Target recipe determination method and device, electronic equipment and intelligent kitchen system

Abstract

The application discloses a target recipe determination method and device, electronic equipment and an intelligent kitchen system. The method comprises the following steps: in response to a cooking instruction of a target object, obtaining an initial recipe set corresponding to the target object, target health information of the target object and an initial trunk part; each initial recipe is traversed in turn, and for the current initial recipe traversed, current object health information, a current trunk part and a current recipe load level of the current initial recipe are obtained; the target health information and the current object health information are subjected to health information matching processing to obtain a current health matching degree of the current initial recipe; the current load adaptation degree of the current initial recipe is determined according to the initial trunk part, a current trunk part corresponding to the current initial recipe and the current recipe load level; and the target recipe is determined according to the current health matching degree and the current load adaptation degree of the current initial recipe. The application reduces the fatigue degree of the target object in the cooking process.

Description

Technical Field

[0001] This application relates to the field of smart kitchen appliance technology, and in particular to a method, apparatus, electronic device, and smart kitchen system for determining a target recipe. Background Technology

[0002] With the improvement of people's living standards and the application of computer technology in the kitchen appliance field, kitchen appliances have developed rapidly, providing users with methods to optimize the cooking process and realizing multi-appliance collaborative cooking, thus continuously improving people's cooking experience. However, current kitchen appliance systems focus on being set according to the cooking steps in recipes, without considering the actual human element of the cook and failing to provide adaptive assistance.

[0003] Currently, cooking in the kitchen is a tedious and time-consuming process, making the repetitive kitchen activities tedious and grueling. Furthermore, improper cooking procedures can lead to disorganization and inappropriate workload, causing fatigue and discomfort such as back pain. The impact is even greater on groups sensitive to movement and intensity during cooking, such as the elderly, pregnant women, or those with pre-existing physical conditions. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and intelligent kitchen system for determining a target recipe, which can reduce the fatigue of the target user during the cooking process.

[0005] On the one hand, this application provides a method for determining a target recipe, the method comprising: In response to a cooking instruction for a target object, the system acquires an initial recipe set corresponding to the target object, the target object's target health information, and an initial torso position; the initial recipe set includes at least two initial recipes; the initial torso position is the torso position of the target object that undergoes deformation during the cooking process. Iterate through each initial recipe in turn, and for the current initial recipe, obtain the current object's health information, current torso position, and current recipe load level; The target health information and the current object health information are matched to obtain the current health matching degree of the current initial recipe. The current load fit of the current initial recipe is determined based on the initial torso position, the current torso position corresponding to the current initial recipe, and the load level of the current recipe. The current recipe score is determined based on the current health matching degree and the current load adaptability of the current initial recipe. The target recipe is determined based on the recipe score of each initial recipe.

[0006] In one exemplary embodiment, the step of sequentially traversing each initial recipe and, for the current initial recipe, obtaining the current object's health information, current torso position, and current recipe load level for that current initial recipe includes: Each initial recipe is traversed sequentially. For the current initial recipe, the health information of the current object in the current initial recipe is obtained. The current initial recipe includes at least two cooking steps. Iterate through each cooking step in the current initial recipe, and for the current cooking step, obtain the torso position and initial step load level corresponding to the current cooking step. Obtain the real-time heart rate value of the target object; If the real-time heart rate value is greater than the preset heart rate value, the initial step load level is updated to obtain the updated step load level. The current recipe load level is determined based on the updated step load level corresponding to each cooking step. The current torso position is determined based on the torso position corresponding to each cooking step.

[0007] In one exemplary embodiment, before sequentially traversing each initial recipe and, for the current initial recipe, obtaining the current object's health information, current torso position, and current recipe load level, the method further includes: Obtain the torso weight value corresponding to each torso part of the target object and the historical recipes corresponding to the target object; the torso weight value represents the sensitivity of the torso part of the target object during the cooking process; Based on the torso position weight value corresponding to each torso position and the historical recipes corresponding to the target object, the cooking information of the target object is determined; The cooking information of the target object is input into the torso position weight value prediction model to perform torso position weight value prediction processing, so as to obtain the actual torso position weight value corresponding to each torso position. Based on the mapping relationship between each torso position and the actual torso position weight value corresponding to each torso position, a torso weight value relationship library is constructed.

[0008] In one exemplary embodiment, determining the current load fit of the current initial recipe based on the initial torso position, the current torso position corresponding to the current initial recipe, and the load level of the current recipe includes: Determine the target torso position based on the current torso position corresponding to the current initial recipe and the initial torso position; Search the trunk weight value database for the trunk position weight value that matches the target trunk position to obtain the target trunk position weight value; The current load fit of the current initial recipe is determined based on the target torso weight value and the current recipe load level.

[0009] In one exemplary embodiment, determining the target recipe based on the recipe score of each initial recipe includes: Based on the recipe score of each initial recipe, candidate recipes are determined; each candidate recipe includes at least two candidate cooking steps. The current candidate torso position is obtained by searching the step part relationship library for the torso position that matches the current candidate cooking step; the step part relationship library includes a preset mapping relationship between cooking steps and preset torso positions; the current candidate cooking step is any one of the candidate cooking steps in the candidate recipe. If the current candidate torso position is the target torso position, then the current candidate cooking step is determined to be the target candidate cooking step; The target candidate cooking steps are updated to obtain the updated cooking steps; The target recipe is determined based on the remaining candidate cooking steps in the candidate recipes and the updated cooking steps; the remaining candidate cooking steps are the cooking steps in the candidate recipes other than the target candidate cooking steps.

[0010] In one exemplary embodiment, after determining the target recipe based on the recipe score of each initial recipe, the method further includes: During the process of the target object cooking based on the target recipe, the real-time posture of the target object is acquired by an image acquisition device in the kitchen; If the real-time posture meets the preset conditions, obtain the duration of the real-time posture and the real-time torso position weight value corresponding to the real-time posture. The real-time fatigue value of the target object is determined based on the duration of the real-time posture and the real-time torso position weight value. If the real-time fatigue value is greater than the preset fatigue threshold, an exercise prompt message is generated.

[0011] In one exemplary embodiment, determining the current recipe score of the current initial recipe based on the current health matching degree and the current load adaptability of the current initial recipe includes: Determine a first weight value corresponding to the current health matching degree and a second weight value corresponding to the current load adaptability degree; Calculate the product of the current health matching degree and the first weight value to obtain the health score of the current initial recipe; Calculate the product of the current load fit and the second weight value to obtain the load score of the current initial recipe; The sum of the health score and the load score of the current initial recipe is calculated to obtain the current recipe score.

