Healthy recipe adjusting method and device, equipment and storage medium

Abstract

The invention belongs to the technical field of information, and particularly relates to a healthy recipe adjusting method and device, equipment and a storage medium, and the method comprises the steps: determining the physical characteristics of a user, inputting the preference information of the user and the physical characteristics into a pre-trained recipe recommendation model, and obtaining a recommended recipe output by the recipe recommendation model; obtaining feedback information of the recommended recipe, wherein the feedback information comprises first image data, first sound data and first physiological data after the user diets according to the recommended recipe; according to the feedback information, the health index change degree of the user is determined based on the feedback information, and the recommended recipe is adjusted under the condition that the health index change degree does not reach the preset condition, so that the recommended recipe used by the user can be dynamically adjusted along with the actual body condition of the user, and the body health of the user is continuously promoted.

Description

Technical Field

[0001] This application belongs to the field of information technology, and particularly relates to a method, device, equipment, and storage medium for adjusting a healthy diet recipe. Background Art

[0002] With the development of science and technology and the improvement of people's living standards, people's attention to health preservation and health management is increasing day by day. More and more users will use smart wearable devices and health management applications in their daily lives to help themselves with health monitoring and diet management.

[0003] Users can monitor their health indicators, such as pulse, blood pressure, and blood oxygen, through the detection device of the smart wearable device, view these health indicators through the corresponding health management application, and can also learn health preservation diet knowledge by reading the regularly updated content in the health management application.

[0004] However, it is difficult for users to accurately determine their physical conditions and promptly adopt a health preservation diet recipe suitable for their physical conditions only by viewing health indicators and health preservation diet knowledge, resulting in insufficient pertinence and timeliness of the user's diet recipe and poor health management effect. Summary of the Invention

[0005] This application provides a method, device, equipment, and storage medium for adjusting a healthy diet recipe to solve the problems of insufficient pertinence and timeliness of users' self-determined healthy diet recipes and poor health management effects.

[0006] In a first aspect, this application provides a method for adjusting a healthy diet recipe, and the method includes:

[0007] Determine the physical characteristics of the user, and input the user's preference information and the physical characteristics into a pre-trained diet recipe recommendation model to obtain a recommended diet recipe output by the diet recipe recommendation model;

[0008] Obtain feedback information of the recommended diet recipe, where the feedback information includes: first image data, first sound data, and first physiological data after the user eats according to the recommended diet recipe;

[0009] Based on the feedback information, determine the degree of change in the user's health index, and adjust the recommended diet recipe when the degree of change in the health index does not meet the preset conditions.

[0010] In a possible design, the determining the physical characteristics of the user includes:

[0011] Obtain second image data, second sound data, and second physiological data of the user before eating according to the recommended diet recipe;

[0012] Determine the physical characteristics of the user according to the second image data, the second sound data, and the second physiological data.

[0013] In a possible design, the method further includes:

[0014] According to the second physiological data and a preset mapping relationship between different physiological data and different health levels, determine the health index corresponding to the second physiological data as the health index of the user.

[0015] In a possible design, the determining the degree of change in the health index of the user based on the feedback information includes:

[0016] Determine an updated health index according to the feedback information;

[0017] According to the health index and the updated health index, determine the degree of change in the health index of the user, where the degree of change in the health index is the difference between the updated health index and the health index;

[0018] After determining the degree of change in the health index of the user, the method further includes:

[0019] Judge whether the degree of change in the health index is greater than a first threshold, where the first threshold is a positive number;

[0020] If so, determine that the degree of change in the health index reaches a preset condition;

[0021] If not, determine that the degree of change in the health index does not reach a preset condition.

[0022] In a possible design, the adjusting the recommended recipe includes:

[0023] In the case where the degree of change in the health index does not meet the physical type change condition, adjust the recommended recipe according to the feedback information and the degree of change in the health index, where the physical type change condition includes: the degree of change in the health index is less than or equal to a second threshold, and the second threshold is a negative number;

[0024] In the case where the degree of change in the health index meets the physical type change condition, obtain an updated physical type according to the feedback information and the degree of change in the health index, and adjust the recommended recipe according to the updated physical type.

