the value. When the current odor index data is not within the index error range corresponding to the actual odor index data, it means that the odor calculation strategy needs to be adjusted, and multiple groups of sampling data in the current scene can be obtained, wherein the sampled odor gas data represents the odor gas data collected by one sampling, and the actual sampled odor index data represents the actual odor index data corresponding to the sampled odor gas data. The acquisition of the actual sampled odor index data is similar to the acquisition method of the actual odor index data described in the above embodiment, and will not be repeated here. After collecting multiple groups of sampling data under the current environment of the current scene, these multiple groups of sampling data are fitted to obtain an adjusted odor calculation formula, and the adjusted odor calculation formula is more adaptable to the current environment, so that the odor detection is more accurate. The fitting method includes but is not limited to linear fitting, nonlinear fitting, etc.

[0053] In the above embodiment, the odor detection device installed in a certain scene can obtain multiple groups of sampling data when the current odor index data is not within the index error range corresponding to the actual odor index data, and perform fitting based on the multiple groups of sampling data to obtain an adjusted odor calculation formula. The adjusted odor calculation formula can better adapt to the current environment, thereby making odor detection more accurate. Therefore, the odor detection device can adaptively adjust the stored odor calculation formula according to environmental changes to make odor detection more accurate.

[0054] In some embodiments, the odor calculation strategy is a pre-trained odor detection model, and adjusting the odor calculation strategy based on the current odor index data and the actual odor index data includes:

[0055] When the current odor index data is not within the index error range corresponding to the actual odor index data, the odor gas data, the current odor index data and the actual odor index data are sent to a server so that the server can update and train the odor detection model;

[0056] Receive the updated trained odor detection model sent by the server.

[0057] In this embodiment, the odor calculation strategy is a pre-trained odor detection model. The odor detection model can be pre-trained in the server, and then the trained odor detection model is sent to the odor detection device. When the current odor index data is not within the index error range corresponding to the actual odor index data, it means that the odor detection model needs to be adjusted. At this time, the odor detection device can send the acquired multiple data to the server so that the server can retrain the odor detection model to obtain an updated trained odor detection model. The multiple data include but are not limited to odor gas data, current odor index data and actual odor index data.

[0058] In the above embodiment, the odor detection device installed in a certain scene can send the acquired multiple data to the server so that the server can update and train the odor detection model when the current odor index data is not within the index error range corresponding to the actual odor index data. The updated and trained odor detection model can better adapt to the current environment, thereby making odor detection more accurate.

[0059] like Figure 4 As shown, Figure 4 This is a flow chart of a method for detecting odor in another embodiment; the flow chart includes the following steps:

[0060] S41. The odor detection device obtains odor gas data in the current scene collected by the sensor component.

[0061] S42. The odor detection device calculates the current odor index data in the current scene based on the odor gas data and using a pre-trained odor detection model.

[0062] S43: The odor detection device obtains actual odor index data in the current scene.

[0063] S44. When the current odor index data is not within the index error range corresponding to the actual odor index data, the odor detection device sends the odor gas data, the current odor index data and the actual odor index data to the server.

[0064] S45. The server adjusts the odor detection model based on the current odor index data and the actual odor index data, and sends the adjusted odor detection model to the odor detection device.

[0065] S46. The odor detection device calculates the odor index data in the current scene based on the adjusted odor detection model.

[0066] In this embodiment, steps S41-S44 and S46 have been described in one or more of the above embodiments and will not be repeated here.

[0067] In some embodiments, the server receives the odor gas data, the current odor index data and the actual odor index data sent by the odor detection device; when the current odor index data is not within the index error range corresponding to the actual odor index data, the server uses the odor gas data as a newly added training sample, and the actual odor index data as a newly added training sample label, adds the newly added training sample and the newly added training sample label to the training data set, continues to train the odor detection model until the training termination condition is reached, and uses the odor detection model after the training termination condition is reached as the updated trained odor detection model.

[0068] In this embodiment, the odor detection model is obtained by training based on a training data set, each sample in the training data set includes a training sample and a training sample label, and the odor gas data is used as a newly added training sample and the actual odor index data is used as a newly added training sample label, and added to the training data set to retrain the odor detection model. In order to speed up the convergence of the model, as many newly added training samples as possible can be collected for training. The training termination conditions include but are not limited to the current number of iterations being greater than or equal to the preset number of iterations.

