Cerebral stroke rehabilitation diet strategy recommendation method, medium and equipment

Abstract

The invention relates to a cerebral apoplexy rehabilitation diet strategy recommendation method, a medium and equipment, and the method comprises the steps: determining a corresponding disease type through analyzing the medical history text information of a patient, and then determining a first rehabilitation diet strategy corresponding to the patient from a historical diet strategy library based on the disease type, calculating age information, diet preference information and disease type corresponding to the patient through a first neural network model to obtain a first strategy adjustment factor, and obtaining a second rehabilitation diet strategy based on the first strategy adjustment factor and the first rehabilitation diet strategy; meanwhile, the diet formula corresponding to the subsequent second rehabilitation period and the time interval for suggesting to adopt the diet formula are continuously adjusted based on the disease improvement condition of the patient in the second rehabilitation period, so that the recommendation of the stroke rehabilitation diet is more targeted.

Description

Technical Field

[0001] The present invention relates to the field of intelligent rehabilitation medicine, and in particular to a method, medium and device for recommending a dietary strategy for stroke rehabilitation. Background Art

[0002] For stroke patients, nutritional intervention can be carried out by improving the dietary structure to achieve the purpose of preventing or inhibiting the onset of the disease. Even in some mild patients, nutritional therapy and drug therapy can achieve the same therapeutic effect. Not only that, nutritional intervention for patients with chronic diseases can also reduce medical costs. However, existing dietary rehabilitation programs are usually relatively general, without specific dietary recommendations and dietary monitoring for different patients, and the monitoring cycle is often fixed and unchanging, which cannot meet the rehabilitation dietary needs of different patients. Summary of the invention

[0003] In view of the above problems, the present invention provides a method, medium and device for recommending a stroke rehabilitation dietary strategy, which is used to solve the problem that the stroke dietary plan is relatively general and does not set different monitoring cycles for different patients, resulting in the inability to meet the personalized needs of patients' dietary rehabilitation strategies.

[0004] To achieve the above objectives, in a first aspect, the present invention provides a method for recommending dietary strategies for stroke rehabilitation, comprising:

[0005] Acquiring patient information, the patient information including user name, user identification information, age information, medical history text information, first physiological characteristic parameter information, and dietary preference information;

[0006] Performing semantic analysis on the medical history text information to obtain a symptom feature vector corresponding to the patient, determining a symptom type corresponding to the patient according to the symptom feature vector, and determining a first rehabilitation diet strategy corresponding to the patient from a historical diet strategy library based on the symptom type, wherein the first rehabilitation diet strategy includes a first diet formula and a first rehabilitation cycle;

[0007] Inputting the patient's corresponding age information, dietary preference information and the type of disease corresponding to the patient into the trained first neural network model, outputting a first strategy adjustment factor, wherein the first strategy adjustment factor includes a first dietary formula adjustment factor and a first rehabilitation cycle adjustment factor, adjusting the first dietary formula according to the first dietary formula adjustment factor and adjusting the first rehabilitation cycle according to the first rehabilitation cycle adjustment factor, to obtain a second rehabilitation dietary strategy, wherein the second rehabilitation dietary strategy includes a second dietary formula and a second rehabilitation cycle, wherein the second rehabilitation cycle includes a plurality of second rehabilitation periods arranged in chronological order, and each second rehabilitation period corresponds to a set of second dietary formulas;

[0008] After each of one or more second rehabilitation periods, the patient's current second physiological characteristic parameter information is collected, and the improvement of the patient's current condition is determined according to a comparison result of the collected second physiological characteristic parameter information and the first physiological characteristic parameter information, and the second dietary formula corresponding to the next second rehabilitation period is adjusted based on the improvement of the condition to obtain a third dietary formula, and the third dietary formula is used as the dietary formula corresponding to the next second rehabilitation period;

[0009] After the second rehabilitation cycle is over, the second physiological characteristic parameter information of all patients collected during the second rehabilitation period and the corresponding dietary formula are obtained and input into the trained second neural network model, and a rehabilitation report corresponding to the patients in the second rehabilitation cycle is output. The rehabilitation report includes the improvement of the patient's symptoms after the second rehabilitation cycle, and predicts the future improvement trend of the patient's symptoms after continuing to implement the second rehabilitation dietary strategy, and the prediction results are presented in the form of animation.

