Artificial intelligence-based exercise recommendation method, device, server and medium

Abstract

The present application is applicable to the field of artificial intelligence, and in particular to an exercise recommendation method, device, server and medium based on artificial intelligence. The method determines an exercise plan based on the patient's personal health data, and adds the exercise plan to the electronic calendar. When the first exercise type and the first exercise index under the target date are modified to the second exercise type and the second exercise index, the difference between the first exercise amount calculated according to the first exercise type and the first exercise index and the second exercise amount calculated according to the second exercise type and the second exercise index is determined. When the difference is greater than the difference threshold, the second exercise index is adjusted until the difference is less than or equal to the difference threshold, so as to automatically plan a reasonable exercise plan for the patient, avoid the patient failing to meet the exercise amount requirement when modifying the exercise plan, ensure the rationality of the exercise plan, and add the corresponding exercise plan to the electronic calendar to achieve the supervision effect.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence, and in particular, relates to an artificial intelligence-based exercise recommendation method, device, server and medium. Background Art

[0002] At present, patients with chronic non-communicable diseases need medication control, a proper diet, and proper exercise during treatment. Since there are many types of exercise and different patients have different physical data, which leads to different exercises they can perform, patients are unable to choose appropriate and effective exercise methods, resulting in poor control of their condition. Medical staff will give corresponding exercise suggestions based on the patient's diagnosis and treatment, but will not plan exercise plans for patients, and cannot urge patients to exercise properly in a reasonable form, resulting in the inability to effectively control the patient's condition. Therefore, how to provide patients with reasonable exercise plans and urge them to execute them has become an urgent problem to be solved. Summary of the invention

[0003] In view of this, the embodiments of the present application provide an artificial intelligence-based exercise recommendation method, device, server and medium to solve the problem of providing patients with reasonable exercise plans and urging them to execute them.

[0004] In a first aspect, an embodiment of the present application provides an artificial intelligence-based exercise recommendation method, the exercise recommendation method comprising:

[0005] Determine an exercise plan based on the patient's personal health data, wherein the exercise plan includes the exercise type and its corresponding exercise index for each day in N cycles, where N is a positive integer;

[0006] Adding the exercise plan to the electronic calendar, and obtaining the patient's modification information for the target date, wherein the modification information includes: a second exercise type obtained by modifying the first exercise type on the target date, and a second exercise index obtained by modifying the first exercise index on the target date;

[0007] Calculate a first exercise amount according to the first exercise type and its corresponding first exercise index;

[0008] Calculate a second exercise amount according to the second exercise type and its corresponding second exercise index;

[0009] When the difference between the first exercise amount and the second exercise amount is greater than a difference threshold, the second exercise index is adjusted and the adjusted second exercise amount is calculated until the difference between the first exercise amount and the adjusted second exercise amount is less than or equal to the difference threshold.

[0010] In a second aspect, an embodiment of the present application provides an artificial intelligence-based exercise recommendation device, the exercise recommendation device comprising:

[0011] A plan determination module, used to determine an exercise plan based on the patient's personal health data, wherein the exercise plan includes the exercise type and its corresponding exercise index for each day in N cycles, where N is a positive integer;

[0012] A modification acquisition module, used for adding the exercise plan to the electronic calendar, and acquiring the patient's modification information for the target date, wherein the modification information includes: a second exercise type obtained by modifying the first exercise type under the target date, and a second exercise index obtained by modifying the first exercise index under the target date;

[0013] A first calculation module, configured to calculate a first exercise amount according to the first exercise type and its corresponding first exercise index;

[0014] A second calculation module, configured to calculate a second exercise amount according to the second exercise type and its corresponding second exercise index;

[0015] The motion adjustment module is used to adjust the second motion index and calculate the adjusted second motion amount when the difference between the first motion amount and the second motion amount is greater than a difference threshold, until the difference between the first motion amount and the adjusted second motion amount is less than or equal to the difference threshold.

[0016] In a third aspect, an embodiment of the present application provides a server, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the exercise recommendation method as described in the first aspect when executing the computer program.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the exercise recommendation method as described in the first aspect is implemented.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a server, the server executes the exercise recommendation method described in the first aspect above.