[0069] In an optional implementation, an iterative method is used to iteratively train the odor detection model, input samples are obtained from the training data set as the input of the odor detection model, and odor index data of this iteration is output; based on the loss function, the odor index data of this iteration, and the training label corresponding to the input sample, the loss value of this iteration is calculated, and based on the loss value of this iteration, it is determined whether this iteration meets the training termination condition; if this iteration does not meet the training termination condition, continue to obtain input samples from the training data set for training until the training termination condition is met, thereby using the odor detection model that meets the training termination condition as the updated trained odor detection model.

[0070] In the above embodiment, the server retrains the odor detection model that needs to be adjusted, and takes the data sent by the odor detection device corresponding to the odor detection model that needs to be adjusted as new samples and adds them to the training data set. In this way, during the training process, the odor detection model can learn more characteristics of odorous gases from the new samples. After the training is completed, the updated trained odor detection model can better adapt to the current environment, thereby making odor detection more accurate.

[0071] In some embodiments, the server stores multiple odor detection models, and the odor detection models corresponding to different areas are trained based on different training data sets, wherein each training sample in each training data set is sample odor gas data and sample actual odor index data collected within the same location area, wherein the sample actual odor index data is the training label corresponding to the sample odor gas data.

[0072] In this embodiment, the odor detection equipment may be distributed in multiple different locations. Since the environment in different regions may be different, different training data sets are used to train the odor detection models in different regions. For example, China is divided into regions A, B and C. Region A represents the southern region, region B represents the northern region, and region C represents the central region. There are 10,000 odor detection devices in region A. Therefore, for regions A, B and C, it is necessary to collect corresponding training samples in their respective regions separately to train various odor detection models. Since the environments are different in different regions, the odor gas detection is also different. For example, for region A, a variety of training samples are obtained at multiple locations in region A, and the odor detection model corresponding to region A is obtained through training. Therefore, each odor detection model is associated with a region.

[0073] In the above embodiment, using different training data sets to train the odor detection model in different areas can make the odor detection model more adaptable to odor detection in the local environment, thereby making odor detection more accurate.

[0074] In some embodiments, the server obtains current environmental data in the current scene, and sends a data collection request to the odor detection device at the current scene when the current environmental data meets the model update condition;

[0075] After receiving the data collection request, the odor detection device collects the current odor gas data in the current environment at the current scene and obtains the actual odor index data in the current environment, and sends them to the server;

[0076] The server uses the current odor gas data as a newly added training sample, and the actual odor index data under the current environment as a newly added training sample label, and adds the newly added training sample and the newly added training sample label to the training data set, and continues to train the odor detection model until the training termination condition is reached, and uses the odor detection model after the training termination condition is reached as the updated trained odor detection model;

[0077] The server sends the updated trained odor detection model to the odor detection device, and the odor detection device updates the stored odor detection model to the updated trained odor detection model.

[0078] In this embodiment, the server can obtain the current environmental data corresponding to the location of the odor detection device through the network. The server will also record the update time of the odor detection model in the odor detection device. When the environmental data corresponding to the update time is not within the environmental error range corresponding to the current environmental data, it means that the model update condition has been met and the odor detection model in the odor detection device needs to be updated. Then the server can actively send a data collection request to the odor detection device. After receiving the data collection request, the odor detection device collects the current odor gas data in the current environment at the current scene and obtains the actual odor index data in the current environment, and sends the obtained multiple data to the server. The server uses the multiple data as newly added training samples to update the odor detection model.

[0079] In the above embodiment, the server monitors the environmental data of the odor detection device, and when the current environmental data meets the model update conditions, it actively sends a data collection request to the odor detection device. The server takes the data sent by the odor detection device corresponding to the odor detection model that needs to be adjusted as new samples and adds them to the training data set. In this way, during the training process, the odor detection model can learn more characteristics of odorous gases from the new samples. After the training is completed, the updated trained odor detection model can better adapt to the current environment, thereby making odor detection more accurate.

[0080] On the other hand, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the odor detection method described in any embodiment of the present application.

[0081] Among them, in the computer program product, the optional implementation form of the program module architecture of the computer program that implements each step of the method can be an odor detection device. Figure 5 On the other hand, an embodiment of the present application provides an odor detection device, including: an acquisition module 51, used to acquire odor gas data in a current scene collected by a sensor component; a calculation module 52, used to calculate current odor index data in the current scene based on the odor gas data and using an odor calculation strategy; the acquisition module 51 is also used to acquire actual odor index data in the current scene; an adjustment module 52 is used to adjust the odor calculation strategy based on the current odor index data and the actual odor index data, and calculate the odor index data in the current scene based on the adjusted odor calculation strategy.