[0010] Furthermore, the method further comprises:

[0011] Calculate a score according to the improvement of the patient's symptoms after the second rehabilitation cycle, and determine a second strategy adjustment factor according to the calculated score, wherein the second strategy adjustment factor includes a second diet formula adjustment factor and a second rehabilitation cycle adjustment factor;

[0012] The first diet formula recorded in the historical diet strategy library is updated according to the second diet formula adjustment factor, and the first rehabilitation cycle recorded in the historical diet strategy library is adjusted according to the second rehabilitation cycle adjustment factor to obtain an updated first rehabilitation diet strategy.

[0013] Furthermore, the method further comprises:

[0014] After each one or more second rehabilitation periods, the monitoring risk level of the current patient is determined based on the collected second physiological characteristic parameter information of the patient, and the duration of the next second rehabilitation period is adjusted according to the monitoring risk level. The higher the monitoring risk level, the shorter the duration of the next second rehabilitation period corresponding to the patient.

[0015] Furthermore, the method comprises:

[0016] When the monitored risk level is higher than the preset risk level, a second prompt message is sent to a preset terminal.

[0017] Furthermore, the method further comprises:

[0018] generating a corresponding diet data table based on the second diet formula and the second rehabilitation period, and generating an interactive animation according to the diet data table;

[0019] During each of the second rehabilitation periods, interaction data between the user and the interactive animation is received, and the completion percentage of the current patient's dietary formula during the current second rehabilitation period is determined based on the interaction data, and a first prompt message is issued when the completion percentage is lower than a preset completion percentage.

[0020] Furthermore, the method further comprises:

[0021] Determining a first rehabilitation exercise strategy corresponding to the patient from a historical exercise strategy library based on the disease type, wherein the first rehabilitation exercise strategy includes a plurality of preset action sequences corresponding to action rehabilitation periods;

[0022] Receive the patient's motion data uploaded during each motion rehabilitation period, compare the collected motion data with the preset motion sequence, determine the difference between the two according to the comparison result, output motion correction suggestions based on the difference, and adjust the preset motion sequence corresponding to the next motion rehabilitation period according to the size of the difference.

[0023] Furthermore, the first neural network model is trained according to the following method:

[0024] Acquire first sample data, wherein the first sample data includes sample age information, sample dietary preference information, and sample rehabilitation dietary strategy;

[0025] The first sample data is input into a first neural network model to be trained, and relevant parameters of the first neural network model are iteratively updated to obtain a trained first neural network model.

[0026] Furthermore, the second neural network model is trained according to the following method:

[0027] Acquiring second sample data, the second sample data comprising a plurality of groups of sample recovery periods and sample dietary formulas;

[0028] The second sample data is input into a second neural network model to be trained, and relevant parameters of the second neural network model are iteratively updated to obtain a trained second neural network model.

[0029] In a second aspect, the present invention further provides a computer-readable storage medium storing computer program instructions, which implement the method described in the first aspect when executed by a processor.

[0030] In a third aspect, the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0031] Different from the prior art, in the above technical solution, the corresponding symptom type is determined by analyzing the patient's medical history text information, and then the first rehabilitation diet strategy corresponding to the patient is determined from the historical diet strategy library based on the symptom type, and the patient's corresponding age information, diet preference information and symptom type are calculated through the first neural network model to obtain the first strategy adjustment factor, and the second rehabilitation diet strategy is obtained based on the first strategy adjustment factor and the first rehabilitation diet strategy. At the same time, based on the patient's symptom improvement in the second rehabilitation period, the dietary formula corresponding to the subsequent second rehabilitation period and the time interval for recommending the use of the dietary formula are continuously adjusted, so that the recommendation of stroke rehabilitation diet is more targeted. In addition, after the second rehabilitation cycle, the present application also generates a rehabilitation report by collecting the second physiological characteristic parameter information and the corresponding dietary formula of the patient collected in each second rehabilitation period, and predicts the patient's future symptom improvement trend based on the rehabilitation report, which can play a good intervention role.