[0012] On the other hand, a device for determining a target recipe is provided, the device comprising: The first acquisition module is used to acquire, in response to the cooking instructions of the target object, an initial recipe set corresponding to the target object, the target health information of the target object, and an initial torso position; the initial recipe set includes at least two initial recipes; the initial torso position is the torso position of the target object that undergoes deformation during the cooking process; The second acquisition module is used to sequentially traverse each initial recipe and, for the current initial recipe, acquire the current object's health information, current torso position, and current recipe load level. The current health matching degree determination module is used to perform health information matching processing on the target health information and the current object health information to obtain the current health matching degree of the current initial recipe; The current load adaptability determination module is used to determine the current load adaptability of the current initial recipe based on the initial torso position, the current torso position corresponding to the current initial recipe, and the load level of the current recipe. The current recipe score determination module is used to determine the current recipe score of the current initial recipe based on the current health matching degree and the current load adaptability of the current initial recipe; The target recipe determination module is used to determine the target recipe based on the recipe score of each initial recipe.

[0013] On the other hand, an electronic device is provided, the device including a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded by the processor and executed by the method for determining the target recipe as described above.

[0014] On the other hand, an intelligent kitchen system is provided for performing the target recipe determination method as described above.

[0015] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction or at least one program is stored therein, the at least one instruction or at least one program being loaded and executed by a processor to implement the method for determining the target recipe as described above.

[0016] On the other hand, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method for determining the target recipe as described above.

[0017] This application provides a method, apparatus, electronic device, and intelligent kitchen system for determining a target recipe, which has the following technical effects: Responding to a cooking instruction from a target object, this application acquires an initial recipe set corresponding to the target object, the target health information of the target object, and an initial torso position; the initial recipe set includes at least two initial recipes; the initial torso position is the torso position of the target object that deforms during cooking; each initial recipe is traversed sequentially, and for the current initial recipe, the current object health information, current torso position, and current recipe load level of the current initial recipe are acquired; health information matching processing is performed between the target health information and the current object health information to obtain the current health matching degree of the current initial recipe; the current load adaptability of the current initial recipe is determined based on the initial torso position, the current torso position corresponding to the current initial recipe, and the current recipe load level; the current recipe score of the current initial recipe is determined based on the current health matching degree and the current load adaptability; and the target recipe is determined based on the recipe score of each initial recipe. By determining the recipe score for each initial recipe to filter recipes that are suitable for the target audience, the adaptability of the recipes is improved. Furthermore, the recipe score is calculated based on the health matching degree of the initial recipe, the torso position of the initial recipe, the recipe load level, and the initial torso position of the target audience, taking into account the physical condition of the target audience. This enables personalized recipe customization for different users, improves cooking efficiency, reduces user fatigue, and enhances the physical comfort of the target audience during the cooking process. Attached Figure Description

[0018] To more clearly illustrate the technical solutions and advantages in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating a method for determining a target recipe provided in an embodiment of this specification; Figure 2 This is a flowchart illustrating a method for determining information of the current initial recipe provided in an embodiment of this specification. Figure 3 This is a flowchart illustrating a method for constructing a trunk weight relation library as provided in the embodiments of this specification; Figure 4 This is a flowchart illustrating a method for determining current load adaptability provided in an embodiment of this specification. Figure 5 This is a flowchart illustrating a method for determining the current recipe score provided in an embodiment of this specification; Figure 6 This is a flowchart illustrating a method for determining a target recipe provided in an embodiment of this specification; Figure 7 This is a flowchart illustrating a method for generating motion prompt information provided in an embodiment of this specification; Figure 8 This is a recipe selection and cooking method provided in the embodiments of this specification; Figure 9 This is a schematic diagram of the structure of the target recipe determination device provided in the embodiments of this specification.

[0020] Figure 10 This is a schematic diagram of the server structure for a method of determining a target recipe provided in an embodiment of this specification. Detailed Implementation

[0021] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0023] The following describes a method for determining the target recipe according to this application. Figure 1 This is a flowchart illustrating a method for determining a target recipe provided in an embodiment of this specification. This specification provides the operational steps of the method described in the embodiment or flowchart, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiment is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server product execution, the method can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment) as shown in the embodiment or drawings. Specifically, as... Figure 1 As shown, the method is applied to the control unit corresponding to the smart kitchen system, and the method includes: S101: In response to a cooking instruction for the target object, obtain the initial recipe set corresponding to the target object, the target health information of the target object, and the initial torso position; the initial recipe set includes at least two initial recipes; the initial torso position is the torso position of the target object that undergoes deformation during the cooking process.

[0024] In the embodiments of this specification, the target object is a user. When the user needs to cook, they send a cooking command to the kitchen system. The control unit of the kitchen system responds to the cooking command sent by the target object and obtains the initial recipe set corresponding to the target object, the target health information of the target object, and the initial torso position. The initial recipe set includes at least two initial recipes. The target health information is the target object's physical condition information. For example, the target object has diabetes, lacks dietary fiber, and needs to lose weight. The initial torso position is the torso position of the target object that undergoes deformation during cooking, and this torso position is subject to restrictions during cooking. For example, the waist of a pregnant woman is an initial torso position, while the waist of a healthy user is not.

[0025] S103: Iterate through each initial recipe in sequence, and for the current initial recipe, obtain the current object's health information, current torso position, and current recipe load level.

[0026] In the embodiments of this specification, each initial recipe is traversed sequentially. For the current initial recipe, the current health information, current torso position, and current recipe load level of the current initial recipe are obtained. The current health information is a score calculated based on the food in the current initial recipe. For example, if the current initial recipe contains oatmeal, the score is calculated based on the oatmeal content, glycemic index (GI) value, carbohydrate content, dietary fiber content, and calories to obtain the current health information. The current torso position is the torso position corresponding to each cooking step in the current initial recipe, and the current recipe load level is the step load level corresponding to each cooking step in the current initial recipe.

[0027] In the embodiments of this specification, each initial recipe is traversed sequentially, and for the current initial recipe, the current object's health information, current torso position, and current recipe load level are obtained, such as... Figure 2 As shown, Figure 2 A flowchart illustrating a method for determining information of a current initial recipe, provided in an embodiment of this specification, includes: S201: Iterate through each initial recipe in sequence, and for the current initial recipe, obtain the current object health information of the current initial recipe; the current initial recipe includes at least two cooking steps.

[0028] In the embodiments of this specification, each initial recipe is traversed sequentially. For the current initial recipe that is traversed, the health information of the current object of the current initial recipe is obtained, and the current initial recipe includes at least two cooking steps.

[0029] S202: Iterate through each cooking step in the current initial recipe, and for the current cooking step, obtain the torso position and initial step load level corresponding to the current cooking step.

[0030] In the embodiments of this specification, each cooking step in the current initial recipe is traversed sequentially. For the current cooking step that is traversed, the torso position corresponding to the current cooking step and the load level of the initial step are obtained. The torso position corresponding to the current cooking step is the torso position required by the current cooking step during the cooking process. For example, as shown in Table 1, Table 1 is a mapping table of cooking action-torso position-load level.

