Organic waste treatment method, system and equipment based on smart toilet

Abstract

The invention provides an organic waste treatment method, system and equipment based on a smart toilet, and relates to the technical field of non-flushing smart toilets. The method comprises the following steps: firstly, acquiring a first waste data sequence corresponding to a target smart toilet; secondly, determining at least one associated smart toilet corresponding to the target smart toilet, and obtaining at least one second waste data sequence corresponding to the at least one associated smart toilet; and then, based on the at least one second waste data sequence, performing association mining on the first waste data sequence, outputting organic waste component characteristics corresponding to the target smart toilet, and based on the organic waste component characteristics, determining an organic waste treatment scheme corresponding to the target smart toilet. Based on the content, the problem that in the prior art, the reliability of organic waste treatment is relatively low can be solved.

Description

Technical Field

[0001] The present application relates to the technical field of non-flush smart toilets, and specifically, to an organic waste treatment method, system and equipment based on smart toilets. Background Art

[0002] The non-flushing smart toilet combines advanced technology and environmental protection concepts, and can effectively treat organic waste. Specifically, after use, the user can send the organic waste into the anaerobic digester, where it will be degraded by microorganisms under anaerobic conditions to produce biogas (mainly methane) and organic fertilizer. In this way, the degradation of organic waste by microorganisms can not only convert the waste into organic fertilizer, but also save water (i.e., no need to flush and transport it with water). However, the inventors have found that in the prior art, the placement of microorganisms is generally managed based on experience, so there is a problem of relatively low reliability in the treatment of organic waste. Summary of the invention

[0003] In view of this, the purpose of the present application is to provide an organic waste treatment method, system and equipment based on a smart toilet, so as to improve the problem of relatively low reliability of organic waste treatment in the prior art.

[0004] To achieve the above objectives, this application adopts the following technical solutions: A method for treating organic waste based on a smart toilet, comprising: Obtain a first waste data sequence corresponding to a target smart toilet, wherein the first waste data sequence includes a plurality of first waste component data sorted according to corresponding collection time, each of the first waste component data is used to reflect the organic waste component in the target smart toilet, and the target smart toilet is a non-flushing, microbial degradation toilet; Determine at least one associated smart toilet corresponding to the target smart toilet, and obtain at least one second waste data sequence corresponding to the at least one associated smart toilet, wherein each of the second waste data sequences includes a plurality of second waste component data sorted according to the corresponding collection time, each of the second waste component data is used to reflect the organic waste component in the target smart toilet, and each of the associated smart toilets is a non-flushing, microbial degradation toilet; Based on the at least one second waste data sequence, the first waste data sequence is associated with mining, and the organic waste component characteristics corresponding to the target smart toilet are output, and based on the organic waste component characteristics, the organic waste treatment plan corresponding to the target smart toilet is determined, wherein the organic waste treatment plan includes at least the type, quantity and environmental information of the microorganisms placed in the microbial degradation equipment corresponding to the target smart toilet.

[0005] In a preferred embodiment of the present application, in the above-mentioned organic waste treatment method based on smart toilets, the steps of performing association mining on the first waste data sequence based on the at least one second waste data sequence, outputting the organic waste component characteristics corresponding to the target smart toilet, and determining the organic waste treatment scheme corresponding to the target smart toilet based on the organic waste component characteristics include: Using the first feature mining model in the target solution determination network, feature mining is performed on each first waste component data in the first waste data sequence to obtain a first waste component feature sequence including a plurality of first waste component features, wherein the target solution determination network is a neural network formed by training with sample data, and the first waste component features are used to reflect semantic information of the first waste component data; Determine a second feature mining model in the network by using the target solution, perform feature mining on each second waste component data in the second waste data sequence for each second waste data sequence in the at least one second waste data sequence, and obtain a second waste component feature sequence including a plurality of second waste component features, wherein the second waste component features are used to reflect semantic information of the second waste component data; The target solution is used to determine the feature fusion model in the network, and based on at least one second waste component feature sequence corresponding to the at least one second waste data sequence, the first waste component feature sequence is feature-associated and fused, and the organic waste component feature corresponding to the target smart toilet is output, wherein the organic waste component feature has semantic information of each second waste component feature sequence and the first waste component feature sequence; The solution determination model in the target solution determination network is used to determine the organic waste treatment solution corresponding to the target smart toilet based on the organic waste component characteristics, wherein the solution determination model belongs to a generative model or a discriminant model.

[0006] In a preferred embodiment of the present application, in the organic waste treatment method based on smart toilets, the step of using the target solution to determine the first feature mining model in the network, performing feature mining on each first waste component data in the first waste data sequence, and obtaining a first waste component feature sequence including multiple first waste component features, includes: Using the target solution to determine the first vectorization unit in the first feature mining model in the network, respectively vectorize each first waste component data in the first waste data sequence to obtain a corresponding first waste component vector sequence; Based on the difference waste component data between every two adjacent first waste component data in the first waste data sequence, a corresponding difference waste component data sequence is determined, and each difference waste component data in the difference waste component data sequence is vectorized by the first vectorization unit to obtain a corresponding difference waste component vector sequence; The first waste component vector sequence and the difference waste component vector sequence are combined to obtain a first waste component feature sequence including a plurality of first waste component features, wherein the first waste component feature belongs to the first waste component vector or the difference waste component vector.

[0007] In a preferred embodiment of the present application, in the above-mentioned organic waste treatment method based on smart toilets, the step of using the target solution to determine the second feature mining model in the network, performing feature mining on each second waste component data in the second waste data sequence for each second waste data sequence in the at least one second waste data sequence, and obtaining a second waste component feature sequence including multiple second waste component features, includes: Using the target solution to determine the second vectorization unit in the second feature mining model in the network, for each second waste data sequence in the at least one second waste data sequence, respectively perform vectorization processing on each second waste component data in the second waste data sequence to obtain a corresponding second waste component vector sequence; For each of the at least one second waste data sequence, based on the difference waste component data between every two adjacent second waste component data in the second waste data sequence, a corresponding difference waste component data sequence is determined, and using the second vectorization unit, each difference waste component data in the difference waste component data sequence is vectorized to obtain a corresponding difference waste component vector sequence; For each second waste data sequence in the at least one second waste data sequence, the second waste component vector sequence and the corresponding difference waste component vector sequence corresponding to the second waste data sequence are combined and processed to obtain a second waste component feature sequence corresponding to the second waste data sequence including multiple second waste component features, wherein the second waste component feature belongs to the second waste component vector or the difference waste component vector.