[0025] In a possible design, adjusting the recommended recipe according to the feedback information and the degree of change in the health index includes:

[0026] Calculate a recipe recommendation reward value according to the feedback information and the degree of change in the health index;

[0027] Update the parameters of the recipe recommendation model according to the recipe recommendation reward value to obtain an updated recipe recommendation model;

[0028] Input the preference information and the physical characteristics into the updated recipe recommendation model, and obtain an adjusted recommended diet plan output by the updated recipe recommendation model.

[0029] In a possible design, the obtaining the updated physical type and adjusting the recommended recipe according to the updated physical type includes:

[0030] Calculate a physical classification reward value according to the feedback information and the degree of change in the health index;

[0031] Update the parameters of the physical classification model according to the physical classification reward value to obtain an updated physical classification model;

[0032] Input the feedback information into the updated physical classification model, and obtain updated physical characteristics output by the updated physical classification model;

[0033] Input the preference information and the updated physical characteristics into the recipe recommendation model, and obtain an adjusted recommended recipe output by the recipe recommendation model.

[0034] In a second aspect, the present application provides a recipe adjustment device, and the device includes:

[0035] A determination module, configured to determine the physical characteristics of a user, and input the preference information and the physical characteristics of the user into a pre-trained recipe recommendation model to obtain a recommended recipe output by the recipe recommendation model;

[0036] An acquisition module, configured to acquire feedback information of the recommended recipe, where the feedback information includes: first image data, first voice data, and first physiological data after the user eats according to the recommended recipe;

[0037] An operation module, configured to determine the degree of change in the health index of the user based on the feedback information, and adjust the recommended recipe when the degree of change in the health index does not meet a preset condition.

[0038] In a third aspect, the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0039] The memory stores computer execution instructions;

[0040] The processor executes the computer-executable instructions stored in the memory to implement the method for adjusting a healthy recipe as described in the first aspect.

[0041] In a third aspect, the present application provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method for adjusting a healthy recipe as described in the first aspect when executed by a processor.

[0042] In a fourth aspect, the present application provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method for adjusting a healthy recipe as described in the first aspect when executed by a computer.

[0043] In a fifth aspect, the present application provides a program product including a computer program, which implements the method for adjusting a healthy recipe as described in the first aspect when executed by a processor.

[0044] The method, device, equipment, and storage medium for adjusting a healthy recipe provided by the present application determine the physical characteristics of a user, input the preference information and physical characteristics of the user into a pre-trained recipe recommendation model, and obtain a recommended recipe output by the recipe recommendation model; obtain feedback information of the recommended recipe, where the feedback information includes: first image data, first sound data, and first physiological data after the user eats according to the recommended recipe; based on the feedback information, determine the degree of change in the user's health index, and adjust the recommended recipe when the degree of change in the health index does not meet a preset condition, thus realizing that the recommended recipe used by the user can be dynamically adjusted according to the user's actual physical condition, and continuously promoting the user's physical health. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0046] Figure 1 Schematic flowchart of the method for adjusting a healthy recipe provided by an embodiment of the present application Figure 1 ;

[0047] Figure 2 Schematic flowchart of the method for adjusting a healthy recipe provided by an embodiment of the present application Figure 2 ;

[0048] Figure 3 Schematic structural diagram of a recipe adjustment device provided by an embodiment of the present application;

[0049] Figure 4A schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0050] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and more detailed descriptions will be given in the following text. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0051] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts shall fall within the protection scope of the present application.

[0052] With the development of science and technology and the improvement of people's living standards, people's attention to health preservation and health management has been increasing day by day. More and more users will use smart wearable devices and health management applications in their daily lives to help themselves with health monitoring and diet management.

