Intelligent interactive control method, system and medium for aging-friendly kitchen equipment

Abstract

The present invention discloses a method, system, and medium for intelligent interactive control of aging-friendly kitchen equipment, including: obtaining the behavioral characteristics of elderly users in terms of hearing, vision, touch, and cognition to generate multimodal behavioral characteristics; using historical operation data of different kitchen equipment to extract operation time characteristics and operation program characteristics, setting kitchen equipment interaction priorities in different time periods, and determining the elderly user's control preference data; constructing a user profile based on the multimodal behavioral characteristics, kitchen equipment interaction priorities in different time periods, and control preference data, determining the optimal interaction mode based on the user profile, and generating interactive control guidance workflows for different kitchen equipment that meet the control preferences based on the optimal interaction mode, thereby providing interactive prompts for the elderly user. The present invention ensures that elderly users are proficient in operating intelligent kitchen equipment by setting reasonable interactive prompts based on user control preferences, thereby improving the elderly group's efficiency in operating intelligent kitchen equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent kitchen equipment, and more specifically, to an intelligent interactive control method, system and medium for aging-friendly kitchen equipment. Background Art

[0002] In the era of intelligent technology and the rapid development of new technologies, the "digital divide" created by elderly users' use of smart products is gaining increasing attention from all sectors of society. As one of the most frequently used spaces for seniors in their home care, the kitchen's importance is self-evident. Today's products are increasingly incorporating intelligent controls, and smart kitchen appliances are bringing significant convenience. However, with these smart kitchen appliances comes the application of intelligent interactive control systems. Today's elderly have certain obstacles with interactive interfaces and the internet. As interfaces replace buttons, these "conveniences" have become a nuisance for them, resulting in the phenomenon of "excluding aging" from smart home appliances.

[0003] Currently, most popular smart kitchen devices on the market are designed for younger users, neglecting the specific needs of vulnerable groups. Consequently, many issues remain with the aging-friendly design of kitchen equipment, such as inconvenient design, mismatched interactions, and clunky operation, making it difficult for seniors to live independently. Smart kitchen devices often fail to adapt to the specific needs of the elderly, increasing the time it takes to operate and the difficulty of intelligent control. Furthermore, the control process cannot accurately determine whether the control efficiency meets the needs of the elderly, leading to irrational control and reduced efficiency in the elderly's actions. Therefore, in the interactive control of smart kitchen devices, analyzing the needs of elderly users and reducing the burden of memorizing control steps are urgent issues that need to be addressed. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention proposes an intelligent interactive control method, system and medium for aging-friendly kitchen equipment. The purpose is to match the interactive control of intelligent kitchen equipment according to the needs of users, and ensure that elderly users are proficient in operating intelligent kitchen equipment through reasonable interactive prompts, thereby solving the problem of difficulty in operating intelligent kitchen equipment for the elderly.

[0005] A first aspect of the present invention provides an intelligent interactive control method for aging-friendly kitchen equipment, comprising:

[0006] Evaluate the behavioral characteristics of elderly users in terms of vision, hearing, touch and cognition, and integrate the behavioral characteristics of different aspects to generate multimodal behavioral characteristics of elderly users;

[0007] Utilizing historical operating data of different kitchen appliances to extract operating time characteristics and operating program characteristics, the interaction priorities of kitchen appliances in different time periods are determined based on the operating time characteristics, and the control preference data of elderly users is determined based on the operating program characteristics of different kitchen appliances;

[0008] Building a user profile based on the multimodal behavior characteristics, kitchen equipment interaction priorities at different time periods, and control preference data, and determining the optimal interaction mode based on the user profile;

[0009] Based on the optimal interaction mode, the interactive control guidance workflow of different kitchen equipment that meets the control preferences of elderly users is obtained, the key control steps in the interactive control guidance workflow are extracted, and the interactive prompt information of the key control steps is generated based on the interactive control guidance workflow, and multi-channel interactive prompts are provided to elderly users.

[0010] In this solution, we evaluate the behavioral characteristics of elderly users in terms of hearing, vision, touch, and cognition, and fuse these behavioral characteristics to generate multimodal behavioral characteristics of elderly users. Specifically,

[0011] Obtaining program operation data for different types of kitchen equipment, using the program operation data to extract icon keyword data, guidance prompt sound data, touch vibration data, and icon position data, and establishing behavioral characteristic assessment projects in auditory, visual, tactile, and cognitive aspects based on the extracted multi-dimensional data;

[0012] Sending the behavior characteristic assessment items to a preset terminal device, and using the preset terminal device to obtain the elderly user's visual behavior characteristics, auditory behavior characteristics, tactile behavior characteristics, and cognitive behavior characteristics;

[0013] The benchmark values of each modal behavior feature are set based on the mean of the evaluation results of different modal behavior features of young users, and a metric function is constructed using Euclidean distance. The Euclidean distance between the visual behavior features, auditory behavior features, tactile behavior features, and cognitive behavior features of elderly users and the corresponding benchmark values is obtained through the metric function.

[0014] Normalization is performed on the Euclidean distance to generate feature scores of different modal behavior features of elderly users, the feature scores are matched with corresponding modal behavior features, and all modal behavior features of elderly users are integrated to generate multimodal behavior features.