[0008] In a preferred embodiment of the present application, in the above-mentioned organic waste treatment method based on smart toilets, the step of using the target solution to determine the feature fusion model in the network, performing feature association fusion on the first waste component feature sequence based on at least one second waste component feature sequence corresponding to the at least one second waste data sequence, and outputting the organic waste component features corresponding to the target smart toilet includes: For each second waste component feature sequence in at least one second waste component feature sequence corresponding to the at least one second waste data sequence, determining a feature fusion model in the network using the target solution, performing feature association mining on the first waste component feature sequence based on the second waste component feature sequence, and outputting corresponding waste component association features; The waste component association features corresponding to each of the second waste component feature sequences are aggregated to output the organic waste component features corresponding to the target smart toilet.

[0009] In a preferred embodiment of the present application, in the organic waste treatment method based on smart toilets, for each second waste component feature sequence in at least one second waste component feature sequence corresponding to the at least one second waste data sequence, the feature fusion model in the network is determined using the target solution, and feature association mining is performed on the first waste component feature sequence based on the second waste component feature sequence, and the step of outputting the corresponding waste component association feature comprises: splicing the first waste component features in the first waste component feature sequence to obtain a corresponding first waste component splicing feature, and splicing the second waste component features in each second waste component feature sequence in at least one second waste component feature sequence corresponding to the at least one second waste data sequence to obtain a corresponding second waste component splicing feature; Determine a feature fusion model in the network by using the target solution, perform feature association mining on at least two local features in the first waste component splicing feature based on at least two local features in the second waste component splicing feature for any second waste component splicing feature, and output corresponding at least two local waste component association features; The at least two local waste component association features are aggregated to output a waste component association feature corresponding to the second waste component splicing feature.

[0010] In a preferred embodiment of the present application, in the organic waste treatment method based on smart toilets, the step of using the target solution to determine the feature fusion model in the network, for any second waste component splicing feature, performing feature association mining on at least two local features in the second waste component splicing feature, and outputting the corresponding at least two local waste component association features, includes: For any second waste component splicing feature, the second waste component splicing feature is divided into a first waste component local feature corresponding to the second waste component data and a second waste component local feature corresponding to the difference waste component data, and the first waste component splicing feature is divided into a third waste component local feature corresponding to the first waste component data and a fourth waste component local feature corresponding to the difference waste component data; The target solution is used to determine the multiple first deep mining units included in the feature fusion model in the network, and the local features of the first waste component are deep mined in sequence to output the corresponding multiple first waste component deep features, and the local features of the third waste component are deep mined in sequence to output the corresponding multiple third waste component deep features, and, for each first deep mining unit, the first waste component deep feature corresponding to the first deep mining unit and the corresponding third waste component deep feature are multiplied to obtain the corresponding feature association parameter, and the third waste component deep feature is updated based on the feature association parameter to obtain the corresponding third waste component updated feature; Using the plurality of second deep mining units included in the feature fusion model, sequentially perform deep mining on the second waste component local features, output a plurality of corresponding second waste component deep features, and sequentially perform deep mining on the fourth waste component local features, output a plurality of corresponding fourth waste component deep features, and, for each second deep mining unit, perform multiplication calculation of transposed features based on the second waste component deep feature corresponding to the second deep mining unit and the fourth waste component deep feature corresponding to the second deep mining unit to obtain a corresponding feature association parameter, and, based on the feature association parameter, update the fourth waste component deep feature to obtain a corresponding fourth waste component updated feature; The obtained multiple third waste component update characteristics are superimposed or spliced ​​to output a corresponding local waste component association characteristic, and the obtained multiple fourth waste component update characteristics are superimposed or spliced ​​to output a corresponding local waste component association characteristic.

[0011] In a preferred embodiment of the present application, in the above-mentioned organic waste treatment method based on smart toilets, the step of determining at least one associated smart toilet corresponding to the target smart toilet and obtaining at least one second waste data sequence corresponding to the at least one associated smart toilet includes: Acquire the first location information corresponding to the target smart toilet, and acquire the second location information corresponding to a plurality of other smart toilets, and, based on the first location information and the second location information, determine at least one other smart toilet that is correlated with the target smart toilet in terms of distribution position among the plurality of other smart toilets, so as to obtain at least one candidate smart toilet; Acquire the first user information corresponding to the target smart toilet, and acquire the second user information corresponding to each of the candidate smart toilets, and, based on the first user information and the second user information, determine at least one candidate smart toilet that is relevant to the target smart toilet in terms of user dimension from among the at least one candidate smart toilet, as at least one associated smart toilet corresponding to the target smart toilet; The second waste data sequence corresponding to each associated smart toilet in the at least one associated smart toilet is obtained respectively to obtain at least one corresponding second waste data sequence.

[0012] The present application also provides an organic waste treatment system based on a smart toilet, comprising: A first data acquisition module is used to acquire a first waste data sequence corresponding to a target smart toilet, wherein the first waste data sequence includes a plurality of first waste component data sorted according to corresponding collection time, each of the first waste component data is used to reflect the organic waste component in the target smart toilet, and the target smart toilet is a non-flushing, microbial degradation toilet; A second data acquisition module is used to determine at least one associated smart toilet corresponding to the target smart toilet, and acquire at least one second waste data sequence corresponding to the at least one associated smart toilet, wherein each of the second waste data sequences includes a plurality of second waste component data sorted according to the corresponding collection time, each of the second waste component data is used to reflect the organic waste component in the target smart toilet, and each of the associated smart toilets is a non-flushing, microbial degradation toilet; A treatment scheme determination module is used to perform association mining on the first waste data sequence based on the at least one second waste data sequence, output the organic waste component characteristics corresponding to the target smart toilet, and determine the organic waste treatment scheme corresponding to the target smart toilet based on the organic waste component characteristics, wherein the organic waste treatment scheme at least includes the type, quantity and environmental information of the microorganisms placed in the microbial degradation equipment corresponding to the target smart toilet.