[0053] Users can monitor their health indicators, such as pulse, blood pressure, and blood oxygen, through the detection device of the smart wearable device, view these health indicators through the corresponding health management application, and also learn health preservation diet knowledge by reading the content updated regularly in the health management application.

[0054] However, it is difficult for users to accurately determine their physical conditions and promptly adopt a health preservation diet recipe suitable for their physical conditions only by viewing health indicators and health preservation diet knowledge, resulting in insufficient pertinence and timeliness of the user's diet recipe and poor health management effects.

[0055] In response to the above problems, the present application proposes the following technical concept: before formulating a diet recipe, determine the physical characteristics of the user, input the user's preference information and the physical characteristics into a pre-trained diet recipe recommendation model, and obtain the recommended diet recipe output by the diet recipe recommendation model; after the user has followed the recommended diet recipe for a period of time, obtain the user's image data, voice data, and physiological data as feedback information, and adjust the user's recommended diet recipe according to the feedback information, that is, it is realized that the recommended diet recipe used by the user can be dynamically adjusted according to their actual physical conditions, which plays a continuous promoting role in the user's physical health.

[0056] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. These several specific embodiments below can exist independently or be combined with each other. For the same or similar concepts or processes, they may not be elaborated in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0057] Figure 1 Flow schematic of the adjustment method for the healthy recipe provided by the embodiment of this application Figure 1 As Figure 1 shown, the adjustment method for the healthy recipe provided by the embodiment of this application includes:

[0058] S101: Determine the physical characteristics of the user, and input the preference information and the physical characteristics of the user into a pre-trained recipe recommendation model to obtain the recommended recipe output by the recipe recommendation model.

[0059] Among them, the physical characteristics are multiple preset physical types and their manifestation characteristics. For example, it can be 9 traditional Chinese medicine physical types classified according to traditional Chinese medicine physical theory; the preference information is the individual attribute data of the user. For example, it can include the user's dietary preferences, eating habits, occupation, allergy history, and multiple data such as the season, region, environmental temperature and humidity where the user is located.

[0060] Specifically, the recipe recommendation device determines the physical characteristics of the user according to a preset physical determination algorithm. The physical determination algorithm can, for example, obtain the physical diagnosis result of the user from the corresponding storage location and determine the physical characteristics of the user according to the physical diagnosis result, or can provide a physical questionnaire to the user and determine the physical characteristics of the user according to the survey result of the physical questionnaire and the preset physical determination rules. The embodiment of this application does not make special restrictions on the specific content of the physical determination algorithm; perform data preprocessing on the preference information and physical characteristics of the user, and input the preprocessed preference information and physical characteristics into a pre-trained recipe recommendation model to obtain the recommended recipe output by the recipe recommendation model. The recipe recommendation model is pre-trained through a machine learning algorithm on a large-scale pre-annotated recipe dataset.

[0061] S102: Obtain the feedback information of the recommended recipe.

[0062] Among them, the feedback information includes: the first image data, the first sound data, and the first physiological data after the user has dieted according to the recommended recipe. The first image data, the first sound data, and the first physiological data can all include multiple sets of data corresponding to different moments; the first image data is a picture of a specific part of the user's body obtained through a corresponding image acquisition device. For example, it can include facial photos, tongue photos, and eye photos taken and uploaded by the user using a mobile phone; the first sound data is the audio of the user collected through a corresponding audio acquisition device. For example, it can be a recorded audio of the user's natural voice, cough sound, snoring sound, breathing sound, etc. recorded through a mobile phone; the first physiological data includes various physiological index values of the user read from the corresponding storage location. For example, it can be the various physiological index values in the user's physical examination results and diagnosis and treatment records uploaded by a medical institution, and also includes the physiological parameter data of the user collected by a corresponding intelligent wearable device. For example, it can be various data such as the user's body temperature, heart rate, pulse waveform, and sleep quality collected by an intelligent bracelet.

