Neural Network-Based Method and Product for Allocating Dishwashing Liquid in Rental Dishwashers

Abstract

The present application relates to a method and product for dispensing washing liquid of a rental dishwashing machine based on a neural network, which is applied to the field of data analysis. The method includes: obtaining an image of the rental dishwashing machine before the washing liquid cleaning stage and the current attribute information; identifying the load information of the image; inputting the load information and the attribute information into a prediction model to obtain a first washing liquid dispensing amount; generating a control instruction for a washing liquid pump according to the first washing liquid dispensing amount, and using the control instruction to control the operation of the washing liquid pump. The present application obtains an image of the item to be washed, and identifies the load amount of the item to be washed and the stain degree of the item to be washed in the image. These two pieces of information can indicate the amount of washing tasks. By inputting the load amount, the stain degree, the water temperature set by the rental dishwashing machine, and the washing mode into the prediction model, the first washing liquid dispensing amount of the washing liquid can be quickly and accurately obtained, so as to achieve the accurate dispensing of the washing liquid.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular, to a method and product for dispensing washing liquid of a rental dishwasher based on a neural network. Background Art

[0002] At present, the application of rental dishwashers in the market shows an increasing trend, which is mainly due to their convenience and economy. However, although rental dishwashers have made significant progress in technology, there are still some challenges in the dispensing of washing liquid. Conventional products rely mostly on manual operation by users for the dispensing of washing liquid, which not only increases the operation burden on users but also makes it difficult to achieve intelligent management of the washing liquid.

[0003] In related technologies, a preset fixed dispensing amount is used to add the washing liquid. However, this method has significant limitations because it cannot be flexibly adjusted according to actual washing needs. When washing tableware with lighter stains, it may cause waste of the washing liquid; while when washing tableware with heavier stains, it may lead to poor washing effect due to insufficient washing liquid.

[0004] Therefore, how to achieve intelligent management of the dispensing of washing liquid has become the key to improving the performance of rental dishwashers. Summary of the Invention

[0005] The purpose of this application is to provide a method and product for dispensing washing liquid of a rental dishwasher based on a neural network, which can accurately determine the dispensing amount of the washing liquid.

[0006] In the first aspect, a method for dispensing washing liquid of a rental dishwasher based on a neural network is provided, including:

[0007] Obtaining an image of the rental dishwasher before the washing liquid cleaning stage and current attribute information; the image is an image of the items to be washed inside the rental dishwasher, and the attribute information includes: water temperature and washing mode;

[0008] Identifying the load information of the image, where the load information includes: the load amount of the items to be washed and the stain degree of the items to be washed;

[0009] Inputting the load information and the attribute information into a prediction model to obtain a first washing liquid dispensing amount; the prediction model is obtained by training a neural network model with a plurality of first training samples, and the first training samples include first load information, first attribute information, and the actual washing liquid dispensing amount;

[0010] Generating a control instruction for the washing liquid pump according to the first washing liquid dispensing amount, and using the control instruction to control the operation of the washing liquid pump.

[0011] By adopting the above technical solution, an image of the item to be washed is obtained, and the load amount of the item to be washed and the stain degree of the item to be washed in the image are identified. These two pieces of information can indicate the amount of the washing task. By inputting the load amount, the stain degree, the water temperature set by the rental dishwasher, and the washing mode into the prediction model, the first washing liquid ration of the washing liquid can be obtained quickly and accurately, so as to realize the accurate dispensing of the washing liquid.

[0012] In a possible implementation manner, the generating a control instruction for the washing liquid pump according to the first washing liquid ration includes:

[0013] Obtain water quality information, and correct the first washing liquid ration based on the water quality information to obtain a second washing liquid ration;

[0014] Generate a control instruction for the washing liquid pump based on the second washing liquid ration.

[0015] By adopting the above technical solution, when generating the control instruction for the washing liquid pump, the influence of the water quality information on the washing effect is considered, and thus the washing liquid ration is corrected according to the water quality information, which can ensure the effective use of the washing liquid under different water quality conditions and further improve the washing effect and user satisfaction.

[0016] In a possible implementation manner, the correcting the first washing liquid ration based on the water quality information to obtain a second washing liquid ration includes:

[0017] Determine the water quality difference between the water quality information and the standard water quality information;

[0018] According to the water quality difference and the first correspondence relationship, determine the adjustment value corresponding to the water quality difference, where the first correspondence relationship is the correspondence relationship between multiple water quality differences and multiple adjustment values;

[0019] Correct the first washing liquid ration according to the adjustment value corresponding to the water quality difference to obtain a second washing liquid ration.

[0020] By adopting the above technical solution, when correcting the washing liquid ration based on the water quality information, the water quality difference between the water quality information and the standard water quality information is determined, and then the corresponding adjustment value is quickly determined according to the preset correspondence relationship to realize the correction of the ration to obtain the second washing liquid ration.