[0013] Based on the above, the present application also provides an electronic device, including: Memory for storing computer programs; A processor connected to the memory is used to execute the computer program stored in the memory to implement the above-mentioned organic waste treatment method based on smart toilets.

[0014] The organic waste treatment method, system and device based on smart toilets provided in the present application first obtain a first waste data sequence corresponding to the target smart toilet; secondly, determine at least one associated smart toilet corresponding to the target smart toilet, and obtain at least one second waste data sequence corresponding to at least one associated smart toilet; then, based on at least one second waste data sequence, perform association mining on the first waste data sequence, output the organic waste component characteristics corresponding to the target smart toilet, and determine the organic waste treatment scheme corresponding to the target smart toilet based on the organic waste component characteristics. Based on the above content, since in the process of data mining, the data corresponding to the target smart toilet will be combined with the data corresponding to the associated smart toilets to perform association mining, so that the mined organic waste component characteristics not only carry the semantic information of the data of the target smart toilet, but also carry the semantic information of the data of the associated smart toilets, and the data of the associated smart toilets has a positive effect on the data of the target smart toilet, therefore, it can ensure that the semantic information of the obtained organic waste component characteristics is richer and more reliable, thereby ensuring the reliability of the determined organic waste treatment scheme, thereby improving the relatively low reliability of organic waste treatment in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings.

[0016] Figure 1 A structural block diagram of an electronic device provided in an embodiment of the present application.

[0017] Figure 2 A schematic flow chart of an organic waste treatment method based on a smart toilet provided in an embodiment of the present application.

[0018] Figure 3A schematic diagram of feature association mining of local features provided in an embodiment of the present application.

[0019] Figure 4 A block diagram of an organic waste treatment system based on a smart toilet provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0022] like Figure 1 As shown, an embodiment of the present application provides an electronic device. The electronic device may include a memory, a storage device, and an organic waste treatment system based on a smart toilet.

[0023] In detail, the memory and the memory are electrically connected directly or indirectly to realize data transmission or interaction. For example, the memory and the memory can be electrically connected through one or more communication buses or signal lines. The organic waste treatment system based on smart toilets includes at least one software function module stored in the memory in the form of software or firmware. The memory is used to execute the executable computer program stored in the memory, for example, the software function module and computer program included in the organic waste treatment system based on smart toilets, so as to realize the organic waste treatment method based on smart toilets provided in the embodiment of the present application.

[0024] Optionally, the memory may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.

[0025] Furthermore, the memory may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a system on chip (SoC), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0026] Understandably, Figure 1 The structure shown is for illustration only, and the electronic device may also include Figure 1 More or fewer components as shown, or with Figure 1 The different configurations shown, for example, may also include a communication unit for exchanging information with other devices.

[0027] Combination Figure 2 The embodiment of the present application also provides an organic waste treatment method based on a smart toilet that can be applied to the above electronic device. Among them, the method steps defined in the process related to the organic waste treatment method based on a smart toilet can be implemented by the electronic device.

[0028] The following will Figure 2 The specific process shown is explained in detail.

[0029] Step S110, obtaining a first waste data sequence corresponding to the target smart toilet.

[0030] In an embodiment of the present application, the electronic device can obtain a first waste data sequence corresponding to the target smart toilet. The first waste data sequence includes a plurality of first waste component data sorted according to the corresponding collection time, each of which is used to reflect the organic waste components in the target smart toilet (such as protein content A, fat content B, cellulose content C, etc.), and the target smart toilet is a non-flushing, microbial degradation toilet, that is, feces and other excrement are degraded by microorganisms.

[0031] Step S120, determining at least one associated smart toilet corresponding to the target smart toilet, and obtaining at least one second waste data sequence corresponding to the at least one associated smart toilet.

[0032] In an embodiment of the present application, the electronic device can determine at least one associated smart toilet corresponding to the target smart toilet, and obtain at least one second waste data sequence corresponding to the at least one associated smart toilet. Each of the second waste data sequences includes a plurality of second waste component data sorted according to the corresponding collection time, and each of the second waste component data is used to reflect the organic waste components in the target smart toilet, and each of the associated smart toilets is a non-flushing, microbial degradation toilet. It should be noted that the target smart toilet can be a toilet or multiple toilets in similar locations (as a whole). Similarly, the associated smart toilet can also be a toilet or multiple toilets in similar locations.

[0033] Step S130, based on the at least one second waste data sequence, perform association mining on the first waste data sequence, output the organic waste component characteristics corresponding to the target smart toilet, and based on the organic waste component characteristics, determine the organic waste treatment plan corresponding to the target smart toilet.

[0034] In an embodiment of the present application, the electronic device can perform association mining on the first waste data sequence based on the at least one second waste data sequence, output the organic waste component characteristics corresponding to the target smart toilet, and determine the organic waste treatment plan corresponding to the target smart toilet based on the organic waste component characteristics. The organic waste treatment plan at least includes the type, quantity and environmental information of the microorganisms placed in the microbial degradation device corresponding to the target smart toilet (such as factors that affect the microorganisms, such as temperature and humidity).

[0035] Based on the above content, in the process of data mining, the data corresponding to the target smart toilet will be combined with the data corresponding to the associated smart toilets for associated mining, so that the mined organic waste component characteristics not only carry the semantic information of the target smart toilet data, but also carry the semantic information of the associated smart toilet data. The data of the associated smart toilets has a positive effect on the data of the target smart toilet. Therefore, it can ensure that the semantic information of the obtained organic waste component characteristics is richer and more reliable, thereby ensuring the reliability of the determined organic waste treatment plan (different waste formations require different types and quantities of microorganisms), thereby improving the problem of relatively low reliability of organic waste treatment in the existing technology.

[0036] It should be noted that for step S120, the specific method of determining at least one second waste data sequence corresponding to at least one associated smart toilet is not limited and can be selected according to actual needs.

[0037] For example, in an alternative implementation, in order to ensure that the determined second waste data sequence has a higher reliability, the above-mentioned step S120 may further include step S121, step S122 and step S123, and the specific content of each step is described as follows.

[0038] Step S121, obtain the first location information corresponding to the target smart toilet, and obtain the second location information corresponding to multiple other smart toilets, and, based on the first location information and the second location information, determine at least one other smart toilet that is relevant to the target smart toilet in terms of distribution location among the multiple other smart toilets to obtain at least one candidate smart toilet.