[0063] Specifically, the recipe adjustment device obtains the feedback information uploaded by various acquisition devices from the corresponding storage location.

[0064] S103: Based on the feedback information, determine the degree of change in the user's health index, and adjust the recommended recipe when the degree of change in the health index does not meet the preset conditions.

[0065] Specifically, the recipe adjustment device determines the degree of change in the user's health index according to the feedback information and a preset calculation algorithm for the degree of change in the health index. The calculation algorithm can be, for example, determining the health index corresponding to each moment based on the first image data, the first sound data, and the first physiological data corresponding to each moment, and then determining the degree of change in the health index based on the health index corresponding to each moment; determining whether the degree of change in the health index meets the preset conditions. The preset conditions can be, for example, that the degree of change in the health index indicates an improvement in the user's health status; when the degree of change in the health index does not meet the preset conditions, adjust the recommended recipe according to a preset recipe adjustment algorithm. The recipe adjustment algorithm can be, for example, determining the user's physical characteristics again. When the user's physical characteristics have changed compared to the previous time, input the user's preference information and the changed physical characteristics into a pre-trained recipe recommendation model to obtain the recommended recipe output by the recipe recommendation model as the adjusted recommended recipe. The specific contents of the calculation algorithm, the preset conditions, and the recipe adjustment algorithm are not particularly limited in the embodiments of the present application.

[0066] The adjustment method of the healthy diet recipe provided by the embodiment of the present application formulates a recommended diet for the user by combining the physical characteristics and preference information of the user, and realizes symptomatic eating on the premise of considering the user's preferences and habits; after the user has eaten according to the recommended diet for a period of time, the user's image data, voice data and physiological data are obtained as feedback information, and according to the feedback information, the recommended diet for the user is adjusted, that is, the recommended diet used by the user can be dynamically adjusted according to the actual physical condition of the user, which plays a continuous promoting role in the user's physical health.

[0067] Figure 2 Schematic flow of the adjustment method of the healthy diet recipe provided by the embodiment of the present application Figure 2 As Figure 2 shown, the adjustment method of the healthy diet recipe provided by the embodiment of the present application includes:

[0068] S201: Obtain the second image data, the second voice data and the second physiological data of the user before eating according to the recommended diet.

[0069] Among them, the second image data, the second voice data and the second physiological data can all include multiple groups of data corresponding to different moments; the second image data is a picture of a specific part of the user's body obtained through a corresponding image acquisition device, for example, it can include the face photo, tongue photo and eye photo taken and uploaded by the user through the mobile phone; the second voice data is the audio of the user collected through a corresponding audio acquisition device, for example, it can be the recorded audio of the user's natural voice, cough sound, snoring sound, breathing sound, etc. recorded through the mobile phone; the second physiological data includes the values of various physiological indexes of the user read from the corresponding storage location, for example, it can be the values of various physiological indexes in the physical examination results and diagnosis and treatment records of the user uploaded by the medical institution, and also includes the physiological parameter data of the user collected by the corresponding intelligent wearable device, for example, it can be the data of the user's body temperature, heart rate, pulse waveform and sleep quality collected by the intelligent bracelet.

[0070] The implementation manner of step S201 is similar to that of step S102, and will not be elaborated here in this embodiment.

[0071] S202: Determine the physical characteristics of the user according to the second image data, the second voice data and the second physiological data.

[0072] Specifically, the recipe adjustment device performs data preprocessing on the second image data, the second voice data and the second physiological data, and inputs the second image data, the second voice data and the second physiological data after data preprocessing into a pre-trained reinforcement learning model, and the reinforcement learning model can be pre-trained through algorithms such as Q-learning algorithm or policy gradient algorithm.

[0073] S203: Input the user's preference information and physical characteristics into a pre-trained recipe recommendation model to obtain the recommended recipes output by the recipe recommendation model.

[0074] The implementation method of step S203 and the implementation method of step S101 will not be elaborated herein in this embodiment.