[0021] In a possible implementation manner, the generating a control instruction for the washing liquid pump based on the second washing liquid ration includes:

[0022] Read the remaining amount of the washing liquid;

[0023] If the second washing liquid ration is not less than the remaining amount of the washing liquid, generate a control instruction for the washing liquid pump according to the second washing liquid ration;

[0024] If the amount of the second washing liquid dispensed is less than the remaining amount of the washing liquid, adjust the attribute information, and based on the load information and the adjusted attribute information, utilize the prediction model again to obtain a new amount of the second washing liquid dispensed until a preset condition is met, where the preset condition is that the new amount of the second washing liquid dispensed is not less than the remaining amount of the washing liquid, or the attribute information reaches the attribute information threshold.

[0025] When the preset condition is that the new amount of the second washing liquid dispensed is not less than the remaining amount of the washing liquid, generate a control instruction for the washing liquid pump according to the new amount of the second washing liquid dispensed.

[0026] When the preset condition is that the attribute information reaches the attribute information threshold, generate a prompt message to prompt the user that washing liquid replenishment is required.

[0027] By adopting the above technical solution, before generating the control instruction for the washing liquid pump, the remaining amount of the washing liquid will be checked to determine whether the remaining amount of the washing liquid meets the requirement. If it does not meet the requirement, the attribute information will be adjusted according to the remaining amount, and the amount of the second washing liquid dispensed after adjustment will be determined iteratively until the preset condition is reached. If the remaining amount of the washing liquid meets the new amount of the second washing liquid dispensed, based on the new attribute information, control the washing liquid pump according to the new amount of the second washing liquid dispensed. Otherwise, prompt the user to replenish the washing liquid in time to ensure that the washing task can proceed normally.

[0028] In a possible implementation manner, the rule for adjusting the attribute information is as follows: first, adjust the water temperature according to the water temperature adjustment step. When the water temperature reaches the preset water temperature threshold, then adjust the washing mode. Correspondingly, the attribute information threshold is the threshold corresponding to the washing mode.

[0029] By adopting the above technical solution, when adjusting the attribute information, first adjust the water temperature according to the water temperature adjustment step, and then adjust the washing mode when the water temperature reaches the preset threshold. This adjustment rule can give priority to ensuring the influence of the water temperature on the washing effect, and at the same time avoid the interference of frequently changing the washing mode on the washing process, realizing a more stable and efficient washing process.

[0030] In a possible implementation manner, after controlling the washing liquid pump to work by using the control instruction, it further includes:

[0031] After completing the washing task, obtain the user feedback information.

[0032] If the feedback information is positive information, a second training sample is generated based on the load information, the final attribute information, and the second washing liquid ration; if the feedback information is negative information, the second washing liquid ration is corrected based on the feedback information to obtain a third washing liquid ration, and a second training sample is generated based on the load information, the final attribute information, and the third washing liquid ration;

[0033] When the number of second training samples reaches a preset number threshold, the prediction model is retrained based on all the obtained second training samples.

[0034] By adopting the above technical solution, after the washing task is completed, user feedback information is obtained, and based on the processing of the positive and negative information of the feedback information, the system can more comprehensively understand user needs and washing effects, collect training samples, and retrain the prediction model, which can continuously optimize the prediction performance of the model and improve the accuracy and efficiency of the washing liquid ration.

[0035] In a possible implementation manner, the generating a control instruction for the washing liquid pump according to the first washing liquid ration includes:

[0036] Determine the first working time and the first working speed of the washing liquid pump corresponding to the washing mode;

[0037] Judge whether the stain degree of the item to be washed is greater than a preset stain degree threshold;

[0038] If not, generate a control instruction for the washing liquid pump according to the first washing liquid ration, the first working time, and the first working speed of the washing liquid pump;

[0039] If so, determine the working adjustment time and the working adjustment speed corresponding to the item to be washed according to the stain degree of the item to be washed and a second corresponding relationship, where the second corresponding relationship is the corresponding relationship among the stain degree, the working adjustment time, and the working adjustment speed; and adjust the first working time and the first working speed respectively according to the working adjustment time and the working adjustment speed to obtain a second working time and a second working speed, and generate a control instruction for the washing liquid pump according to the first washing liquid ration, the second working time, and the second working speed of the washing liquid pump.

[0040] By adopting the above technical solution, when generating a control instruction for the washing liquid pump, the working time and the working speed of the washing liquid pump can be dynamically adjusted according to the stain degree of the item to be washed. This dynamic adjustment mechanism can ensure the reasonable use of the washing liquid under different stain degrees, more precisely control the washing process, and improve the washing effect and efficiency.

[0041] In a second aspect, an electronic device is provided, and the electronic device includes:

[0042] One or more processors;

[0043] A memory;

[0044] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to: execute operations corresponding to the methods shown in any possible implementation manner of the first aspect.

[0045] In a third aspect, a computer-readable storage medium is provided, and the storage medium stores at least one instruction, at least one program segment, a code set or an instruction set, and the at least one instruction, at least one program segment, the code set or the instruction set is loaded and executed by a processor to implement the method shown in any possible implementation manner of the first aspect.

[0046] In a fourth aspect, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the method shown in any possible implementation manner of the first aspect are implemented.

