Digital odor fingerprint generation method and device, equipment, storage medium and product
By generating digital odor fingerprints, the hardware differences between electronic nose devices are resolved, and the odor response characteristics are standardized and portable, supporting cross-device applications and large-scale deployment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHONGKE WEIGAN (NINGBO) TECH CO LTD
- Filing Date
- 2026-01-13
- Publication Date
- 2026-04-21
AI Technical Summary
The sensor arrays of different electronic nose devices have hardware differences, which makes it difficult to compare the response values obtained by the same gas on different devices. This makes it difficult to achieve model transfer and cross-device application, and limits the collaborative networking and large-scale deployment of electronic nose technology.
By acquiring the odor dynamic characteristics and response values of the sensor array and combining them with sensor calibration factors, a digital odor fingerprint is generated to uniformly characterize odor features, eliminate hardware and environmental interference, and achieve cross-device feature alignment.
It achieves the standardization and transferability of odor response characteristics, supports collaborative networking and data interoperability of sensor arrays, facilitates the construction of a unified and universal recognition model, and enables model reuse and remote deployment across devices.
Smart Images
Figure CN121899335A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of sensor technology, and in particular to a method, apparatus, device, storage medium, and product for generating digital odor fingerprints. Background Technology
[0002] With the rapid development of electronic nose technology, it has been widely applied in scenarios such as odor recognition, environmental monitoring, food freshness detection, in-vehicle air quality assessment, and early warning of premature mold growth in stored grains. However, due to significant differences in sensitivity, response speed, amplification gain, and operating temperature among electronic nose devices from different manufacturers, models, and batches, the original response values obtained for the same gas on different devices lack comparability.
[0003] In related technologies, a simple single-channel normalization index is typically used to characterize the sensor response of electronic noses. However, under multi-channel array conditions, the responses of different channels to the same gas vary significantly, and the single-channel normalization index cannot reflect the overall characteristics of the response patterns between channels. Different devices' sensor arrays exhibit hardware differences (such as batch-to-batch sensitivity drift and inconsistent channel arrangements). Single-channel normalization not only fails to eliminate this hardware heterogeneity but also amplifies the feature scale shifts and distribution differences between different devices. Therefore, odor signals output from different sensor arrays cannot be directly compared. Even using the same algorithm model, the output features of different devices still exhibit scale shifts and distribution differences, making model transfer and cross-device applications difficult. This results in the inability to achieve collaborative networking and data interoperability of electronic nose devices in practical applications, and also makes it difficult to build a unified, universal recognition model. Ultimately, this limits the formation of a universal recognition model for electronic nose technology in multi-source heterogeneous environments, and also restricts large-scale deployment and the promotion of cloud services. Summary of the Invention
[0004] To address the aforementioned technical problems, this disclosure provides a method, apparatus, device, storage medium, and product for generating digital odor fingerprints, thereby resolving the issue that odor signals output by different sensor arrays cannot be directly compared, making it difficult to form a universal recognition model.
[0005] In a first aspect, this disclosure provides a method for generating a digital odor fingerprint. The method includes: acquiring at least one dynamic odor feature and a target response value after the response stabilizes for each sensor channel of a target sensor array exposed to a target odor within a preset time period; acquiring a sensor calibration factor of the target sensor array and a standard response value of each sensor channel exposed to air; determining multiple feature values based on the target response value, the standard response value, and the sensor calibration factor, wherein each feature value is used to indicate the relative contribution of the response value of each sensor channel to the total response value of the sensor array; and generating a digital odor fingerprint corresponding to the target odor based on at least one dynamic odor feature value and multiple feature values.
[0006] In one optional implementation, at least one odor dynamic feature includes an odor rise time constant, an odor recovery time constant, and a total stimulation level value of the target odor on the target sensor array. Acquiring at least one odor dynamic feature of each sensor channel of the target sensor array exposed to the target odor within a preset time period includes: acquiring the response value of each sensor channel to the target odor at each of multiple moments within the preset time period; obtaining the total response value of the target sensor array at each of the multiple moments within the preset time period based on the multiple response values; generating a response curve of the target sensor array over time within the preset time period based on the multiple total response values; determining the time required for the target sensor array to rise from the initial total response value to the peak total response value based on the response curve, thus obtaining the odor rise time constant; obtaining the time required for the target sensor array to rise from the peak total response value to the final total response value after the target odor is removed from the target sensor array based on the response curve, thus obtaining the odor recovery time constant; and performing an integral operation on the response curve to obtain the total stimulation level value.