[0075] S204: According to the second physiological data and the preset mapping relationship between different physiological data and different health levels, determine the health index corresponding to the second physiological data as the user's health index.

[0076] Among them, the health index can be, for example, a health score with a total score of 100 points. The preset mapping relationship can be, for example, a function relationship established in advance with the health score as the dependent variable and the values of each physiological data as the independent variables. For example, the absolute value of the difference between the value of each physiological data and the upper or lower bound of its normal range can be calculated, and the absolute value is negatively correlated with the health score. After weighted summation of the absolute values corresponding to each physiological data, the weighted summation result can be subtracted from the total score of 100 points. That is, when the user's each physiological data is within its normal range, the health score is 100 points, and the more the user's each physiological data deviates from the normal range, the lower the health score.

[0077] S205: Obtain the feedback information of the recommended recipes, and determine the updated health index according to the feedback information.

[0078] Among them, the feedback information includes: the first image data, the first sound data, and the first physiological data after the user eats according to the recommended recipes.

[0079] The implementation method of step S205 is similar to the implementation methods of step S102 and step S204, and will not be elaborated herein in this embodiment.

[0080] S206: Determine the change degree of the user's health index according to the health index and the updated health index.

[0081] Among them, the change degree of the health index is the difference between the updated health index and the health index.

[0082] Specifically, the recipe adjustment device subtracts the health index from the updated health index, and the obtained difference is the change degree of the user's health index.

[0083] S207: Determine whether the change degree of the health index is greater than the first threshold.

[0084] Among them, the first threshold is a positive number, and the first threshold can be, for example, 5.

[0085] S208: If so, determine that the degree of change in the health index reaches a preset condition.

[0086] S209: If not, determine that the degree of change in the health index does not reach the preset condition.

[0087] It can be understood that when the degree of change in the health index is greater than the first threshold, it can be considered that after the user eats according to the recommended recipe, the health condition has improved significantly, and the recipe is more suitable for the user's physical condition. At this time, there is no need to adjust the recipe; on the contrary, the recipe needs to be adjusted.

[0088] S210: In the case where the degree of change in the health index does not reach the preset condition, determine whether the degree of change in the health index meets the physical type change condition.

[0089] Among them, the physical type change condition includes: the degree of change in the health index is less than or equal to a second threshold, and the second threshold is a negative number, for example, it can be -10.

[0090] It can be understood that when the degree of change in the health index is less than or equal to the second threshold, it can be considered that after the user eats according to the recommended recipe, the health condition has not improved but deteriorated, and the degree of deterioration is large. The previously determined physical characteristics of the user may be inaccurate or have changed. At this time, not only does the recipe need to be adjusted, but the physical characteristics of the user also need to be determined again, and a new recommended recipe is formulated according to the updated physical characteristics and feedback information to improve the suitability of the recommended recipe for the user's actual physical condition; when the degree of change in the health index is less than the first threshold and greater than the second threshold, it can be considered that after the user eats according to the recommended recipe, the health condition has not improved but deteriorated, but the degree of deterioration is small. At this time, the recipe can be adjusted according to the feedback information without re-determining the physical characteristics of the user.

[0091] S211: In the case where the degree of change in the health index does not meet the physical type change condition, adjust the recommended recipe according to the feedback information and the degree of change in the health index.

[0092] Optionally, the specific method steps for the recipe adjustment device to adjust the recommended recipe according to the feedback information and the degree of change in the health index can be as follows:

[0093] Step 1: Calculate the recipe recommendation reward value according to the feedback information and the degree of change in the health index.

[0094] Specifically, the recipe adjustment device obtains the degree of change in the indicators of each identical data item of the first physiological data and the second physiological data in the feedback information; according to the degree of change in each indicator and the degree of change in the health index, and in accordance with a preset reward mechanism, calculates a recipe recommendation reward value. The reward mechanism can be, for example, that the reward value for the improved data item is positive, and the reward value for the unimproved data item is negative. The reward value corresponding to each data item is determined according to the mapping relationship between the degree of change in the data item and the reward value set in advance. The embodiments of the present application do not particularly limit the specific content of the reward mechanism.

