Intelligent recommendation method and device and computer readable storage medium

Abstract

The invention discloses an intelligent recommendation method and device and a computer readable storage medium, and relates to the technical field of information processing, and the intelligent recommendation method comprises the steps: combining an MBTI personality type of a user with user body data, constructing a user portrait, analyzing the user portrait through a clustering algorithm, determining a user classification result, and sending the user classification result to a user terminal. The diet exercise preference corresponding to the MBTI personality type of the user and the diet exercise demand corresponding to the body data of the user are identified, and the recommendation scheme is generated according to the diet exercise preference and demand of the user, so that the technical defect that the recommendation scheme is not accurate enough due to low recommendation individuation degree is overcome, and the recommendation efficiency is improved. The technical effect of improving the accuracy of the recommendation scheme is achieved.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to an intelligent recommendation method, device, and computer-readable storage medium. Background Art

[0002] In today's digital age, the recommended methods of diet, exercise and / or weight loss methods designed based on the principle of energy balance aim to achieve the purpose of weight loss or weight management by controlling energy intake and increasing energy expenditure. According to the user's different physical condition, metabolic rate, activity level and weight loss goal, a scientific and reasonable diet, exercise and / or weight loss plan is tailored for the user.

[0003] The current method of recommending diet, exercise and / or weight loss methods based on calories only considers the balance between calorie intake and expenditure, but does not consider multi-dimensional information such as the user's personal preferences, physical condition, eating habits, exercise habits, etc. The recommendation is not personalized enough, resulting in inaccurate recommended plans.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide an intelligent recommendation method, device and computer-readable storage medium, aiming to solve the technical problem of how to improve the accuracy of recommendation solutions.

[0006] To achieve the above objectives, the present application proposes an intelligent recommendation method, which includes: Combine the user's MBTI personality type and user's physical data to build a user portrait; Performing cluster analysis on the user portraits by using a clustering algorithm to determine a user classification result; Based on the user classification result, the diet and exercise preferences corresponding to the user's MBTI personality type and the diet and exercise needs corresponding to the user's body data are determined, and a recommendation plan is generated according to the user's diet and exercise preferences and needs.

[0007] In one embodiment, the step of combining the user's MBTI personality type and the user's physical data to construct a user portrait includes: Determine the MBTI personality type of the user and corresponding user preference data according to the MBTI personality test result of the user; Collect and organize the user's health monitoring data to determine the user's physical data; The user preference data and the user physical data are combined to construct a user portrait.

[0008] In one embodiment, the step of combining the user preference data and the user physical data to construct a user portrait includes: Determining the preference characteristics of the user according to the user preference data; According to the user's physical data, assess the user's physical health and dietary and exercise needs, and determine the user's demand characteristics; The user profile is constructed based on the basic information of the user and combined with the preference characteristics and the demand characteristics.

[0009] In one embodiment, before the step of performing cluster analysis on the user portraits by using a clustering algorithm to determine the user classification result, the step includes: Cleaning and standardizing the data of the user portrait; According to the characteristics of the user portrait and the clustering requirements, the clustering algorithm is determined and the parameters of the clustering algorithm are set.

[0010] In one embodiment, the step of performing cluster analysis on the user portraits by using a clustering algorithm to determine the user classification result includes: Inputting the data of the user portrait into the clustering algorithm, performing the clustering analysis, and clustering according to the similarity of the user's diet and exercise preferences and diet and exercise needs; The users are classified according to the clustering result to determine the user classification result.

[0011] In one embodiment, the step of determining the diet and exercise preferences corresponding to the user's MBTI personality type and the diet and exercise requirements corresponding to the user's physical data based on the user classification result, and generating a recommendation plan according to the user's diet and exercise preferences and requirements includes: Determining a recommendation direction according to the needs of the users in the user classification; The recommendation plan corresponding to the recommended direction is generated according to the user's diet and exercise preferences and needs.

[0012] In one embodiment, the step of generating the recommendation scheme corresponding to the recommended direction according to the user's diet and exercise preferences and needs, the recommendation scheme includes any one of the following: Generate a diet plan based on the user's diet type preferences and diet improvement needs; Generate an exercise plan based on the user's exercise type preferences and physical fitness improvement needs.

[0013] In one embodiment, the step of determining the diet and exercise preferences corresponding to the user's MBTI personality type and the diet and exercise requirements corresponding to the user's physical data based on the user classification result, and generating a recommendation plan according to the user's diet and exercise preferences and requirements includes: Determine changes in the user's health data based on the collected health data, and determine customer needs based on the collected feedback; Adjust the content of the recommendation plan according to the changes and the customer needs.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes an intelligent recommendation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the intelligent recommendation method described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the intelligent recommendation method described above are implemented.

