Washing control method and device, electronic equipment and storage medium

Abstract

This disclosure relates to a washing control method, apparatus, electronic device, and storage medium. The method includes, in response to a washing command for a target dishwasher, acquiring at least one set of stain information and stain load level corresponding to at least one stain on the dishes to be washed; inputting the at least one stain information into a preset decision model to make a washing decision and obtain an initial washing strategy; performing component prediction based on the initial washing strategy and the at least one stain information to obtain component prediction information; performing spectral detection on the washing water in the target dishwasher to obtain first component information while the target dishwasher is performing a washing operation based on the initial washing strategy; determining the current washing state based on the component prediction information and the at least one first component information; and adjusting the initial washing strategy based on the current washing state and stain load level. This allows for precise matching of the washing mode, real-time adjustment of the washing strategy, improved real-time performance and accuracy of stain analysis, and significantly enhanced washing results.

Description

Technical Field

[0001] This disclosure relates to the field of dishwasher control technology, and in particular to a washing control method, apparatus, electronic device and storage medium. Background Technology

[0002] With the increasing popularity of dishwashers, the requirements for stain removal effectiveness are also constantly improving. How to accurately adjust the washing strategy according to the degree of stain has become the key to improving the washing precision of the product.

[0003] In related technologies, spectral sensors are often used to detect the composition of washing water to determine the degree of stains and then adjust the washing strategy. Alternatively, image recognition technology is used to identify stains on the surface of tableware and match them with preset washing modes. However, in these technologies, spectral detection can only be carried out after the stains and washing water are fully mixed, and it is impossible to obtain the dynamic changes in stain dissolution in real time. Image recognition can only determine the distribution of stains and cannot quantify the composition and concentration of stains. This results in the matching washing modes lacking specificity and failing to achieve on-demand adjustment. The real-time performance and accuracy of stain analysis are also low, leading to problems such as poor washing performance of dishwashers. Summary of the Invention

[0004] This disclosure provides a washing control method, apparatus, electronic device, and storage medium to at least solve the problems in related technologies, such as the inability to achieve on-demand control, low real-time performance and accuracy of stain analysis, leading to poor washing results in dishwashers. The technical solution of this disclosure is as follows: In response to a washing command for a target dishwasher, information on at least one stain corresponding to at least one stain on the dishes to be washed and the stain load level corresponding to the at least one stain are obtained. Input the at least one stain information into a preset decision model to make a washing decision and obtain an initial washing strategy; Based on the initial washing strategy and the at least one stain information, the composition of the at least one stain is predicted to obtain the composition prediction information of the at least one stain; the composition prediction information is used to indicate the composition information of the at least one stain within a preset time period after the target dishwasher performs the washing operation based on the initial washing strategy; When the target dishwasher performs a washing operation based on the initial washing strategy, the washing water in the target dishwasher is subjected to spectral detection to obtain the first component information corresponding to the at least one stain; Based on the component prediction information and the information of at least one first component, the current washing status is determined; The initial washing strategy is adjusted based on the current washing status and the degree of stain load.

[0005] In an optional embodiment, determining the current washing state based on the component prediction information and the at least one first component information includes: Based on the information of the at least one first component, determine the rate of change information corresponding to the at least one stain; Based on the prediction information of the at least one component and the information of the at least one first component, determine the component prediction deviation corresponding to the at least one stain; The current washing state is determined based on the at least one rate of change information and the prediction deviation of the at least one component.

[0006] In an optional embodiment, determining the current washing state based on the at least one rate of change information and the at least one component prediction deviation includes: Obtain preset mapping information; the preset mapping information represents the mapping relationship between preset change rate information and preset component prediction deviation corresponding to each preset washing state in at least one preset washing state; Based on the preset mapping information, the at least one rate of change information, and the at least one component prediction deviation, the current washing state is determined from the at least one preset washing state.