[0007] In one optional implementation, obtaining the sensor calibration factor of the target sensor array includes: obtaining the standard response ratio of a preset sensor array under a standard gas and the target response ratio of the target sensor array under a standard gas; calculating the ratio between the standard response ratio and the target response ratio to obtain the sensor calibration factor.
[0008] In one optional implementation, multiple characteristic values are determined based on the target response value, the standard response value, and the sensor calibration factor, including: calculating the ratio between the target response value and the standard response value to obtain the initial response ratio of each sensor channel; calculating the sum of multiple initial response ratios to obtain the total response ratio of the target sensor array; calculating the product between the initial response ratio and the sensor calibration factor to obtain the calibration response ratio of each sensor channel; and calculating the ratio between the calibration response ratio of each sensor channel and the total response ratio to obtain multiple characteristic values.
[0009] In one optional implementation, generating a digital odor fingerprint corresponding to a target odor based on at least one dynamic odor feature value and multiple feature values includes: merging multiple feature values with at least one dynamic odor feature value to generate a digital odor fingerprint corresponding to the target odor.
[0010] In an optional implementation, the method further includes generating a data structure in a preset format from the digital odor fingerprint, the identifier and model of the target sensor array, the sensor calibration factor, environmental parameters, the sampling timestamp, and the encoding version number.
[0011] Secondly, the present invention provides a digital odor fingerprint generation apparatus, comprising: an acquisition module, configured to acquire at least one dynamic odor feature of each sensor channel of a target sensor array exposed to a target odor and a target response value after the response stabilizes within a preset time period, and to acquire a sensor calibration factor of the target sensor array and a standard response value of each sensor channel exposed to air; a processing module, configured to determine multiple feature values based on the target response value, the standard response value, and the sensor calibration factor, wherein each feature value indicates the relative contribution of the response value of each sensor channel to the total response value of the sensor array; and a generation module, configured to generate a digital odor fingerprint corresponding to the target odor based on at least one dynamic odor feature value and multiple feature values.
[0012] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the digital odor fingerprint generation method described in the first aspect or any corresponding embodiment thereof.
[0013] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the method for generating a digital odor fingerprint as described in the first aspect or any corresponding embodiment thereof.
[0014] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the method for generating a digital odor fingerprint as described in the first aspect or any corresponding embodiment.
[0015] The technical solution provided in this disclosure has the following advantages: This disclosure provides a method, apparatus, device, storage medium, and product for generating digital odor fingerprints. The method generates a digital odor fingerprint corresponding to a target odor using at least one dynamic odor feature value and multiple feature values. Since the digital odor fingerprint includes calibrated steady-state proportion feature values and dynamic odor feature values, it comprehensively characterizes odor attributes from two dimensions: "dynamic action process" and "steady-state response ratio." Dynamic features can distinguish odors with similar components but different volatility characteristics and sensor action mechanisms, while steady-state proportion features eliminate hardware and environmental interference, preserving the core response pattern of the odor. The combination of these two features gives the digital odor fingerprint stronger discriminative power, effectively distinguishing easily confused odors. The digital odor fingerprint preserves the odor distribution pattern across channels while eliminating differences caused by device amplification, gas concentration, and environmental drift. It solves the problem of inability to directly compare odor signals output by different sensor arrays, achieving standardization and transferability of odor response features. It enables collaborative networking and data interoperability of sensor arrays, facilitating the construction of a unified, universal recognition model, and enabling model reuse and remote deployment across devices. Attached Figure Description
[0016] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.
[0017] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart illustrating a method for generating digital odor fingerprints according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating a method for obtaining at least one dynamic odor feature according to an embodiment of the present invention; Figure 3 This is a structural block diagram of a digital odor fingerprint generation device according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0019] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.
[0020] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.
[0021] This application's embodiments are applied to converting the outputs of different electronic nose sensor arrays into a unified, comparable vector form of digital odor fingerprints, enabling the use of digital odor fingerprints in scenarios such as odor recognition, environmental monitoring, food freshness detection, in-vehicle air quality assessment, and early warning of mold growth in stored grains. For example, the digital odor fingerprint is input into an odor recognition model, which outputs the odor type.