[0016] The present application provides an intelligent recommendation method. The present application first combines the user's MBTI personality type and the user's physical data to construct a user portrait that not only includes the user's behavioral data, but also incorporates the user's psychological characteristics and preference tendencies. The user portrait construction is more comprehensive and specific, and the accuracy of the user portrait is improved. The user portrait is analyzed by a clustering algorithm. The clustering algorithm can automatically identify the similarities and differences in the user portrait. The classification results are more accurate and can more accurately reflect the internal connections and differences between users. Based on the accurate user classification results, differentiated recommendation plans are designed for different user groups, which improves the personalization of the recommendation and effectively improves the accuracy of the recommendation plan.

[0017] In summary, the present application combines the user's MBTI personality type and the user's physical data to construct a user portrait, and then analyzes the user portrait through a clustering algorithm to determine the user classification result, identify the diet and exercise preferences corresponding to the MBTI personality type of the user in the same classification and the diet and exercise needs corresponding to the user's physical data, and generate a recommendation plan based on the user's diet and exercise preferences and needs, thereby overcoming the technical defect of low personalization of recommendations, which leads to inaccurate recommended plans, and achieving the technical effect of improving the accuracy of recommended plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 A flowchart of the first embodiment of the intelligent recommendation method of this application is provided; Figure 2 A flowchart of the second embodiment of the intelligent recommendation method of this application is provided; Figure 3 A flowchart of the third embodiment of the intelligent recommendation method of this application is provided; Figure 4 A flowchart of the fourth embodiment of the intelligent recommendation method of this application is provided; Figure 5 A flowchart of the fifth embodiment of the intelligent recommendation method of this application is provided; Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the intelligent recommendation method in the embodiment of the present application.

[0021] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0023] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0024] The main solutions of the embodiments of this application are: At present, the recommendation methods for intelligent diet, exercise and weight loss methods that integrate user portraits are unable to accurately construct user portraits due to the diversity and complexity of data sources and the dynamic changes in user behavior, resulting in inaccurate and unreasonable recommended solutions.

[0025] This application combines the user's MBTI personality type and the user's physical data to construct a user portrait, and then analyzes the user portrait through a clustering algorithm to determine the user classification result, identify the diet and exercise preferences corresponding to the MBTI personality type of the user in the same classification and the diet and exercise needs corresponding to the user's physical data, and generate a recommendation plan based on the user's diet and exercise preferences and needs, thereby overcoming the technical defect of low personalization of recommendations, which leads to inaccurate recommended plans, and achieving the technical effect of improving the accuracy of recommended plans.

[0026] It should be noted that the execution subject of this embodiment can be an intelligent recommendation application, or a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a control device for intelligent recommendation that can realize the above functions, etc. This embodiment does not specifically limit this. The following takes the intelligent recommendation application as an example of the execution subject to illustrate this embodiment and the following embodiments.

[0027] Embodiment 1 Based on this, this application proposes a first embodiment of the intelligent recommendation method, please refer to Figure 1 , the intelligent recommendation method comprises: Step S100, combining the user's MBTI personality type and the user's physical data to construct a user portrait.

[0028] In this embodiment, personality type is a relatively stable and unique set of psychological, emotional and behavioral characteristics of an individual. These characteristics affect the individual's way of thinking, behavior pattern, values ​​and response to external stimuli. The user's personality type is obtained through a pre-test. Common personality type classification systems include MBTI (Myers-Briggs Type Indicator), Big Five (Big Five Personality Traits), etc. MBTI divides personality into four dimensions, each of which has two directions, resulting in a total of 16 different types of personality. The four dimensions are: energy acquisition (extroversion E-introversion I), information acquisition (sensation S-intuition N), decision-making method (thinking T-emotion F) and action method (judgment J-perception P). User physical data refers to various data related to the user's physical condition and health, including but not limited to height, weight, BMI (body mass index), body fat percentage, muscle mass, basal metabolic rate, etc. User portrait is a virtual representation constructed based on user data and personality type, including multiple dimensions such as user's basic attributes, behavioral characteristics, and psychological characteristics.

[0029] As an optional implementation, the collected MBTI personality type data of the user is integrated with the user's physical health data to form a complete user data set, the data is cleaned and preprocessed, and valuable features are extracted from the integrated data set. Based on the extracted features, the user is labeled accordingly according to the MBTI type and physical data, and a user portrait model is constructed for analysis. According to the analysis results, a user portrait is generated. Among them, the physical data is collected through health monitoring equipment or filled in by the user himself.

[0030] Exemplarily, the MBTI type data of the user is collected through the MBTI test questionnaire, the user's preferences in four dimensions are evaluated, the MBTI type of the user is determined, and the basic physical health data of the user, such as height, weight, BMI, body fat percentage, muscle mass, basal metabolic rate, etc., are collected using health monitoring equipment. The collected MBTI type data and the basic physical health data of the user are integrated to form a unified user data set, the data is cleaned, and duplicate, erroneous or invalid data is removed. The user is labeled accordingly according to the MBTI type and physical data. For the MBTI type, the label is "extroverted", "intuitive", etc.; for the physical data, the label is "high BMI", "low fat rate", etc. The characteristics of eating habits, exercise preferences, weight loss methods, etc. related to the MBTI type are extracted from the basic physical health data of the user, and the association analysis is performed using data analysis tools. Based on the MBTI type and user characteristics, a personalized user portrait is constructed for each user.