[0007] In an optional embodiment, adjusting the initial washing strategy based on the current washing state and the degree of stain load includes: Obtain preset decision mapping information; the preset decision mapping information represents the mapping relationship between the preset washing state and the preset stain load degree corresponding to each preset washing strategy adjustment information in at least one preset washing strategy adjustment information. Based on the preset decision mapping information, the current washing state, and the degree of stain load, washing strategy adjustment information is determined from at least one preset washing strategy adjustment information; Based on the washing strategy adjustment information, the initial washing strategy is adjusted.

[0008] In an optional embodiment, the at least one stain information includes the stain area corresponding to each of the at least one stains and the confidence level information corresponding to each stain; the stain load degree corresponding to the at least one stain is obtained in the following manner: Based on the stain area corresponding to each stain and the confidence information corresponding to each stain, determine the stain load information corresponding to the at least one stain; Determine the upper limit value of the stain load information in the at least one stain load information; The target stain severity threshold is determined from at least one preset stain severity threshold, based on the upper limit value of the stain load information. Based on the target stain severity threshold, the stain load severity corresponding to the at least one stain is obtained.

[0009] In an optional embodiment, the at least one stain information is obtained in the following manner: In response to a washing command for the target dishwasher, an image of the tableware to be washed is acquired; The tableware image is processed to identify stains based on a preset stain recognition model, thereby obtaining at least one stain information.

[0010] In an optional embodiment, the method further includes: In response to a washing end command triggered based on a preset washing duration corresponding to the washing instruction, the washing water in the target dishwasher is subjected to spectral detection processing to obtain the second component information corresponding to the at least one stain; Update the information of the at least one stain and the information of the at least one second component to the preset training data; Based on the updated preset training data, the preset stain recognition model and the preset decision model are trained.

[0011] According to a second aspect of the present disclosure, a washing control device is provided, comprising: The acquisition module is used to acquire, in response to a washing command for a target dishwasher, at least one stain information corresponding to at least one stain on the dishes to be washed and the stain load degree corresponding to the at least one stain. An initial washing strategy determination module is used to input the at least one stain information into a preset decision model to make a washing decision and obtain an initial washing strategy. The component prediction module is used to predict the component of the at least one stain based on the initial washing strategy and the at least one stain information, and obtain the component prediction information of the at least one stain; the component prediction information is used to indicate the component information of the at least one stain within a preset time period after the target dishwasher performs the washing operation based on the initial washing strategy; The first spectral detection module is used to perform spectral detection on the washing water in the target dishwasher when the target dishwasher performs a washing operation based on the initial washing strategy, so as to obtain the first component information corresponding to the at least one stain. The current washing status determination module is used to determine the current washing status based on the component prediction information and the information of at least one first component; The initial washing strategy adjustment module is used to adjust the initial washing strategy based on the current washing state and the degree of stain load.

[0012] In an optional embodiment, the current washing status determination module includes: A rate of change information determination unit is used to determine the rate of change information corresponding to the at least one stain based on the at least one first component information; The component prediction deviation determination unit is used to determine the component prediction deviation corresponding to the at least one stain based on the at least one component prediction information and the at least one first component information; The current washing state determination unit is used to determine the current washing state based on the at least one change rate information and the at least one component prediction deviation.

[0013] In an optional embodiment, the current washing status determination unit includes: A preset mapping information acquisition subunit is used to acquire preset mapping information; the preset mapping information represents the mapping relationship between preset change rate information and preset component prediction deviation corresponding to each preset washing state in at least one preset washing state; The current washing state determination subunit is used to determine the current washing state from the at least one preset washing state based on the preset mapping information, the at least one rate of change information, and the at least one component prediction deviation.

[0014] In an optional embodiment, the initial washing strategy adjustment module includes: A preset decision mapping information acquisition unit is used to acquire preset decision mapping information; the preset decision mapping information represents the mapping relationship between the preset washing state and the preset stain load degree corresponding to each preset washing strategy adjustment information in at least one preset washing strategy adjustment information. A washing strategy adjustment information determination unit is used to determine washing strategy adjustment information from at least one preset washing strategy adjustment information based on the preset decision mapping information, the current washing state, and the degree of stain load. An initial washing strategy adjustment unit is used to adjust the initial washing strategy based on the washing strategy adjustment information.