[0047] In summary, the present application includes at least one of the following beneficial technical effects:

[0048] 1. Obtain an image of the item to be washed, identify the load amount of the item to be washed and the stain degree of the item to be washed in the image. These two pieces of information can indicate the amount of the washing task. By inputting the load amount, the stain degree, the water temperature set by the rental dishwasher, and the washing mode into the prediction model, the first washing liquid ration of the washing liquid can be obtained quickly and accurately, so as to achieve the accurate dispensing of the washing liquid;

[0049] 2. After completing the washing task, obtain user feedback information, and based on the processing of the positive and negative information of the feedback information, the system can more comprehensively understand the user's needs and the washing effect, collect training samples, and retrain the prediction model, so as to continuously optimize the prediction performance of the model and improve the accuracy and efficiency of the washing liquid rationing;

[0050] 3. When generating the control instruction of the washing liquid pump, consider the influence of the water quality information on the washing effect, and thus correct the washing liquid ration according to the water quality information, which can ensure the effective use of the washing liquid under different water quality conditions, and further improve the washing effect and user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of an application scenario of a method for dispensing washing liquid of a rental dishwasher based on a neural network provided by an embodiment of the present application;

[0052] Figure 2It is a schematic flowchart of a method for dispensing washing liquid of a rental dishwasher based on a neural network provided by an embodiment of the present application;

[0053] Figure 3 It is a schematic flowchart of a method for determining a new amount of the second washing liquid provided by an embodiment of the present application;

[0054] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0055] The following will further describe the present application in detail with reference to the attached Figure 1 to the attached Figure 4 drawings.

[0056] This specific embodiment is only an interpretation of the present application, and it is not a limitation of the present application. Those skilled in the art can make modifications without creative contributions to this embodiment after reading this specification, but as long as it is within the scope of the present application, it is protected by the patent law.

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present application.

[0058] It should be noted that in the optional embodiments of the present application, for relevant data such as object information, when the embodiments in the present application are applied to specific products or technologies, object permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards of relevant countries and regions. That is to say, if the embodiments in the present application involve data related to an object, it needs to be obtained under the authorization and consent of the object, the authorization and consent of relevant departments, and compliance with relevant laws, regulations, and standards of relevant countries and regions. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained, and the embodiments also need to be implemented under the authorization and consent of the object.

[0059] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0060] Rental dishwashers are a flexible and cost-effective option in the catering industry, allowing restaurants or other food service establishments to obtain high-quality dishwashing equipment without making large one-time investments. The process of washing dishes in a dishwasher typically includes: before putting the dishes into the dishwasher, first removing large food residues and stains on the tableware; putting the dishes into the dishwasher, closing and locking the dishwasher door; then filling with water, heating, spraying the washing liquid, draining and flushing, rinsing, and drying.

[0061] In the related art, a preset fixed ration is used for adding the washing liquid. However, this method has significant limitations because it cannot be flexibly adjusted according to the actual washing needs, resulting in waste of the washing liquid when washing tableware with lighter stains; while when washing tableware with heavier stains, the washing effect may be poor due to insufficient washing liquid.

[0062] This application provides a method for rationing the washing liquid of a rental dishwasher based on a neural network, which can accurately determine the ration of the washing liquid.

[0063] Reference Figure 1 , Figure 1 is a schematic diagram of the application scenario of a method for rationing the washing liquid of a rental dishwasher based on a neural network provided in an embodiment of this application. A camera is set on the rental dishwasher to collect images of the rental dishwasher before the washing liquid cleaning stage and send the images to an electronic device through a network. The electronic device can be a rental dishwasher or a server. A program for rationing the washing liquid of a rental dishwasher based on a neural network is deployed on the rental dishwasher or the server, and the method for rationing the washing liquid of a rental dishwasher based on a neural network can be realized.

[0064] In some possible cases, the user can issue instructions to the rental dishwasher through the control interface or buttons set on the rental dishwasher, or issue instructions to the rental dishwasher through the client device.

[0065] Specifically, an embodiment of this application provides a method for rationing the washing liquid of a rental dishwasher based on a neural network. As Figure 2 shown, the method provided in the embodiment of this application can be executed by an electronic device. The electronic device can be a server or a rental dishwasher. Among them, the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The rental dishwasher and the server can be directly or indirectly connected through wired or wireless communication methods. This application does not limit this here. The method includes:

[0066] S101. Obtain an image of the items to be washed in the rental dishwasher before the washing liquid cleaning stage and the current attribute information; the image is an image of the items to be washed inside the rental dishwasher, and the attribute information includes: water temperature and washing mode;

[0067] This step is usually executed before the washing liquid cleaning stage, that is, before the dishwasher starts to clean with detergent. In the embodiments of the present application, the image represents an image of the items to be washed inside the dishwasher obtained by a camera, that is, the appearance images of items such as tableware and kitchen utensils. The current attribute information refers to the current working state and related parameters of the dishwasher, including water temperature and washing mode. The water temperature is the temperature of the water inside the dishwasher, which directly affects the washing effect; the washing mode is the washing program selected by the user, such as strong washing, energy-saving washing, quick washing, etc. Different washing modes correspond to different washing times and washing intensities.