[0031] Step S200, performing cluster analysis on the user portrait by using a clustering algorithm to determine a user classification result.

[0032] In this embodiment, the clustering algorithm is an unsupervised learning algorithm that divides the samples in the data set into several classes so that the similarity of samples in the same class is high, while the similarity of samples in different classes is low, including K-means algorithm, DBSCAN algorithm, hierarchical clustering algorithm, etc. Cluster analysis is a data analysis technology that uses a clustering algorithm to divide the samples in the data set into different groups. The user classification result is the user grouping obtained after cluster analysis, and the users in each group have similar characteristics or behavior patterns.

[0033] As an optional implementation, a clustering algorithm is selected based on the user portrait data, the parameters of the clustering algorithm are set, the user portrait data is clustered and analyzed by the clustering algorithm to obtain user classification results, the clustering results are evaluated, and the clustering effect is checked.

[0034] Exemplarily, the K-means algorithm is applied for clustering, the number of clusters is determined to be 16, the K-means algorithm is used to cluster the user portrait data, the users are divided into 16 clusters, the users are assigned to the nearest cluster according to the similarity of the user portraits, the silhouette coefficient is used to evaluate the clustering effect, the average of the silhouette coefficients of all users is calculated as the evaluation indicator of the entire clustering effect, the clustering effect is analyzed according to the value of the silhouette coefficient, if the effect is not good, the number of clusters or the type of clustering algorithm is changed and clustering is performed again.

[0035] Step S300, based on the user classification result, determining the diet and exercise preferences corresponding to the user's MBTI personality type and the diet and exercise needs corresponding to the user's body data, and generating a recommendation plan according to the user's diet and exercise preferences and needs.

[0036] In this embodiment, the diet and exercise requirements are the specific diet and exercise requirements of the user obtained through analysis based on the user's physical data and health conditions. The recommendation scheme is a personalized suggestion or strategy tailored for different categories of users based on the user classification results.

[0037] As an optional implementation, according to the classification results of the user, according to the same MBTI personality type and user physical data in the user classification results, the user's corresponding diet and exercise preference data is determined, the user's diet and exercise needs are analyzed by algorithm, combined with the user's diet and exercise preferences and needs, and then according to the health goals set by the user, a personalized diet and exercise recommendation plan is formulated. Among them, the health goals are set by the user himself or recommended by the system, including weight loss, muscle gain, cardiopulmonary function enhancement, sleep improvement, etc.

[0038] Optionally, step S300 includes: Step S310: determining a recommendation direction according to the needs of the users in the user classification.

[0039] In this embodiment, the recommendation direction is the direction of a specific recommendation plan determined according to the needs of the user, including directions such as diet, exercise, and weight loss methods.

[0040] As an optional implementation, the user classification results are analyzed to determine the common characteristics of users in each classification, collect users' expectations for their own needs, and determine the recommendation direction based on user needs.

[0041] For example, if a large number of users in a user category show a preference for a specific food type, taste, or diet, or their physical health data show that they need to adjust their diet to improve, then it can be determined that one of the needs of users in this category is diet recommendation; if users in a user category generally express a desire to enhance physical fitness, shape their bodies, improve cardiopulmonary function, and other sports-related needs, or their physical health data indicate that they need to improve through exercise, then exercise recommendation can be an important direction for users in this category; for some user categories, their needs may cover both diet and exercise. At this time, it is necessary to comprehensively judge whether the recommendation direction should focus on diet, exercise, or both based on the actual situation and priority of the users.

[0042] Step S320: generating the recommendation plan corresponding to the recommendation direction according to the user's diet and exercise preferences and needs.

[0043] In this embodiment, the recommendation direction refers to the focus area or goal orientation determined when providing services or suggestions to users, including diet, exercise, weight loss, health management, etc., depending on the user's personal needs and goals. The recommendation plan is a specific action plan formulated based on the user classification results and the recommendation direction, including diet plans, exercise methods, weight loss methods, etc.

[0044] Optionally, step S320 includes: Step S321, generating a diet plan according to the user's diet type preference and diet improvement needs.

[0045] In this embodiment, the dietary improvement demand refers to the need to adjust the diet based on factors such as the user's health status, nutritional needs or living habits. The dietary plan is a dietary arrangement customized for the user based on the user's dietary type preferences and dietary improvement needs, including food types, intake, eating time, etc., to meet the user's nutritional needs or health goals.