[0015] In an optional embodiment, the at least one stain information includes the stain area corresponding to each of the at least one stains and the confidence level information corresponding to each stain; the stain load degree corresponding to the at least one stain is obtained in the following manner: A stain load information determination module is used to determine the stain load information corresponding to at least one stain based on the stain area corresponding to each stain and the confidence information corresponding to each stain. A stain load information upper limit value determination module is used to determine the upper limit value of stain load information in the at least one type of stain load information; A target stain severity threshold determination module is used to determine, from at least one preset stain severity threshold, the target stain severity threshold reached by the upper limit value of the stain load information; The stain load level acquisition module is used to obtain the stain load level corresponding to the at least one stain based on the target stain level threshold.

[0016] In an optional embodiment, the at least one stain information is obtained in the following manner: A tableware image acquisition module is used to acquire tableware images of the tableware to be washed in response to a washing command for the target dishwasher. A stain recognition and processing module is used to perform stain recognition processing on the tableware image based on a preset stain recognition model to obtain at least one stain information.

[0017] In an optional embodiment, the apparatus further includes: The second spectral detection module, in response to a washing end command triggered based on a preset washing duration corresponding to the washing instruction, performs spectral detection processing on the washing water in the target dishwasher to obtain the second component information corresponding to the at least one stain; A preset training data update module is used to update the at least one stain information and the at least one second component information to the preset training data; The preset model training module is used to train the preset stain recognition model and the preset decision model based on the updated preset training data.

[0018] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method as described in any one of the first aspects above.

[0019] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided such that, when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method described in any of the first aspects of the present disclosure.

[0020] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: In response to a washing command from a target dishwasher, the system acquires information on at least one type of stain and its corresponding stain load on the dishes to be washed. It then inputs this stain information into a pre-defined decision model to make a washing decision, resulting in an initial washing strategy. Based on the initial washing strategy and the stain information, it predicts the composition of the stain, obtaining component prediction information. While the target dishwasher executes the washing operation based on the initial washing strategy, it performs spectral analysis on the washing water in the target dishwasher to obtain first component information corresponding to the stain. Based on the component prediction information and the first component information, it determines the current washing state. By adjusting the initial washing strategy based on the current washing state and stain load, it can accurately match the washing mode, adjust the washing strategy in real time, improve the real-time performance and accuracy of stain analysis, and significantly enhance the washing effect.

[0021] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0023] Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment; Figure 2 This is a flowchart illustrating a washing control method according to an exemplary embodiment; Figure 3 This is a block diagram of a washing control device according to an exemplary embodiment; Figure 4 This is a block diagram illustrating an electronic device for washing control according to an exemplary embodiment. Detailed Implementation

[0024] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0025] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar different contents and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0026] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0027] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment, such as... Figure 1 As shown, the application environment may include a dishwasher 100 and a server 200.

[0028] In an alternative embodiment, the dishwasher 100 can be used to provide washing services for dishes to be washed.

[0029] In an optional embodiment, server 200 can provide background services to dishwasher 100 and perform washing control on dishwasher 100. Optionally, server 200 can pre-train a preset decision model. Accordingly, washing decisions can be made in conjunction with the preset decision model. Specifically, server 200 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0030] In addition, it should be noted that, Figure 1 The example shown is merely one application environment provided by this disclosure. In practical applications, other application environments may also be included.

[0031] In the embodiments described in this specification, the dishwasher 100 and the server 200 can be directly or indirectly connected via wired or wireless communication, and this disclosure does not impose any limitations.

[0032] Figure 2This is a flowchart illustrating a washing control method according to an exemplary embodiment, the washing control method being used in a server, such as... Figure 2 As shown, it includes the following steps.