[0015] In this solution, the interaction priorities of kitchen appliances in different time periods are determined based on the operating time characteristics, and the control preference data of elderly users are determined based on the operating program characteristics of different kitchen appliances, specifically:

[0016] Extract historical operating data of different kitchen appliances within a preset time step in the elderly user's kitchen scenario. The historical operating data is divided into natural day periods. The operating time data of different kitchen appliances within a natural day is extracted to determine the operating time characteristics of different kitchen appliances.

[0017] Soft clustering is performed using the operating time characteristics of different kitchen appliances. Based on the clustering results, clustered datasets are obtained for each time period. The data volume of different categories of kitchen appliances in the clustered datasets is extracted. Based on this data volume, the interaction priority of kitchen appliances relative to elderly users in different time periods is determined.

[0018] Obtaining operating program features of different kitchen appliances based on the historical operating data, obtaining operating program feature sequences of different kitchen appliances through time series integration, and repeatedly dividing the operating program feature sequences of different kitchen appliances using different time division standards;

[0019] For any kitchen appliance, the subsequences of running program features of different lengths are divided and embedded into low-dimensional vectors. A multi-head attention mechanism is introduced to weight each low-dimensional vector. The weighted low-dimensional vectors are then concatenated to form a feature vector that contains all the low-dimensional vector features.

[0020] The feature vector is imported into a multi-layer perceptron, and a double-layer multi-layer perceptron structure is used to determine the control preference data of elderly users on kitchen equipment.

[0021] In this solution, a user profile is constructed based on the multimodal behavior characteristics, interaction priorities of kitchen appliances at different time periods, and control preference data. Specifically,

[0022] User similarity is calculated based on the elderly user's multimodal behavioral characteristics, kitchen equipment interaction priorities at different time periods, and control preference data. Users who meet the preset similarity criteria are selected as similar users of the elderly user, and social graph data is constructed based on the elderly user and similar users.

[0023] Constructing interaction graph data based on kitchen equipment in elderly users' kitchen scenarios, constructing an elderly user graph using the interaction graph data in the social graph dataset, treating elderly users and kitchen equipment as nodes in the elderly user graph, setting directed edges based on whether there are associations between the nodes, adding elderly users' multimodal behavioral characteristics as additional attributes of the elderly user nodes, and adding kitchen equipment interaction priorities and control preference data at different time periods as additional attributes of the kitchen equipment nodes;

[0024] A graph neural network is used to learn the graph data of the elderly user graph. Neighborhood random sampling is used to select the neighboring nodes of the elderly user node. A multi-head attention mechanism is introduced to weight each neighboring node. The weighted neighboring nodes are used for aggregate updates.

[0025] Obtain the elderly user node after aggregation and update, obtain the updated embedding representation of the elderly user node, and after multiple aggregations, splice the updated embedding representation of the elderly user node with the original embedding representation to output the user portrait of the elderly user.

[0026] In this solution, the optimal interaction mode is determined by the user portrait, specifically:

[0027] Obtaining examples of age-friendly interactive design for kitchen equipment, performing graphic processing on the examples of age-friendly interactive design for kitchen equipment to generate graph structure data, encoding the graph structure data, and obtaining user portraits in each example;

[0028] Obtain different user portrait groups through clustering, and obtain a user evaluation matrix of the interaction modality within the user portrait groups, where the elements in the evaluation matrix represent the user's evaluation of the interaction modality;

[0029] Use the user profiles of elderly users to determine the corresponding user profile groups, perform similarity calculations within the user profile groups to select a preset number of similar users, and select the interaction mode with the highest evaluation based on the evaluation matrix of similar users;

[0030] According to the selected interaction mode, the interaction prompts of different kitchen equipment are simulated, the feedback of elderly users on the interaction prompts of different interaction modes is obtained through the terminal device, and the optimal interaction mode is selected based on the feedback.

[0031] In this solution, based on the optimal interaction mode, we obtain the interactive control guidance workflow for different kitchen appliances that meets the control preferences of elderly users, extract the key control steps in the interactive control guidance workflow, and generate interactive prompt information for the key control steps based on the interactive control guidance workflow. Specifically,

[0032] Determining corresponding function program information based on the elderly user's control preference data, reading the operation procedures of the function program information of different kitchen equipment, and constructing an interactive control guidance workflow based on the operation procedures through the optimal interaction mode;

[0033] When an elderly user enters the kitchen scene, an operation interaction prompt is generated based on the kitchen equipment interaction priority at different time periods. The system determines whether the kitchen equipment operated by the elderly user meets the kitchen equipment interaction priority. The frequency of non-satisfaction is counted. When the non-satisfaction frequency exceeds a preset threshold, the kitchen equipment interaction priority for the current time period is reset.

[0034] Obtain the kitchen equipment operated by the elderly user, determine the corresponding interactive control guidance workflow based on the elderly user's operation information, and obtain the elderly user's average response time for each operation control step in the interactive control guidance workflow. If the average response time is greater than a preset time threshold, it is marked as a critical control step;

[0035] Generate interactive prompt information of different interactive modes based on the key control steps, provide multi-channel prompts to elderly users, statistically analyze the average reaction time of elderly users to key control steps, and cancel the interactive prompt information of different interactive modes when the average reaction time is less than 0.

[0036] When the elderly user's reaction time to the operation control step is less than the average reaction time, the corresponding guidance in the interactive control guidance workflow is removed, and the interactive control guidance workflow is updated according to the subsequent feedback from the elderly user.