[0046] As an optional implementation method, the user classification results are analyzed to determine the dietary preferences and needs of users of different categories, and the dietary preferences and needs of users are analyzed. According to the user's dietary taste preferences, food suitable for their taste is recommended, and the food types and nutrient ratios are adjusted according to the user's dietary improvement needs, suitable ingredients and recipes are provided, and specific meal arrangements are made, and a recommendation plan for the user's personalized diet plan is made. Among them, dietary characteristics include age, gender, weight, health status, dietary preferences, etc.

[0047] For example, for users who prefer a high-protein, low-carb diet, like seafood and vegetables, dislike high-sugar and high-fat foods, and hope to lose weight and increase muscle mass by adjusting their diet while improving their blood lipid levels, a high-protein, low-carb diet plan is developed for them, ensuring that every meal has seafood as a protein source, choosing carbohydrates with low GI (glycemic index), choosing an appropriate amount of healthy fats, avoiding excessive intake of saturated fat and trans fat, choosing vegetables and fruits of different colors to obtain rich vitamins and minerals, and determining a high-protein, low-carb recipe that contains the user's preferred seafood and vegetables.

[0048] Step S322: Generate an exercise plan based on the user's exercise type preference and physical fitness improvement needs.

[0049] In this embodiment, the physical fitness improvement demand refers to the user's demand for improving physical quality, enhancing physical fitness, shaping body or improving health through exercise. The exercise plan refers to an exercise guidance plan tailored for the user based on the user's exercise type preference and physical fitness improvement demand, including exercise type, intensity, frequency, duration and other contents.

[0050] As an optional implementation, the user classification results are analyzed to determine the exercise preferences and needs of users of different categories, and a recommendation plan for a personalized exercise plan for the user is formulated based on the user's physical fitness level and preference, providing exercise guidance. The exercise plan includes exercise type, exercise frequency, exercise intensity, etc.

[0051] For example, by analyzing the user classification results, we can understand the user's physical fitness level, exercise habits and preferences, and recommend different types of exercises based on the user's goals. For users who need to gain muscle, we can combine aerobic exercise and strength training to achieve the goal of reducing fat and gaining muscle. We can set the appropriate exercise intensity based on the user's physical fitness level, use a heart rate monitor to control the target heart rate range during aerobic exercise, develop a weekly exercise frequency and time plan, and provide exercise video tutorials, action diagrams or on-site guidance.

[0052] Optionally, the diet plan and the exercise plan are combined to generate a weight loss plan.

[0053] As an optional implementation, the user classification results are analyzed to determine the dietary preferences and needs as well as the exercise preferences and needs of users in different categories, and a recommendation for a comprehensive weight loss plan for the user is formulated in combination with the dietary plan and the exercise plan.

[0054] For example, the user classification results are analyzed to understand the user's weight, health status, physical fitness level, body fat percentage and other characteristics, and a diet plan is formulated to provide users with low-calorie, high-satiety, nutritionally balanced diet recommendations. Combined with the user's physical fitness and exercise preferences, targeted exercise plans are formulated to promote calorie consumption and encourage users to develop good living habits.

[0055] The present embodiment provides an intelligent recommendation method. The present embodiment first constructs a user portrait by combining the user's MBTI personality type and the user's physical data, and then analyzes the user portrait through a clustering algorithm to determine the user classification result, identify the diet and exercise preferences corresponding to the MBTI personality type of the user in the same classification and the diet and exercise needs corresponding to the user's physical data, and generate a recommendation plan based on the user's diet and exercise preferences and needs, thereby overcoming the technical defect of low personalization of recommendations, which leads to inaccurate recommended plans, and achieving the technical effect of improving the accuracy of recommended plans.

[0056] Based on the first embodiment, the second embodiment of the present application proposes an intelligent recommendation method, referring to Figure 2 , step S100 includes: Step S110, determining the MBTI personality type of the user and corresponding user preference data according to the MBTI personality test result of the user.

[0057] In this embodiment, the MBTI personality type is based on the results of the MBTI test, and individuals are classified into one of 16 personality types. These types describe the preferences and tendencies of individuals in four key dimensions, including energy acquisition (extraversion E-introversion I), information acquisition (sensing S-intuition N), decision-making style (thinking T-feeling F) and action style (judgment J-perception P).

[0058] As an optional implementation, the user is guided to take a personality test through the MBTI test tool, and the test results of the user are analyzed and classified according to the test scoring criteria and analysis methods to determine the personality type. The MBTI test tool includes a paper questionnaire, an online test platform and a mobile application.

[0059] Exemplarily, a questionnaire is distributed to the user, the purpose, process and importance of the MBTI test are introduced to the user, it is ensured that the user understands and is willing to participate in the MBTI test and clear test guidance is provided, the questionnaire data submitted by the user is collected, and the user's score is automatically calculated according to the MBTI scoring criteria and analysis method, the user's test results are analyzed, the user is classified according to the test results, the user's personality type is determined, and the meaning and characteristics of his or her MBTI personality type are explained and displayed to the user.