[0019] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the present application determines an exercise plan based on the patient's personal health data and adds the exercise plan to an electronic calendar. At the same time, when the first exercise type and its corresponding first exercise index under the target date are modified to the second exercise type and its corresponding second exercise index, the difference between the first exercise amount calculated according to the first exercise type and its corresponding first exercise index and the second exercise amount calculated according to the second exercise type and its corresponding second exercise index is determined. When the difference is greater than a difference threshold, the second exercise index is adjusted until the difference is less than or equal to the difference threshold, thereby automatically planning a reasonable exercise plan for the patient, avoiding the patient's failure to meet the exercise amount requirement when modifying the exercise plan, ensuring the rationality of the exercise plan, and adding the corresponding exercise plan to the electronic calendar can achieve a supervisory effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0021] Figure 1 This is a flowchart of an artificial intelligence-based exercise recommendation method provided in Example 1 of the present application;

[0022] Figure 2 This is a flow chart of an artificial intelligence-based exercise recommendation method provided in Example 2 of the present application;

[0023] Figure 3 It is a structural diagram of an artificial intelligence-based sports recommendation device provided in Embodiment 3 of the present application;

[0024] Figure 4 This is a structural diagram of a server provided in Example 4 of the present application. DETAILED DESCRIPTION

[0025] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0026] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0027] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0028] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0029] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0030] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0031] The server in the embodiment of the present application can be a handheld computer, a desktop computer, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a cloud server, a personal digital assistant (PDA), etc. The embodiment of the present application does not impose any restrictions on the specific type of the server.

[0032] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0033] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0034] It should be understood that the size of the serial numbers of the steps in the following embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0035] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0036] See also Figure 1 , is a flowchart of an artificial intelligence-based exercise recommendation method provided in Example 1 of the present application. The above exercise recommendation method is applied to a server, and the server provides a recommendation interface for patients to trigger exercise recommendation services for client APPs or mini-programs on the patient's terminal device. Patients need to log in to the client APP or mini-program and trigger the above exercise recommendation service through the trigger button on the recommendation interface. The corresponding database connected by the server to obtain the corresponding data. Figure 1 As shown, the exercise recommendation method may include the following steps:

[0037] Step S101, determining an exercise plan based on the patient's personal health data.

[0038] The exercise plan includes the exercise type and the corresponding exercise index of each day in N cycles, where N is a positive integer. A cycle can be one day, one week, one month, etc. The exercise type and the corresponding exercise index of each day in a cycle can be the same or different, and the exercise type of one day can include at least one sport.

[0039] For example, the cycle of the exercise plan is 7 days, and the specific exercise plan is as follows: on the first day: exercise A, exercise duration is 30 minutes, on the second day: exercise B, exercise duration is 30 minutes, on the third day: exercise C, exercise duration is 30 minutes, on the fourth day: exercise A, exercise duration is 20 minutes and exercise B, exercise duration is 20 minutes, on the fifth day: exercise B, exercise duration is 20 minutes and exercise C, exercise duration is 20 minutes, on the sixth day: exercise A, exercise duration is 20 minutes and exercise C, exercise duration is 20 minutes, on the seventh day: exercise A, exercise duration is 100 minutes, exercise B, exercise duration is 100 minutes and exercise C, exercise duration is 10 minutes.

[0040] The above exercise recommendation interface is configured with a component for patients to fill in information, so as to collect the patient's medical history, height and weight, examination indicators, lifestyle, etc. filled in the component. If the patient fills in the medical history, height and weight, examination indicators, lifestyle, etc. in the exercise recommendation interface, at least one keyword is extracted through text classification and recognition, and the at least one keyword can be used to characterize the patient's personal health data. Therefore, personal health data can include the patient's disease, the patient's height and weight, the results of the examination, work and rest, etc.

[0041] In one embodiment, if the patient fills in the information by recording audio in the above-mentioned exercise recommendation interface, it is also necessary to convert the recorded audio into text, and perform text classification and recognition on the obtained text content, so as to extract at least one keyword. Furthermore, after filling in the medical history in the component, the patient can click the "Submit" or "Finish" button displayed below the component, and the server can obtain the information filled in by the patient after submission. In addition, filling instructions can also be displayed in the component, such as "Please fill in yes or no" on the component named "Adverse Drug Reaction" to prompt the patient to fill in the format. In addition, filling rules, such as word count requirements and character requirements, can also be configured for the above-mentioned components. When the patient fills in inconsistent with the rules, corresponding prompts are output to remind the patient to fill in according to the instructions, otherwise it cannot be submitted.