[0039] In the embodiment of the present application, the first location information corresponding to the target smart toilet can be obtained, and the second location information corresponding to multiple other smart toilets can be obtained, and based on the first location information and the second location information, at least one other smart toilet that is correlated with the target smart toilet in terms of distribution position is determined among the multiple other smart toilets to obtain at least one candidate smart toilet. In other words, other smart toilets with similar locations (such as a distance less than a preset distance, the preset distance can be selected according to actual needs) can be screened out as candidate smart toilets, because there is generally user circulation between smart toilets with similar locations, so that the components of organic waste are correlated, ensuring the reliability of subsequent correlation mining.

[0040] Step S122, obtaining the first user information corresponding to the target smart toilet, and obtaining the second user information corresponding to each of the candidate smart toilets, and, based on the first user information and the second user information, determining at least one candidate smart toilet that is relevant to the target smart toilet in the user dimension among the at least one candidate smart toilet, as at least one associated smart toilet corresponding to the target smart toilet.

[0041] In an embodiment of the present application, after determining the candidate smart toilets, the first user information (user registration information of the smart toilet platform) corresponding to the target smart toilet can be obtained, and the second user information corresponding to each of the candidate smart toilets can be obtained, and, based on the first user information and the second user information, at least one candidate smart toilet that is relevant to the target smart toilet in the user dimension is determined among the at least one candidate smart toilet as at least one associated smart toilet corresponding to the target smart toilet. For example, a candidate smart toilet with a high degree of user overlap can be determined as an associated smart toilet, and a candidate smart toilet with similar corresponding age, gender, and other information can be determined as an associated smart toilet. The reason is that similar information such as age and gender will also have similar eating habits, and therefore, the composition of organic waste may also be similar.

[0042] Step S123, respectively obtain the second waste data sequence corresponding to each associated smart toilet in the at least one associated smart toilet to obtain the corresponding at least one second waste data sequence.

[0043] In an embodiment of the present application, after the associated smart toilets are determined, the second waste data sequence corresponding to each of the at least one associated smart toilets can be obtained respectively to obtain the corresponding at least one second waste data sequence.

[0044] It should be noted that for step S130, the specific method of determining the organic waste treatment solution corresponding to the target smart toilet is not limited and can be selected according to actual needs.

[0045] For example, in an alternative embodiment, in order to improve the reliability of the determined organic waste treatment solution, the above-mentioned step S130 may further include step S131, step S132, step S133 and step S134, and the specific content of each step is described as follows.

[0046] Step S131, using the target solution to determine the first feature mining model in the network, performing feature mining on each first waste component data in the first waste data sequence, and obtaining a first waste component feature sequence including a plurality of first waste component features.

[0047] In an embodiment of the present application, the first feature mining model in the target solution determination network can be used to perform feature mining on each first waste component data in the first waste data sequence to obtain a first waste component feature sequence including multiple first waste component features. Wherein, the target solution determination network belongs to a neural network formed by training with sample data (wherein, the processing process of the sample data by the initial neural network can be the same as the processing method of the first waste data sequence and the second waste data sequence, and the corresponding sample solution is determined, and then the error between the sample solution and the actual solution, that is, the error between the sample solution and the solution label is calculated, and finally, the network parameters of the initial neural network can be updated in the direction of reducing the error until the error converges, thereby forming the target solution determination network), and the first waste component feature is used to reflect the semantic information of the first waste component data.

[0048] Step S132, using the target solution to determine the second feature mining model in the network, for each second waste data sequence in the at least one second waste data sequence, feature mining is performed on each second waste component data in the second waste data sequence to obtain a second waste component feature sequence including multiple second waste component features.

[0049] In the embodiment of the present application, the target solution may also be used to determine a second feature mining model in the network, and for each second waste data sequence in the at least one second waste data sequence, feature mining is performed on each second waste component data in the second waste data sequence to obtain a second waste component feature sequence including a plurality of second waste component features. The second waste component features are used to reflect the semantic information of the second waste component data.

[0050] Step S133, using the target solution to determine the feature fusion model in the network, based on at least one second waste component feature sequence corresponding to the at least one second waste data sequence, perform feature association fusion on the first waste component feature sequence, and output the organic waste component features corresponding to the target smart toilet.

[0051] In the embodiment of the present application, after obtaining the first waste component feature sequence and the second waste component feature sequence, the target solution can be used to determine the feature fusion model in the network, and based on at least one second waste component feature sequence corresponding to the at least one second waste data sequence, the first waste component feature sequence is feature-correlated and fused, and the organic waste component feature corresponding to the target smart toilet is output. The organic waste component feature has the semantic information of each second waste component feature sequence and the first waste component feature sequence.

[0052] Step S134, using the solution determination model in the target solution determination network, based on the organic waste component characteristics, determine the organic waste treatment solution corresponding to the target smart toilet.

[0053] In an embodiment of the present application, after obtaining the organic waste component characteristics, the solution determination model in the target solution determination network can be used to determine the organic waste treatment solution corresponding to the target smart toilet based on the organic waste component characteristics. Among them, the solution determination model belongs to a generative model or a discriminant model, that is, when the solution determination model belongs to a generative model, the solution determination model can be a decoder to gradually generate each element (text or word) in the sequence (organic waste treatment solution). When the solution determination model belongs to a discriminant model, the solution determination model can include a classification function (such as softmax, etc.), so that the most matching reference waste treatment solution can be determined from a plurality of predetermined reference waste treatment solutions as the organic waste treatment solution corresponding to the target smart toilet.

[0054] It should be noted that the composition of the scheme determination model is not specifically limited here and can be configured according to relevant existing technologies. The focus of the embodiment of the present application is on feature mining. Therefore, step S131, step S132 and step S133 will be explained in detail in the following text.