[0037] A second aspect of the present invention provides an intelligent interactive control system for aging-friendly kitchen equipment, comprising a user multimodal behavior feature evaluation unit, an equipment operation data analysis unit, a user portrait construction unit, an interactive control guide determination unit, and a control feedback unit;

[0038] The user multimodal behavior characteristic evaluation unit evaluates the behavioral characteristics of the elderly user in terms of hearing, vision, touch and cognition, and integrates the behavioral characteristics of different aspects to generate the multimodal behavior characteristics of the elderly user;

[0039] The device operation data analysis unit uses the historical operation data of different kitchen appliances to extract operation time characteristics and operation program characteristics, determines the interaction priority of kitchen appliances in different time periods based on the operation time characteristics, and determines the control preference data of elderly users based on the operation program characteristics of different kitchen appliances;

[0040] The user portrait construction unit constructs a user portrait based on multimodal behavior characteristics, kitchen equipment interaction priorities at different time periods, and control preference data;

[0041] The interactive control guidance determination unit determines the optimal interaction mode and the interactive control guidance workflow that meets the control preferences of different kitchen appliances based on the user profile, extracts the key control steps of the interactive control guidance workflow, generates interactive prompt information for the key control steps based on the optimal interaction mode, and performs multi-channel interactive prompts;

[0042] The control feedback unit obtains the elderly user's selection feedback on the interactive control guidance workflow, as well as the reaction time to each operation control step of the kitchen equipment under the interactive control guidance workflow, and analyzes and updates the interactive prompt information and the interactive control guidance workflow.

[0043] A third aspect of the present invention provides a computer-readable storage medium, which includes a smart interactive control method program for aging-friendly kitchen equipment. When the smart interactive control method program for aging-friendly kitchen equipment is executed by a processor, the steps of the smart interactive control method for aging-friendly kitchen equipment are implemented.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention analyzes the multimodal behavioral characteristics of elderly users and selects the most suitable interactive prompt mode for elderly users, ensuring that the interactive prompt can provide multi-channel interactive prompts for elderly users to the greatest extent possible to meet their actual needs and reduce the memory burden of traditional device control steps.

[0046] The present invention ensures that elderly users are proficient in operating smart kitchen equipment by setting reasonable interactive prompts through user control preferences. Key control steps are extracted according to the elderly users' proficiency in operating the equipment, and key interactive prompts are set in the key control steps. This reduces the time elderly users spend on interactive interface selection and improves the operating efficiency of smart kitchen equipment for the elderly group. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or exemplary descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to these drawings without paying any creative work.

[0048] Figure 1 A flow chart showing an intelligent interactive control method for aging-friendly kitchen equipment is shown;

[0049] Figure 2 A flowchart illustrating an embodiment of obtaining kitchen device interaction priority and control preference data for elderly users in different time periods is shown;

[0050] Figure 3 A flowchart of an embodiment of the present invention is shown for determining the optimal interaction mode for elderly users through user portraits;

[0051] Figure 4 A block diagram of an intelligent interactive control system for aging-friendly kitchen equipment is shown. DETAILED DESCRIPTION

[0052] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0054] Figure 1 A flow chart of an intelligent interactive control method for aging-friendly kitchen equipment is shown.

[0055] like Figure 1 As shown, this embodiment provides an intelligent interactive control method for aging-friendly kitchen equipment, including:

[0056] S102, evaluating the behavioral characteristics of the elderly user in terms of vision, hearing, touch, and cognition, and integrating the behavioral characteristics of different aspects to generate a multimodal behavioral characteristic of the elderly user;

[0057] S104, extracting operation time characteristics and operation program characteristics from historical operation data of different kitchen appliances, determining kitchen appliance interaction priorities in different time periods based on the operation time characteristics, and determining control preference data of elderly users based on the operation program characteristics of different kitchen appliances;

[0058] S106, constructing a user profile based on the multimodal behavior characteristics, the interaction priorities of the kitchen appliances at different time periods, and the control preference data, and determining an optimal interaction mode based on the user profile;

[0059] S108, based on the optimal interaction mode, obtain the interactive control guidance workflow of different kitchen equipment that meets the control preferences of elderly users, extract the key control steps in the interactive control guidance workflow, generate interactive prompt information of the key control steps based on the interactive control guidance workflow, and provide multi-channel interactive prompts to elderly users.

[0060] It should be noted that the human multi-channel perception system primarily involves the perception of three sensory channels: vision, hearing, and touch, and feedback from the cognitive channel. The sensory channel is primarily used to perceive information, while the cognitive channel is primarily used to process perceived information and execute actions. In the multimodal behavioral characteristic evaluation process for elderly users, program operation data for different types of kitchen equipment is obtained, such as the corresponding operation behavior of the cooking function program of a smart rice cooker. This program operation data is used to extract icon keyword data, guidance prompt sound data, touch vibration data, and icon position data. Based on this extracted multidimensional data, behavioral characteristic evaluation items for the auditory, visual, tactile, and cognitive aspects are established. The behavioral characteristic evaluation project is sent to a preset terminal device, and the visual behavioral characteristics, auditory behavioral characteristics, tactile behavioral characteristics and cognitive behavioral characteristics of the elderly user are obtained by using the preset terminal device; preferably, the elderly user's vision and visual adjustment ability, brightness and discrimination ability, flicker value, contrast and color recognition ability are measured based on the kitchen equipment button and icon keyword data, shape data, color data, and size data to obtain the elderly user's visual behavioral characteristics, and by setting kitchen equipment buttons and chart keywords of different sizes, the elderly user's feedback on charts of different sizes is obtained, and the corresponding focus adjustment distance curve is generated to obtain the corresponding vision. and vision adjustment ability; when distinguishing small objects, a certain level of illumination is usually required, so the illumination required by elderly users for distinction is obtained to obtain their distinction ability and light brightness recognition ability; the flicker value is the frequency that can be felt by people when the stimulus light is quickly lit or extinguished. The changes in the stimulation perception of elderly users are most obvious, so the normal frequency will also appear as continuous light for elderly people with declining vision. The flicker value is used to judge the elderly users' ability to capture flickering light; due to the yellowing of the color of the lens of elderly users, their vision tends to be yellowish. Set buttons and icon keywords of different colors to obtain the elderly users' ability to recognize different colors.