[0042] In one embodiment, after the patient clicks the "Submit" or "Finish" button, each window in the component is checked to see if it is filled in. If it is detected that one or more windows are not filled in, the submission failure is output, the server cannot obtain the filled in information, and a prompt is output to remind the patient that the form is not filled in completely, requiring the patient to fill in completely, thereby ensuring the accuracy of the generated exercise plan.

[0043] After obtaining the personal health data, the server matches the corresponding exercise plan from the corresponding database according to the personal health data. For example, for a disease of a symptom type in the personal health data, the server retrieves the exercise plan for the symptom type from the corresponding database, and then screens the exercise plan according to the patient's height, weight, examination indicators, lifestyle, etc. in the personal health data to determine the target exercise plan.

[0044] Step S102, adding the exercise plan to the electronic calendar and obtaining the patient's modification information for the target date.

[0045] The modification information includes: a second exercise type obtained by modifying a first exercise type on a target date, and a second exercise index obtained by modifying a first exercise index on a target date.

[0046] The exercise type may include one or more exercises, each of which corresponds to an exercise index, which may be time, number of times, etc. The modification may be to exchange the exercise type and / or adjust the exercise index, for example, to exchange exercise A in the first exercise type with exercise B, or to increase the exercise index of exercise A in the first exercise type.

[0047] The above-mentioned electronic calendar is a calendar on the terminal device used by the patient or a calendar provided by the client APP or applet on the terminal device. The electronic calendar can add plans and set reminders on each day. If the current date of the electronic calendar is used as the first day of the exercise plan, the exercise type and exercise index of the first day are added under the current date, that is, as the plan for the current date, and the corresponding exercise types and exercise indexes of the second day, third day, etc. of the exercise plan are added to the corresponding dates in order of date. In addition, after adding the plan, the reminder time is automatically set, such as generating a reminder message at 5 pm every day, and displaying the reminder message through the terminal device.

[0048] If the electronic calendar is a calendar on the terminal device used by the patient, then before adding an exercise plan, it is necessary to obtain permission to edit the electronic calendar. The exercise plan can be added to the electronic calendar only with the patient's permission, otherwise the exercise recommendation service for that time will be terminated. In addition, if the patient does not allow editing of the electronic calendar, a delegation reminder can also be output to remind the patient that the exercise recommendation service can only be performed after allowing editing of the electronic calendar.

[0049] When the electronic calendar is a calendar built into the terminal device, the client APP or applet on the terminal device can monitor the electronic calendar through the monitoring function of the terminal device to monitor whether the exercise plan for a certain date in the electronic calendar has been modified. If the patient modifies the exercise plan for a certain date, the modified exercise plan is obtained, and the modification information is obtained. For example, the exercise plan for August 1 is exercise A, and the exercise duration is 30 minutes. The patient changes the exercise plan for that day to exercise B, and the exercise duration is not adjusted. Therefore, exercise B and exercise duration of 30 minutes are the modification information.

[0050] If the electronic calendar is a calendar provided by a client APP or a mini-program on a terminal device, a modification button with the functions of adding, deleting, modifying, and checking is configured on the electronic calendar, and the exercise plan can be modified through the corresponding buttons. Since the electronic calendar is a calendar provided by a client APP or a mini-program on a terminal device, the exercise plan can be monitored by the triggering action of the button to see if it has been modified, and the modification information can be collected by the triggering action of the button.

[0051] Optionally, after determining the exercise plan, it also includes:

[0052] Get the start date selected by the patient;

[0053] Accordingly, adding exercise plans to your electronic calendar includes:

[0054] In the electronic calendar, add the exercise type and its corresponding exercise index for each day in the exercise plan starting from the start date.

[0055] After determining the exercise plan, the patient can select a start date, add the exercise type and exercise indicators corresponding to the first day of the exercise plan under the start date, add the exercise type and exercise indicators corresponding to the second day of the exercise plan one day after the start date, and so on, to realize adding the exercise plan to the electronic calendar.

[0056] Optionally, the above exercise recommendation method further includes:

[0057] After the exercise plan on the electronic calendar is completed, obtain the patient's physical examination results;

[0058] If the physical examination result meets the preset conditions, the exercise plan and the patient's personal health data are stored in the first database.