[0031] Table 1. Cooking Action - Trunk Position - Load Level Mapping Table

[0032] As can be seen, for the current cooking step, the current cooking action corresponding to the current cooking step is determined, thereby determining the torso position corresponding to the current cooking action and the initial step load level. For example, if the current cooking action corresponding to the current cooking step is tossing the wok, then the torso position corresponding to the current cooking action is the wrist, shoulder and core muscle group, and the initial step load level corresponding to the current cooking step is 4.

[0033] S203: Obtain the real-time heart rate value of the target object.

[0034] In the embodiments described in this specification, the real-time heart rate value of the target object is obtained.

[0035] S204: If the real-time heart rate value is greater than the preset heart rate value, the initial step load level is updated to obtain the updated step load level.

[0036] In the embodiments of this specification, the resting heart rate of the target object is obtained. The preset heart rate value can be the resting heart rate of the target object + 20%. If the real-time heart rate value is greater than the preset heart rate value, the initial step load level is incremented by 1 to obtain the updated step load level. At the same time, if the real-time heart rate value is less than or equal to the preset heart rate value, the initial step load level is directly used as the updated step load level.

[0037] S205: Determine the current recipe load level based on the updated step load level corresponding to each cooking step.

[0038] In the embodiments of this specification, the current recipe load level is determined by comprehensively considering the updated step load levels corresponding to each cooking step in the current initial recipe.

[0039] S206: Determine the current torso position based on the torso position corresponding to each cooking step.

[0040] In the embodiments of this specification, the current torso position is determined by comprehensively considering the torso positions corresponding to each cooking step, i.e., all torso positions involved in the current initial recipe. By mapping the cooking steps, the torso positions corresponding to each cooking step and the initial step load level are obtained, which helps to subsequently calculate the recipe score and filter out target recipes that are suitable for the target object.

[0041] In the embodiments of this specification, before sequentially traversing each initial recipe and, for the current initial recipe, obtaining the current object's health information, current torso position, and current recipe load level, as follows: Figure 3 As shown, Figure 3 This is a flowchart illustrating a method for constructing a trunk weight relation library as provided in an embodiment of this specification. The method further includes: S301: Obtain the torso weight value corresponding to each torso part of the target object and the historical recipe corresponding to the target object; the torso weight value represents the sensitivity of the torso part of the target object during the cooking process.

[0042] In the embodiments of this specification, the weight value of each torso part of the target object and the historical recipes corresponding to the target object are obtained. The historical recipes are the recipes used by the target object in the historical cooking process, and the historical recipes indicate which steps the target object skipped in the historical cooking process. The torso part weight value represents the sensitivity of the target object's torso part in the cooking process. It is a weight value between 0 and 1. When the torso part weight value is 0, it means that there is no restriction on the torso part in the cooking process. When the torso part weight value is 1, it means that the torso part is completely disabled in the cooking process. The torso part weight value corresponding to each torso part can be obtained based on user active input, wearable device / camera monitoring, medical report analysis, and other methods. Specifically, the user can manually input the following: the target object selects "slight lower back discomfort" through the interactive interface, and then the system searches for the torso position weight value corresponding to the slight lower back discomfort based on the mapping preset rule library. For example, it can be 0.4. The mapping preset rule library includes the preset mapping relationship between the target object's torso position and the preset torso position weight value. The target object can set the torso position weight value itself based on the sensitivity of the torso position. For example, for a healthy user's lower back, the torso position weight value can be set to 0, indicating that the user's lower back is not restricted when cooking. For a pregnant woman's lower back, the frequency of use should be reduced but bending over is not prohibited. The torso position weight value can be set to 0.3, indicating that the user's lower back is slightly sensitive when cooking. For a patient in the postoperative recovery period, the torso position weight value can be set to 0.8, indicating that the user's arm is severely sensitive when cooking. For a patient with a lumbar fracture, the torso position weight value can be set to 1, indicating that the user's lower back should not be used when cooking. Wearable device / camera monitoring can detect wearable device data, including activity decay rate, electromyography (EMG) fatigue index, and stress overshoot ratio. Activity decay rate represents the rate at which overall activity intensity decreases with activity duration, reflecting the user's persistent fatigue. A higher activity decay rate indicates a faster decline in activity intensity and relatively poor endurance. EMG fatigue index represents the degree of physiological fatigue in the user's muscles; a larger change or a faster decrease in EMG indicates more severe physiological muscle fatigue. Stress overshoot ratio represents how many times higher the user's current physiological stress level is compared to their normal resting stress baseline. It is an indicator reflecting the comprehensive physiological stress state regulated by the autonomic nervous system, such as tension, anxiety, overload, and physical discomfort. For example, a ratio of 1.5 means the current stress level is 1.5 times the resting state. A higher stress overshoot ratio indicates a more significant physiological stress response. The torso weight value can be calculated by combining activity decay rate, EMG fatigue index, and stress overshoot ratio using a weighted algorithm. The formula for calculating the torso weight value is as follows: The weighting value for the trunk position is calculated as follows: min(1, 0.5 × activity decay rate + 0.3 × electromyographic fatigue index + 0.2 × stress overshoot ratio). It can be seen that different weight values ​​are assigned to the activity decay rate, electromyographic fatigue index and pressure overshoot ratio according to their different importance. The final result of the weight value of the trunk position needs to be the minimum value of 1 and 0.5×activity decay rate + 0.3×electromyographic fatigue index + 0.2×pressure overshoot ratio, so that the output range is limited to [0,1].

[0043] Activity decay rate = max(0, 1 - (real-time activity range / baseline activity range)) The calculation of the activity decay rate requires combining the user's real-time activity range and baseline activity range. The activity decay rate for the torso position is calculated based on the actual needs. The baseline activity range is pre-set based on the torso position to be calculated. The wearable device can be worn on different torso positions of the target object based on the required torso position. For example, to calculate the target object's stride or step length decay, the wearable device can be worn on the target object's ankle or waist to collect the target object's real-time activity range. To calculate the target object's arm swing amplitude decay, the wearable device can be worn on the target object's wrist to collect the target object's real-time activity range. Meanwhile, since the activity decay rate is negative when the real-time activity range is greater than the baseline activity range, a negative value will reduce the weight value of the torso position when weighting the calculation, thus affecting the judgment of the sensitivity of the torso position. Therefore, when the real-time activity range is greater than the baseline activity range, the activity decay rate is taken as 0.

[0044] Electromyography fatigue index = Real-time mean electromyography value / Baseline mean electromyography value The baseline electromyography (EMG) mean is the average value of the initial or resting state, while the real-time EMG mean is the average amplitude of the current EMG signal.

[0045] Pressure exceedance rate = max(0, Real-time pressure - Average baseline pressure) / Average baseline pressure Among them, real-time pressure is the pressure value of the target object monitored in real time by the wearable device, and the average baseline pressure is the average pressure value of the target object when it is in the initial or resting state. When the real-time pressure is greater than the average baseline pressure, the pressure exceedance rate is higher. When the real-time pressure is less than the average baseline pressure, the value is 0 to avoid negative values ​​affecting the calculation results of the torso weight value.