[0061] The hearing and sound discrimination abilities of elderly users are tested through guidance tone data, and the auditory behavior characteristics of elderly users are obtained. The natural aging of the auditory system makes presbycusis particularly common. The thickening of the walls of the blood vessels in the inner ear and the narrowing of the lumen lead to functional impairment of sound waves from the inner ear to the brain, making it difficult for the elderly to hear external sounds. By setting guidance tone data of different decibels, the hearing stimulation threshold curve of elderly users is obtained, the hearing ability of elderly users is evaluated, and the feedback of elderly users on the stimulation is obtained to determine whether there is mishearing or misunderstanding. The judgment results of different levels of hearing stimulation show that elderly users often have a decreased hearing accuracy, which leads to an increased error rate and slower speed in sound information processing. The sound discrimination ability of elderly users is obtained by playing guidance information with different contents.

[0062] The vibration perception threshold and reaction threshold of elderly users are measured by touch vibration data to obtain the tactile behavior characteristics of elderly users, and the vibration sensory feedback of elderly users is obtained through different vibration intensities; the short-term memory capacity of elderly users is obtained through icon position data, and the memory of the position of kitchen equipment buttons or icons is evaluated based on the position data of kitchen equipment buttons or icons. The cognitive behavior characteristics of elderly users are obtained through the memory coherence of the positions of different buttons or icons. The changes in icon positions are used to judge the degree to which elderly users can capture the icon positions, and the cognitive behavior characteristics of elderly users are obtained.

[0063] The evaluation results of several young users on behavioral characteristics evaluation projects in auditory, visual, tactile and cognitive aspects are obtained, and the benchmark value of each modal behavioral feature is set according to the mean value of the evaluation results of different modal behavioral features of young users. The Euclidean distance is used to construct a measurement function, and the Euclidean distance between the visual behavioral features, auditory behavioral features, tactile behavioral features and cognitive behavioral features of elderly users and the corresponding benchmark values is obtained through the measurement function; the Euclidean distance is normalized according to the Euclidean distance to generate feature scores of different modal behavioral features of elderly users, and the higher the feature score, the more normal the corresponding behavioral feature is. The feature score is matched with the corresponding modal behavioral feature. The feature score can be used to distinguish the weak behavioral features of elderly users, which provides a basis for subsequently determining the best interaction mode for elderly users, and the splicing operation is used to integrate all modal behavioral features after the feature score is matched to generate multimodal behavioral features of elderly users.

[0064] Figure 2 A flowchart of an embodiment for obtaining kitchen equipment interaction priority and control preference data of elderly users in different time periods is shown.

[0065] According to an embodiment of the present invention, the interaction priorities of kitchen appliances in different time periods are determined based on the operating time characteristics, and the control preference data of elderly users are determined based on the operating program characteristics of different kitchen appliances, specifically:

[0066] S202: extracting historical operating data of different kitchen appliances in the elderly user's kitchen scene within a preset time step, dividing the historical operating data into natural day periods, extracting operating time data of different kitchen appliances within a natural day, and determining operating time characteristics of different kitchen appliances;

[0067] S204: Soft clustering is performed using the operating time characteristics of different kitchen appliances. Based on the clustering results, clustered data sets for each time period are obtained. The data volume of different categories of kitchen appliances in the clustered data sets is extracted. Based on the data volume, interaction priorities of the kitchen appliances with respect to the elderly users in different time periods are determined.

[0068] S206, obtaining operating program features of different kitchen appliances based on the historical operating data, obtaining operating program feature sequences of different kitchen appliances through time series integration, and repeatedly dividing the operating program feature sequences of different kitchen appliances using different time length division standards;

[0069] S208: For any kitchen appliance, embed the subsequences of running program features of different lengths obtained by segmentation into low-dimensional vectors, introduce a multi-head attention mechanism to weight each low-dimensional vector, and concatenate the weighted low-dimensional vectors to form a feature vector containing all low-dimensional vector features;

[0070] S210: Import the feature vector into a multi-layer perceptron, and use a double-layer multi-layer perceptron structure to determine the elderly user's control preference data for kitchen equipment.