[0059] Among them, the client APP or applet of the terminal device used by the patient is provided with a component for the patient to provide the physical examination results. After completing the above exercise plan, the patient undergoes a physical examination for the disease filled in in step S101, and after obtaining the physical examination results, fills the physical examination results into the component. The physical examination results meeting the preset conditions may mean that the physical examination results are improved, recovered, etc., and the physical examination results not meeting the preset conditions may mean that the physical examination results are unsatisfactory, not improved, etc.

[0060] The first database is used to store exercise plans and corresponding personal health data. The server is connected to the first database and can match the corresponding exercise plan according to the acquired personal health data.

[0061] Optionally, before storing the exercise plan and the patient's personal health data in the first database, the method further includes:

[0062] Detect whether the motion plan has been modified;

[0063] Accordingly, storing the exercise plan and the patient's personal health data in the first database includes:

[0064] If it is detected that the exercise plan is modified, the modified exercise plan and the patient's personal health data are stored in the first database;

[0065] If it is detected that the exercise plan has not been modified, the exercise plan is marked, and the mark is used to prove that the exercise plan is effective for the patient.

[0066] When the exercise plan is modified, if the modified exercise plan does not exist in the first database, the modified exercise plan and the personal health data need to be saved in the first database. If the modified exercise plan exists in the first database, the modified exercise plan is marked, and the mark is used to prove that the exercise plan is effective for the patient.

[0067] If the motion plan is not modified, since the motion plan obtained by the server from the first database indicates that the motion plan already exists in the first database, the motion plan is marked to indicate that the motion plan is valid.

[0068] The mark for the exercise plan can be a numerical value, which is used to indicate that the patients with the corresponding numerical value currently think that the exercise plan is effective. Whenever a patient executes the exercise plan and the physical examination results after execution meet the preset conditions, the mark of the exercise plan increases by 1.

[0069] After the above steps, the present application will obtain the motion plan with the most marks in the first database through the survival of the fittest, and when matching motion plans for the server, the motion plans with more marks will be given priority.

[0070] Step S103, calculating a first exercise amount according to the first exercise type and its corresponding first exercise index, and calculating a second exercise amount according to the second exercise type and its corresponding second exercise index.

[0071] The amount of exercise mentioned above may refer to the energy consumed by exercise, such as calories, etc. According to the exercise energy consumption calculation formula corresponding to different exercises, the exercise index is brought into the formula to calculate the corresponding exercise and the exercise energy consumed under the exercise index.

[0072] If the exercise plan for a certain day includes two or more types of exercise, calculate the amount of exercise for each exercise, and then add up the amount of exercise for each exercise. The result of the addition is the amount of exercise in the exercise plan for that day.

[0073] In one embodiment, the server is provided with the corresponding amount of exercise for each sport under the unit exercise index. For example, playing badminton for 1 minute consumes 8 kcal, therefore, playing badminton for 30 minutes consumes 240 kcal, 1 sit-up consumes 0.5 kcal, and 50 sit-ups consume 25 kcal.

[0074] By calculating the first exercise type and its corresponding first exercise index, the first exercise amount can be obtained, and by calculating the second exercise type and its corresponding second exercise index, the second exercise amount can be obtained, that is, the first exercise amount is the exercise amount corresponding to the exercise plan for the target date before modification, and the second exercise amount is the exercise amount corresponding to the exercise plan for the target date after modification.

[0075] Step S104, when the difference between the first exercise amount and the second exercise amount is greater than the difference threshold, adjust the second exercise index and calculate the adjusted second exercise amount until the difference between the first exercise amount and the adjusted second exercise amount is less than or equal to the difference threshold.

[0076] Among them, the difference between the first amount of exercise and the second amount of exercise is calculated, and the difference can be expressed as the value corresponding to the subtraction of the two and the absolute value. If the value is greater than the difference threshold, it is determined that the modification does not comply with the modification rules and needs to be adjusted again until it complies with the modification rules. For example, the first amount of exercise is 240 kcal, the second amount of exercise is 200 kcal, and the difference threshold is 5 kcal. The difference between the two is greater than 5 kcal, and the second exercise index corresponding to the second exercise type needs to be adjusted. For example, the second exercise index of the second exercise type is 20min, and the exercise amount corresponding to the second exercise type per minute is 5 kcal, then the second exercise index is adjusted between 27min and 29min.

[0077] The adjustment is for the amount of exercise, including increasing and decreasing. When the modified amount of exercise is much larger than the first amount of exercise, it is necessary to keep the second exercise type and reduce the amount of exercise; when the modified amount of exercise is much smaller than the first amount of exercise, it is necessary to keep the second exercise type and increase the amount of exercise.