[0082] Optionally, the acquisition module 51 is further used for:

[0083] Acquire current actual odor index data fed back by the odor feedback component in the current scene, and determine the actual odor index data based on the current actual odor index data; or

[0084] Requesting a server to send the actual odor index data, wherein the actual odor index data is calculated based on the target odor index data fed back by the target odor feedback component in the target area where the current scene is located; or

[0085] A request is made to the server to send the target odor index data fed back by the odor feedback component in the target area where the current scene is located, and the actual odor index data is determined according to the target odor index data.

[0086] Optionally, the acquisition module 51 is further used for:

[0087] The odor index input operation corresponding to the odor index input control that triggers the odor index input control is obtained through the odor feedback component, and the odor index data corresponding to the obtained odor index input operation is used as the current actual odor index data, wherein the odor index input control includes at least one of the following: a physical button, an interface control on a user interface, wherein different physical buttons correspond to different odor indices, and different odor indices can be input through the interface control.

[0088] Optionally, the odor calculation strategy is an odor calculation formula, and the adjustment module 52 is further used to:

[0089] When the current odor index data is not within the index error range corresponding to the actual odor index data, multiple groups of sampling data are obtained, each group of sampling data includes the sampled odor gas data collected in the current scene, and the actual sampled odor index data corresponding to the obtained sampled odor gas data;

[0090] A group of sampling data is taken as a sampling point, and multiple sampling points are formed based on the multiple groups of sampling data. The multiple sampling points are fitted to obtain an adjusted odor calculation formula.

[0091] Optionally, the odor calculation strategy is a pre-trained odor detection model, and the adjustment module 52 is further used to:

[0092] When the current odor index data is not within the index error range corresponding to the actual odor index data, the odor gas data, the current odor index data and the actual odor index data are sent to a server so that the server can update and train the odor detection model;

[0093] Receive the updated trained odor detection model sent by the server.

[0094] It should be noted that the structure provided in the embodiment of the present application does not constitute a limitation on the odor detection device, and the various modules can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of the controller in the device in the form of hardware, or can be stored in the memory in the device in the form of software, so that the controller can call and execute the operations corresponding to the above modules. In other embodiments, the odor detection device may include more or fewer modules than shown in the figure.

[0095] See also Figure 6 On the other hand, the present application provides an odor detection device 10, which includes a memory 3011 of one or more computer-readable storage media and a processor 3012 of one or more processing cores. Those skilled in the art will understand that Figure 6 The structure of the odor detection device shown in the figure does not constitute a limitation on the odor detection device 100, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. The memory 3011 stores a computer program, and when the computer program is executed by the processor 3012, the processor 3012 executes the odor detection method provided by any of the above embodiments of the present application.

[0096] The processor 3012 is the control center of the odor detection device, which uses various interfaces and lines to connect various parts of the entire device, and executes various functions of the device and processes data by running or executing software programs and / or modules stored in the memory 3011, and calling data stored in the memory 3011. Optionally, the processor 3012 may include one or more processing cores; preferably, the processor 3012 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user pages and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 3012.

[0097] The memory 3011 can be used to store software programs and modules. The processor 3012 executes various functional applications and data processing by running the software programs and modules stored in the memory 3011. The memory 3011 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory 3011 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 3011 may also include a memory controller to provide the processor 3012 with access to the memory 3011.

[0098] On the other hand, an embodiment of the present application further provides an air-conditioning system, comprising the odor detection device provided in any of the above embodiments of the present application, and at least one air-conditioning device communicatively connected to the odor detection device.

[0099] On the other hand, an embodiment of the present application further provides a storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the odor detection method provided by any of the above embodiments of the present application.

[0100] Those skilled in the art can understand that all or part of the processes in the methods provided in the above embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0101] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for detecting odor, characterized in that: include: Obtain odorous gas data in the current scene collected by the sensor component; Based on the odor gas data, current odor index data in the current scene is calculated using an odor calculation strategy; Obtaining actual odor index data in the current scenario; Based on the current odor index data and the actual odor index data, the odor calculation strategy is adjusted, and based on the adjusted odor calculation strategy, the odor index data in the current scene is calculated.