[0055] It can be understood that, in the above step S131, the specific manner of performing feature mining on each first waste component data in the first waste data sequence is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to improve the semantic representation ability of the mined first waste component feature sequence, the above step S131 can further include the following content: First, the target solution can be used to determine the first vectorization unit in the first feature mining model in the network, and each first waste component data in the first waste data sequence is vectorized to obtain a corresponding first waste component vector sequence; illustratively, the first vectorization unit can be a word embedding model, so that the first waste component data can be word embedded to obtain a corresponding first waste component vector. For example, if the cellulose content accounts for 5%, the corresponding first waste component vector can be "cellulose: [0.12, -0.34, 0.45, 0.67, -0.23, 0.11, -0.07 , 0.29, 0.55, -0.01, 0.42, -0.13, 0.28, 0.33, -0.16, 0.19, 0.04, -0.22, 0.36, 0.49, ...]; of: [0.00, 0.02, -0.01, 0.03, 0.04, 0.05, 0.01, -0.02, 0.03, 0.01, -0.01, 0.02, -0.03, 0.00, 0.04, -0.01, 0.02, 0.01, -0.01, 0.00, ...]; content: [0.15, 0.25, -0.35, 0.50, 0.60, -0.15, 0.10, 0.35, -0.20, 0.05, 0.30, -0.10, 0.40, 0.20, 0.10, -0.05, 0.30, -0.15, 0.25, 0.45, ...]; percentage: [0.10, 0.20, 0.30, -0.10, 0.40, -0.20, 0.50, 0.15, -0.25, 0.05, 0.45, 0.35, -0.15, 0.00, 0.20, 0.10, 0.05, 0.30, -0.10, 0.25, ...]; for: [0.01, 0. 01, 0.02, -0.01, 0.02, 0.03, 0.00, -0.01, 0.02, 0.00, 0.01, 0.01, 0.01, 0.00, 0.01, 0.02, 0.00, 0.01, 0.00, ........]; 5%: [0.25, 0.15, -0.05, 0.20, 0.10, 0.30, 0.25, -0.10, 0.05, 0.15, 0.20, 0.10, -0.20, 0.25, 0.15, 0.30, 0.20, -0.05, 0.10, 0.20, ........]"; Secondly, based on the difference waste component data between every two adjacent first waste component data in the first waste data sequence (such as the difference data between the first first waste component data and the second first waste component data, the difference data between the second first waste component data and the third first waste component data, etc., to characterize the change of organic waste components), a corresponding difference waste component data sequence can be determined, and the first vectorization unit can be used to perform vectorization processing on each difference waste component data in the difference waste component data sequence (as described above), so as to obtain a corresponding difference waste component vector sequence; Then, the first waste component vector sequence and the difference waste component vector sequence can be spliced ​​to obtain a first waste component feature sequence including multiple first waste component features, wherein the first waste component feature belongs to the first waste component vector or the difference waste component vector, that is, either belongs to the first waste component vector or the difference waste component vector.

[0056] It is understandable that, in the above step S132, the specific manner of performing feature mining on each second waste component data in the second waste data sequence is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to improve the semantic representation capability of the mined second waste component feature sequence, the above step S132 can further include the following content: First, the target solution may be used to determine a second vectorization unit in a second feature mining model in the network (which may be the same word embedding model as the first vectorization unit or a different word embedding model), and for each second waste data sequence in the at least one second waste data sequence, vectorization processing is performed on each second waste component data in the second waste data sequence (as described above) to obtain a corresponding second waste component vector sequence; Secondly, for each second waste data sequence in the at least one second waste data sequence, a corresponding difference waste component data sequence can be determined based on the difference waste component data between every two adjacent second waste component data in the second waste data sequence, and each difference waste component data in the difference waste component data sequence can be vectorized using the second vectorization unit (as described above) to obtain a corresponding difference waste component vector sequence; Then, for each second waste data sequence in the at least one second waste data sequence, the second waste component vector sequence and the corresponding difference waste component vector sequence corresponding to the second waste data sequence can be combined and processed to obtain a second waste component feature sequence corresponding to the second waste data sequence, which includes multiple second waste component features, wherein the second waste component feature belongs to the second waste component vector or the difference waste component vector.

[0057] It can be understood that, in the above-mentioned step S133, the specific method of performing feature association and fusion on the first waste component feature sequence based on at least one second waste component feature sequence corresponding to the at least one second waste data sequence is not limited and can be selected according to actual needs. For example, in an alternative embodiment, in order to achieve more comprehensive and reliable feature association and fusion, the above-mentioned step S133 can further include step S133a and step S133b, and the specific content of each step is described as follows.

[0058] Step S133a, for each second waste component feature sequence in at least one second waste component feature sequence corresponding to the at least one second waste data sequence, use the target solution to determine the feature fusion model in the network, perform feature association mining on the first waste component feature sequence based on the second waste component feature sequence, and output the corresponding waste component association feature.

[0059] In the embodiment of the present application, for each second waste component feature sequence in at least one second waste component feature sequence corresponding to the at least one second waste data sequence, the feature fusion model in the target solution determination network can be used to perform feature association mining on the first waste component feature sequence based on the second waste component feature sequence, and output the corresponding waste component association feature. In this way, for at least one second waste component feature sequence, at least one corresponding waste component association feature can be output, so that feature association mining can be performed separately and mining accuracy can be improved.

[0060] Step S133b, aggregating the waste component association features corresponding to each of the second waste component feature sequences, and outputting the organic waste component features corresponding to the target smart toilet.

[0061] In an embodiment of the present application, the waste component association features corresponding to each of the second waste component feature sequences may be aggregated (such as splicing or superposition processing) to output the organic waste component features corresponding to the target smart toilet.

[0062] It can be understood that in the above-mentioned step S133a, the specific method of performing feature association mining is not limited and can be selected according to actual needs. For example, in an alternative embodiment, in order to ensure that the semantic information of the mined waste component association features can be richer and hierarchical to achieve the representation of different information, the above-mentioned step S133a can further include step a1, step a2 and step a3, and the specific content of each step is described as follows.

[0063] Step a1, splicing the first waste component features in the first waste component feature sequence to obtain the corresponding first waste component splicing features, and splicing the second waste component features in each second waste component feature sequence in at least one second waste component feature sequence corresponding to the at least one second waste data sequence to obtain the corresponding second waste component splicing features.

[0064] In an embodiment of the present application, the first waste component features in the first waste component feature sequence can be spliced ​​together to obtain a corresponding first waste component splicing feature, and the second waste component features in each second waste component feature sequence in at least one second waste component feature sequence corresponding to the at least one second waste data sequence can be spliced ​​together to obtain a corresponding second waste component splicing feature, that is, to obtain at least one second waste component splicing feature.