[0046] Medical report analysis can be performed on medical reports provided by users, which may include specific precautions. For example, a medical report may state "Squatting is prohibited for 6 weeks after knee replacement surgery." By analyzing the medical report, the weight value of the torso position corresponding to the knee joint can be determined to be 1.

[0047] S302: Determine the cooking information of the target object based on the weight value of each torso position and the historical recipes corresponding to the target object.

[0048] In the embodiments of this specification, the cooking information of the target object can be obtained by combining the weight value of each torso position and the historical recipes corresponding to the target object.

[0049] S303: Input the cooking information of the target object into the torso position weight value prediction model to perform torso position weight value prediction processing, and obtain the actual torso position weight value corresponding to each torso position.

[0050] In the embodiments of this specification, the torso position weight prediction model is a machine learning model, trained based on the target object's historical cooking information and the historical torso position weight value corresponding to each torso position. The target object's cooking information is input into the torso position weight prediction model for torso position weight prediction processing, yielding the actual torso position weight value corresponding to each torso position. Simultaneously, the torso position weight prediction processing based on the torso position weight prediction model analyzes the target object's behavioral patterns through long-term learning. Additionally, there is a short-term feedback mechanism. Specifically, during the historical cooking process, when the target object manually skips a step and labels the reason for skipping the step as "physical discomfort," the torso position corresponding to that step is determined, and the torso position weight value corresponding to that torso position is updated. This update can be min(current value + 0.1, 1.0), while limiting the maximum value to 1. The torso position weight values ​​are updated based on short-term feedback, and the updated torso position weight values ​​are introduced into long-term learning. Ultimately, the torso position weight prediction model can be directly used to predict the actual torso position weight value of the target object.

[0051] S304: Construct a trunk weight value relationship library based on the mapping relationship between each trunk position and the actual trunk position weight value corresponding to each trunk position.

[0052] In the embodiments of this specification, a torso weight relationship library is constructed based on the mapping relationship between each torso position and its corresponding actual torso position weight value. By pre-obtaining the torso position weight value corresponding to each torso position of the target object and historical recipes, the target object's cooking information is determined, which helps predict the actual torso position weight value of the target object. This integrates short-term feedback and long-term learning, improving the accuracy of the prediction results. Furthermore, constructing the torso weight value relationship library facilitates faster acquisition of the torso position weight value of each initial recipe, shortening processing time and improving cooking efficiency.

[0053] S105: Perform health information matching processing on the target health information and the current object health information to obtain the current health matching degree of the current initial recipe.

[0054] In the embodiments of this specification, health information matching processing is performed on the target health information and the current object health information to obtain the current health matching degree of the current initial recipe; for example, the current health matching degree can be obtained by matching the branch of the current object health information with the target health information.

[0055] S107: Determine the current load fit of the current initial recipe based on the initial torso position, the current torso position corresponding to the current initial recipe, and the load level of the current recipe.

[0056] In the embodiments of this specification, the target torso position can be obtained based on the initial torso position and the current torso position corresponding to the current initial recipe. That is, the torso position of the target object in the current initial recipe that will be deformed during the cooking process and may hinder the health of the target object. Based on the target torso position, the target torso position weight value is determined. Combining the target torso position weight value and the current recipe load level, the current load fit of the current initial recipe can be calculated.

[0057] In this embodiment of the specification, the determination of the current load fit of the current initial recipe is based on the initial torso position, the current torso position corresponding to the current initial recipe, and the load level of the current recipe. Figure 4 As shown, Figure 4 A flowchart illustrating a method for determining current load adaptability provided in an embodiment of this specification includes: S401: Determine the target torso position based on the current torso position corresponding to the current initial recipe and the initial torso position.

[0058] In the embodiments of this specification, the target torso position is obtained by finding the same torso position as the initial torso position in the current torso position corresponding to the current initial recipe, that is, by taking the intersection of the two. There can be multiple target torso positions. Specifically, there are multiple cooking steps in the current initial recipe, and the torso positions corresponding to these cooking steps are one or more of the initial torso positions. The torso positions corresponding to these cooking steps are combined to obtain the current torso position corresponding to the current initial recipe.

[0059] S402: Search the trunk weight value database for a trunk position weight value that matches the target trunk position to obtain the target trunk position weight value.

[0060] In the embodiments of this specification, the torso weight value that matches the target torso position is found in the torso weight value relation library to obtain the target torso position weight value.

[0061] S403: Determine the current load fit of the current initial recipe based on the target torso weight value and the current recipe load level.

[0062] In the embodiments of this specification, the current recipe load level includes the updated step load level corresponding to each cooking step. Based on the determined target cooking step, the updated step load level corresponding to the target cooking step can be determined. Therefore, by combining the target torso weight value and the updated step load level corresponding to the target cooking step, the current load fit of the current recipe can be calculated. Specifically, firstly, the step load of each cooking step is calculated, and then the sum of the step loads of each cooking step is calculated to obtain the total load of the current initial recipe. The formula for calculating the total load is as follows: Total load = sum(step.load level × target object.torseudobody weight value[step.associated body part]) As can be seen from the formula, the load level corresponding to each cooking step in the current initial recipe, the associated torso position corresponding to each cooking step, and the torso position weight value corresponding to the associated torso position of the target object are determined separately. The step load of each step is then calculated, and the total load of the current initial recipe is obtained by summing them up. Since the torso position weight value corresponding to the torso position without restrictions during the cooking process is 0, the step load of the steps with restricted torso positions of the target object during the cooking process can be calculated only, and the total load of the current initial recipe can be obtained by summing them up.

[0063] Next, the step load of each cooking step is filtered to obtain the maximum single-step load. Finally, different weight values ​​are assigned to the total load and the maximum single-step load to calculate the current load fit of the current recipe. The formula for calculating the current load fit is as follows: Current load fit = 1 / (Total load × 0.7 + Maximum single-step load × 0.3) As can be seen, a weight value of 0.7 is assigned to the total load, and a weight value of 0.3 is assigned to the maximum single-step load, thereby calculating the current load fit of the current initial recipe. By combining the total load and the maximum single-step load of the current initial recipe to calculate the current load fit, the risks of chronic strain and acute injury are taken into account, and the feasibility of the recipe is reasonably assessed. This provides the target audience with the most suitable recipe, enabling them to alleviate fatigue and improve physical comfort during the cooking process.

[0064] S109: Determine the current recipe score of the current initial recipe based on the current health matching degree and the current load adaptability degree.

[0065] In the embodiments of this specification, different weight values ​​are assigned to the current health matching degree and the current load adaptability, and then the current recipe score of the current initial recipe is calculated based on the current health matching degree, the weight value corresponding to the current health matching degree, the current load adaptability, and the weight value corresponding to the current load adaptability.

[0066] In this embodiment of the specification, the current recipe score of the current initial recipe is determined based on the current health matching degree and the current load adaptability of the current initial recipe, such as... Figure 5 As shown, Figure 5 A flowchart illustrating a method for determining the current recipe score provided in an embodiment of this specification includes: S501: Determine the first weight value corresponding to the current health matching degree and the second weight value corresponding to the current load adaptability degree.