[0060] Exemplarily, based on the relative preferences of the four dimensions of MBTI personality types, extroverts (E) usually like social activities, tend to exercise with friends, and like to try new foods; introverts (I) tend to be alone or in small groups, like to exercise alone, pay attention to the quality and nutrition of food, and tend to choose a healthy and balanced diet; sensing (S) pays attention to reality and details, tends to choose familiar and traditional ways of eating and exercising; intuitive (N) likes to explore and innovate, is willing to try new ways of eating and exercising, pays attention to the nutritional value and health benefits of diet, and the long-term effects of exercise on physical and mental health, and tends to choose sports that can stimulate creativity and imagination; thinking (T) pays attention to logic and is willing to try new ways of eating and exercising. The emotional type (F) focuses on emotions and interpersonal relationships, tends to choose diets and exercise methods that can bring pleasure and relaxation, pays attention to the taste and cooking methods of food, as well as the emotional experience during exercise, and likes sports that can enhance social interaction and teamwork; the judging type (J) likes planning and organization, tends to make clear diet and exercise plans, and likes regular and structured exercise methods; the perceiving type (P) is flexible and casual, not willing to be bound by fixed plans, tends to choose diet and exercise methods based on the feelings and needs of the day, and likes to try different activities and experiences. Therefore, the preference data corresponding to the sixteen MBTI personality types are analyzed as follows: ESTJ / ISTJ: Like regular exercise and healthy eating, and focus on practical results.

[0061] ESTP / ISTP: Likes exciting and challenging sports, such as extreme sports. They are not too picky about diet but pay attention to nutrition.

[0062] ENFJ / INFJ: Prefers exercise and eating styles that provide emotional satisfaction and social interaction.

[0063] ENFP / INFP: Enjoy creative and expressive forms of exercise and eating, such as dancing and cooking.

[0064] ENTJ / INTJ: Like efficient and scientific exercise and diet methods, focus on results and efficiency.

[0065] ENTP / INTP: Enjoy exploring new ways of exercising and eating and are skeptical of traditional methods.

[0066] ESFJ / ISFJ: Prefer warm and comfortable eating environments, and exercise methods that allow for social interaction.

[0067] ESFP / ISFP: Enjoy the pleasure of food and sports, and focus on sensory experience and emotional satisfaction.

[0068] Step S120, collecting and organizing the health monitoring data of the user to determine the user's physical data.

[0069] In this embodiment, health monitoring data refers to data and information about the user's physical health status collected through various medical and health monitoring equipment, software or manual records, including but not limited to physiological indicators such as heart rate, blood pressure, blood sugar, weight, body fat percentage, sleep quality, number of steps, exercise volume, as well as subjective information such as the user's self-reported health status, eating habits, exercise habits, etc.

[0070] As an optional implementation method, guide users to wear wearable devices that monitor physiological indicators and download professional health monitoring software to conduct health monitoring, collect users' eating habits and exercise habits data through questionnaires, clean and integrate the collected data, organize user information, use data analysis tools to analyze, and determine user physical data.

[0071] As another optional implementation, collect users' personal data through questionnaires or cooperate with third-party data service providers, clean and integrate the collected data, organize the user data, use data analysis tools to analyze, and determine the user's physical data.

[0072] For example, users are encouraged to wear wearable devices such as smart bracelets and smart watches to automatically monitor and record the user's heart rate, number of steps, sleep quality and other physiological indicators, guide users to download and connect to professional health monitoring software, and ask users to manually fill in and submit data such as eating habits and exercise habits that cannot be monitored by smart devices. The collected health monitoring data are classified into different categories, and errors and outliers in the data are checked and corrected. The classified and cleaned data are integrated into a unified database, and statistical software or data analysis tools are used to further analyze and process the physical data to understand the user's physical health status and changing trends and determine the user's physical data.

[0073] Step S130, combining the user preference data and the user physical data to construct a user portrait.

[0074] In this embodiment, the user portrait is a virtual representation constructed based on user data and personality type, including multiple dimensions such as the user's basic attributes, behavioral characteristics, and psychological characteristics.

[0075] As an optional implementation method, user preference data is integrated with physical data, key features are extracted from the integrated data, potential connections or patterns between the two are found, users are labeled accordingly, a user portrait model is constructed for analysis, and a user portrait is generated based on the analysis results.

[0076] Optionally, step S130 includes: Step S131, determining the preference characteristics of the user according to the user preference data.

[0077] In this embodiment, preference data refers to the user's preference choices or scores for each dimension in the MBTI test or assessment, reflecting the user's preferences and habits in terms of diet and exercise. Preference characteristics refer to the user's unique preferences and needs in terms of diet and exercise determined based on the user's MBTI personality type and its corresponding diet and exercise preference data.

[0078] As an optional implementation, each MBTI type is analyzed to determine its general preferences in diet and exercise, and the user's preference characteristics in diet and exercise are determined based on the user's MBTI type and with reference to the diet and exercise preference data obtained through analysis.