[0071] It should be noted that the historical operating data of different kitchen appliances is aggregated and analyzed to analyze the operating conditions of kitchen appliances in different time periods. The amount of data in different clusters is used to distinguish the usage and operation of kitchen appliances. The higher the data volume, the more frequently used the kitchen appliance is in the current time period. Based on this operating condition, the most frequently used kitchen appliance is determined and selected as the preferred kitchen appliance for the corresponding time period. Due to the deterioration of memory ability of elderly users, they often forget what to do next. To avoid this in the kitchen scene, when an IoT device detects an elderly user entering the kitchen scene, it will provide interaction reminders for the elderly user based on the interaction priority of the kitchen appliance in the current time period.

[0072] Elderly users typically have their own usage habits for different kitchen appliances. Based on the historical operation data of each appliance, we identify the commonly used functions and programs. We then use the corresponding operation data to obtain program features. Using time series integration, we obtain program feature sequences for each appliance. These feature sequences are then repeatedly divided according to preset length ratios, such as 1 / 5, 1 / 3, 1 / 2, and 1, to obtain four feature sequences of different lengths. These feature sequences capture both the short-term and long-term preferences of elderly users. We first embed these feature sequences into a low-dimensional vector space using an embedding layer. A multi-head attention mechanism is then introduced to calculate the obtained low-dimensional vectors using scaled dot-product attention. Within each attention head, different linear transformations are performed to determine the importance of different low-dimensional vectors. These vectors' parameters can then be learned, ensuring that relevant features are learned from different subspaces. The attention results from all attention heads are then fed into a connection layer for concatenation and concatenation, forming a feature vector containing all features. This vector is then passed through an MLP multi-layer perceptron to determine the elderly user's control preferences for different kitchen appliances. A multi-layer perceptron is used to generate the usage representation of kitchen equipment by elderly users based on the feature sequences of the operating programs of different kitchen equipment. Multiple fully connected layers are adopted, and each fully connected layer performs feature transformation through linear transformation and nonlinear activation function. The short-term and long-term preferences of elderly users are integrated to determine the control preference data of elderly users for kitchen equipment.

[0073] It should be noted that user similarity is calculated based on the multimodal behavioral characteristics of elderly users, the interaction priority and control preference data of kitchen equipment in different time periods, and users who meet the preset similarity standards are selected as similar users of the elderly users. Social graph data is constructed based on the elderly users and similar users; interaction graph data is constructed based on the kitchen equipment in the kitchen scenes of elderly users. The elderly users and kitchen equipment are combined through the constructed interaction graph data, so that the user portrait can learn the strong correlation between elderly users and the influence of different degrees of interaction between elderly users and kitchen equipment during the training process.

[0074] The social graph data and interaction graph data are used to construct an elderly user graph, and the representations of the social graph data and interaction graph data are converted into triples to construct an elderly user graph, in which the elderly user is the head node, the relationship is the interaction attribute or similarity attribute, and the tail node is the similar user or kitchen equipment. In the elderly user graph, the elderly users and kitchen equipment are used as nodes, and directed edges are set according to whether there is an association between the nodes. If elderly user A and elderly user B are similar users, there is an edge structure between the elderly user A node and the elderly user B node. If elderly user A interacts with kitchen equipment C and D, there is an edge structure between the elderly user A node and the kitchen equipment C and D nodes. The multimodal behavioral characteristics of the elderly user are added as additional attributes of the elderly user node, and the interaction priority and control preference data of the kitchen equipment in different time periods are added as additional attributes of the kitchen equipment node.

[0075] A graph neural network is used to learn from graph data representing the elderly user graph. During the aggregation process, random neighborhood sampling is used to select the neighbors of the elderly user node, reducing the amount of computational data required for aggregation. A preset number of neighboring nodes are randomly selected for aggregation, and a different neighborhood is randomly selected in each iteration to ensure that most neighboring nodes participate in the neighbor aggregation. This random neighborhood sampling also mitigates the overfitting problem of the graph neural network to a certain extent. A multi-head attention mechanism is introduced to weight each neighboring node, and this weighted neighborhood is used to update the aggregation. When aggregating information about neighboring users or kitchen appliances, the multi-head attention mechanism assigns weights to kitchen appliances and similar users based on the elderly user's preference control data and similarity, emphasizing the corresponding neighboring nodes and preserving their information. After the aggregation, the updated elderly user node is obtained and calculated using a nonlinear activation function to obtain an updated embedding representation for the elderly user node. After multiple aggregations, the updated embedding representation is concatenated with the original embedding representation, strengthening the weight of the elderly user's attributes in the user profile. Finally, the output layer of the graph neural network outputs the elderly user's user profile.

[0076] Figure 3 A flowchart of an embodiment of determining the optimal interaction mode for elderly users through user portraits is shown.

[0077] According to an embodiment of the present invention, the optimal interaction mode is determined based on the user portrait, specifically:

[0078] S302: Obtaining examples of age-friendly interactive design for kitchen equipment, performing graph processing on the examples to generate graph structure data, encoding the graph structure data, and obtaining user profiles in each example;

[0079] S304, obtaining different user portrait groups through clustering, and obtaining a user evaluation matrix for interaction modalities within the user portrait groups, where the elements in the evaluation matrix represent the user's evaluation of the interaction modality;

[0080] S306: Using the user profile of the elderly user, determine a corresponding user profile group, perform similarity calculation within the user profile group, select a preset number of similar users, and select the interaction mode with the highest evaluation based on the evaluation matrix of the similar users;

[0081] S308: Simulate interaction prompts of different kitchen appliances according to the selected interaction modality, obtain feedback from the elderly user on the interaction prompts of different interaction modalities through the terminal device, and select the best interaction modality according to the feedback.