[0095] Step Two: Update the parameters of the recipe recommendation model according to the recipe recommendation reward value to obtain an updated recipe recommendation model.

[0096] Specifically, the recipe adjustment device updates the parameters of the recipe recommendation model according to the recipe recommendation reward value in accordance with a preset reinforcement learning algorithm to obtain an updated recipe recommendation model. The reinforcement learning algorithm can be, for example, a policy gradient algorithm, an Actor-Critic algorithm, etc. The embodiments of the present application do not particularly limit this.

[0097] Step Three: Input the preference information and the physical characteristics into the updated recipe recommendation model, and obtain an adjusted recommended diet plan output by the updated recipe recommendation model.

[0098] S212: In the case where the degree of change in the health index meets the physical type change condition, obtain an updated physical type according to the feedback information and the degree of change in the health index, and adjust the recommended recipe according to the updated physical type.

[0099] Optionally, the specific method steps for the recipe adjustment device to obtain an updated physical type according to the feedback information and the degree of change in the health index, and adjust the recommended recipe according to the updated physical type can be as follows:

[0100] Step One: Calculate a physical classification reward value according to the feedback information and the degree of change in the health index.

[0101] Specifically, the recipe adjustment device obtains the degree of change in the indicators of each identical data item in the feedback information; according to the degree of change in each indicator and the degree of change in the health index, and in accordance with a preset reward mechanism, calculates a physical classification reward value. The reward mechanism can be, for example, that the reward value for the improved data item is positive, and the reward value for the unimproved data item is negative. The reward value corresponding to each data item is determined according to the mapping relationship between the degree of change in the data item and the reward value set in advance. The embodiments of the present application do not particularly limit the specific content of the reward mechanism.

[0102] Step 2: Update the parameters of the physical constitution classification model according to the physical constitution classification reward value to obtain an updated physical constitution classification model.

[0103] Specifically, the recipe adjustment device updates the parameters of the physical constitution classification model according to the physical constitution classification reward value according to a preset reinforcement learning algorithm to obtain an updated physical constitution classification model. The reinforcement learning algorithm can be, for example, a policy gradient algorithm, an Actor-Critic algorithm, etc. The embodiments of the present application do not make special limitations on this.

[0104] Step 3: Input the feedback information into the updated physical constitution classification model, and obtain the updated physical constitution characteristics output by the updated physical constitution classification model.

[0105] Step 4: Input the preference information and the updated physical constitution characteristics into the recipe recommendation model, and obtain the adjusted recommended recipe output by the recipe recommendation model.

[0106] The method for adjusting a healthy recipe provided by the embodiments of the present application determines the degree of change in the user's health index according to the user's feedback information, and then, according to the degree of change in the user's health index, adopts different recipe adjustment strategies for different situations of the degree of change in the health index, further improving the accuracy of recipe adjustment.

[0107] Figure 3 is a schematic structural diagram of a recipe adjustment device provided by an embodiment of the present application; as Figure 3 shown, the present application provides a recipe adjustment device; the recipe adjustment device 300 provided by the embodiments of the present application includes:

[0108] A determination module 301, configured to determine the physical constitution characteristics of a user, and input the preference information and the physical constitution characteristics of the user into a pre-trained recipe recommendation model to obtain a recommended recipe output by the recipe recommendation model;

[0109] An acquisition module 302, configured to acquire feedback information of the recommended recipe, where the feedback information includes: first image data, first voice data, and first physiological data after the user eats according to the recommended recipe;

[0110] An operation module 303, configured to determine the degree of change in the user's health index based on the feedback information, and adjust the recommended recipe when the degree of change in the health index does not reach a preset condition.