[0033] In step S201, in response to a washing command for the target dishwasher, information on at least one stain corresponding to at least one stain on the dishes to be washed and the stain load level corresponding to at least one stain are obtained. In one specific embodiment, a washing instruction can be used to trigger a target dishwasher to perform a washing operation. The dishes to be washed can be dishes inside the target dishwasher. At least one stain can include at least one of the following: grease or starch. At least one stain information can be used to indicate at least one stain on the dishes to be washed. At least one stain information can be at least one stain label corresponding to at least one stain. The stain load corresponding to at least one stain can be the stain degree corresponding to at least one stain. Specifically, the stain degree can include light stain, medium stain, and heavy stain.

[0034] In an optional embodiment, the above-mentioned at least one stain information can be obtained in the following manner: In response to a washing command for the target dishwasher, acquire an image of the dishes to be washed; Based on a preset stain recognition model, stain recognition processing is performed on tableware images to obtain at least one stain information.

[0035] In one specific embodiment, the tableware image can be an image corresponding to the tableware to be washed. Optionally, it can be a photo or video frame image of the tableware to be washed taken by the camera inside the target dishwasher. Specifically, at the same time as the camera takes a picture, light waves of a preset wavelength corresponding to each of the at least one stain can be irradiated to obtain an image of the tableware to be washed under the light waves. The preset wavelength corresponding to the at least one stain can be determined by using the light sensitivity of the at least one stain. For example, the preset wavelength corresponding to grease can be 850 nm, and the preset wavelength corresponding to starch can be 470 nm.

[0036] In one specific embodiment, a preset stain recognition model can be used to perform stain recognition processing on tableware images. Specifically, the preset stain recognition model can be a semantic segmentation network with an encoder-decoder structure.

[0037] In the above embodiments, by performing stain recognition processing on tableware images using a preset stain recognition model, it is possible to automatically acquire tableware stain information, solve the problem of spectral detection lag, lay a data foundation for the feedback control of the subsequent initial washing strategy, and improve the accuracy and intelligence of dishwasher washing control.

[0038] In an optional embodiment, the above method may further include: In response to a washing end command triggered by a preset washing duration based on a washing instruction, the washing water in the target dishwasher is subjected to spectral detection processing to obtain information on the second component corresponding to at least one stain. Update the preset training data with at least one stain information and at least one second component information; Based on the updated preset training data, train the preset stain recognition model and the preset decision model.

[0039] In one specific embodiment, the washing end command can be used to control the target dishwasher to end the washing operation. The washing end command can be triggered based on the preset washing time corresponding to the washing command. The second component information can be the water spectral data of the washing water in the target dishwasher obtained by spectral detection triggered by the washing end command.

[0040] In a specific embodiment, the preset training data can be the training data corresponding to the preset stain recognition model and the preset decision model. Specifically, the preset training data can include at least one stain information within a historical time period, the component information corresponding to at least one stain when the washing instruction is triggered within a historical time period, and the component information corresponding to at least one stain when the washing end instruction is triggered within a historical time period. Accordingly, the at least one stain information and the second component information can be updated to the preset training data.

[0041] In the above embodiments, the final residual information of the stain is obtained by spectral detection, and then integrated with the initial stain information to update the training data and retrain the model. This optimizes the stain recognition model and the decision model, effectively improves the generalization ability of the model, and reduces the manual cost of model optimization.

[0042] In an optional embodiment, at least one stain information may include the stain area corresponding to each stain and the confidence level information corresponding to each stain; the stain load degree corresponding to at least one stain may be obtained in the following manner: Based on the stain area and confidence information corresponding to each stain, determine the stain load information corresponding to at least one stain. Determine the upper limit value of stain load information in at least one type of stain load information; The target stain severity threshold is determined by setting at least one preset stain severity threshold to achieve the upper limit of stain load information. Based on the target stain severity threshold, the stain load level corresponding to at least one stain is obtained.

[0043] In a specific embodiment, through the formula Calculate the stain load information for each type of stain in at least one type of stain, where, For each type of stain, the corresponding stain area. For each type of stain, the confidence level information is provided. The number of stain instances is specific, and the confidence information can be the confidence level corresponding to the stain area.