[0078] When there are multiple sports in the first and second sports types under the target date, the first exercise amount of all sports under the first exercise type and the second exercise amount of all sports under the second exercise type are calculated. The exercise amount corresponding to each sport under its exercise index is obtained, and when adjusting, the exercise index corresponding to the maximum or minimum exercise amount is prioritized. When adjusting to a smaller amount, the exercise index corresponding to the maximum exercise amount is prioritized to be reduced, and when adjusting to a larger amount, the exercise index corresponding to the minimum exercise amount is prioritized to be increased.

[0079] For example, if a patient suffers from a chronic disease such as diabetes, an exercise plan is matched for the patient based on the type of diabetes and the patient's age, gender, behavioral ability and other diseases that affect exercise. The exercise plan has a cycle of 7 days and is as follows: Day 1: Exercise A, exercise duration is 30 minutes, Day 2: Exercise B, exercise duration is 30 minutes, Day 3: Exercise C, exercise duration is 30 minutes, Day 4: Exercise A, exercise duration is 20 minutes and Exercise B, exercise duration is 20 minutes, Day 5: Exercise B, exercise duration is 20 minutes and Exercise C, exercise duration is 20 minutes, Day 6: Exercise A, exercise duration is 20 minutes and Exercise C, exercise duration is 20 minutes in, the seventh day: exercise A, exercise duration 10 minutes, exercise B, exercise duration 10 minutes and exercise C, exercise duration 10 minutes, and the above exercise plan is generated in the electronic calendar. The current date is July 1st, then the exercise plan is filled in from July 1st to July 7th in sequence. The electronic calendar is provided with a modification button. The patient changes the exercise A on the first day to exercise B, and the exercise duration remains unchanged. The exercise consumption calculated based on exercise A and 30 minutes is 100 kcal, and the exercise consumption calculated based on exercise B and 30 minutes is 150 kcal. Since the difference between the two is 50 kcal, which is greater than the threshold of 10 kcal, the exercise duration of exercise B on the first day is automatically modified to 25 minutes.

[0080] The embodiment of the present application determines an exercise plan based on the patient's personal health data and adds the exercise plan to an electronic calendar. At the same time, when the first exercise type and its corresponding first exercise index under the target date are modified to the second exercise type and its corresponding second exercise index, the difference between the first exercise amount calculated according to the first exercise type and its corresponding first exercise index and the second exercise amount calculated according to the second exercise type and its corresponding second exercise index is determined. When the difference is greater than a difference threshold, the second exercise index is adjusted until the difference is less than or equal to the difference threshold. This realizes automatic planning of a reasonable exercise plan for the patient, avoids the situation where the patient fails to meet the exercise amount requirement when modifying the exercise plan, ensures the rationality of the exercise plan, and adding the corresponding exercise plan to the electronic calendar can achieve a supervisory effect.

[0081] See also Figure 2 , is a flow chart of an artificial intelligence-based exercise recommendation method provided in Example 2 of the present application, such as Figure 2 As shown, the exercise recommendation method may include the following steps:

[0082] Step S201, profiling the patient based on the patient's personal health data to obtain a patient portrait.

[0083] The above-mentioned patient profiling can be performed by extracting keywords from the patient's personal health data and mapping them with the generated portrait identity document (ID) to obtain the patient portrait. There can be more than one keyword, such as diabetes, type 2, height 170 cm, weight 60 kg, etc.

[0084] Patient profiling mainly relies on machine learning. Before profiling, the information needs to be organized and converted into feature vectors of the same dimension. Only then can clustering, regression, association, classifiers, etc. be used to extract features such as keywords.

[0085] Optionally, a patient profile is created based on the patient's personal health data, and the patient profile includes:

[0086] Identify the patient’s personal health data and obtain keywords;

[0087] Create a patient portrait ID, map keywords with the portrait ID, and obtain the patient portrait.

[0088] The above-mentioned patient profiling can be performed by extracting keywords from the patient's personal health data and mapping them with the created patient profile ID.

[0089] The above-mentioned portrait ID can be generated based on the patient's basic information, such as the patient's ID number, account number, account name, etc. If the patient is found in the server based on the patient's basic information, there is no need to generate a new portrait ID for the patient, and the patient's original portrait ID can be used. If the patient is not found in the server based on the patient's basic information, a new portrait ID is generated according to the portrait ID generation rules.