[0111] Optionally, the determining module 301 is specifically configured to obtain second image data, second sound data, and second physiological data of the user before eating according to the recommended recipe; and determine the physical characteristics of the user according to the second image data, the second sound data, and the second physiological data.

[0112] Optionally, the operation module 303 is further configured to determine a health index corresponding to the second physiological data as the health index of the user according to the second physiological data and a preset mapping relationship between different physiological data and different health levels.

[0113] Optionally, the operation module 303 is specifically configured to determine an updated health index according to the feedback information; and determine a change degree of the health index of the user according to the health index and the updated health index, where the change degree of the health index is the difference between the updated health index and the health index.

[0114] The determining module 301 is further configured to determine whether the change degree of the health index is greater than a first threshold, where the first threshold is a positive number; when the change degree of the health index is greater than the first threshold, determine that the change degree of the health index reaches a preset condition; and when the change degree of the health index is less than or equal to the first threshold, determine that the change degree of the health index does not reach the preset condition.

[0115] Optionally, the operation module 303 is specifically configured to adjust the recommended recipe according to the feedback information and the change degree of the health index when the change degree of the health index does not meet the physical type change condition, where the physical type change condition includes: the change degree of the health index is less than or equal to a second threshold, and the second threshold is a negative number; and when the change degree of the health index meets the physical type change condition, obtain an updated physical type according to the feedback information and the change degree of the health index, and adjust the recommended recipe according to the updated physical type.

[0116] Optionally, the operation module 303 is specifically configured to calculate a recipe recommendation reward value according to the feedback information and the change degree of the health index; update parameters of the recipe recommendation model according to the recipe recommendation reward value to obtain an updated recipe recommendation model; and input the preference information and the physical characteristics into the updated recipe recommendation model to obtain an adjusted recommended diet plan output by the updated recipe recommendation model.

[0117] Optionally, the operation module 303 is specifically configured to calculate a physical fitness classification reward value according to the feedback information and the degree of change in the health index; update the parameters of the physical fitness classification model according to the physical fitness classification reward value to obtain an updated physical fitness classification model; input the feedback information into the updated physical fitness classification model, and obtain updated physical characteristics output by the updated physical fitness classification model; input the preference information and the updated physical characteristics into the recipe recommendation model, and obtain an adjusted recommended recipe output by the recipe recommendation model.

[0118] The recipe adjustment device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0119] Figure 4 It is a hardware schematic diagram of an electronic device provided in an embodiment of the present application. As Figure 4 shown, the electronic device 400 provided in this embodiment includes: at least one processor 401 and a memory 402. The electronic device 400 also includes a communication interface 403. Among them, the processor 401, the memory 402, and the communication interface 403 are connected through a bus 404.

[0120] In a specific implementation process, at least one processor 401 executes computer execution instructions stored in the memory 402, so that at least one processor 401 executes the above method for adjusting a healthy recipe.

[0121] The specific implementation process of the processor 401 can be referred to in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0122] In the above Figure 4 shown embodiment, it should be understood that the processor may be a central processing unit (English: Central Processing Unit, abbreviated: CPU), or may also be other general-purpose processors, digital signal processors (English: Digital Signal Processor, abbreviated: DSP), application specific integrated circuits (English: Application SpecificIntegrated Circuit, abbreviated: ASIC), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed and completed by a hardware processor, or executed and completed by a combination of hardware and software modules in the processor.

[0123] The memory may include a random access memory (RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0124] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0125] In addition, this embodiment also provides a computer-readable storage medium, on which a computer program is stored. The computer program is executed by a processor to implement the adjustment method of the healthy recipe in the above embodiment.

[0126] For the above-mentioned computer-readable storage medium, the readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disc. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0127] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0128] The division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0129] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0130] In addition, in each embodiment of the present invention, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0131] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention, in essence, or the part that makes contributions to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks and other various media that can store program codes.

[0132] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When this program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disks, or optical disks and other various media that can store program codes.