[0022] In related technologies, a simple single-channel normalization index is typically used to characterize the sensor response of an electronic nose (also known as a sensor array). However, under multi-channel array conditions, the responses of different channels to the same gas vary significantly, and the single-channel normalization index cannot reflect the overall characteristics of the response patterns between channels. Different devices' sensor arrays have hardware differences, and single-channel normalization not only fails to eliminate this hardware heterogeneity but also amplifies the feature scale shifts and distribution differences between different devices. Therefore, even using the same algorithm model, the output features of different devices still exhibit scale shifts and distribution differences, making model transfer and cross-device applications difficult. This results in the inability to achieve collaborative networking and data interoperability of electronic nose devices in practical applications, and also makes it difficult to build a unified, universal recognition model. Ultimately, this limits the formation of a universal recognition model for electronic nose technology in multi-source heterogeneous environments, and also restricts large-scale deployment and the promotion of cloud services.
[0023] To address the aforementioned technical problems, this application provides a method for generating a digital odor fingerprint. This method acquires at least one dynamic odor feature and a stable target response value for each sensor channel of a target sensor array exposed to a target odor within a preset time period, as well as the sensor calibration factor of the target sensor array and the standard response value of each sensor channel exposed to air. Based on the target response value, the standard response value, and the sensor calibration factor, multiple feature values are determined, each feature value indicating the relative contribution of each sensor channel's response value to the total response value of the sensor array. Based on at least one dynamic odor feature value and multiple feature values, a digital odor fingerprint corresponding to the target odor is generated. This generated digital odor fingerprint constructs a unified odor feature representation system across devices and batches. By fusing sensor dynamic response features, steady-state response relative contributions, and standardized calculation logic embedding calibration factors and air baselines, the original response data of electronic nose sensor arrays of different models and batches are transformed into digital odor fingerprints with unified dimensions, unified feature dimensions, and unified discrimination standards.
[0024] Figure 1This is a flowchart illustrating a method for generating a digital odor fingerprint according to an embodiment of the present invention. The method can be executed by a digital odor fingerprint generating device, which can be implemented in software and / or hardware. The digital odor fingerprint generating device can be configured in an electronic device, such as a server or terminal, wherein the terminal specifically includes an in-vehicle terminal, a computer, or a tablet computer, etc.
[0025] like Figure 1 As shown, the method for generating digital odor fingerprints provided in this embodiment includes the following steps.
[0026] S101, acquire at least one odor dynamic characteristic of each sensor channel of the target sensor array exposed to the target odor within a preset time period and the target response value after the response stabilizes, and acquire the sensor calibration factor of the target sensor array and the standard response value of each sensor channel exposed to air.
[0027] In this embodiment, the preset time period is the time period from when the target sensor array comes into contact with the target odor until the response stabilizes, from when the response stabilizes until the target odor is removed, and from when the target odor is removed until the response returns to the preset value.
[0028] The preset response value can be set according to actual needs and is not limited. For example, the preset response value can be 30% of the target response value.
[0029] The target gas can be any kind of gas. For example, the target gas could be the gas produced by the volatilization of meat.
[0030] In this embodiment, at least one odor dynamic feature includes an odor rise time constant, an odor recovery time constant, and a total stimulation level value of the target odor on the target sensor array. It is understood that at least one odor dynamic feature may also include other dynamic features, without limitation.
[0031] In this embodiment, the target response value after stabilization can be the stable resistance value of each sensor channel after exposure to the target odor. The standard response value can be the resistance value of each sensor channel exposed to air.
[0032] The sensor calibration factor is a quantitative compensation parameter used to correct hardware characteristic deviations and environmental interference deviations of individual sensor channels in an electronic nose sensor array, so that different sensors have consistent responses to the same odor.
[0033] Specifically, the digital odor fingerprint generation device can acquire at least one dynamic odor feature through the following steps: Figure 2 As shown, Figure 2 This is a flowchart illustrating a method for obtaining at least one dynamic odor feature according to an embodiment of the present invention, comprising the following steps: S1011, obtain the response value of each sensor channel in contact with the target odor at each moment in multiple moments within a preset time period.
[0034] S1012, based on multiple response values, obtain the total response value of the target sensor array at each moment within a preset time period.
[0035] S1013, based on multiple total response values, generates the response curve of the target sensor array over a preset time period.
[0036] S1014, based on the response curve, determine the time required for the target sensor array to rise from the initial total response value to the peak total response value, and obtain the odor rise time constant.
[0037] S1015, based on the response curve, obtains the time required from the peak total response value to the end total response value after the target odor is removed from the target sensor array, and obtains the odor recovery time constant.
[0038] S1016, perform integration on the response curve to obtain the total stimulus intensity value.