[0044] In one specific embodiment, the upper limit of stain load information can be the upper limit corresponding to at least one stain load information, the at least one preset stain degree threshold can be the threshold corresponding to at least one preset stain degree, and the target stain degree threshold can be the upper limit of stain load information reaching the threshold among at least one preset stain degree threshold. Specifically, the at least one preset stain degree threshold can be stain load information ≥ 0.15 (light stain), stain load information ≥ 0.55 (moderate stain), and stain load information ≥ 0.85 (heavy stain). Optionally, when the upper limit of stain load information is 0.9 and the stain type corresponding to the upper limit of stain load information is grease, the target stain degree threshold can be 0.85 (heavy stain), and the stain load degree can be heavy grease.

[0045] In the above embodiments, stain load information is calculated by stain area and confidence level, and the degree of stain load is determined by matching a preset threshold based on the upper limit of the load. This accurately determines the degree of stain, provides a grading basis for subsequent washing decision-making processes, and improves the pertinence of washing control.

[0046] In step S203, at least one stain information is input into a preset decision model to make a washing decision and obtain an initial washing strategy; In one specific embodiment, the initial washing strategy can be used to instruct the target dishwasher on the washing operation during the washing process. The initial washing strategy can be obtained by a preset decision model based on at least one stain information. Specifically, the initial washing strategy can include at least one of the following: detergent type, detergent dosage, washing water temperature, etc.

[0047] In step S205, based on the initial washing strategy and at least one stain information, the composition of at least one stain is predicted to obtain the composition prediction information of at least one stain. In one specific embodiment, the component prediction information can be used to indicate the component information of at least one stain within a preset time period after the target dishwasher performs a washing operation based on the initial washing strategy. Specifically, this can be achieved through a pre-trained regression model. The decay constant associated with the initial washing strategy is obtained, where, It's the washing water temperature. It's the detergent concentration, and then through... Obtain composition prediction information for at least one stain.

[0048] In step S207, when the target dishwasher performs a washing operation based on the initial washing strategy, the washing water in the target dishwasher is subjected to spectral detection to obtain information on the first component corresponding to at least one stain. In a specific embodiment, the first component information may be the water spectral data of the washing water in the target dishwasher obtained by spectral detection when the target dishwasher performs the washing operation based on the initial washing strategy. Specifically, the first component information corresponding to at least one stain may be collected by a spectral sensor according to a preset collection period.

[0049] In step S209, the current washing state is determined based on the component prediction information and at least one first component information; In one specific embodiment, the current washing state can represent the current washing state of the dishes to be washed.

[0050] In an optional embodiment, determining the current washing state based on component prediction information and at least one first component information may include: Based on information about at least one first component, determine the rate of change information corresponding to at least one stain. Based on at least one component prediction information and at least one first component information, determine the component prediction bias corresponding to at least one stain; The current washing status is determined based on at least one rate of change information and at least one component prediction bias.

[0051] In one specific embodiment, the rate of change information corresponding to at least one stain can be the instantaneous rate of change of at least one stain over time. Specifically, it can be obtained through... Calculated.

[0052] In one specific embodiment, the component deviation information can be the difference between the first component information and the component prediction information, which can be obtained through... The calculation yields , where is the component prediction information, is the first component information, and is . Number of sampling periods The sampling period.

[0053] In the above embodiments, the washing status can be determined by the dynamic changes and prediction deviations of the stain components, which can achieve accurate perception of the washing process and provide a basis for the dynamic adjustment and intelligent optimization of the subsequent washing strategy.

[0054] In an optional embodiment, determining the current washing state based on at least one rate of change information and at least one component prediction bias may include: Obtain preset mapping information; The current washing state is determined from at least one preset washing state based on preset mapping information, at least one rate of change information, and at least one component prediction deviation.