[0067] In the embodiments of this specification, different weight values ​​are assigned to the current health matching degree and the current load adaptability, namely, a first weight value corresponding to the current health matching degree and a second weight value corresponding to the current load adaptability. For example, under the condition of prioritizing the interception of dangerous actions while taking into account nutrition, the first weight value can be set to 0.4 and the second weight value can be set to 0.6; under the condition of prioritizing nutrition while taking into account safety, the first weight value can be set to 0.7 and the second weight value can be set to 0.3.

[0068] S502: Calculate the product of the current health matching degree and the first weight value to obtain the health score of the current initial recipe.

[0069] In the embodiments of this specification, the product of the current health matching degree and the first weight value is calculated to obtain the health score of the current initial recipe.

[0070] S503: Calculate the product of the current load fit and the second weight value to obtain the load score of the current initial recipe.

[0071] In the embodiments of this specification, the product of the current load fit and the second weight value is calculated to obtain the load score of the current initial recipe.

[0072] S504: Calculate the sum of the health score and the load score of the current initial recipe to obtain the current recipe score of the current initial recipe.

[0073] In the embodiments of this specification, the sum of the health score and the load score of the current initial recipe is calculated to obtain the current recipe score. By assigning different weight values ​​to the current health matching degree and the current load adaptability degree, the nutritional needs of the target group and the avoidance of dangerous actions are combined to determine the recipe score, so that the feasibility of the recipe can be evaluated based on the recipe score. This realizes the creation of zero-risk self-adaptive recipes for sensitive groups.

[0074] S111: Determine the target recipe based on the recipe score of each initial recipe.

[0075] In the embodiments of this specification, the initial recipe with the highest recipe score is selected as the candidate recipe based on the recipe score of each initial recipe, and the candidate recipe is updated based on the target torso position of the target object to finally obtain the target recipe.

[0076] In the embodiments of this specification, the step of determining the target recipe based on the recipe score of each initial recipe is as follows: Figure 6 As shown, Figure 6 A flowchart illustrating a method for determining a target recipe provided in an embodiment of this specification includes: S601: Based on the recipe score of each initial recipe, determine candidate recipes; the candidate recipes include at least two candidate cooking steps.

[0077] In the embodiments of this specification, there may be one or more candidate recipes; when there is one candidate recipe, the initial recipe with the highest recipe score among each initial recipe is selected as the candidate recipe based on the recipe score of each initial recipe, and the candidate recipe includes at least two candidate cooking steps; when there are multiple candidate recipes, a preset number of recipes with higher scores in the initial recipe set are selected as candidate recipes.

[0078] S602: Search the step part relationship library for the torso position that matches the current candidate cooking step to obtain the current candidate torso position; the step part relationship library includes the mapping relationship between preset cooking steps and preset torso positions; the current candidate cooking step is any one of the candidate cooking steps in the candidate recipe.

[0079] In the embodiments of this specification, the step-part relationship database can be a formula, a table, or other form, but all include a mapping relationship between preset cooking steps and preset torso parts. If the step-part relationship database is a table, it can be as follows: Figure 1 As shown, the torso position that matches the cooking step is directly searched in the table. For each candidate recipe, each candidate cooking step is traversed sequentially. For the current candidate cooking step, the torso position that matches the current candidate step is searched in the step part relation database to obtain the current candidate torso position.

[0080] S603: If the current candidate torso position is the target torso position, determine the current candidate cooking step as the target candidate cooking step.

[0081] In the embodiments of this specification, if the current candidate torso position is the target torso position, the current candidate cooking step is determined to be the target candidate cooking step.

[0082] S604: Update the target candidate cooking steps to obtain the updated cooking steps.

[0083] In the embodiments of this specification, if the target torso position is prohibited from use, that is, the weight value of the torso position corresponding to the target torso position is 1, the target candidate cooking step is deleted and its cooking action is replaced with the automated action of the device. Specifically, as shown in Table 2, Table 2 is a mapping table of cooking action-associated body part-alternative solution-prohibition reminder.

[0084] Table 2. Mapping Table of Cooking Actions - Associated Body Parts - Alternatives - Contraindications

[0085] As can be seen from Table 2, for example, if the cooking action corresponding to the target candidate cooking step is tossing the wok, and the target object is a patient with frozen shoulder, that is, the weight value of the torso position corresponding to the wrist, shoulder and core muscle group in the torso position of the target object is 1, then the target candidate step is deleted from the candidate recipe and updated to use a non-stick pan without tossing and an intelligent stir-fry machine for automatic stir-frying.

[0086] S605: Determine the target recipe based on the remaining candidate cooking steps in the candidate recipes and the updated cooking steps; the remaining candidate cooking steps are the cooking steps in the candidate recipes other than the target candidate cooking steps.

[0087] In the embodiments of this specification, when there is one candidate recipe, the cooking steps in the candidate recipe other than the target candidate cooking steps are collectively referred to as the remaining candidate cooking steps, which are candidate cooking steps that do not need to be updated. After the target candidate cooking steps are updated, the remaining candidate cooking steps and the updated cooking steps are combined, and all cooking steps are reordered to automatically arrange the timing of the cooking steps to obtain the target recipe. That is, the pre-optimization of the candidate recipe has been completed at this time, and the target object will use the target recipe for cooking. When there are multiple candidate recipes, the recipes are filtered according to the cooking time of the recipes after pre-optimization, and the recipe with the shortest cooking time is selected as the target recipe.

[0088] Simultaneously, during subsequent cooking, the load of the current step in the cooking process is monitored in real time to determine whether it exceeds the target object's real-time tolerance capacity. The target object's real-time tolerance capacity can be 80% of its daily tolerance threshold. If the current step load exceeds this capacity, the current cooking step is dynamically downgraded, generating a simplified version. For example, shredded pork with garlic sauce is downgraded to a no-stir-fry version, skipping non-core steps such as decorative knife work. After downgrading, a downgrading completion message is generated and pushed to the target device. For example, this could be "Target object fatigue detected, subsequent steps simplified: skip step X, enable device Y." The load of each cooking step is continuously monitored until cooking is complete. At this point, the optimal recipe is generated and stored. Candidate recipes are selected based on recipe scores to obtain recipes suitable for the target object. These candidate recipes are then pre-optimized to shorten cooking time, improve cooking efficiency, alleviate target object fatigue during cooking, and enhance cooking comfort.

[0089] In the embodiments of this specification, after determining the target recipe based on the recipe score of each initial recipe, as follows: Figure 7 As shown, Figure 7 This is a flowchart illustrating a method for generating motion prompt information provided in an embodiment of this specification. The method further includes: S701: During the process of the target object cooking based on the target recipe, the real-time posture of the target object is acquired by the image acquisition device in the kitchen.