[0068] Specifically, after the user puts the items to be washed into the dishwasher and selects the washing mode, but before the formal washing process starts, the dishwasher will trigger the startup of the image acquisition device, such as the built-in camera. After receiving the startup signal, the camera automatically adjusts the focal length and light to ensure that the captured image is clear, then takes an image of the inside of the dishwasher, especially information such as the position, quantity, and type of the items to be washed, and transmits the image to the electronic device. At the same time, the electronic device will read the attribute information such as the current water temperature and the washing mode selected by the user.

[0069] S102. Identify the load information of the image, and the load information includes: the load quantity of the items to be washed and the degree of stain of the items to be washed;

[0070] The load information is used to evaluate the workload that the dishwasher needs to handle during the washing process. The load quantity of the items to be washed refers to the quantity or total volume of the items to be washed inside the dishwasher, which is used to judge the working load of the dishwasher. The degree of stain of the items to be washed refers to the degree of stain on the surface of the items to be washed, such as oil stains and water stains, which is used to evaluate the difficulty of washing and the required washing intensity.

[0071] In some embodiments, the load information of the image can be identified in various ways:

[0072] In one implementation, image processing algorithms are used to preprocess the original image, such as denoising and enhancing contrast. Object detection algorithms (such as YOLO, SSD, etc.) are used to identify the items to be washed in the preprocessed image and obtain their position and bounding box information; the load quantity of the items to be washed is estimated based on the number and size of the bounding boxes. For the evaluation of the degree of stain, the system can use image segmentation algorithms to separate the items from the background and extract features such as the color and texture of the item surface; a pre-trained classifier or prediction model is used to analyze the features to evaluate the degree of stain.

[0073] In another implementation method, a neural network model is constructed, including: a feature extraction layer, and two parallel prediction layers (convolutional layer + fully connected layer + activation function) connected to the feature extraction layer, where the first prediction layer is used to output the load amount, and the second prediction layer is used to output the stain degree; obtaining a plurality of training samples, each training sample including a washing item image and a corresponding label, where the label includes the load amount and the stain degree; inputting the washing item image into the neural network model to obtain an identification result, calculating a loss value by using the identification result and the label with a loss function, and iteratively training the neural network model based on the loss value until the number of iterations reaches a preset iteration number threshold or the loss value is less than a preset loss threshold to obtain a target model; and identifying an image of the rental dishwasher before the washing liquid cleaning stage according to the target model to obtain load information. This method simplifies the identification process and improves the efficiency and accuracy of identification.

[0074] S103. Input the load information and the attribute information into a prediction model to obtain a first washing liquid ration; the prediction model is obtained by training a preset model based on a plurality of first training samples, and the first training samples include first load information, first attribute information, and the actual washing liquid ration.

[0075] The prediction model is used to predict the first washing liquid ration based on the input load information and attribute information, and the first washing liquid ration is used to guide the dishwasher to add an appropriate amount of washing liquid during the washing process. The prediction model learns the relationship between the input and the output through training so that it can predict the corresponding output when given a new input. The first training samples are sample data for training the prediction model and include first load information and first attribute information.

[0076] The first training sample includes: load information, attribute information, and the actual amount of washing liquid dispensed. For the first training sample, the water used for washing the items is the water in a certain area, and the water quality is the same. The prediction model is trained through multiple first training samples to obtain a trained prediction model. The structure of the preset model is not limited in the embodiments of the present application, and the user can select according to actual needs. Preferably, the preset model can be a BP neural network, with an input layer, a hidden layer, and an output layer set. The input data is passed to the neurons in the input layer; after the neurons in the input layer perform weighted summation on the input data, the output value is calculated through an activation function and passed to the next layer (hidden layer); the neurons in the hidden layer perform weighted summation on the output value of the previous layer (input layer or the previous hidden layer), calculate the output value through the activation function, and continue to pass it downward; the neurons in the output layer perform weighted summation on the output value of the last hidden layer, calculate the final predicted output value through the activation function, calculate the loss value based on the predicted output value and the actual amount of washing liquid dispensed, backpropagate according to the loss value to update the model parameters, and perform model training again until the loss value is less than the preset loss threshold or the number of iterations reaches the preset number threshold to obtain the prediction model.

[0077] S104. Generate a control command for the washing liquid pump according to the first amount of washing liquid dispensed, and use the control command to control the operation of the washing liquid pump.

[0078] The washing liquid pump is a key component in the dishwasher. Its main function is to pump the washing liquid out of the storage container and transport it to the washing area of the dishwasher so that it can be mixed with water and the items to be washed during the washing process to achieve a cleaning effect. Generate a control command for the amount of washing liquid required for the current washing task, send the command to the drive circuit of the washing liquid pump through a cable or other communication means, and the washing liquid pump starts to work according to the command, pumps the washing liquid out of the storage container, and transports it to the washing area through a pipeline to be mixed with water and the items to be washed for cleaning.

[0079] It can be seen that in the embodiments of the present application, the image of the item to be washed is obtained, and the load amount and the stain degree of the item to be washed in the image are identified. These two pieces of information can indicate the amount of the washing task. By inputting the load amount, the stain degree, the water temperature set by the rental dishwasher, and the washing mode into the prediction model, the first amount of washing liquid dispensed can be quickly and accurately obtained, thereby realizing the accurate dispensing of the washing liquid.