[0065] Step a2, using the target solution to determine the feature fusion model in the network, for any second waste component splicing feature, based on at least two local features in the second waste component splicing feature, feature association mining is performed on at least two local features in the first waste component splicing feature, and the corresponding at least two local waste component association features are output.

[0066] In the embodiment of the present application, after the splicing is completed, the target solution can be used to determine the feature fusion model in the network, and for any second waste component splicing feature, at least two local features in the first waste component splicing feature are respectively based on at least two local features in the second waste component splicing feature, and feature association mining is performed on at least two local features in the first waste component splicing feature, and the corresponding at least two local waste component association features are output. For example, based on the first local feature in the second waste component splicing feature, feature association mining is performed on the first local feature in the first waste component splicing feature to obtain the first local waste component association feature. And, based on the second local feature in the second waste component splicing feature, feature association mining is performed on the second local feature in the first waste component splicing feature to obtain the second local waste component association feature.

[0067] Step a3, aggregating the at least two local waste component association features, and outputting the waste component association feature corresponding to the second waste component splicing feature.

[0068] In an embodiment of the present application, after obtaining at least two local waste component association features, the at least two local waste component association features can be aggregated (such as splicing or superposition) to output the waste component association feature corresponding to the second waste component splicing feature.

[0069] It is understandable that the specific method of performing feature association mining of local features in the above step a2 is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to improve the reliability of feature association mining of local features, Figure 3 , the above step a2 may further include the following contents: Firstly, for any second waste component splicing feature, the second waste component splicing feature can be divided into a first waste component local feature corresponding to the second waste component data (i.e., the second waste component vector mentioned above) and a second waste component local feature corresponding to the difference waste component data (i.e., the difference waste component vector mentioned above), and the first waste component splicing feature can be divided into a third waste component local feature corresponding to the first waste component data (i.e., the first waste component vector mentioned above) and a fourth waste component local feature corresponding to the difference waste component data (i.e., the difference waste component vector mentioned above); Secondly, the target solution is used to determine the multiple first deep mining units included in the feature fusion model in the network, and the local features of the first waste component are deeply mined in turn, and the corresponding multiple first waste component deep features are output (wherein, the input data of the first first deep mining unit is the local feature of the first waste component, and the input data of the second first deep mining unit and each subsequent first deep mining unit is the output data of the previous first deep mining unit, that is, the first waste component deep feature), and the local features of the third waste component are deeply mined in turn, and the corresponding multiple third waste component deep features are output (wherein, the input data of the first first deep mining unit is the local feature of the third waste component, and the input data of the second first deep mining unit and each subsequent first deep mining unit is the output data of the previous first deep mining unit According to the invention, the first waste component depth feature and the third waste component depth feature are used as the basis for the first deep mining unit, and for each first deep mining unit, the first waste component depth feature corresponding to the first deep mining unit and the third waste component depth feature are multiplied by the transposed feature to obtain the corresponding feature association parameter, and the third waste component depth feature is updated based on the feature association parameter to obtain the corresponding third waste component updated feature (for example, the first waste component depth feature and the third waste component depth feature can be multiplied by the transposed result to obtain the corresponding feature association parameter, and then the feature association parameter is used as the weight coefficient to multiply the third waste component depth feature to obtain the corresponding third waste component updated feature); it should be noted that the deep mining can be a convolution process or a self-attention process, or a convolution process is performed first and then a self-attention process is performed, etc.; Then, using the multiple second deep mining units included in the feature fusion model, the local features of the second waste component are deep mined in sequence to output the corresponding multiple second waste component deep features, and the local features of the fourth waste component are deep mined in sequence to output the corresponding multiple fourth waste component deep features, and, for each second deep mining unit, the transposed feature is multiplied based on the second waste component deep feature corresponding to the second deep mining unit and the corresponding fourth waste component deep feature to obtain the corresponding feature association parameter, and the fourth waste component deep feature is updated based on the feature association parameter to obtain the corresponding fourth waste component updated feature, as described in the previous step; Finally, the multiple third waste component update features obtained can be superimposed or spliced ​​to output a corresponding local waste component association feature, and the multiple fourth waste component update features obtained can be superimposed or spliced ​​to output a corresponding local waste component association feature. Based on this, two local waste component association features can be obtained.

[0070] Combination Figure 4The embodiment of the present application also provides an organic waste treatment system based on a smart toilet that can be applied to the above electronic device. The organic waste treatment system based on a smart toilet can include a first data acquisition module, a second data acquisition module and a treatment solution determination module.

[0071] In detail, the first data acquisition module can be used to acquire the first waste data sequence corresponding to the target smart toilet, wherein the first waste data sequence includes a plurality of first waste component data sorted according to the corresponding collection time, each of the first waste component data is used to reflect the organic waste component in the target smart toilet, and the target smart toilet is a non-flushing, microbial degradation toilet. In the embodiment of the present application, the first data acquisition module can be used to execute Figure 2 As shown in step S110, the relevant contents of the first data acquisition module can refer to the above description of step S110.

[0072] In detail, the second data acquisition module can be used to determine at least one associated smart toilet corresponding to the target smart toilet, and obtain at least one second waste data sequence corresponding to the at least one associated smart toilet, wherein each of the second waste data sequences includes a plurality of second waste component data sorted according to the corresponding collection time, each of the second waste component data is used to reflect the organic waste components in the target smart toilet, and each of the associated smart toilets is a non-flushing, microbial degradation toilet. In an embodiment of the present application, the second data acquisition module can be used to execute Figure 2 As shown in step S120, the relevant contents of the second data acquisition module can refer to the above description of step S120.

[0073] In detail, the treatment scheme determination module can be used to perform association mining on the first waste data sequence based on the at least one second waste data sequence, output the organic waste component characteristics corresponding to the target smart toilet, and determine the organic waste treatment scheme corresponding to the target smart toilet based on the organic waste component characteristics, wherein the organic waste treatment scheme at least includes the type, quantity and environmental information of the microorganisms placed in the microbial degradation equipment corresponding to the target smart toilet. In an embodiment of the present application, the treatment scheme determination module can be used to execute Figure 2 As shown in step S130, the relevant contents of the processing scheme determination module can refer to the above description of step S130.