[0082] It should be noted that examples of kitchen equipment aging-friendly interaction design are obtained, and aging-friendly measures set for elderly users in the examples are analyzed and extracted, such as setting tactile modal feedback on buttons and auditory modal guidance for elderly users with impaired vision. Based on the aging-friendly measures set for elderly users in the examples, associations between elderly users and aging-friendly interaction modalities are generated. Graph processing is performed using these associations, and each example corresponds to a unique graph structure. The graph structures are associated and spliced through similarity associations between nodes, completing the graph processing of the kitchen equipment aging-friendly interaction design examples. Based on the graph processing, the kitchen equipment aging-friendly interaction design examples are constructed into corresponding graph structures, which contain user nodes and interaction modal nodes. Based on the attribute information of the corresponding user profiles of elderly users, a portrait model trained with a graph neural network is used to embed the user nodes and interaction modal nodes in the graph structure. The user profiles in each example are obtained, and the interaction modal nodes are sorted using clustering and recall algorithms. The user evaluation of the interaction modal in the example is obtained based on the user operation fluency obtained through feedback. The higher the operation fluency, the better the corresponding evaluation. The interaction mode is selected based on the highest evaluation of similar users, and operation interaction prompts are virtually generated on the preset terminal device. Feedback is obtained to obtain the interaction fluency and target capture degree of the elderly user to determine the optimal interaction mode. The optimal interaction mode can be one or more, determined based on the feedback from the elderly user.

[0083] It should be noted that the corresponding function program information is determined based on the elderly user's control preference data, and the operational flow of the function program information of different kitchen equipment is read, such as rotating the lid to open - removing the inner pot - replacing the inner pot - screwing the lid back on - turning on the power - pressing the start button - pressing the function key - selecting a subsequent sub-function - setting the time - starting the function. The operational flow is then configured with corresponding interactive guidance using the optimal interaction modality. For example, voice broadcast, icon-based process guidance, vibration feedback on incorrect selection, etc. are used to construct an interactive control guidance workflow. Preferably, the functional program operational flow based on the elderly user's control preference data is used to obtain the elderly user's dietary habits. Based on these dietary habits, the optimal operational flow for the corresponding functional program is obtained based on a large number of historical cooking examples. The deviation between the optimal operational flow and the elderly user's habitual operational flow is determined. When the deviation exceeds a preset deviation threshold, a modification coefficient is set to slightly adjust the user's habitual operational flow. The interactive control guidance workflow is generated based on the adjusted operational flow, and feedback from the elderly user on the cooking process is obtained. The modification coefficient is reset based on the feedback to improve the taste of the cooked food.

[0084] When an elderly user enters the kitchen scene, an operation interaction prompt is generated according to the interaction priority of kitchen equipment in different time periods, and it is judged whether the kitchen equipment operated by the elderly user meets the kitchen equipment interaction priority, and the frequency of non-satisfaction is counted. When the non-satisfaction frequency is greater than a preset threshold, the kitchen equipment interaction priority of the current time period is reset; the kitchen equipment operated by the elderly user is obtained, and the demand information is estimated according to the operation information of the elderly user. The corresponding interaction control guidance workflow is determined according to the elderly user's selection feedback on the estimated demand information, and the average reaction time of the elderly user for each operation control step in the interaction control guidance workflow is obtained. When the average reaction time is greater than the preset time threshold, it proves that the elderly user does not understand the interaction guidance, and it is marked as critical. Control steps; based on the key control steps, interactive prompt information of different interactive modes is generated, multi-channel prompts are given to elderly users, and the average reaction time of elderly users to key control steps is statistically analyzed. When the average reaction time is less than, the interactive prompt information of different interactive modes is canceled; when the reaction time of the elderly user to the operation control step is less than the average reaction time, it proves that the elderly user is sufficiently proficient in operating a certain step of the functional program, and the corresponding guidance in the interactive control guidance workflow is removed. The interactive control guidance workflow is updated according to the subsequent feedback from the elderly users. By dynamically updating the interactive control guidance workflow, the memory ability of the elderly users can be trained to a certain extent, and the acceptance of the elderly users to smart kitchen equipment can be improved.

[0085] A second embodiment of the present invention provides an intelligent interactive control system for aging-friendly kitchen equipment, comprising a user multimodal behavior feature evaluation unit, an equipment operation data analysis unit, a user portrait construction unit, an interactive control guide determination unit, and a control feedback unit;

[0086] The user multimodal behavior characteristic evaluation unit evaluates the behavioral characteristics of the elderly user in terms of hearing, vision, touch and cognition, and integrates the behavioral characteristics of different aspects to generate the multimodal behavior characteristics of the elderly user;

[0087] The device operation data analysis unit uses the historical operation data of different kitchen appliances to extract operation time characteristics and operation program characteristics, determines the interaction priority of kitchen appliances in different time periods based on the operation time characteristics, and determines the control preference data of elderly users based on the operation program characteristics of different kitchen appliances;

[0088] The user portrait construction unit constructs a user portrait based on multimodal behavior characteristics, kitchen equipment interaction priorities at different time periods, and control preference data;

[0089] The interactive control guidance determination unit determines the optimal interaction mode and the interactive control guidance workflow that meets the control preferences of different kitchen appliances based on the user profile, extracts the key control steps of the interactive control guidance workflow, generates interactive prompt information for the key control steps based on the optimal interaction mode, and performs multi-channel interactive prompts;

[0090] The control feedback unit obtains the elderly user's selection feedback on the interactive control guidance workflow, as well as the reaction time to each operation control step of the kitchen equipment under the interactive control guidance workflow, and analyzes and updates the interactive prompt information and the interactive control guidance workflow.