[0080] Furthermore, different water qualities will affect the effect and efficiency of the washing liquid. Therefore, in order to accurately determine the dispensed amount, generating a control command for the washing liquid pump according to the first amount of washing liquid dispensed includes:

[0081] Obtain water quality information, and correct the first amount of washing liquid dispensed based on the water quality information to obtain the second amount of washing liquid dispensed;

[0082] Generate a control instruction for the washing liquid pump based on the second washing liquid ration.

[0083] Among them, the water quality information represents the hardness information of water.

[0084] The electronic device obtains the current water quality information. The water quality information can be input by the user. The input can be the regional information. Different regions correspond to different hardness information. Then, based on the regional information, the hardness information corresponding to the regional information is determined from the pre-stored corresponding relationship between hardness and region, or it is detected by a sensor set in the dishwasher. When generating the control instruction for the washing liquid pump, the influence of the water quality information on the washing effect is considered, so as to correct the washing liquid ration according to the water quality information, which can ensure the effective use of the washing liquid under different water quality conditions, and further improve the washing effect and user satisfaction.

[0085] Specifically, correcting the first washing liquid ration based on the water quality information to obtain the second washing liquid ration includes: determining the water quality difference between the water quality information and the standard water quality information; determining the adjustment value corresponding to the water quality difference according to the water quality difference and the first corresponding relationship, where the first corresponding relationship is the corresponding relationship between multiple water quality differences and multiple adjustment values; correcting the first washing liquid ration according to the adjustment value corresponding to the water quality difference to obtain the second washing liquid ration.

[0086] Among them, the standard water quality information is the hardness information of water used when the prediction model is trained. Calculate the water quality difference between the water quality information and the standard water quality information, and then look up the first corresponding relationship to determine the adjustment value corresponding to the water quality difference. The first corresponding relationship is set by technicians based on experience. If the water quality is poor, the ration is increased. If the water quality is excellent, the ration remains unchanged, so as to dynamically adjust the ration in combination with the water quality information so that the finally determined ration can achieve the optimal washing effect with less ration and save resources.

[0087] In the embodiment of the present application, when correcting the washing liquid ration based on the water quality information, determine the water quality difference between the water quality information and the standard water quality information, and then quickly determine the corresponding adjustment value according to the preset corresponding relationship to realize the correction of the ration to obtain the second washing liquid ration.

[0088] In an implementable embodiment, generating a control instruction for the washing liquid pump based on the second washing liquid ration includes: S10 - S15 (not shown in the drawings), where:

[0089] S10. Read the remaining amount of the washing liquid;

[0090] S11. Determine whether the second washing liquid ration is less than the remaining amount of the washing liquid;

[0091] S12. If the second washing liquid dispensing amount is not less than the remaining amount of the washing liquid, generate a control command for the washing liquid pump according to the second washing liquid dispensing amount;

[0092] S13. If the second washing liquid dispensing amount is less than the remaining amount of the washing liquid, adjust the attribute information, and based on the load information and the adjusted attribute information, use the prediction model again to obtain a new second washing liquid dispensing amount until the preset condition is met, where the preset condition is: the new second washing liquid dispensing amount is not less than the remaining amount of the washing liquid, or the attribute information reaches the attribute information threshold;

[0093] The attribute information includes: water temperature and washing mode. When adjusting the attribute information, it can be to adjust the water temperature alone, or adjust the washing mode alone, or adjust both the water temperature and the washing mode;

[0094] Therefore, in an implementable manner, when only one attribute information is adjusted, increase the water temperature / raise the washing mode according to the preset step size to obtain the adjusted attribute information; then, based on the load information and the adjusted attribute information, use the prediction model again to obtain a new second washing liquid dispensing amount, and then repeat S11 - S13. When the preset condition is reached, if the new second washing liquid dispensing amount is not less than the remaining amount of the washing liquid, execute S14, and if the water temperature reaches the preset water temperature threshold / the washing mode reaches the maximum level, execute S15.

[0095] In another implementable manner, when two attribute information can be adjusted, first adjust the water temperature according to the water temperature adjustment step size. When the water temperature reaches the preset water temperature threshold, then adjust the washing mode; correspondingly, the attribute information threshold is the threshold corresponding to the washing mode. The specific process refers to Figure 3 . When adjusting the attribute information, first adjust the water temperature according to the water temperature adjustment step size, and then adjust the washing mode when the water temperature reaches the preset threshold. This adjustment rule can give priority to ensuring the influence of the water temperature on the washing effect, and at the same time avoid the interference of frequently changing the washing mode on the washing process, realizing a more stable and efficient washing process.

[0096] S14. When the preset condition is that the new second washing liquid dispensing amount is not less than the remaining amount of the washing liquid, generate a control command for the washing liquid pump according to the new second washing liquid dispensing amount;

[0097] S15. When the preset condition is that the attribute information reaches the attribute information threshold, generate a prompt message to prompt the user that washing liquid replenishment is required.