[0079] Step S132: assessing the user's physical health and dietary and exercise needs based on the user's physical data, and determining the user's demand characteristics.

[0080] In this embodiment, the physical health status is a comprehensive evaluation result based on the user's physical data, reflecting the user's current physical health level and potential health risks. The demand characteristics are based on a comprehensive analysis of the user's physical health status and diet and exercise needs, and the user's specific needs and preferences in diet and exercise are obtained.

[0081] As an optional implementation method, medical expertise and assessment tools are used to conduct a comprehensive analysis of the user's physical data to determine the user's physical health status. Based on the user's physical health status and assessment results, combined with expertise in nutrition and kinesiology, a comprehensive analysis of the user's physical health status and dietary and exercise needs is conducted to extract the user's specific needs in diet and exercise, forming the user's unique demand characteristics.

[0082] Step S133, constructing the user portrait based on the basic information of the user, combined with the preference characteristics and the demand characteristics.

[0083] In this embodiment, basic information refers to data about the user's identity, age, gender, occupation, place of residence and other basic information, based on which the user's background and living environment are understood. Demand characteristics are determined based on the user's physical health status, and the specific needs in terms of diet and exercise.

[0084] As an optional implementation method, the collected basic information of users, dietary exercise preferences, and dietary exercise demand data are integrated to form a complete user data set, and the user data is analyzed using data analysis tools to determine the framework and dimensions of the user portrait. Based on the user portrait framework, specific user roles are created, and detailed descriptions are written for each user role to construct a user portrait, which is then presented through visualization tools. The visualization tools include charts, tag clouds, etc.

[0085] This embodiment provides an intelligent recommendation method. This embodiment first uses MBTI personality type analysis to more accurately understand the user's preferences such as thinking, emotions, energy acquisition methods and behavior methods, so as to provide users with more personalized diet and exercise content recommendations. Combined with the user's physical data and diet and exercise demand characteristics, a personalized health improvement plan can be formulated for the user to more effectively meet the user's health needs. Combined with the analysis of user preferences and demand characteristics, the user's needs and preferences can be more comprehensively understood, the quality of user portrait construction can be improved, and the accuracy of recommendation plans can be improved.

[0086] Based on Example 1, Example 3 of the present application proposes an intelligent recommendation method, referring to Figure 3 , before step S200, including: Step S400, cleaning and standardizing the user portrait data.

[0087] In this embodiment, data cleaning refers to the process of identifying and correcting errors, anomalies or inconsistencies in data, including processing missing values, duplicate values, data in incorrect formats, and removing noise data, etc. Data standardization refers to adjusting data according to certain rules or standards to make it conform to a specific format or range and eliminate differences between different data sources.

[0088] As an optional implementation, the user portrait data is cleaned, noise data is identified and removed, and the cleaned data is standardized and converted into a standard format.

[0089] Exemplarily, by comparing key fields in data records, duplicate records are identified and deduplication is performed. For obviously erroneous data, manual review and correction are required, and noise data is identified and removed by setting thresholds. For numerical data, the minimum-maximum standardization method is used for standardization; for categorical data, encoding is performed to convert it into numerical data; for time data, the format is unified and timestamp conversion, time zone adjustment and other processing are performed according to analysis requirements; for text data, word segmentation, stop word removal, stemming, word form restoration and other processing are performed.

[0090] Step S500, determining the clustering algorithm and setting the parameters of the clustering algorithm according to the characteristics of the user portrait and the clustering requirements.

[0091] In this embodiment, the parameters refer to a series of values ​​or options that need to be preset when executing the clustering algorithm and that affect the algorithm performance and results.

[0092] As an optional implementation method, the collected user portrait data is analyzed to determine the user's preference characteristics, analyze the clustering requirements, select a suitable clustering algorithm and set the algorithm parameters.

[0093] For example, the collected user portrait data is analyzed in detail to understand the characteristics of users, analyze clustering requirements, clarify the purpose of clustering and the expected clustering effect. For user portrait data with large scale and high requirements for clustering efficiency, select the K-means algorithm and set the number of clusters, initialization method, number of iterations and convergence conditions of the algorithm.

[0094] Exemplarily, the preprocessed data is analyzed in detail, and the user's preference characteristics are identified through statistical analysis and data mining techniques, and the purpose of clustering and the expected clustering effect are clarified. For user portrait data with a large scale and high requirements on the accuracy of clustering results, it is necessary to select an algorithm that can handle large amounts of data and ensure clustering quality. Since the hierarchical clustering algorithm can generate a clustering hierarchy, it is convenient to observe the clustering effects under different numbers of clusters, and there is no need to pre-specify the number of clusters, so the hierarchical clustering algorithm is selected, the similarity measurement method of the algorithm is set, the criteria for merging or splitting data points are determined, and the stop conditions of the clustering process are set.