[0039] Understandably, different odors interact with sensor arrays through different mechanisms. Some odors trigger sensor responses rapidly, reaching peak values, while others exhibit a slow, gradual increase in response. Furthermore, the recovery speed of the sensors after the removal of different odors also varies. This method extracts rise and recovery time constants, which accurately characterize the dynamic differences in the interaction between odors and sensors. The total stimulus intensity value quantifies the cumulative effect of the odor over time through integral calculation. Combining these dynamic features with steady-state response features effectively distinguishes odors with similar components but different effects, significantly improving the recognition accuracy of digital odor fingerprints. Moreover, by analyzing the response curves over the entire time period, the dynamic differences caused by concentration changes are captured, providing a more accurate reflection of subtle fluctuations in odor concentration compared to a single steady-state value.
[0040] In some optional implementations, the digital odor fingerprint generation apparatus can obtain the standard response ratio of a preset sensor array under a standard gas and the target response ratio of a target sensor array under a standard gas; calculate the ratio between the standard response ratio and the target response ratio to obtain the sensor calibration factor.
[0041] The preset sensor array can be either a standard sensor array or an ideal sensor array. The standard response ratio refers to the response ratio of the "standard device / ideal sensor array" to a standard gas, while the target response ratio refers to the response ratio of the "device to be calibrated" to the same standard gas.
[0042] Understandably, in order to eliminate the systematic offset caused by differences in amplification gain, sensor aging and manufacturing of different sensor arrays, the calibration factor obtained based on the response ratio can be adapted to different models and batches of electronic nose devices, greatly improving the universality of calibration, ensuring that the fingerprint vectors output by different devices under the same odor conditions are consistent in spatial distribution, and achieving cross-device feature alignment.
[0043] S102 determines multiple characteristic values based on the target response value, the standard response value, and the sensor calibration factor.
[0044] Each feature value indicates the relative contribution of the response value of each sensor channel to the total response value of the sensor array.
[0045] In some optional implementations, the digital odor fingerprint generation device calculates the ratio between the target response value and the standard response value to obtain the initial response ratio of each sensor channel; calculates the sum of multiple initial response ratios to obtain the total response ratio of the target sensor array; calculates the product between the initial response ratio and the sensor calibration factor to obtain the calibration response ratio of each sensor channel; and calculates the ratio between the calibration response ratio of each sensor channel and the total response ratio to obtain multiple feature values.
[0046] Understandably, the feature value represents the weight of a single channel's response within the overall array response. Compared to the response value, this weight has a uniform numerical range, a clear physical meaning, and is completely decoupled from the sensor's hardware model and response amplitude scale. This ensures a high degree of consistency in the feature values output by different models and batches of electronic nose devices, allowing direct use for cross-device feature comparison and training of general recognition models, truly achieving data consistency and interoperability across multiple devices. Furthermore, the weight can indicate the collaborative response pattern of the multi-channel array to the target odor, such as which channels are strong response channels, which are weak response channels, and the contribution ratio of each channel. Compared to a single response amplitude feature, this weight is better at distinguishing odors with similar components, significantly improving the recognizability of digital odor fingerprints.
[0047] S103, Generate a digital odor fingerprint corresponding to the target odor based on at least one odor dynamic feature value and multiple feature values.
[0048] In some alternative implementations, the digital odor fingerprint generation apparatus merges multiple feature values with at least one odor dynamic feature value to generate a digital odor fingerprint corresponding to the target odor.
[0049] Digital odor fingerprints can be interpreted at the physical layer as an "odor pattern proportion map" and can also serve as standard input for machine learning models, maintaining good interpretability and engineering feasibility. Numerical odor fingerprints can also be called digital odor fingerprint vectors and can be represented by a vector array. For example, a digital odor fingerprint can be represented as: [Feature 1, Feature 2, Feature 3, ..., Odor Dynamic Feature 1, Odor Dynamic Feature 2, ...].
[0050] Furthermore, the digital odor fingerprint generation device can generate a data structure in a preset format from the digital odor fingerprint, the identifier and model of the target sensor array, the sensor calibration factor, environmental parameters, sampling timestamp, and encoding version number.
[0051] In this embodiment of the application, the data structure can be as shown in Table 1 below. Table 1 is a data structure table of the data structure.
[0052] Table 1: Data Structure Table
[0053] The default format can be JavaScript object notation (also known as JSON) or Protocol Buffers. JSON is suitable for readable parsing, while Protobuf is suitable for high-concurrency network transmission. Understandably, by defining field specifications, naming rules, and validation mechanisms, fast parsing across multiple systems, unified invocation, and compatibility with remote model interfaces can be achieved.