[0090] In the embodiments provided by the present invention, the patient's ID number, account number, account name and other data are obtained with the user's consent, and all the patient's data obtained complies with relevant policies and laws.

[0091] Step S202, matching the patient portrait with the portrait data in the second database to obtain a target object matching the patient portrait, and determining that the exercise plan selected by the target object is the patient's exercise plan.

[0092] The server is connected to a second database which stores exercise plans and corresponding patient portraits. The server sends the patient portraits to the second database and matches similar patients therefrom, and uses the exercise plan selected by the patient data as the patient's exercise plan.

[0093] Specifically, after generating a patient portrait, similarity matching is performed between the patient portrait and the portrait data in the second database to obtain the target object. For example, similarity matching is to compare a keyword with a keyword of any portrait in the database, collect portraits corresponding to a similarity of more than 95%, and then match the next keyword with the keyword of each portrait respectively, and select portraits with a similarity of more than 95%, until all keywords are matched, and the target portrait is obtained. The target ID to which the target portrait belongs is the target object.

[0094] The first database and the second database may be the same database. The personal health data in the first database may be replaced by a patient portrait. The database may feed back the exercise plan of the matched target object to the server.

[0095] If the first database and the second database are not the same database, after matching the target object, the motion plan corresponding to the target object is matched from the first database according to the information of the target object. At this time, the first database can record the corresponding relationship between the created portrait ID and the motion plan through the map table.

[0096] Optionally, after matching the patient portrait with the portrait data in the second database to obtain a target object matching the patient portrait, the method further includes:

[0097] If there are at least two target objects that match the patient portrait, then obtaining the number of markings corresponding to the selected motion plan of each of the target objects, wherein the number of markings increases once when the motion plan is selected and valid;

[0098] Accordingly, determining the movement plan selected by the target object as the movement plan of the patient includes:

[0099] The movement plan with the most marks is determined to be the patient's movement plan.

[0100] When a motion plan is selected and valid, the number of markings increases once. Therefore, the better the motion plan, the higher the number of markings. In the matching process, multiple objects may appear with a close or even equal matching degree with the patient's portrait. At this time, the number of markings of the motion plan corresponding to each object is used as a judgment basis to determine the motion plan. Therefore, the motion plan with the most markings is used as the patient's motion plan.

[0101] Step S203, adding the exercise plan to the electronic calendar and obtaining the patient's modification information for the target date.

[0102] Step S204: a first exercise amount is calculated according to the first exercise type and its corresponding first exercise index, and a second exercise amount is calculated according to the second exercise type and its corresponding second exercise index.

[0103] Step S205, when the difference between the first exercise amount and the second exercise amount is greater than the difference threshold, adjust the second exercise index and calculate the adjusted second exercise amount until the difference between the first exercise amount and the adjusted second exercise amount is less than or equal to the difference threshold.

[0104] Among them, the contents of step S203 to step S205 are respectively the same as those of the above-mentioned step S102 to step S104, and the description of step S102 to step S104 may be referred to, and will not be repeated here.

[0105] The embodiment of the present application creates a portrait of the patient based on the patient's personal health data, and matches the obtained patient portrait with the portrait in the second database to obtain a target object that matches the patient portrait, thereby determining an exercise plan with higher matching accuracy.

[0106] Corresponding to the exercise recommendation method in the above embodiment, Figure 3The structural block diagram of the exercise recommendation device based on artificial intelligence provided in the third embodiment of the present application is shown. The above-mentioned exercise recommendation device is applied to the server. The server provides a recommendation interface for the patient to trigger the exercise recommendation service for the client APP or applet on the patient's terminal device. The patient needs to log in to the client APP or applet and trigger the above-mentioned exercise recommendation service through the trigger button on the recommendation interface. The corresponding database connected to the server to obtain the corresponding data. For the convenience of explanation, only the part related to the embodiment of the present application is shown.