[0098] It can be seen that in the embodiment of the present application, before generating the control instruction for the washing liquid pump, the remaining amount of the washing liquid is checked to determine whether the remaining amount of the washing liquid meets the requirement. If it does not meet the requirement, the attribute information is adjusted according to the remaining amount, and the second washing liquid ration obtained after adjustment is iteratively determined until a preset condition is reached. If the remaining amount of the washing liquid meets the new second washing liquid ration, the washing liquid pump is controlled according to the new second washing liquid ration based on the new attribute information; otherwise, the user is prompted to replenish the washing liquid in time to ensure that the washing task can proceed normally.

[0099] In an implementable embodiment, after controlling the washing liquid pump to work by using the control instruction, it further includes:

[0100] After completing the washing task, obtain user feedback information;

[0101] If the feedback information is positive information, a second training sample is generated based on the load information, the final attribute information, and the second washing liquid ration; if the feedback information is negative information, the second washing liquid ration is corrected based on the feedback information to obtain a third washing liquid ration, and a second training sample is generated based on the load information, the final attribute information, and the third washing liquid ration;

[0102] When the number of the second training samples reaches a preset number threshold, the prediction model is retrained based on all the obtained second training samples.

[0103] After completing the current washing task, the user can provide feedback information through the washing machine interface or the application program to evaluate the washing effect, including positive information (excellent washing result) and negative information (poor washing result and the amount of washing liquid to be added). If it is positive information, a second training sample for iterative training is generated; if it is negative information, the second washing liquid ration is corrected based on the amount of washing liquid to be added in the negative result, and a second training sample is generated.

[0104] When the number reaches the preset number threshold, the model is retrained to optimize the performance of the model, making the prediction effect of the model more and more excellent.

[0105] It can be seen that in the embodiment of the present application, after obtaining the user feedback information after completing the washing task and according to the processing of the positive and negative information of the feedback information, the system can more comprehensively understand the user's needs and the washing effect, collect training samples, retrain the prediction model, continuously optimize the prediction performance of the model, and improve the accuracy and efficiency of the washing liquid rationing.

[0106] In an implementable embodiment, generating the control instruction for the washing liquid pump according to the first washing liquid ration includes:

[0107] Determine the first working time and the first working speed of the washing liquid pump corresponding to the washing mode;

[0108] Judge whether the stain degree of the item to be washed is greater than the preset stain degree threshold;

[0109] If not, generate a control command for the washing liquid pump according to the first washing liquid ration, the first working time of the washing liquid pump, and the first working speed;

[0110] If so, determine the working adjustment time and the working adjustment speed corresponding to the item to be washed according to the stain degree of the item to be washed and the second corresponding relationship. The second corresponding relationship is the corresponding relationship among the stain degree, the working adjustment time, and the working adjustment speed; and adjust the first working time and the first working speed respectively according to the working adjustment time and the working adjustment speed to obtain the second working time and the second working speed, and generate a control command for the washing liquid pump according to the first washing liquid ration, the second working time of the washing liquid pump, and the second working speed.

[0111] Each washing mode corresponds to the working duration and speed of the washing liquid pump.

[0112] When the stain degree of the item to be washed is large, although the corresponding washing liquid can be matched, the washing effect may still be poor. Therefore, a stain degree threshold is set. When the stain degree of the item to be washed is greater than the preset stain degree threshold, the working time and the working speed are adjusted to improve the washing effect. The second corresponding relationship can be set according to experience.

[0113] In the embodiment of the present application, when generating the control command for the washing liquid pump, the working time and the working speed of the washing liquid pump can be dynamically adjusted according to the stain degree of the item to be washed. This dynamic adjustment mechanism can ensure the reasonable use of the washing liquid under different stain degrees, more precisely control the washing process, and improve the washing effect and efficiency.

[0114] In the above embodiment, a method for dispensing washing liquid of a rental dishwasher based on a neural network is introduced from the perspective of the method flow. The following embodiment introduces a device for dispensing washing liquid of a rental dishwasher based on a neural network from the perspective of modules or units. For details, see the following embodiment.

[0115] The embodiment of the present application provides a device for dispensing washing liquid of a rental dishwasher based on a neural network, including:

[0116] A data acquisition module, configured to acquire an image of the rental dishwasher before the washing liquid cleaning stage and the current attribute information; the image is an image of the item to be washed in the rental dishwasher, and the attribute information includes: water temperature and washing mode; identify the load information of the image, and the load information includes: the load amount of the item to be washed and the stain degree of the item to be washed;

[0117] A neural network processing module is used to input the load information and the attribute information into a prediction model to obtain a first detergent dispensing amount; the prediction model is obtained by training the neural network model based on a plurality of first training samples, the first training samples including the first load information and the first attribute information;

[0118] The dispensing execution module is used to generate a control instruction of the washing liquid pump according to the first washing liquid dispensing amount, and use the control instruction to control the operation of the washing liquid pump.

[0119] In an embodiment of the present application, the data acquisition module can obtain an image of the items to be washed, identify the load amount of the items to be washed and the degree of stains of the items to be washed in the image, these two pieces of information can indicate the amount of washing tasks, and can also obtain attribute information; the neural network processing module can use the prediction model to predict based on the load amount, the degree of stains, the water temperature set for the rental dishwasher, and the washing mode, and obtain the first washing liquid dosage amount, and quickly and accurately obtain the first washing liquid dosage amount of the washing liquid; then the dosage execution module is linked to control the operation of the washing liquid pump, thereby achieving accurate delivery of the washing liquid.