[0074] In an embodiment of the present application, corresponding to the above-mentioned organic waste treatment method based on a smart toilet applied to the electronic device, a computer-readable storage medium is also provided, in which a computer program is stored, and when the computer program is run, each step of the organic waste treatment method based on a smart toilet is executed.

[0075] Among them, the steps executed when the aforementioned computer program is running will not be described one by one here, and reference can be made to the previous explanation of the organic waste treatment method based on smart toilets.

[0076] In summary, the organic waste treatment method, system and device based on smart toilets provided by the present application first obtain the first waste data sequence corresponding to the target smart toilet; secondly, determine at least one associated smart toilet corresponding to the target smart toilet, and obtain at least one second waste data sequence corresponding to at least one associated smart toilet; then, based on at least one second waste data sequence, perform association mining on the first waste data sequence, output the organic waste component characteristics corresponding to the target smart toilet, and determine the organic waste treatment scheme corresponding to the target smart toilet based on the organic waste component characteristics. Based on the above content, since in the process of mining, the data corresponding to the target smart toilet will be combined with the data corresponding to the associated smart toilets for association mining, so that the mined organic waste component characteristics not only carry the semantic information of the data of the target smart toilet, but also carry the semantic information of the data of the associated smart toilets, and the data of the associated smart toilets has a positive effect on the data of the target smart toilet, therefore, it can ensure that the semantic information of the obtained organic waste component characteristics is richer and more reliable, thereby ensuring the reliability of the determined organic waste treatment scheme, and then improving the problem of relatively low reliability of organic waste treatment in the prior art.

[0077] In several embodiments provided in the embodiments of the present application, it should be understood that the disclosed device and method can also be implemented in other ways. The device and method embodiments described above are merely schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0078] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0079] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code. It should be noted that in this article, the term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. Without more constraints, an element defined by the phrase "comprising a..." does not exclude the existence of other identical elements in the process, method, article or apparatus comprising the element.

[0080] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for treating organic waste based on a smart toilet, characterized in that: include: Obtain a first waste data sequence corresponding to a target smart toilet, wherein the first waste data sequence includes a plurality of first waste component data sorted according to corresponding collection time, each of the first waste component data is used to reflect the organic waste component in the target smart toilet, and the target smart toilet is a non-flushing, microbial degradation toilet; Determine at least one associated smart toilet corresponding to the target smart toilet, and obtain at least one second waste data sequence corresponding to the at least one associated smart toilet, wherein each of the second waste data sequences includes a plurality of second waste component data sorted according to the corresponding collection time, each of the second waste component data is used to reflect the organic waste component in the target smart toilet, and each of the associated smart toilets is a non-flushing, microbial degradation toilet; Based on the at least one second waste data sequence, the first waste data sequence is associated with mining, and the organic waste component characteristics corresponding to the target smart toilet are output, and based on the organic waste component characteristics, the organic waste treatment plan corresponding to the target smart toilet is determined, wherein the organic waste treatment plan includes at least the type, quantity and environmental information of the microorganisms placed in the microbial degradation equipment corresponding to the target smart toilet.

2. The organic waste treatment method based on smart toilets according to claim 1 is characterized in that: The step of performing association mining on the first waste data sequence based on the at least one second waste data sequence, outputting the organic waste component characteristics corresponding to the target smart toilet, and determining the organic waste treatment solution corresponding to the target smart toilet based on the organic waste component characteristics includes: Using the first feature mining model in the target solution determination network, feature mining is performed on each first waste component data in the first waste data sequence to obtain a first waste component feature sequence including a plurality of first waste component features, wherein the target solution determination network is a neural network formed by training with sample data, and the first waste component features are used to reflect semantic information of the first waste component data; Determine a second feature mining model in the network by using the target solution, perform feature mining on each second waste component data in the second waste data sequence for each second waste data sequence in the at least one second waste data sequence, and obtain a second waste component feature sequence including a plurality of second waste component features, wherein the second waste component features are used to reflect semantic information of the second waste component data; The target solution is used to determine the feature fusion model in the network, and based on at least one second waste component feature sequence corresponding to the at least one second waste data sequence, the first waste component feature sequence is feature-associated and fused, and the organic waste component feature corresponding to the target smart toilet is output, wherein the organic waste component feature has semantic information of each second waste component feature sequence and the first waste component feature sequence; The solution determination model in the target solution determination network is used to determine the organic waste treatment solution corresponding to the target smart toilet based on the organic waste component characteristics, wherein the solution determination model belongs to a generative model or a discriminant model.

3. The organic waste treatment method based on smart toilets according to claim 2 is characterized in that: The step of using the target solution to determine the first feature mining model in the network, performing feature mining on each first waste component data in the first waste data sequence, and obtaining a first waste component feature sequence including a plurality of first waste component features, comprises: Using the target solution to determine the first vectorization unit in the first feature mining model in the network, respectively vectorize each first waste component data in the first waste data sequence to obtain a corresponding first waste component vector sequence; Based on the difference waste component data between every two adjacent first waste component data in the first waste data sequence, a corresponding difference waste component data sequence is determined, and each difference waste component data in the difference waste component data sequence is vectorized by the first vectorization unit to obtain a corresponding difference waste component vector sequence; The first waste component vector sequence and the difference waste component vector sequence are combined to obtain a first waste component feature sequence including a plurality of first waste component features, wherein the first waste component feature belongs to the first waste component vector or the difference waste component vector.

4. The organic waste treatment method based on smart toilets according to claim 2 is characterized in that: The step of using the target solution to determine the second feature mining model in the network, and performing feature mining on each second waste component data in the at least one second waste data sequence to obtain a second waste component feature sequence including a plurality of second waste component features, comprises: Using the target solution to determine the second vectorization unit in the second feature mining model in the network, for each second waste data sequence in the at least one second waste data sequence, respectively perform vectorization processing on each second waste component data in the second waste data sequence to obtain a corresponding second waste component vector sequence; For each of the at least one second waste data sequence, based on the difference waste component data between every two adjacent second waste component data in the second waste data sequence, a corresponding difference waste component data sequence is determined, and using the second vectorization unit, each difference waste component data in the difference waste component data sequence is vectorized to obtain a corresponding difference waste component vector sequence; For each second waste data sequence in the at least one second waste data sequence, the second waste component vector sequence and the corresponding difference waste component vector sequence corresponding to the second waste data sequence are combined and processed to obtain a second waste component feature sequence corresponding to the second waste data sequence including multiple second waste component features, wherein the second waste component feature belongs to the second waste component vector or the difference waste component vector.