[0095] This embodiment provides an intelligent recommendation method. This embodiment first cleans and standardizes the user portrait data to ensure the accuracy and reliability of the data, improve the accuracy and effectiveness of clustering analysis, selects a suitable clustering algorithm and sets reasonable parameters according to the characteristics of the user portrait and clustering requirements, and can more accurately divide user groups, reveal the similarities and differences between users, and more accurately classify users. Then, recommendations are made based on user needs, thereby improving the accuracy of recommendation schemes.

[0096] Based on the first embodiment, the fourth embodiment of the present application proposes an intelligent recommendation method, referring to Figure 4 , step S200 includes: Step S210, inputting the data of the user portrait into the clustering algorithm, executing the clustering analysis, and clustering according to the similarity of the user's diet and exercise preferences and diet and exercise needs.

[0097] In this embodiment, the clustering algorithm is an unsupervised learning data analysis method used to group user portraits. Cluster analysis is the process of grouping data sets using clustering algorithms. By analyzing the similarities and differences between data, similar data points are grouped into one category.

[0098] As an optional implementation, the user portrait data is organized into a format suitable for clustering algorithm processing, a clustering algorithm is selected based on the user portrait data, parameters of the clustering algorithm are set, the user portrait data is input into the selected clustering algorithm, and clustering analysis is performed.

[0099] Step S220: classify the users according to the clustering result to determine the user classification result.

[0100] In this embodiment, user classification is a process of dividing user portraits into different categories or groups based on certain standards or rules.

[0101] As an optional implementation, the similarity of features of user portraits in each class of the clustering results is analyzed, each class of the clustering results is used as a user classification, and the user classification result is determined.

[0102] As another optional implementation, the similarity of the features of the user portraits in each class of the clustering results is analyzed, each class of the clustering results is used as a preliminary user classification, the specific demand direction of the user is obtained, and the preliminary user classification is adjusted according to the specific demand direction to determine the user classification result. The demand direction includes diet, exercise, weight loss methods, etc.

[0103] Exemplarily, the similarities of users in each class in the clustering results are analyzed, and these classes are used as preliminary user classifications. Then the specific demand directions of the users are obtained, and further classification is performed according to the different demand directions. Those with a demand direction of diet are classified into one class, those with a demand direction of exercise are classified into another class, and those with a demand direction of weight loss methods are classified into another class, and the final user classification results are determined.

[0104] The present embodiment provides an intelligent recommendation method. The present embodiment first inputs the data of the user portrait into a clustering algorithm to perform clustering analysis. Based on the multi-dimensional features in the user portrait, the user is automatically divided into groups with similar features, and the user portrait is classified according to the clustering results to determine the user classification results. Through clustering analysis, users can be classified more accurately, and recommendations can be made based on user needs, thereby improving the rationality and accuracy of the recommendation scheme.

[0105] Based on Example 1, Example 5 of the present application proposes an intelligent recommendation method, referring to Figure 5 , after step S300, including: Step S600, determining changes in the user's physical health data based on the collected physical health data, and determining customer needs based on the collected feedback.

[0106] In this embodiment, feedback is the evaluation, suggestions or opinions of users on the performance, functions, user experience, etc. of a product or service after using it. The change of physical health data refers to the fluctuation or change trend of the user's physical health data over a period of time. By analyzing the changes, it is possible to understand whether the user's health condition has improved, stabilized or deteriorated, and thus adjust the recommendation plan.

[0107] As an optional implementation method, a user feedback portal is set up to collect user feedback, organize and classify the feedback, identify specific suggestions for user text feedback, let users self-report their health status and data through online health questionnaires, analyze the changes in users' physical health data before and after using the recommended plan, and determine customer needs based on the suggestions and changes in physical health data provided by users.

[0108] As another optional implementation method, use smart wearable devices to monitor users' daily health data, actively collect user feedback through an online evaluation system, follow user discussions on social media or user communities, collect and organize user feedback in a timely manner, classify and organize the collected feedback in combination with changes in user physical health data, use statistical software to quantify the feedback data, display the analysis results through visualization tools, and determine specific customer needs.

[0109] Step S700: adjusting the content of the recommendation plan according to the change and the customer demand.

[0110] In this embodiment, customer demand is the specific requirements, expectations or preferences of customers for products or services. Testing is to verify the adjusted clustering algorithm and evaluate whether it meets customer demand.

[0111] As an optional implementation method, collect and organize the user's physical health data at different time points, use statistical tools to compare and analyze this data, identify data trends and anomalies, make personalized adjustments to the recommended plan based on the user's specific needs and changes, set up a regular evaluation mechanism, conduct regular comprehensive evaluations of users, and make corresponding adjustments to the recommended plan based on the evaluation results.

[0112] For example, if the user's weight continues to drop and he or she reports a poor appetite, dietary recommendations can be adjusted to increase nutritious foods and meal frequency; if the user's exercise intensity is not enough to achieve health goals, the exercise plan can be adjusted to increase exercise time and intensity.