[0054] Based on the above Figure 1 The method shown describes a digital odor fingerprint generation device that can acquire at least one dynamic odor feature and a target response value after the response stabilizes for each sensor channel of a target sensor array exposed to a target odor within a preset time period, as well as acquire the sensor calibration factor of the target sensor array and the standard response value of each sensor channel exposed to air; determine multiple feature values based on the target response value, the standard response value, and the sensor calibration factor; and generate a digital odor fingerprint corresponding to the target odor based on at least one dynamic odor feature value and multiple feature values.
[0055] Digital odor fingerprints, comprising calibrated steady-state proportion features and dynamic odor features, comprehensively characterize odor attributes from two dimensions: "dynamic process" and "steady-state response ratio." Dynamic features can distinguish odors with similar components but different volatility characteristics and sensor mechanisms, while steady-state proportion features eliminate hardware and environmental interference, preserving the core odor response pattern. The combination of these two features gives digital odor fingerprints stronger discriminative power, effectively distinguishing easily confused odors. Digital odor fingerprints retain the odor distribution pattern across channels while eliminating differences caused by device amplification, gas concentration, and environmental drift, achieving standardization and transferability of odor response features. This enables collaborative networking and data interoperability of sensor arrays, facilitating the construction of a unified, universal recognition model, and enabling model reuse and remote deployment across devices.
[0056] This embodiment also provides a digital odor fingerprint generation device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0057] This embodiment provides a digital odor fingerprint generation device, such as... Figure 3 As shown, Figure 3 This is a structural block diagram of a digital odor fingerprint generation apparatus according to an embodiment of the present invention; the digital odor fingerprint generation apparatus includes: The acquisition module 301 is used to acquire at least one odor dynamic characteristic and target response value after the response stabilizes for each sensor channel of the target sensor array exposed to the target odor within a preset time period, as well as to acquire the sensor calibration factor of the target sensor array and the standard response value of each sensor channel exposed to air.
[0058] The processing module 302 is used to determine multiple feature values based on the target response value, the standard response value, and the sensor calibration factor. Each feature value is used to indicate the relative contribution of the response value of each sensor channel to the total response value of the sensor array.
[0059] The generation module 303 is used to generate a digital odor fingerprint corresponding to a target odor based on at least one odor dynamic feature value and multiple feature values.
[0060] In some optional implementations, at least one odor dynamic feature includes an odor rise time constant, an odor recovery time constant, and a total stimulation level value of the target odor on the target sensor array; the acquisition module 301 is specifically used to acquire the response value of each sensor channel contacting the target odor at each moment in multiple moments within a preset time period; based on multiple response values, obtain the total response value of the target sensor array at each moment in multiple moments within the preset time period; based on multiple total response values, generate a response curve of the target sensor array changing with time within the preset time period; based on the response curve, determine the time required for the target sensor array to go from the initial total response value to the peak total response value, and obtain the odor rise time constant; based on the response curve, when the target odor is removed from the target sensor array, acquire the time required from the peak total response value to the end total response value, and obtain the odor recovery time constant; and perform an integral operation on the response curve to obtain the total stimulation level value.
[0061] In some optional implementations, the acquisition module 301 is specifically used to acquire the standard response ratio of the preset sensor array under standard gas and the target response ratio of the target sensor array under standard gas; calculate the ratio between the standard response ratio and the target response ratio to obtain the sensor calibration factor.
[0062] In some optional implementations, the processing module 302 specifically calculates the ratio between the target response value and the standard response value to obtain the initial response ratio of each sensor channel; calculates the sum of multiple initial response ratios to obtain the total response ratio of the target sensor array; calculates the product between the initial response ratio and the sensor calibration factor to obtain the calibration response ratio of each sensor channel; and calculates the ratio between the calibration response ratio of each sensor channel and the total response ratio to obtain multiple characteristic values.
[0063] In some optional implementations, the generation module 303 is specifically used to merge multiple feature values with at least one odor dynamic feature value to generate a digital odor fingerprint corresponding to the target odor.
[0064] In some optional implementations, the generation module 303 is also used to generate a data structure in a preset format from the digital odor fingerprint, the identifier and model of the target sensor array, the sensor calibration factor, environmental parameters, sampling timestamp, and encoding version number.
[0065] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.
[0066] In this embodiment, the digital odor fingerprint generation device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.