[0120] In an achievable embodiment, the dispensing execution module generates a control instruction for the washing liquid pump according to the first washing liquid dispensing amount, which is used to:

[0121] Acquiring water quality information, and correcting the first washing liquid supply amount based on the water quality information to obtain a second washing liquid supply amount;

[0122] Based on the second washer liquid dosing amount, a control command for the washer liquid pump is generated.

[0123] In an achievable embodiment, the dispensing execution module corrects the first washing liquid dispensing amount based on the water quality information to obtain the second washing liquid dispensing amount, which is used to:

[0124] Determine the water quality difference between water quality information and standard water quality information;

[0125] Determine an adjustment value corresponding to the water quality difference according to the water quality difference and a first corresponding relationship, wherein the first corresponding relationship is a corresponding relationship between a plurality of water quality differences and a plurality of adjustment values;

[0126] According to the adjustment value corresponding to the water quality difference, the first washing liquid supply amount is corrected to obtain the second washing liquid supply amount.

[0127] In an achievable embodiment, the dispensing execution module generates a control instruction for the washing liquid pump based on the second washing liquid dispensing amount, which is used to:

[0128] Read the remaining amount of detergent;

[0129] If the second washing liquid dispensing amount is not less than the remaining amount of the washing liquid, a control instruction for the washing liquid pump is generated according to the second washing liquid dispensing amount;

[0130] If the second washing liquid dispensing amount is less than the remaining amount of the washing liquid, the attribute information is adjusted, and the prediction model is used again based on the load information and the adjusted attribute information to obtain a new second washing liquid dispensing amount until a preset condition is met. The preset condition is that the new second washing liquid dispensing amount is not less than the remaining amount of the washing liquid, or the attribute information reaches the attribute information threshold.

[0131] When the preset condition is that the new second washing liquid dispensing amount is not less than the remaining amount of the washing liquid, a control instruction for the washing liquid pump is generated according to the new second washing liquid dispensing amount;

[0132] When the preset condition is that the attribute information reaches the attribute information threshold, a prompt message is generated to prompt the user that the washing liquid needs to be replenished.

[0133] In a feasible embodiment, the rule for adjusting the attribute information is as follows: First, the water temperature is adjusted according to the water temperature adjustment step. When the water temperature reaches the preset water temperature threshold, the washing mode is adjusted. Correspondingly, the attribute information threshold is the threshold corresponding to the washing mode.

[0134] In a feasible embodiment, the device further includes:

[0135] A feedback information acquisition module, configured to acquire user feedback information after the washing task is completed;

[0136] A sample collection module, configured to generate a second training sample based on the load information, the final attribute information, and the second washing liquid dispensing amount if the feedback information is positive; if the feedback information is negative, the second washing liquid dispensing amount is corrected based on the feedback information to obtain a third washing liquid dispensing amount, and a second training sample is generated based on the load information, the final attribute information, and the third washing liquid dispensing amount;

[0137] A model optimization module, configured to retrain the prediction model based on all the obtained second training samples when the number of the second training samples reaches a preset number threshold.

[0138] In a feasible embodiment, the dispensing execution module is further configured to:

[0139] Determine the first working time and the first working speed of the washing liquid pump corresponding to the washing mode;

[0140] Judge whether the stain degree of the item to be washed is greater than a preset stain degree threshold;

[0141] If not, a control instruction for the washing liquid pump is generated according to the first washing liquid dispensing amount, the first working time of the washing liquid pump, and the first working speed;

[0142] If so, determine the working adjustment time and the working adjustment speed corresponding to the item to be washed according to the stain degree of the item to be washed and the second corresponding relationship, where the second corresponding relationship is the corresponding relationship among the stain degree, the working adjustment time, and the working adjustment speed; and adjust the first working time and the first working speed respectively according to the working adjustment time and the working adjustment speed to obtain a second working time and a second working speed, and generate a control command for the washing liquid pump according to the first washing liquid supply amount, the second working time, and the second working speed of the washing liquid pump.

[0143] The washing liquid supply device of a rental dishwasher based on a neural network provided by an embodiment of the present application is applicable to the embodiment of the washing liquid supply method of a rental dishwasher based on a neural network, which will not be elaborated here.

[0144] An embodiment of the present application provides an electronic device, such as Figure 4 shown. Figure 4 The electronic device 300 shown in the figure includes: a processor 301 and a memory 303. Among them, the processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation to the embodiment of the present application.

[0145] The processor 301 may be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in combination with the disclosure of the present application. The processor 301 may also be a combination for implementing a computing function, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0146] The bus 302 may include a path for transmitting information between the above components. The bus 302 can be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 302 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 only a thick line is used to represent it in Figure 4 , but it does not mean that there is only one bus or one type of bus.

[0147] The memory 303 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or it can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0148] The memory 303 is used to store the application program code for executing the solution of this application, and is controlled by the processor 301 to execute. The processor 301 is used to execute the application program code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0149] The embodiments of this application provide a computer-readable storage medium, on which a computer program is stored. When it runs on a computer, it enables the computer to execute the corresponding content in the foregoing method embodiments.