[0107] See also Figure 3 , the exercise recommendation device comprises:

[0108] A plan determination module 31 is used to determine an exercise plan based on the patient's personal health data, wherein the exercise plan includes the exercise type and its corresponding exercise index for each day in N cycles, where N is a positive integer;

[0109] The modification acquisition module 32 is used to add the exercise plan to the electronic calendar and obtain the patient's modification information for the target date, wherein the modification information includes: a second exercise type obtained by modifying the first exercise type under the target date, and a second exercise index obtained by modifying the first exercise index under the target date;

[0110] A first calculation module 33, configured to calculate a first exercise amount according to a first exercise type and a first exercise index corresponding thereto;

[0111] A second calculation module 34, configured to calculate a second exercise amount according to a second exercise type and a second exercise index corresponding thereto;

[0112] The motion adjustment module 45 is used to adjust the second motion index and calculate the adjusted second motion amount when the difference between the first motion amount and the second motion amount is greater than the difference threshold, until the difference between the first motion amount and the adjusted second motion amount is less than or equal to the difference threshold.

[0113] Optionally, the exercise recommendation device further includes:

[0114] A data acquisition module, used to obtain the patient's physical examination results after the exercise plan on the electronic calendar is completed;

[0115] The storage module is used to store the exercise plan and the patient's personal health data in the first database if the physical examination result meets the preset conditions.

[0116] Optionally, the exercise recommendation device further includes:

[0117] A detection module, used for detecting whether the exercise plan is modified before storing the exercise plan and the patient's personal health data in the first database;

[0118] Accordingly, the storage module includes:

[0119] A storage unit, configured to store the modified exercise plan and the patient's personal health data in the first database if it is detected that the exercise plan is modified;

[0120] The marking unit is used to mark the exercise plan if it is detected that the exercise plan has not been modified, and the mark is used to prove that the exercise plan is effective for the patient.

[0121] Optionally, the plan determination module 31 includes:

[0122] A portrait unit, used to profile the patient based on the patient's personal health data to obtain a patient portrait;

[0123] The plan determination unit is used to match the patient portrait with the portrait data in the second database to obtain a target object that matches the patient portrait, and determine that the movement plan selected by the target object is the patient's movement plan.

[0124] Optionally, the above-mentioned portrait unit includes:

[0125] The identification subunit is used to identify the patient's personal health data and obtain keywords;

[0126] The portrait subunit is used to create a patient portrait ID, map keywords with the portrait ID, and obtain the patient portrait.

[0127] Optionally, the exercise recommendation device further includes:

[0128] a marking acquisition module, for, after matching the patient portrait with the portrait data in the second database to obtain a target object matching the patient portrait, if there are at least two target objects matching the patient portrait, obtaining the number of markings corresponding to the selected motion plan of each of the target objects, wherein the number of markings increases once when the motion plan in the second database is selected and valid;

[0129] Accordingly, the plan determination unit is specifically used for:

[0130] The movement plan with the most marks is determined to be the patient's movement plan.

[0131] Optionally, the above-mentioned exercise recommendation device further includes:

[0132] A date acquisition module is used to obtain the start date selected by the patient after the exercise plan is determined;

[0133] Accordingly, the modification acquisition module 32 includes:

[0134] The adding unit is used to add the exercise type and its corresponding exercise index of each day in the exercise plan in the electronic calendar starting from the start date.

[0135] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0136] Figure 4 This is a schematic diagram of the structure of a server provided in Example 4 of this application. Figure 4 As shown, the server 4 of this embodiment includes: at least one processor 40 ( Figure 4 Only one is shown in the figure), a memory 41, and a computer program 42 stored in the memory 41 and executable on at least one processor 40, wherein the processor 40 implements the steps of any of the above-mentioned embodiments of the exercise recommendation method when executing the computer program 42.

[0137] The server 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of the server 4 and does not constitute a limitation on the server 4. The server 4 may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0138] The processor 40 may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0139] In some embodiments, the memory 41 may be an internal storage unit of the server 4, such as a hard disk or memory of the server 4. In other embodiments, the memory 41 may also be an external storage device of the server 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the server 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the server 4. The memory 41 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as program codes of a computer program. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0140] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0141] The present application implements all or part of the processes in the above-mentioned embodiment method, and may also be completed through a computer program product. When the computer program product runs on a server, the server can implement the steps in the above-mentioned method embodiment when executing.