[0067] This invention also provides an electronic device having the above-described features. Figure 3 The device shown is for generating digital odor fingerprints.
[0068] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an optional embodiment of the present invention, such as... Figure 4 As shown, the electronic device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise as required. The processors can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 4 Take a processor 10 as an example.
[0069] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.
[0070] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.
[0071] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0072] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.
[0073] The electronic device also includes a communication interface 30 for communicating with other devices or communication networks.
[0074] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.
[0075] This invention provides a computer program product, which includes computer instructions for causing a computer to execute the method of any embodiment of this invention.
[0076] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0077] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for generating digital odor fingerprints, characterized in that, The method includes: Acquire at least one odor dynamic characteristic and target response value after response stabilization for each sensor channel of the target sensor array exposed to the target odor within a preset time period, and acquire the sensor calibration factor of the target sensor array and the standard response value of each sensor channel exposed to air; Based on the target response value, the standard response value, and the sensor calibration factor, a plurality of feature values are determined, each feature value being used to indicate the relative contribution of the response value of each sensor channel to the total response value of the sensor array; A digital odor fingerprint corresponding to the target odor is generated based on at least one of the odor dynamic feature values and multiple of the feature values.
2. The method according to claim 1, characterized in that, The at least one odor dynamic feature includes an odor rise time constant, an odor recovery time constant, and the total stimulation level value of the target odor on the target sensor array; The acquisition of at least one odor dynamic feature of each sensor channel of the target sensor array exposed to the target odor within a preset time period includes: Obtain the response value of each sensor channel in contact with the target odor at each of the multiple moments within the preset time period; Based on the multiple response values, the total response value of the target sensor array at each of the multiple moments within the preset time period is obtained; Based on multiple total response values, a response curve of the target sensor array as a function of time is generated within the preset time period; Based on the response curve, the time required for the target sensor array to rise from the initial total response value to the peak total response value is determined, and the odor rise time constant is obtained. Based on the response curve, after the target odor is removed from the target sensor array, the time required from the peak total response value to the end total response value is obtained, and the odor recovery time constant is obtained. The total stimulus intensity value is obtained by integrating the response curve.
3. The method according to claim 1, characterized in that, The step of obtaining the sensor calibration factor of the target sensor array includes: Obtain the standard response ratio of the preset sensor array under standard gas, and the target response ratio of the target sensor array under the same standard gas; The sensor calibration factor is obtained by calculating the ratio between the standard response ratio and the target response ratio.
4. The method according to claim 1, characterized in that, The determination of multiple feature values based on the target response value, the standard response value, and the sensor calibration factor includes: Calculate the ratio between the target response value and the standard response value to obtain the initial response ratio of each sensor channel; The sum of the initial response ratios is calculated to obtain the total response ratio of the target sensor array; The product of the initial response ratio and the sensor calibration factor is calculated to obtain the calibration response ratio of each sensor channel; The ratio between the calibration response ratio of each sensor channel and the total response ratio is calculated to obtain a plurality of the characteristic values.
5. The method according to claim 1, characterized in that, The step of generating a digital odor fingerprint corresponding to the target odor based on at least one of the odor dynamic feature values and multiple of the feature values includes: The multiple feature values are combined with at least one of the odor dynamic feature values to generate the digital odor fingerprint corresponding to the target odor.
6. The method according to any one of claims 1-5, characterized in that, The method further includes: The digital odor fingerprint, the identifier, model, sensor calibration factor, environmental parameters, sampling timestamp, and encoding version number of the target sensor array are used to generate a data structure in a preset format.
7. A device for generating digital scent fingerprints, characterized in that, The digital odor fingerprint generation device includes: The acquisition module is used to acquire at least one odor dynamic characteristic and target response value after response stabilization for each sensor channel of the target sensor array exposed to the target odor within a preset time period, as well as to acquire the sensor calibration factor of the target sensor array and the standard response value of each sensor channel exposed to air. The processing module is configured to determine multiple feature values based on the target response value, the standard response value, and the sensor calibration factor, wherein each feature value is used to indicate the relative contribution of the response value of each sensor channel to the total response value of the sensor array; The generation module is used to generate a digital odor fingerprint corresponding to the target odor based on at least one of the odor dynamic feature values and multiple of the feature values.
8. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for generating a digital odor fingerprint as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method for generating a digital odor fingerprint according to any one of claims 1 to 6.
10. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the method for generating a digital odor fingerprint according to any one of claims 1 to 6.