[0090] In the embodiments of this specification, the image acquisition device can be a camera or other visual sensor. During the process of the target object cooking based on the target recipe, the image acquisition device in the kitchen captures real-time kitchen images, and a preset algorithm is used to analyze the real-time kitchen images. The preset algorithm can be the OpenPose algorithm to obtain the real-time pose of the target object.

[0091] S702: If the real-time posture meets the preset conditions, obtain the duration of the real-time posture and the real-time torso position weight value corresponding to the real-time posture.

[0092] In the embodiments of this specification, the preset condition is an undesirable posture, that is, a posture that will cause fatigue to the target object. For example, it can be a head tilted forward for more than 15° for 1 minute. If the real-time posture meets the preset condition, that is, the real-time posture is an undesirable posture, the duration of the real-time posture and the real-time torso position weight value corresponding to the real-time posture are obtained.

[0093] S703: Determine the real-time fatigue value of the target object based on the duration of the real-time posture and the real-time torso position weight value.

[0094] In the embodiments of this specification, the posture of the target object is obtained throughout the cooking process, and when there is an undesirable posture, the duration of each undesirable posture and the torso position weight value corresponding to that undesirable posture are obtained. First, the product of the duration of the real-time posture and the real-time torso position weight value is calculated to obtain the fatigue level of a single undesirable posture. Then, the sum of the fatigue values ​​of each undesirable posture of the target object from the start of cooking until the current detection time is calculated to obtain the real-time fatigue value of the target object.

[0095] S704: If the real-time fatigue value is greater than the preset fatigue threshold, generate a motion prompt message.

[0096] In the embodiments of this specification, the preset fatigue threshold is based on the individual user and the preset fatigue threshold is different for different users. If the real-time fatigue value is greater than the preset fatigue threshold, a movement prompt message is generated. The movement prompt message can be generated based on multimodal feedback data. For example, when the target user is continuously stir-frying, if the real-time fatigue value is detected to be greater than the preset fatigue threshold and the pressure sensor on the spatula detects a decreasing trend in grip strength, a movement prompt message is generated five seconds in advance and broadcast via voice. At this time, the movement prompt message can be "Stir-frying is about to be completed, and it is recommended to stretch your fingers next." When the real-time fatigue value is greater than the preset fatigue threshold, the movement prompt message can be inserted into the steps of the target recipe. At this time, the movement prompt message can be "Within 3 minutes of waiting for the water to boil, please follow the screen to do neck lateral flexion stretches." In addition, the target user can use a smart spatula with resistance adjustment to provide progressive muscle strength training during the stirring process, which can be used for hand rehabilitation of Parkinson's patients. Simultaneously, the generation of motion prompts can be based on the torso position of the poor posture and the cooking scenario. For example, if the target object's poor posture is in the lower back, motion prompts can be generated during the stewing / cooking waiting period. These prompts could include, for example, suggesting a cat-cow stretch using a chair when the target object is pregnant, while avoiding excessive lumbar rotation; and recommending pelvic floor muscle training, such as Kegel exercises, in ordinary scenarios other than the stewing / cooking waiting period, while avoiding supine exercises. If the target object's poor posture is in the shoulders, motion prompts can be generated after the target object washes dishes. These prompts could include recommending wall angel exercises to improve rounded shoulders, and prohibiting external rotation for patients with rotator cuff injuries; and suggesting a prone elbow support stretch instead of standing stretches for patients with lumbar disc herniation. Furthermore, the kitchen system can be equipped with a cooking-motion co-optimization model, using motion prompts as a negative load to offset the consumption of cooking movements, thereby ensuring that the target object's total load is less than or equal to their daily tolerance threshold. By identifying poor postures and dynamically calculating the cumulative fatigue of the target user, the system achieves real-time assessment of the target user's fatigue level. When the real-time fatigue value exceeds a preset fatigue threshold, it generates exercise prompts, which not only enables personalized exercise recommendations but also alleviates the target user's fatigue during the cooking process and improves the target user's physical comfort.

[0097] In one exemplary implementation, such as Figure 8 As shown, Figure 8 A flowchart illustrating a recipe selection and cooking method provided for embodiments of this specification includes: S801: User inputs body data.

[0098] In the embodiments of this specification, the user actively inputs body data, including the torso parts that the user is uncomfortable, thereby determining the torso part weight value of the uncomfortable torso parts.

[0099] S802: Initial screening of recipes.

[0100] In the embodiments of this specification, there are multiple recipes. The total load of each recipe is calculated based on the load level of each cooking step in the recipe and the weight value of the unsuitable torso position. The recipes are then initially screened based on the total load of the recipes and the health matching degree of the recipes to obtain candidate recipes. There can be one or more candidate recipes.

[0101] S803: Recipe pre-optimization.

[0102] In the embodiments of this specification, candidate recipes are pre-optimized, specifically by replacing the cooking steps of the candidate recipes and rearranging parallel steps to reduce the total time consumed by the recipes.

[0103] S804: Generate a pre-optimized recipe list.

[0104] In the embodiments of this specification, a pre-optimized recipe list can be generated based on the pre-optimized recipe.

[0105] S805: User selects a recipe.

[0106] In the embodiments described in this specification, the user selects the desired recipe from the pre-optimized recipe list to obtain the target recipe.

[0107] S806: Dynamic optimization of recipes.

[0108] In the embodiments of this specification, the target recipe is dynamically optimized during the cooking process. Specifically, the steps of the target recipe can be dynamically downgraded.

[0109] S807: Real-time monitoring.

[0110] In the embodiments described in this specification, the user's real-time posture is monitored during the cooking process.

[0111] S808: Real-time feedback and exercise recommendations.

[0112] In the embodiments described in this specification, motion recommendations are made based on real-time feedback of detected postures.

[0113] In this embodiment, recipes are initially screened for specific users to obtain recipes suitable for the current user. Then, the recipes are pre-optimized to shorten cooking time and prevent the current user from performing dangerous actions. The current user selects from the pre-optimized recipes to obtain target recipes. Cooking is then carried out based on the target recipes, and the target recipes are dynamically optimized during the cooking process. This improves the automation performance of cooking and monitors the current user's poor posture in real time, generating timely exercise prompts and recommending exercises to effectively alleviate the current user's fatigue and improve the current user's physical comfort.

[0114] This instruction manual also provides a device for determining the target recipe, such as... Figure 9 As shown, the device includes: The first acquisition module 901 is used to acquire, in response to the cooking instructions of the target object, an initial recipe set corresponding to the target object, the target health information of the target object, and an initial torso position; the initial recipe set includes at least two initial recipes; the initial torso position is the torso position of the target object that undergoes deformation during the cooking process; The second acquisition module 902 is used to sequentially traverse each initial recipe and, for the current initial recipe, acquire the current object's health information, current torso position, and current recipe load level. The current health matching degree determination module 903 is used to perform health information matching processing on the target health information and the current object health information to obtain the current health matching degree of the current initial recipe; The current load adaptability determination module 904 is used to determine the current load adaptability of the current initial recipe based on the initial torso position, the current torso position corresponding to the current initial recipe, and the load level of the current recipe. The current recipe score determination module 905 is used to determine the current recipe score of the current initial recipe based on the current health matching degree and the current load adaptability of the current initial recipe; The target recipe determination module 906 is used to determine the target recipe based on the recipe score of each initial recipe.