2. The method for detecting odor according to claim 1, characterized in that: The obtaining of actual odor index data in the current scene includes at least one of the following: Acquire current actual odor index data fed back by the odor feedback component in the current scene, and determine the actual odor index data based on the current actual odor index data; or Requesting a server to send the actual odor index data, wherein the actual odor index data is calculated based on the target odor index data fed back by the target odor feedback component in the target area where the current scene is located; or A request is made to the server to send the target odor index data fed back by the odor feedback component in the target area where the current scene is located, and the actual odor index data is determined according to the target odor index data.

3. The method for detecting odor according to claim 2, characterized in that: The actual current odor index data fed back by the odor feedback component in the current scene is obtained: The odor index input operation corresponding to the odor index input control that triggers the odor index input control is obtained through the odor feedback component, and the odor index data corresponding to the obtained odor index input operation is used as the current actual odor index data, wherein the odor index input control includes at least one of the following: a physical button, an interface control on a user interface, wherein different physical buttons correspond to different odor indices, and different odor indices can be input through the interface control.

4. The method for detecting odor according to any one of claims 1 to 3, characterized in that: The odor calculation strategy is an odor calculation formula, and adjusting the odor calculation strategy based on the current odor index data and the actual odor index data includes: When the current odor index data is not within the index error range corresponding to the actual odor index data, multiple groups of sampling data are obtained, each group of sampling data includes the sampled odor gas data collected in the current scene, and the actual sampled odor index data corresponding to the obtained sampled odor gas data; A group of sampling data is taken as a sampling point, and multiple sampling points are formed based on the multiple groups of sampling data. The multiple sampling points are fitted to obtain an adjusted odor calculation formula.

5. The odor detection method according to any one of claims 1 to 3, characterized in that: The odor calculation strategy is a pre-trained odor detection model, and adjusting the odor calculation strategy based on the current odor index data and the actual odor index data includes: When the current odor index data is not within the index error range corresponding to the actual odor index data, the odor gas data, the current odor index data and the actual odor index data are sent to a server so that the server can update and train the odor detection model; Receive the updated trained odor detection model sent by the server.

6. A peculiar smell detection system, characterized in that: The invention comprises an odor detection device and a server, wherein the odor detection device communicates with the server, wherein the odor detection device is used to execute the odor detection method as described in any one of claims 1 to 3 and 5, wherein the server is used to train and update the odor calculation strategy, wherein the odor calculation strategy is a pre-trained odor detection model.

7. The odor detection system according to claim 6, characterized in that: The server receives the odor gas data, the current odor index data and the actual odor index data sent by the odor detection device; When the current odor index data is not within the index error range corresponding to the actual odor index data, the server uses the odor gas data as a newly added training sample, and the actual odor index data as a newly added training sample label, and adds the newly added training sample and the newly added training sample label to the training data set, and continues to train the odor detection model until the training termination condition is reached, and uses the odor detection model after the training termination condition is reached as the updated trained odor detection model.

8. The odor detection system according to claim 6, characterized in that: The server stores a plurality of odor detection models, and the odor detection models corresponding to different areas are trained based on different training data sets, wherein each training sample in each training data set is sample odor gas data and sample actual odor index data collected within the same area, wherein the sample actual odor index data is the training label corresponding to the sample odor gas data.

9. The odor detection system according to claim 6, characterized in that: The server obtains current environmental data in the current scene, and sends a data collection request to the odor detection device at the current scene when the current environmental data meets the model update condition; After receiving the data collection request, the odor detection device collects the current odor gas data in the current environment at the current scene and obtains the actual odor index data in the current environment, and sends them to the server; The server uses the current odor gas data as a newly added training sample, and the actual odor index data under the current environment as a newly added training sample label, and adds the newly added training sample and the newly added training sample label to the training data set, and continues to train the odor detection model until the training termination condition is reached, and uses the odor detection model after the training termination condition is reached as the updated trained odor detection model; The server sends the updated trained odor detection model to the odor detection device, and the odor detection device updates the stored odor detection model to the updated trained odor detection model.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the odor detection method according to any one of claims 1 to 5 is implemented.

11. An odor detection device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the odor detection method as claimed in any one of claims 1 to 5.

12. An odor detection device, characterized in that: It includes a sensor component, a controller and an odor feedback component; The sensor component collects odorous gas data in the current scene; The odor feedback component obtains actual odor index data in the current scene; The controller calculates the current odor index data in the current scene based on the odor gas data and using an odor calculation strategy; Based on the current odor index data and the actual odor index data, the odor calculation strategy is adjusted, and based on the adjusted odor calculation strategy, the odor index data in the current scene is calculated.

Images