[0113] This embodiment provides an intelligent recommendation method. This embodiment first deeply analyzes the changes in user health data and feedback, and adjusts the content of the recommendation plan accordingly, which can significantly improve user satisfaction and the effectiveness of the recommendation plan.

[0114] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the intelligent recommendation method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0115] The present application provides an intelligent recommendation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intelligent recommendation method in the above-mentioned embodiment 1.

[0116] Reference below Figure 6, which shows a schematic diagram of the structure of an intelligent recommendation device suitable for implementing the embodiment of the present application. The intelligent recommendation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The smart recommendation device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0117] like Figure 6 As shown, the intelligent recommendation device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the intelligent recommendation device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the intelligent recommendation device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an intelligent recommendation device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0118] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0119] The intelligent recommendation device provided by the present application adopts the intelligent recommendation method in the above embodiment, which can solve the technical problem of how to improve the accuracy of the recommendation scheme. Compared with the prior art, the beneficial effects of the intelligent recommendation device provided by the present application are the same as the beneficial effects of the intelligent recommendation method provided by the above embodiment, and the other technical features in the intelligent recommendation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0120] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0121] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0122] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the intelligent recommendation method in the above-mentioned embodiment.

[0123] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0124] The computer-readable storage medium may be included in the intelligent recommendation device; or may exist independently without being assembled into the intelligent recommendation device.

[0125] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the intelligent recommendation device, the intelligent recommendation device can write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof. The programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0126] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0127] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0128] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned intelligent recommendation method, and can solve the technical problem of how to improve the accuracy of the recommendation scheme. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the intelligent recommendation method provided in the above-mentioned embodiment, and will not be repeated here.

[0129] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An intelligent recommendation method, characterized in that: The intelligent recommendation method includes: Combine the user's MBTI personality type and user's physical data to build a user portrait; Performing cluster analysis on the user portraits by using a clustering algorithm to determine a user classification result; Based on the user classification result, the diet and exercise preferences corresponding to the user's MBTI personality type and the diet and exercise needs corresponding to the user's body data are determined, and a recommendation plan is generated according to the user's diet and exercise preferences and needs.

2. The intelligent recommendation method according to claim 1, characterized in that: The step of combining the user's MBTI personality type and the user's physical data to construct a user portrait includes: Determine the MBTI personality type of the user and corresponding user preference data according to the MBTI personality test result of the user; Collect and organize the user's health monitoring data to determine the user's physical data; The user preference data and the user physical data are combined to construct a user portrait.

3. The intelligent recommendation method according to claim 2, characterized in that: The step of combining the user preference data and the user physical data to construct a user portrait includes: Determining the preference characteristics of the user according to the user preference data; According to the user's physical data, assess the user's physical health and dietary and exercise needs, and determine the user's demand characteristics; The user profile is constructed based on the basic information of the user and combined with the preference characteristics and the demand characteristics.

4. The intelligent recommendation method according to claim 1, characterized in that: Before the step of performing cluster analysis on the user portraits by using a clustering algorithm to determine the user classification result, the step includes: Cleaning and standardizing the data of the user portrait; According to the characteristics of the user portrait and the clustering requirements, the clustering algorithm is determined and the parameters of the clustering algorithm are set.

5. The intelligent recommendation method according to claim 1, characterized in that: The step of performing cluster analysis on the user portraits by using a clustering algorithm to determine the user classification result comprises: Inputting the data of the user portrait into the clustering algorithm, performing the clustering analysis, and clustering according to the similarity of the user's diet and exercise preferences and diet and exercise needs; The users are classified according to the clustering result to determine the user classification result.

6. The intelligent recommendation method according to claim 1, characterized in that: The step of determining the diet and exercise preferences corresponding to the user's MBTI personality type and the diet and exercise requirements corresponding to the user's body data based on the user classification result, and generating a recommendation plan according to the user's diet and exercise preferences and requirements includes: Determining a recommendation direction according to the needs of the users in the user classification; The recommendation plan corresponding to the recommended direction is generated according to the user's diet and exercise preferences and needs.

7. The intelligent recommendation method according to claim 6, characterized in that: The step of generating the recommendation scheme corresponding to the recommendation direction according to the user's diet and exercise preferences and needs, the recommendation scheme includes any one of the following: Generate a diet plan based on the user's diet type preferences and diet improvement needs; Generate an exercise plan based on the user's exercise type preferences and physical fitness improvement needs.

8. The intelligent recommendation method according to claim 1, characterized in that: After the step of determining the diet and exercise preferences corresponding to the user's MBTI personality type and the diet and exercise requirements corresponding to the user's body data based on the user classification result, and generating a recommendation plan according to the user's diet and exercise preferences and requirements, the method includes: Determine changes in the user's health data based on the collected health data, and determine customer needs based on the collected feedback; Adjust the content of the recommendation plan according to the changes and the customer needs.

9. An intelligent recommendation device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the intelligent recommendation method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the intelligent recommendation method according to any one of claims 1 to 8 are implemented.

Images