[0055] In a specific embodiment, the preset mapping information can characterize the mapping relationship between the preset change rate information and the preset component prediction deviation corresponding to each preset washing state in at least one preset washing state. Specifically, at least one preset washing state may include a first preset washing state, a second preset washing state, and a third preset washing state. For example, the first preset washing state characterizes the current washing state as normal stain dissolution, the preset change rate information corresponding to the first preset washing state is greater than or equal to a preset target change rate, the preset target change rate can be a pre-set expected change rate, and the preset component prediction deviation corresponding to the first preset washing state is less than or equal to a preset deviation threshold. The second preset washing state characterizes the current washing state as slow stain dissolution, the preset change rate information corresponding to the second preset washing state is less than the preset target change rate, and the preset component prediction deviation corresponding to the second preset washing state is greater than a preset deviation threshold. The third preset washing state characterizes the current washing state as abnormal stain dissolution, and the preset change rate information corresponding to the third preset washing state is a preset change rate information fluctuation greater than a threshold.

[0056] In the above embodiments, by using preset mapping information, the current washing state corresponding to at least one change rate information and at least one component prediction deviation can be quickly determined, thereby improving the determination efficiency.

[0057] In step S2011, the initial washing strategy is adjusted based on the current washing status and the degree of stain load.

[0058] In one specific embodiment, washing strategy adjustment information can be determined based on the current washing status and the degree of stain load, and the initial washing strategy can be adjusted based on the washing strategy adjustment information.

[0059] In an optional embodiment, adjusting the initial washing strategy based on the current washing state and the degree of stain load may include: Obtain preset decision mapping information; Based on preset decision mapping information, current washing status and stain load level, determine washing strategy adjustment information from at least one preset washing strategy adjustment information; Adjust the initial washing strategy based on the washing strategy adjustment information.

[0060] In one specific embodiment, the preset decision mapping information can characterize the mapping relationship between the preset washing state and the preset stain load level corresponding to each preset washing strategy adjustment information in at least one preset washing strategy adjustment information. The washing strategy adjustment information can be used to indicate the adjustment of the washing strategy of the target dishwasher during the washing process.

[0061] In one specific embodiment, when the current washing state is that the stains dissolve slowly and the stain load is heavy grease, the washing strategy adjustment information may be at least one of the following: increasing the amount of alkaline detergent added or increasing the water temperature.

[0062] In the above embodiments, by pre-setting decision mapping information and adjusting the initial washing strategy in combination with the washing status and the degree of stain load, the washing strategy can be precisely adjusted, achieving differentiated adjustment.

[0063] As can be seen from the technical solutions provided in the embodiments of this specification above, in response to a washing command for a target dishwasher, this specification obtains at least one stain information corresponding to at least one stain on the dishes to be washed and the stain load degree corresponding to at least one stain; inputs the at least one stain information into a preset decision model to make a washing decision and obtain an initial washing strategy; based on the initial washing strategy and the at least one stain information, performs component prediction on the at least one stain to obtain component prediction information for the at least one stain; when the target dishwasher performs a washing operation based on the initial washing strategy, performs spectral detection on the washing water in the target dishwasher to obtain first component information corresponding to at least one stain; based on the component prediction information and the at least one first component information, determines the current washing state; and adjusts the initial washing strategy based on the current washing state and stain load degree, which can accurately match the washing mode, adjust the washing strategy in real time, improve the real-time performance and accuracy of stain analysis, and greatly improve the washing effect.

[0064] Figure 3 This is a block diagram illustrating a washing control device according to an exemplary embodiment. (Refer to...) Figure 3 The device includes: The acquisition module 310 is used to acquire, in response to a washing instruction for the target dishwasher, at least one stain information corresponding to at least one stain on the dishes to be washed and the stain load degree corresponding to at least one stain. The initial washing strategy determination module 330 is used to input at least one stain information into a preset decision model to make a washing decision and obtain an initial washing strategy. The component prediction module 350 is used to predict the component of at least one stain based on the initial washing strategy and at least one stain information, and obtain the component prediction information of at least one stain; the component prediction information is used to indicate the component information of at least one stain within a preset time period after the target dishwasher performs the washing operation based on the initial washing strategy. The first spectral detection module 370 is used to perform spectral detection on the washing water in the target dishwasher when the target dishwasher performs a washing operation based on the initial washing strategy, so as to obtain information on the first component corresponding to at least one stain. The current washing status determination module 390 is used to determine the current washing status based on the component prediction information and at least one first component information; The initial washing strategy adjustment module 3110 is used to adjust the initial washing strategy based on the current washing status and the degree of stain load.