[0142] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0143] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0144] In the embodiments provided in the present application, it should be understood that the disclosed devices / servers and methods can be implemented in other ways. For example, the device / server embodiments described above are merely schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0145] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0146] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An artificial intelligence-based exercise recommendation method, characterized in that: The exercise recommendation method comprises: Determining an exercise plan according to the patient's personal health data includes: profiling the patient according to the patient's personal health data to obtain a patient portrait; matching the patient portrait with portrait data in a second database to obtain a target object matching the patient portrait, and determining that the exercise plan selected by the target object is the patient's exercise plan, wherein the exercise plan includes an exercise type and a corresponding exercise index for each day in N cycles, where N is a positive integer; Adding the exercise plan to the electronic calendar, and obtaining the patient's modification information for the target date, wherein the modification information includes: a second exercise type obtained by modifying the first exercise type on the target date, and a second exercise index obtained by modifying the first exercise index on the target date; Calculate a first exercise amount according to the first exercise type and its corresponding first exercise index; Calculate a second exercise amount according to the second exercise type and its corresponding second exercise index; When the difference between the first exercise amount and the second exercise amount is greater than a difference threshold, adjusting the second exercise index and calculating the adjusted second exercise amount until the difference between the first exercise amount and the adjusted second exercise amount is less than or equal to the difference threshold; After the exercise plan on the electronic calendar is completed, obtaining the physical examination results of the patient; If the physical examination result meets the preset conditions, the exercise plan and the patient's personal health data are stored in the first database; Among them, the patient is profiled based on the patient's personal health data to obtain the patient portrait, including: identifying the patient's personal health data to obtain keywords; creating the patient's portrait ID, mapping the keywords with the portrait ID, and obtaining the patient portrait.

2. The exercise recommendation method according to claim 1, characterized in that: Before storing the exercise plan and the patient's personal health data in a first database, the method further includes: detecting whether the motion plan is modified; Accordingly, storing the exercise plan and the patient's personal health data in a first database includes: If it is detected that the exercise plan is modified, storing the modified exercise plan and the patient's personal health data in the first database; If it is detected that the exercise plan has not been modified, the exercise plan is marked, and the mark is used to prove that the exercise plan is effective for the patient.

3. The exercise recommendation method according to claim 1, characterized in that: After matching the patient portrait with the portrait data in the second database to obtain a target object matching the patient portrait, the method further includes: If there are at least two target objects that match the patient portrait, obtaining the number of markings corresponding to the selected motion plan of each of the target objects, wherein the number of markings increases once when the motion plan in the second database is selected and valid; Accordingly, determining the movement plan selected by the target object as the movement plan of the patient includes: The motion plan with the most marks is determined to be the motion plan of the patient.

4. The exercise recommendation method according to any one of claims 1 to 3, characterized in that: After determining the exercise plan, the method further includes: Get the start date selected by the patient; Accordingly, adding the exercise plan to the electronic calendar includes: In the electronic calendar, the exercise type and the corresponding exercise index of each day in the exercise plan are added in sequence starting from the start date.

5. An artificial intelligence-based sports recommendation device, characterized in that: The exercise recommendation device comprises: A plan determination module is used to determine an exercise plan according to the patient's personal health data, including: based on the patient's personal health data, a portrait of the patient is generated to obtain a patient portrait; the patient portrait is matched with the portrait data in the second database to obtain a target object matching the patient portrait, and the exercise plan selected by the target object is determined to be the patient's exercise plan, wherein the exercise plan includes the exercise type and the corresponding exercise index for each day in N cycles, where N is a positive integer; A modification acquisition module, used for adding the exercise plan to the electronic calendar, and acquiring the patient's modification information for the target date, wherein the modification information includes: a second exercise type obtained by modifying the first exercise type under the target date, and a second exercise index obtained by modifying the first exercise index under the target date; A first calculation module, configured to calculate a first exercise amount according to the first exercise type and its corresponding first exercise index; A second calculation module, configured to calculate a second exercise amount according to the second exercise type and its corresponding second exercise index; a motion adjustment module, configured to adjust the second motion index and calculate the adjusted second motion amount when the difference between the first motion amount and the second motion amount is greater than a difference threshold, until the difference between the first motion amount and the adjusted second motion amount is less than or equal to the difference threshold; A data acquisition module, used for acquiring the physical examination results of the patient after the exercise plan on the electronic calendar is completed; A storage module, configured to store the exercise plan and the patient's personal health data in a first database if the physical examination result meets a preset condition; Among them, the plan determination module creates a portrait of the patient based on the patient's personal health data, and obtaining the patient portrait includes: identifying the patient's personal health data to obtain keywords; creating the patient's portrait ID, mapping the keywords with the portrait ID, and obtaining the patient portrait.

6. A server, characterized in that: The server includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the exercise recommendation method according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the exercise recommendation method according to any one of claims 1 to 4 is implemented.

Images