[0091] A third embodiment of the present invention provides a computer-readable storage medium, which includes a smart interactive control method program for aging-friendly kitchen equipment. When the smart interactive control method program for aging-friendly kitchen equipment is executed by a processor, the steps of the smart interactive control method for aging-friendly kitchen equipment are implemented.

[0092] In the several embodiments provided in this application, it should be understood that the disclosed methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the units can be electrical, mechanical or other forms.

[0093] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0094] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0095] Alternatively, if the integrated units described above are implemented as software modules and sold or used as standalone products, they can also be stored on a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

[0096] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. An intelligent interactive control method for aging-friendly kitchen equipment, characterized in that: The following steps are involved: Evaluate the behavioral characteristics of elderly users in terms of vision, hearing, touch and cognition, and integrate the behavioral characteristics of different aspects to generate multimodal behavioral characteristics of elderly users; Utilizing historical operating data of different kitchen appliances to extract operating time characteristics and operating program characteristics, the interaction priorities of kitchen appliances in different time periods are determined based on the operating time characteristics, and the control preference data of elderly users is determined based on the operating program characteristics of different kitchen appliances; Building a user profile based on the multimodal behavior characteristics, kitchen equipment interaction priorities at different time periods, and control preference data, and determining the optimal interaction mode based on the user profile; Based on the optimal interaction mode, the interactive control guidance workflow of different kitchen equipment that meets the control preferences of elderly users is obtained, the key control steps in the interactive control guidance workflow are extracted, and interactive prompt information of the key control steps is generated based on the interactive control guidance workflow to provide multi-channel interactive prompts for elderly users. The interaction priorities of the kitchen appliances in different time periods are determined based on the operating time characteristics, and the control preference data of the elderly user is determined based on the operating program characteristics of different kitchen appliances, specifically: Extract historical operating data of different kitchen appliances within a preset time step in the elderly user's kitchen scenario. The historical operating data is divided into natural day periods. The operating time data of different kitchen appliances within a natural day is extracted to determine the operating time characteristics of different kitchen appliances. Soft clustering is performed using the operating time characteristics of different kitchen appliances. Based on the clustering results, clustered datasets are obtained for each time period. The data volume of different categories of kitchen appliances in the clustered datasets is extracted. Based on this data volume, the interaction priority of kitchen appliances relative to elderly users in different time periods is determined. Obtaining operating program features of different kitchen appliances based on the historical operating data, obtaining operating program feature sequences of different kitchen appliances through time series integration, and repeatedly dividing the operating program feature sequences of different kitchen appliances using different time division standards; For any kitchen appliance, the subsequences of running program features of different lengths are divided and embedded into low-dimensional vectors. A multi-head attention mechanism is introduced to weight each low-dimensional vector. The weighted low-dimensional vectors are then concatenated to form a feature vector that contains all the low-dimensional vector features. The feature vector is imported into a multi-layer perceptron, and a double-layer multi-layer perceptron structure is used to determine the control preference data of elderly users on kitchen equipment.

2. The intelligent interactive control method for aging-friendly kitchen equipment according to claim 1, characterized in that: Evaluate the behavioral characteristics of elderly users in terms of hearing, vision, touch, and cognition, and integrate the behavioral characteristics of different aspects to generate multimodal behavioral characteristics of elderly users, specifically: Obtaining program operation data for different types of kitchen equipment, using the program operation data to extract icon keyword data, guidance prompt sound data, touch vibration data, and icon position data, and establishing behavioral characteristic assessment projects in auditory, visual, tactile, and cognitive aspects based on the extracted multi-dimensional data; Sending the behavior characteristic assessment items to a preset terminal device, and using the preset terminal device to obtain the elderly user's visual behavior characteristics, auditory behavior characteristics, tactile behavior characteristics, and cognitive behavior characteristics; The benchmark values of each modal behavior feature are set based on the mean of the evaluation results of different modal behavior features of young users, and a metric function is constructed using Euclidean distance. The Euclidean distance between the visual behavior features, auditory behavior features, tactile behavior features, and cognitive behavior features of elderly users and the corresponding benchmark values is obtained through the metric function. Normalization is performed on the Euclidean distance to generate feature scores of different modal behavior features of elderly users, the feature scores are matched with corresponding modal behavior features, and all modal behavior features of elderly users are integrated to generate multimodal behavior features.