5. The organic waste treatment method based on smart toilets according to claim 2 is characterized in that: The step of using the target solution to determine the feature fusion model in the network, performing feature association fusion on the first waste component feature sequence based on at least one second waste component feature sequence corresponding to the at least one second waste data sequence, and outputting the organic waste component features corresponding to the target smart toilet includes: For each second waste component feature sequence in at least one second waste component feature sequence corresponding to the at least one second waste data sequence, determining a feature fusion model in the network using the target solution, performing feature association mining on the first waste component feature sequence based on the second waste component feature sequence, and outputting corresponding waste component association features; The waste component association features corresponding to each of the second waste component feature sequences are aggregated to output the organic waste component features corresponding to the target smart toilet.

6. The organic waste treatment method based on smart toilets according to claim 5 is characterized in that: The step of determining the feature fusion model in the network using the target solution for each second waste component feature sequence in at least one second waste component feature sequence corresponding to the at least one second waste data sequence, performing feature association mining on the first waste component feature sequence based on the second waste component feature sequence, and outputting the corresponding waste component association feature comprises: splicing the first waste component features in the first waste component feature sequence to obtain a corresponding first waste component splicing feature, and splicing the second waste component features in each second waste component feature sequence in at least one second waste component feature sequence corresponding to the at least one second waste data sequence to obtain a corresponding second waste component splicing feature; Determine a feature fusion model in the network by using the target solution, perform feature association mining on at least two local features in the first waste component splicing feature based on at least two local features in the second waste component splicing feature for any second waste component splicing feature, and output corresponding at least two local waste component association features; The at least two local waste component association features are aggregated to output a waste component association feature corresponding to the second waste component splicing feature.

7. The organic waste treatment method based on smart toilets according to claim 6 is characterized in that: The step of using the target solution to determine the feature fusion model in the network, performing feature association mining on at least two local features in the first waste component splicing feature based on at least two local features in the second waste component splicing feature for any second waste component splicing feature, and outputting the corresponding at least two local waste component association features includes: For any second waste component splicing feature, the second waste component splicing feature is divided into a first waste component local feature corresponding to the second waste component data and a second waste component local feature corresponding to the difference waste component data, and the first waste component splicing feature is divided into a third waste component local feature corresponding to the first waste component data and a fourth waste component local feature corresponding to the difference waste component data; The target solution is used to determine the multiple first deep mining units included in the feature fusion model in the network, and the local features of the first waste component are deep mined in sequence to output the corresponding multiple first waste component deep features, and the local features of the third waste component are deep mined in sequence to output the corresponding multiple third waste component deep features, and, for each first deep mining unit, the first waste component deep feature corresponding to the first deep mining unit and the corresponding third waste component deep feature are multiplied to obtain the corresponding feature association parameter, and the third waste component deep feature is updated based on the feature association parameter to obtain the corresponding third waste component updated feature; Using the plurality of second deep mining units included in the feature fusion model, sequentially perform deep mining on the second waste component local features, output a plurality of corresponding second waste component deep features, and sequentially perform deep mining on the fourth waste component local features, output a plurality of corresponding fourth waste component deep features, and, for each second deep mining unit, perform multiplication calculation of transposed features based on the second waste component deep feature corresponding to the second deep mining unit and the fourth waste component deep feature corresponding to the second deep mining unit to obtain a corresponding feature association parameter, and, based on the feature association parameter, update the fourth waste component deep feature to obtain a corresponding fourth waste component updated feature; The obtained multiple third waste component update characteristics are superimposed or spliced ​​to output a corresponding local waste component association characteristic, and the obtained multiple fourth waste component update characteristics are superimposed or spliced ​​to output a corresponding local waste component association characteristic.

8. The method for treating organic waste based on a smart toilet according to any one of claims 1 to 7, characterized in that: The step of determining at least one associated smart toilet corresponding to the target smart toilet and acquiring at least one second waste data sequence corresponding to the at least one associated smart toilet includes: Acquire the first location information corresponding to the target smart toilet, and acquire the second location information corresponding to a plurality of other smart toilets, and, based on the first location information and the second location information, determine at least one other smart toilet that is correlated with the target smart toilet in terms of distribution position among the plurality of other smart toilets, so as to obtain at least one candidate smart toilet; Acquire the first user information corresponding to the target smart toilet, and acquire the second user information corresponding to each of the candidate smart toilets, and, based on the first user information and the second user information, determine at least one candidate smart toilet that is relevant to the target smart toilet in terms of user dimension from among the at least one candidate smart toilet, as at least one associated smart toilet corresponding to the target smart toilet; The second waste data sequence corresponding to each associated smart toilet in the at least one associated smart toilet is obtained respectively to obtain at least one corresponding second waste data sequence.

9. An organic waste treatment system based on a smart toilet, characterized in that: include: A first data acquisition module is used to acquire a first waste data sequence corresponding to a target smart toilet, wherein the first waste data sequence includes a plurality of first waste component data sorted according to corresponding collection time, each of the first waste component data is used to reflect the organic waste component in the target smart toilet, and the target smart toilet is a non-flushing, microbial degradation toilet; A second data acquisition module is used to determine at least one associated smart toilet corresponding to the target smart toilet, and acquire at least one second waste data sequence corresponding to the at least one associated smart toilet, wherein each of the second waste data sequences includes a plurality of second waste component data sorted according to the corresponding collection time, each of the second waste component data is used to reflect the organic waste component in the target smart toilet, and each of the associated smart toilets is a non-flushing, microbial degradation toilet; A treatment scheme determination module is used to perform association mining on the first waste data sequence based on the at least one second waste data sequence, output the organic waste component characteristics corresponding to the target smart toilet, and determine the organic waste treatment scheme corresponding to the target smart toilet based on the organic waste component characteristics, wherein the organic waste treatment scheme at least includes the type, quantity and environmental information of the microorganisms placed in the microbial degradation equipment corresponding to the target smart toilet.

10. An electronic device, characterized in that: include: Memory for storing computer programs; A processor connected to the memory is used to execute the computer program stored in the memory to implement the organic waste treatment method based on a smart toilet as described in any one of claims 1-8.

Images