[0115] In some embodiments, the second acquisition module further includes: The first acquisition submodule is used to sequentially traverse each initial recipe, and for the current initial recipe that is traversed, to acquire the current object health information of the current initial recipe; the current initial recipe includes at least two cooking steps; The second acquisition submodule is used to sequentially traverse each cooking step in the current initial recipe, and for the current cooking step that has been traversed, to acquire the torso position and the initial step load level corresponding to the current cooking step. The real-time heart rate value acquisition submodule is used to acquire the real-time heart rate value of the target object; The updated step load level determination submodule is used to update the initial step load level if the real-time heart rate value is greater than the preset heart rate value, so as to obtain the updated step load level. The current recipe load level determination submodule is used to determine the current recipe load level based on the updated step load level corresponding to each cooking step. The current torso position determination submodule is used to determine the current torso position based on the torso positions corresponding to each cooking step.

[0116] In some embodiments, the apparatus further includes: The third acquisition module is used to acquire the torso weight value corresponding to each torso part of the target object and the historical recipes corresponding to the target object; the torso weight value represents the sensitivity of the torso part of the target object during the cooking process; The target object cooking information determination module is used to determine the target object cooking information based on the torso position weight value corresponding to each torso position and the historical recipes corresponding to the target object. The actual torso position weight value determination module is used to input the cooking information of the target object into the torso position weight value prediction model to perform torso position weight value prediction processing, and obtain the actual torso position weight value corresponding to each torso position. The trunk weight value relation library construction module is used to construct a trunk weight value relation library based on the mapping relationship between each trunk position and the actual trunk position weight value corresponding to each trunk position.

[0117] In some embodiments, the current load adaptability determination module further includes: The target torso position determination submodule is used to determine the target torso position based on the current torso position corresponding to the current initial recipe and the initial torso position; The target torso position weight value determination submodule is used to search for the torso position weight value that matches the target torso position in the torso weight value relation library, and obtain the target torso position weight value; The current load fit determination submodule is used to determine the current load fit of the current initial recipe based on the target torso position weight value and the current recipe load level.

[0118] In some embodiments, the target recipe determination module further includes: The candidate recipe determination submodule is used to determine candidate recipes based on the recipe score of each initial recipe; the candidate recipes include at least two candidate cooking steps; The current candidate torso position determination submodule is used to search for the torso position that matches the current candidate cooking step in the step part relation library to obtain the current candidate torso position; the step part relation library includes a preset mapping relationship between cooking steps and preset torso positions; the current candidate cooking step is any one of the candidate cooking steps in the candidate recipe. The target candidate cooking step determination submodule is used to determine the current candidate cooking step as the target candidate cooking step if the current candidate torso position is the target torso position; The updated cooking step determination submodule is used to update the target candidate cooking steps to obtain the updated cooking steps; The target recipe determination submodule is used to determine the target recipe based on the remaining candidate cooking steps in the candidate recipes and the updated cooking steps; the remaining candidate cooking steps are the cooking steps in the candidate recipes other than the target candidate cooking steps.

[0119] In some embodiments, the apparatus further includes: The real-time posture acquisition module is used to acquire the real-time posture of the target object captured by the image acquisition device in the kitchen during the process of the target object cooking based on the target recipe. The fourth acquisition module is used to acquire the duration of the real-time posture and the real-time torso position weight value corresponding to the real-time posture if the real-time posture meets the preset conditions. The real-time fatigue value determination module is used to determine the real-time fatigue value of the target object based on the duration of the real-time posture and the real-time torso position weight value. The exercise prompt information generation module is used to generate exercise prompt information if the real-time fatigue value is greater than a preset fatigue threshold.

[0120] In some embodiments, the current recipe score determination module further includes: The weight value determination submodule is used to determine a first weight value corresponding to the current health matching degree and a second weight value corresponding to the current load adaptability degree; The health score determination submodule is used to calculate the product of the current health matching degree and the first weight value to obtain the health score of the current initial recipe. The load score determination submodule is used to calculate the product of the current load adaptability and the second weight value to obtain the load score of the current initial recipe; The current recipe score determination submodule is used to calculate the sum of the health score and the load score of the current initial recipe to obtain the current recipe score of the current initial recipe.

[0121] The apparatus and method embodiments described herein are based on the same inventive concept.

[0122] This specification provides an electronic device including a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the method for determining a target recipe as provided in the above method embodiments.

[0123] Embodiments of this application also provide a computer storage medium, which can be disposed in a terminal to store at least one instruction or at least one program related to implementing a method for determining a target recipe in the method embodiment. The at least one instruction or at least one program is loaded and executed by the processor to implement the method for determining a target recipe provided in the above method embodiment.

[0124] Embodiments of this application also provide an intelligent kitchen system that executes a method for determining a target recipe as described in the above-described method embodiments.

[0125] Embodiments of this application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method for determining the target recipe provided in the above-described method embodiments.

[0126] The memory described in the embodiments of this specification can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for the functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0127] The method for determining the target recipe provided in the embodiments of this specification can be executed on a mobile terminal, computer terminal, server, or similar computing device. Taking running on a server as an example, Figure 10 This is a hardware structure block diagram of a server for a method of determining a target recipe provided in an embodiment of this specification. For example... Figure 10 As shown, the server 1000 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 1010 (CPUs 1010 may include, but are not limited to, microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 1030 for storing data, and one or more storage media 1020 (e.g., one or more mass storage devices) for storing application programs 1023 or data 1022. The memory 1030 and storage media 1020 may be temporary or persistent storage. The program stored in the storage media 1020 may include one or more modules, each module may include a series of instruction operations on the server. Furthermore, the CPU 1010 may be configured to communicate with the storage media 1020 and execute the series of instruction operations in the storage media 1020 on the server 1000. Server 1000 may also include one or more power supplies 1060, one or more wired or wireless network interfaces 1050, one or more input / output interfaces 1040, and / or one or more operating systems 1021, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0128] The input / output interface 1040 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of server 1000. In one example, the input / output interface 1040 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 1040 may be a radio frequency (RF) module used for wireless communication with the Internet.

[0129] Those skilled in the art will understand that Figure 10 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, server 1000 may also include... Figure 10 The more or fewer components shown, or having the same Figure 10 The different configurations shown.