[0150] The embodiments of this application provide a computer program product, including a computer program, which implements the corresponding content in the foregoing method embodiments when executed by a processor.

[0151] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the indication of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this document, there is no strict order restriction for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0152] The above are only some implementation manners of the present application. It should be pointed out that for those of ordinary skill in the art in this technical field, without departing from the principle of the present application, several improvements and refinements can also be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A method for dispensing washing liquid of a rental dishwashing machine based on a neural network, characterized in that, Including: Obtaining an image of the rental dishwasher before the washing liquid cleaning stage and the current attribute information; The image is an image of the items to be washed inside the rental dishwasher, and the attribute information includes: water temperature and washing mode; Identifying the load information of the image, where the load information includes: the load amount of the items to be washed and the stain degree of the items to be washed; Inputting the load information and the attribute information into a prediction model to obtain a first washing liquid ration; the prediction model is obtained by training a neural network model based on multiple first training samples, and the first training samples include first load information, first attribute information, and the actual washing liquid ration; Generating a control instruction for the washing liquid pump according to the first washing liquid ration, and using the control instruction to control the operation of the washing liquid pump; Among them, the generating a control instruction for the washing liquid pump according to the first washing liquid ration includes: Obtaining water quality information and correcting the first washing liquid ration based on the water quality information to obtain a second washing liquid ration; Generating a control instruction for the washing liquid pump based on the second washing liquid ration; Among them, the generating a control instruction for the washing liquid pump based on the second washing liquid ration includes: Reading the remaining amount of the washing liquid; If the second washing liquid ration is less than the remaining amount of the washing liquid, generating a control instruction for the washing liquid pump according to the second washing liquid ration; If the second washing liquid ration is not less than the remaining amount of the washing liquid, adjusting the attribute information, and based on the load information and the adjusted attribute information, using the prediction model again to obtain a new second washing liquid ration until a preset condition is met, where the preset condition is: the new second washing liquid ration is less than the remaining amount of the washing liquid, or, the attribute information reaches the attribute information threshold; When the preset condition is that the new second washing liquid ration is less than the remaining amount of the washing liquid, generating a control instruction for the washing liquid pump according to the new second washing liquid ration; When the preset condition is that the attribute information reaches the attribute information threshold, generating a prompt message to prompt the user that washing liquid replenishment is required.

2. The method according to claim 1, wherein The correcting the first washing liquid ration based on the water quality information to obtain a second washing liquid ration includes: Determining the water quality difference between the water quality information and the standard water quality information; Determining an adjustment value corresponding to the water quality difference according to the water quality difference and a first correspondence relationship, where the first correspondence relationship is the correspondence relationship between multiple water quality differences and multiple adjustment values; Correcting the first washing liquid ration according to the adjustment value corresponding to the water quality difference to obtain a second washing liquid ration.

3. The method according to claim 1, wherein The rule for adjusting the attribute information is: first adjust the water temperature according to the water temperature adjustment step, and when the water temperature reaches the preset water temperature threshold, then adjust the washing mode. Correspondingly, the attribute information threshold is the threshold corresponding to the washing mode.

4. The method according to any one of claims 1 to 3, characterized in that After using the control instruction to control the operation of the washing liquid pump, it further includes: Obtaining user feedback information after completing the washing task; If the feedback information is positive information, a second training sample is generated based on the load information, the final attribute information, and the second washing liquid ration; if the feedback information is negative information, the second washing liquid ration is corrected based on the feedback information to obtain a third washing liquid ration, and a second training sample is generated based on the load information, the final attribute information, and the third washing liquid ration; When the number of the second training samples reaches a preset number threshold, the prediction model is retrained based on all the obtained second training samples.

5. The method according to any one of claims 1 to 3, characterized in that The generating a control instruction for the washing liquid pump according to the first washing liquid ration includes: Determining a first working time and a first working speed of the washing liquid pump corresponding to the washing mode; Judging whether the stain degree of the article to be washed is greater than a preset stain degree threshold; If not, a control instruction for the washing liquid pump is generated according to the first washing liquid ration, the first working time, and the first working speed of the washing liquid pump; If so, a working adjustment time and a working adjustment speed corresponding to the article to be washed are determined according to the stain degree of the article to be washed and a second corresponding relationship, where the second corresponding relationship is the corresponding relationship among the stain degree, the working adjustment time, and the working adjustment speed; the first working time and the first working speed are adjusted respectively according to the working adjustment time and the working adjustment speed to obtain a second working time and a second working speed, and a control instruction for the washing liquid pump is generated according to the first washing liquid ration, the second working time, and the second working speed of the washing liquid pump.

6. An electronic device, characterized in that, It includes: One or more processors; A memory; One or more applications, where the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to: execute the steps of the method according to any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one segment of program, a code set, or an instruction set, and the at least one instruction, the at least one segment of program, the code set, or the instruction set is loaded and executed by a processor to implement the steps of the method according to any one of claims 1 to 5.

8. A computer program product, characterized in that, It includes a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images