[0133] So far, the technical solution of the present application has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solution of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of each embodiment of the present application.

Claims

1. A method for adjusting a healthy diet, characterized in that: The method comprises: Determine the user's physical characteristics, and input the user's preference information and the physical characteristics into a pre-trained recipe recommendation model to obtain a recommended recipe output by the recipe recommendation model; Acquiring feedback information of the recommended recipe, the feedback information comprising: first image data, first sound data, and first physiological data after the user eats according to the recommended recipe; Based on the feedback information, the degree of change of the user's health index is determined, and if the degree of change of the health index does not reach a preset condition, the recommended recipe is adjusted.

2. The method according to claim 1, characterized in that Determining the user's physical characteristics includes: Acquiring second image data, second sound data, and second physiological data of the user before eating according to the recommended recipe; The user's physical characteristics are determined based on the second image data, the second sound data, and the second physiological data.

3. The method according to claim 2, characterized in that The method further comprises: According to the second physiological data and a preset mapping relationship between different physiological data and different health levels, a health index corresponding to the second physiological data is determined as the health index of the user.

4. The method according to claim 3, characterized in that The determining, based on the feedback information, a degree of change in the user's health index comprises: Determining an updated health index according to the feedback information; Determining a degree of change in the user's health index according to the health index and the updated health index, wherein the degree of change in the health index is a difference between the updated health index and the health index; After determining the degree of change of the user's health index, the method further includes: Determine whether the degree of change of the health index is greater than a first threshold, where the first threshold is a positive number; If so, determining that the degree of change in the health index reaches a preset condition; If not, it is determined that the degree of change of the health index does not meet the preset condition.

5. The method according to claim 3, characterized in that: The adjusting of the recommended recipe comprises: In the case where the degree of change of the health index does not meet the condition for changing the physical type, adjusting the recommended recipe according to the feedback information and the degree of change of the health index, the condition for changing the physical type includes: the degree of change of the health index is less than or equal to a second threshold value, and the second threshold value is a negative number; When the degree of change in the health index satisfies the condition for changing the physical type, the updated physical type is obtained according to the feedback information and the degree of change in the health index, and the recommended recipe is adjusted according to the updated physical type.

6. The method according to claim 5, characterized in that Adjusting the recommended recipe according to the feedback information and the degree of change of the health index includes: Calculating a recipe recommendation reward value according to the feedback information and the degree of change of the health index; According to the recipe recommendation reward value, updating the parameters of the recipe recommendation model to obtain an updated recipe recommendation model; The preference information and the physical characteristics are input into the updated recipe recommendation model to obtain an adjusted recommended diet plan output by the updated recipe recommendation model.

7. The method according to claim 5, characterized in that The obtaining of the updated physical type and adjusting the recommended recipe according to the updated physical type includes: Calculating a physical fitness classification reward value according to the feedback information and the degree of change of the health index; According to the physical fitness classification reward value, the parameters of the physical fitness classification model are updated to obtain an updated physical fitness classification model; Inputting the feedback information into the updated physical classification model to obtain updated physical characteristics output by the updated physical classification model; The preference information and the updated physical characteristics are input into the recipe recommendation model to obtain an adjusted recommended recipe output by the recipe recommendation model.

8. A recipe adjustment device, characterized in that: The device comprises: A determination module, used to determine the user's physical characteristics, and input the user's preference information and the physical characteristics into a pre-trained recipe recommendation model to obtain a recommended recipe output by the recipe recommendation model; An acquisition module, configured to acquire feedback information of the recommended recipe, wherein the feedback information includes: first image data, first sound data, and first physiological data after the user eats according to the recommended recipe; The calculation module is used to determine the degree of change of the user's health index based on the feedback information, and adjust the recommended recipe if the degree of change of the health index does not meet the preset conditions.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method for adjusting a healthy recipe as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method for adjusting a healthy recipe as described in any one of claims 1-7.

Images