3. The intelligent interactive control method for aging-friendly kitchen equipment according to claim 1, characterized in that: A user profile is constructed based on the multimodal behavioral characteristics, interaction priorities of kitchen equipment at different time periods, and control preference data, specifically: User similarity is calculated based on the elderly user's multimodal behavioral characteristics, kitchen equipment interaction priorities at different time periods, and control preference data. Users who meet the preset similarity criteria are selected as similar users of the elderly user, and social graph data is constructed based on the elderly user and similar users. Constructing interaction graph data based on kitchen equipment in elderly users' kitchen scenarios, constructing an elderly user graph using the social graph data and the interaction graph data, wherein elderly users and kitchen equipment are used as nodes in the elderly user graph, and directed edges are set based on whether there is a relationship between the nodes. Multimodal behavioral characteristics of elderly users are added as additional attributes of the elderly user nodes, and interaction priorities and control preference data of kitchen equipment at different time periods are added as additional attributes of the kitchen equipment nodes; A graph neural network is used to learn the graph data of the elderly user graph. Neighborhood random sampling is used to select the neighboring nodes of the elderly user node. A multi-head attention mechanism is introduced to weight each neighboring node. The weighted neighboring nodes are used for aggregate updates. Obtain the elderly user node after aggregation and update, obtain the updated embedding representation of the elderly user node, and after multiple aggregations, splice the updated embedding representation of the elderly user node with the original embedding representation to output the user portrait of the elderly user.

4. The intelligent interactive control method for aging-friendly kitchen equipment according to claim 1, characterized in that: The optimal interaction mode is determined based on the user portrait, specifically: Obtaining examples of age-friendly interactive design for kitchen equipment, performing graph processing on the examples of age-friendly interactive design for kitchen equipment to generate graph structure data, encoding the graph structure data, and obtaining user portraits in each example; Obtain different user portrait groups through clustering, and obtain a user evaluation matrix of the interaction modality within the user portrait groups, where the elements in the evaluation matrix represent the user's evaluation of the interaction modality; Use the user profiles of elderly users to determine the corresponding user profile groups, perform similarity calculations within the user profile groups to select a preset number of similar users, and select the interaction mode with the highest evaluation based on the evaluation matrix of similar users; According to the selected interaction mode, the interaction prompts of different kitchen equipment are simulated, the feedback of elderly users on the interaction prompts of different interaction modes is obtained through the terminal device, and the optimal interaction mode is selected based on the feedback.

5. The intelligent interactive control method for aging-friendly kitchen equipment according to claim 1, characterized in that: Based on the optimal interaction mode, the interactive control guidance workflow of different kitchen equipment that meets the control preferences of elderly users is obtained, the key control steps in the interactive control guidance workflow are extracted, and the interactive prompt information of the key control steps is generated based on the interactive control guidance workflow. Specifically: Determining corresponding function program information based on the elderly user's control preference data, reading the operation procedures of the function program information of different kitchen equipment, and constructing an interactive control guidance workflow based on the operation procedures through the optimal interaction mode; When an elderly user enters the kitchen scene, an operation interaction prompt is generated based on the kitchen equipment interaction priority at different time periods. The system determines whether the kitchen equipment operated by the elderly user meets the kitchen equipment interaction priority. The frequency of non-satisfaction is counted. When the non-satisfaction frequency exceeds a preset threshold, the kitchen equipment interaction priority for the current time period is reset. Obtain the kitchen equipment operated by the elderly user, determine the corresponding interactive control guidance workflow based on the elderly user's operation information, and obtain the elderly user's average response time for each operation control step in the interactive control guidance workflow. If the average response time is greater than a preset time threshold, it is marked as a critical control step; Generate interactive prompt information of different interactive modes based on the key control steps, provide multi-channel prompts to elderly users, statistically analyze the average reaction time of elderly users to key control steps, and cancel the interactive prompt information of different interactive modes when the average reaction time is less than 0. When the elderly user's reaction time to the operation control step is less than the average reaction time, the corresponding guidance in the interactive control guidance workflow is removed, and the interactive control guidance workflow is updated according to the subsequent feedback from the elderly user.

6. An intelligent interactive control system for aging-friendly kitchen equipment, characterized in that: A method for implementing the intelligent interactive control of aging-friendly kitchen equipment according to any one of claims 1 to 5, comprising a user multimodal behavior feature evaluation unit, an equipment operation data analysis unit, a user portrait construction unit, an interactive control guide determination unit, and a control feedback unit; The user multimodal behavior characteristic evaluation unit evaluates the behavioral characteristics of the elderly user in terms of hearing, vision, touch and cognition, and integrates the behavioral characteristics of different aspects to generate the multimodal behavior characteristics of the elderly user; The device operation data analysis unit uses the historical operation data of different kitchen appliances to extract operation time characteristics and operation program characteristics, determines the interaction priority of kitchen appliances in different time periods based on the operation time characteristics, and determines the control preference data of elderly users based on the operation program characteristics of different kitchen appliances; The user portrait construction unit constructs a user portrait based on multimodal behavior characteristics, kitchen equipment interaction priorities at different time periods, and control preference data; The interactive control guidance determination unit determines the optimal interaction mode and the interactive control guidance workflow that meets the control preferences of different kitchen appliances based on the user profile, extracts the key control steps of the interactive control guidance workflow, generates interactive prompt information for the key control steps based on the optimal interaction mode, and performs multi-channel interactive prompts; The control feedback unit obtains the elderly user's selection feedback on the interactive control guidance workflow, as well as the reaction time to each operation control step of the kitchen equipment under the interactive control guidance workflow, and analyzes and updates the interactive prompt information and the interactive control guidance workflow.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a program for the intelligent interactive control method of aging-friendly kitchen equipment. When the program for the intelligent interactive control method of aging-friendly kitchen equipment is executed by a processor, the steps of the intelligent interactive control method of aging-friendly kitchen equipment according to any one of claims 1 to 5 are implemented.

Images