[0065] In an optional embodiment, the current washing status determination module 390 includes: A rate of change information determination unit is used to determine the rate of change information corresponding to at least one stain based on at least one first component information; The component prediction deviation determination unit is used to determine the component prediction deviation corresponding to at least one stain based on at least one component prediction information and at least one first component information. The current washing state determination unit is used to determine the current washing state based on at least one change rate information and at least one component prediction deviation.

[0066] In an optional embodiment, the current washing status determination unit includes: The preset mapping information acquisition subunit is used to acquire preset mapping information; the preset mapping information represents the mapping relationship between the preset change rate information and the preset component prediction deviation corresponding to each preset washing state in at least one preset washing state. The current washing state determination subunit is used to determine the current washing state from at least one preset washing state based on preset mapping information, at least one rate of change information, and at least one component prediction deviation.

[0067] In an optional embodiment, the initial washing strategy adjustment module 3110 includes: A preset decision mapping information acquisition unit is used to acquire preset decision mapping information; the preset decision mapping information represents the mapping relationship between the preset washing state and the preset stain load degree corresponding to each preset washing strategy adjustment information in at least one preset washing strategy adjustment information. The washing strategy adjustment information determination unit is used to determine washing strategy adjustment information from at least one preset washing strategy adjustment information based on preset decision mapping information, current washing status and stain load level; The initial washing strategy adjustment unit is used to adjust the initial washing strategy based on the washing strategy adjustment information.

[0068] In an optional embodiment, at least one stain information includes the stain area corresponding to each stain in at least one stain and the confidence information corresponding to each stain; the stain load degree corresponding to at least one stain is obtained in the following manner: The stain load information determination module is used to determine the stain load information of at least one stain based on the stain area corresponding to each stain and the confidence information corresponding to each stain. A stain load information upper limit value determination module is used to determine the upper limit value of stain load information in at least one type of stain load information; The target stain severity threshold determination module is used to determine the target stain severity threshold that the upper limit of stain load information reaches from at least one preset stain severity threshold; The stain load degree acquisition module is used to obtain the stain load degree corresponding to at least one stain based on the target stain degree threshold.

[0069] In one optional embodiment, at least one stain information is obtained in the following manner: The tableware image acquisition module is used to acquire tableware images of the tableware to be washed in response to the washing command for the target dishwasher; The stain recognition and processing module is used to perform stain recognition processing on tableware images based on a preset stain recognition model to obtain at least one stain information.

[0070] In an optional embodiment, the above-described apparatus further includes: The second spectral detection module, in response to a washing end command triggered based on a preset washing duration corresponding to the washing instruction, performs spectral detection processing on the washing water in the target dishwasher to obtain information on the second component corresponding to at least one stain. A preset training data update module is used to update at least one stain information and at least one second component information to the preset training data; The preset model training module is used to train a preset stain recognition model and a preset decision model based on the updated preset training data.

[0071] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here. Figure 4 This is a block diagram illustrating an electronic device for washing control according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 4As shown, the electronic device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a washing control method. Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the electronic device to which the present disclosure is applied. A specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements. In an exemplary embodiment, an electronic device is also provided, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the washing control method as described in the embodiments of this disclosure.

[0072] In an exemplary embodiment, a computer-readable storage medium is also provided, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the washing control method of the embodiments of this disclosure.

[0073] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0074] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A washing control method, characterized in that, include: In response to a washing command for a target dishwasher, information on at least one stain corresponding to at least one stain on the dishes to be washed and the stain load level corresponding to the at least one stain are obtained. Input the at least one stain information into a preset decision model to make a washing decision and obtain an initial washing strategy; Based on the initial washing strategy and the at least one stain information, the composition of the at least one stain is predicted to obtain the composition prediction information of the at least one stain; the composition prediction information is used to indicate the composition information of the at least one stain within a preset time period after the target dishwasher performs the washing operation based on the initial washing strategy; When the target dishwasher performs a washing operation based on the initial washing strategy, the washing water in the target dishwasher is subjected to spectral detection to obtain the first component information corresponding to the at least one stain; Based on the component prediction information and the information of at least one first component, the current washing status is determined; The initial washing strategy is adjusted based on the current washing status and the degree of stain load.