[0130] As can be seen from the embodiments of the target recipe determination method, apparatus, electronic device, and intelligent kitchen system provided in this application, this application, in response to the cooking instruction of the target object, obtains the initial recipe set corresponding to the target object, the target health information of the target object, and the initial torso position; the initial recipe set includes at least two initial recipes; the initial torso position is the torso position of the target object that deforms during cooking; each initial recipe is traversed sequentially, and for the current initial recipe, the current object health information, the current torso position, and the current recipe load level of the current initial recipe are obtained; health information matching processing is performed on the target health information and the current object health information to obtain the current health matching degree of the current initial recipe; the current load adaptability of the current initial recipe is determined according to the initial torso position, the current torso position corresponding to the current initial recipe, and the current recipe load level; the current recipe score of the current initial recipe is determined according to the current health matching degree and the current load adaptability; and the target recipe is determined according to the recipe score of each initial recipe. The recipe score for the initial recipe is calculated by combining the health fit of the initial recipe with the total load, taking into account the user's nutritional needs and safety factors. This helps to recommend suitable recipes for people with sensitive body movements. The target recipe is dynamically optimized during the user's cooking process, reducing cooking intensity, shortening cooking time, and improving cooking efficiency. By providing exercise recommendations for users, it helps to alleviate user fatigue and improve user physical comfort during the cooking process.

[0131] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0132] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0133] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer storage medium, such as a read-only memory, a disk, or an optical disk.

[0134] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining a target recipe, characterized in that, The method includes: In response to a cooking instruction for a target object, the system acquires an initial recipe set corresponding to the target object, the target object's target health information, and an initial torso position; the initial recipe set includes at least two initial recipes; the initial torso position is the torso position of the target object that undergoes deformation during the cooking process. Iterate through each initial recipe in turn, and for the current initial recipe, obtain the current object's health information, current torso position, and current recipe load level; The target health information and the current object health information are matched to obtain the current health matching degree of the current initial recipe. The current load fit of the current initial recipe is determined based on the initial torso position, the current torso position corresponding to the current initial recipe, and the load level of the current recipe. The current recipe score is determined based on the current health matching degree and the current load adaptability of the current initial recipe. The target recipe is determined based on the recipe score of each initial recipe.

2. The method according to claim 1, characterized in that, The process of sequentially traversing each initial recipe, and for the current initial recipe, obtaining the current object's health information, current torso position, and current recipe load level, includes: Each initial recipe is traversed sequentially. For the current initial recipe, the health information of the current object in the current initial recipe is obtained. The current initial recipe includes at least two cooking steps. Iterate through each cooking step in the current initial recipe, and for the current cooking step, obtain the torso position and initial step load level corresponding to the current cooking step. Obtain the real-time heart rate value of the target object; If the real-time heart rate value is greater than the preset heart rate value, the initial step load level is updated to obtain the updated step load level. The current recipe load level is determined based on the updated step load level corresponding to each cooking step. The current torso position is determined based on the torso position corresponding to each cooking step.

3. The method according to claim 1, characterized in that, Before sequentially traversing each initial recipe and, for the current initial recipe, obtaining the current object's health information, current torso position, and current recipe load level, the method further includes: Obtain the torso weight value corresponding to each torso part of the target object and the historical recipes corresponding to the target object; the torso weight value represents the sensitivity of the torso part of the target object during the cooking process; Based on the torso position weight value corresponding to each torso position and the historical recipes corresponding to the target object, the cooking information of the target object is determined; The cooking information of the target object is input into the torso position weight value prediction model to perform torso position weight value prediction processing, so as to obtain the actual torso position weight value corresponding to each torso position. Based on the mapping relationship between each torso position and the actual torso position weight value corresponding to each torso position, a torso weight value relationship library is constructed.

4. The method according to claim 3, characterized in that, The step of determining the current load fit of the current initial recipe based on the initial torso position, the current torso position corresponding to the current initial recipe, and the load level of the current recipe includes: Determine the target torso position based on the current torso position corresponding to the current initial recipe and the initial torso position; Search the trunk weight value database for the trunk position weight value that matches the target trunk position to obtain the target trunk position weight value; The current load fit of the current initial recipe is determined based on the target torso weight value and the current recipe load level.

5. The method according to claim 4, characterized in that, The step of determining the target recipe based on the recipe score of each initial recipe includes: Based on the recipe score of each initial recipe, candidate recipes are determined; each candidate recipe includes at least two candidate cooking steps. The current candidate torso position is obtained by searching the step part relationship library for the torso position that matches the current candidate cooking step; the step part relationship library includes a preset mapping relationship between cooking steps and preset torso positions; the current candidate cooking step is any one of the candidate cooking steps in the candidate recipe. If the current candidate torso position is the target torso position, then the current candidate cooking step is determined to be the target candidate cooking step; The target candidate cooking steps are updated to obtain the updated cooking steps; The target recipe is determined based on the remaining candidate cooking steps in the candidate recipes and the updated cooking steps; the remaining candidate cooking steps are the cooking steps in the candidate recipes other than the target candidate cooking steps.

6. The method according to claim 1, characterized in that, After determining the target recipe based on the recipe score of each initial recipe, the method further includes: During the process of the target object cooking based on the target recipe, the real-time posture of the target object is acquired by an image acquisition device in the kitchen; If the real-time posture meets the preset conditions, obtain the duration of the real-time posture and the real-time torso position weight value corresponding to the real-time posture. The real-time fatigue value of the target object is determined based on the duration of the real-time posture and the real-time torso position weight value. If the real-time fatigue value is greater than the preset fatigue threshold, an exercise prompt message is generated.

7. The method according to claim 1, characterized in that, The step of determining the current recipe score of the current initial recipe based on the current health matching degree and the current load adaptability includes: Determine a first weight value corresponding to the current health matching degree and a second weight value corresponding to the current load adaptability degree; Calculate the product of the current health matching degree and the first weight value to obtain the health score of the current initial recipe; Calculate the product of the current load fit and the second weight value to obtain the load score of the current initial recipe; The sum of the health score and the load score of the current initial recipe is calculated to obtain the current recipe score.

8. A device for determining a target recipe, characterized in that, The device includes: The first acquisition module is used to acquire, in response to the cooking instructions of the target object, an initial recipe set corresponding to the target object, the target health information of the target object, and an initial torso position; the initial recipe set includes at least two initial recipes; the initial torso position is the torso position of the target object that undergoes deformation during the cooking process; The second acquisition module is used to sequentially traverse each initial recipe and, for the current initial recipe, acquire the current object's health information, current torso position, and current recipe load level. The current health matching degree determination module is used to perform health information matching processing on the target health information and the current object health information to obtain the current health matching degree of the current initial recipe; The current load adaptability determination module is used to determine the current load adaptability of the current initial recipe based on the initial torso position, the current torso position corresponding to the current initial recipe, and the load level of the current recipe. The current recipe score determination module is used to determine the current recipe score of the current initial recipe based on the current health matching degree and the current load adaptability of the current initial recipe; The target recipe determination module is used to determine the target recipe based on the recipe score of each initial recipe.

9. An electronic device, characterized in that, The device includes a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded by the processor and executed as described in any one of claims 1-7 to determine the target recipe.

10. An intelligent kitchen system, characterized in that, The intelligent kitchen system is used to perform the method for determining the target recipe as described in any one of claims 1-7.

Images