2. The washing control method according to claim 1, characterized in that, Determining the current washing state based on the component prediction information and the information of at least one first component includes: Based on the information of the at least one first component, determine the rate of change information corresponding to the at least one stain; Based on the prediction information of the at least one component and the information of the at least one first component, determine the component prediction deviation corresponding to the at least one stain; The current washing state is determined based on the at least one rate of change information and the prediction deviation of the at least one component.

3. The washing control method according to claim 2, characterized in that, Determining the current washing state based on the at least one rate of change information and the at least one component prediction deviation includes: Obtain preset mapping information; the preset mapping information represents the mapping relationship between preset change rate information and preset component prediction deviation corresponding to each preset washing state in at least one preset washing state; Based on the preset mapping information, the at least one rate of change information, and the at least one component prediction deviation, the current washing state is determined from the at least one preset washing state.

4. The washing control method according to claim 1, characterized in that, The adjustment of the initial washing strategy based on the current washing state and the degree of stain load includes: Obtain preset decision mapping information; the preset decision mapping information represents the mapping relationship between the preset washing state and the preset stain load degree corresponding to each preset washing strategy adjustment information in at least one preset washing strategy adjustment information. Based on the preset decision mapping information, the current washing state, and the degree of stain load, washing strategy adjustment information is determined from at least one preset washing strategy adjustment information; Based on the washing strategy adjustment information, the initial washing strategy is adjusted.

5. The washing control method according to claim 1, characterized in that, The at least one stain information includes the stain area corresponding to each of the at least one stains and the confidence level information corresponding to each stain; the stain load degree corresponding to the at least one stain is obtained in the following manner: Based on the stain area corresponding to each stain and the confidence information corresponding to each stain, determine the stain load information corresponding to the at least one stain; Determine the upper limit value of the stain load information in the at least one stain load information; The target stain severity threshold is determined from at least one preset stain severity threshold, based on the upper limit value of the stain load information. Based on the target stain severity threshold, the stain load severity corresponding to the at least one stain is obtained.

6. The washing control method according to claim 1, characterized in that, The at least one stain information is obtained in the following manner: In response to a washing command for the target dishwasher, an image of the tableware to be washed is acquired; The tableware image is processed to identify stains based on a preset stain recognition model, thereby obtaining at least one stain information.

7. The washing control method according to claim 6, characterized in that, The method further includes: In response to a washing end command triggered based on a preset washing duration corresponding to the washing instruction, the washing water in the target dishwasher is subjected to spectral detection processing to obtain the second component information corresponding to the at least one stain; Update the information of the at least one stain and the information of the at least one second component to the preset training data; Based on the updated preset training data, the preset stain recognition model and the preset decision model are trained.

8. A washing control device, characterized in that, include: The acquisition module is used to acquire, in response to a washing command for a target dishwasher, at least one stain information corresponding to at least one stain on the dishes to be washed and the stain load degree corresponding to the at least one stain. An initial washing strategy determination module is used to input the at least one stain information into a preset decision model to make a washing decision and obtain an initial washing strategy. The component prediction module is used to predict the component of the at least one stain based on the initial washing strategy and the at least one stain information, and obtain the component prediction information of the at least one stain; the component prediction information is used to indicate the component information of the at least one stain within a preset time period after the target dishwasher performs the washing operation based on the initial washing strategy; A spectral detection module is used to perform spectral detection on the washing water in the target dishwasher when the target dishwasher performs a washing operation based on the initial washing strategy, so as to obtain the first component information corresponding to the at least one stain. The current washing status determination module is used to determine the current washing status based on the component prediction information and the information of at least one first component; The initial washing strategy adjustment module is used to adjust the initial washing strategy based on the current washing state and the degree of stain load.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the washing control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the washing control method as described in any one of claims 1 to 7.

Images