[0032] The above-mentioned records related to the content of the invention are only an overview of the technical solution of the present invention. In order to enable ordinary technicians in the field to more clearly understand the technical solution of the present invention, and then implement it according to the text of the specification and the contents recorded in the drawings, and in order to make the above-mentioned purpose and other purposes, features and advantages of the present invention easier to understand, the following is a description in combination with the specific implementation mode of the present invention and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings are only used to illustrate the principles, implementations, applications, features and effects of the specific embodiments of the present invention and other related contents, and shall not be considered as limiting the present invention.

[0034] In the drawings of the specification:

[0035] Figure 1 A flowchart of a method for recommending dietary strategies for stroke rehabilitation according to a first exemplary embodiment of the present invention;

[0036] Figure 2 A flowchart of a method for recommending dietary strategies for stroke rehabilitation according to a second exemplary embodiment of the present invention;

[0037] Figure 3 A flowchart of a method for recommending dietary strategies for stroke rehabilitation according to a third exemplary embodiment of the present invention;

[0038] Figure 4 A flowchart of a method for recommending dietary strategies for stroke rehabilitation according to a fourth exemplary embodiment of the present invention;

[0039] Figure 5 A flowchart of a method for recommending dietary strategies for stroke rehabilitation according to a fifth exemplary embodiment of the present invention;

[0040] Figure 6 A flowchart of a method for recommending dietary strategies for stroke rehabilitation according to a sixth exemplary embodiment of the present invention;

[0041] Figure 7 It is a schematic diagram of an electronic device involved in a specific embodiment of the present invention.

[0042] The reference numerals in the above drawings are described as follows:

[0043] 10. Electronic equipment;

[0044] 101. Processor;

[0045] 102. Storage medium. DETAILED DESCRIPTION

[0046] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects of the present invention, the following is a detailed description in combination with the specific embodiments listed and the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present invention, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present invention.

[0047] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The word "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present invention, as long as there is no technical contradiction or conflict, the various technical features mentioned in each embodiment can be combined in any way to form a corresponding implementable technical solution.

[0048] Unless otherwise defined, the technical terms used herein have the same meanings as those generally understood by those skilled in the art to which the present invention belongs; the use of relevant terms herein is only for describing specific embodiments and is not intended to limit the present invention.

[0049] In the description of the present invention, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in a logical relationship of "or".

[0050] In the present invention, terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.

[0051] Without further restrictions, in the present invention, the words "include", "comprises", "has" or other similar open-ended expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.

[0052] In the present invention, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of the present invention, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.

[0053] In a first aspect, the present application provides a method for recommending dietary strategies for stroke rehabilitation, such as Figure 1 As shown, the method comprises the following steps:

[0054] Step S101: Obtain patient information.

[0055] In step S101, the patient information includes user name, user identification information, age information, medical history text information, first physiological characteristic parameter information and dietary preference information. The user identification information is information that can uniquely identify the patient user, such as the patient's ID number or medical insurance card number. The medical history text information refers to the text record information of the patient's condition by the doctor during the patient's historical medical treatment, which is usually stored in the server in the form of an electronic medical record. The first physiological characteristic parameter information refers to the physiological characteristic parameters of the patient collected before the implementation of the rehabilitation diet strategy of this application, such as blood pressure, blood lipids, blood sugar, heart rate, respiratory rate and other indicators, and can also be the patient's level of consciousness, language ability, limb movement ability, etc. uploaded by medical staff. The dietary preference information refers to a list of the patient's daily favorite diets, such as a few specific favorite fruits and a few specific favorite vegetables.

[0056] Step S102: Perform semantic analysis on the medical history text information to obtain a symptom feature vector corresponding to the patient, determine the disease type corresponding to the patient according to the symptom feature vector, and determine the first rehabilitation diet strategy corresponding to the patient from a historical diet strategy library based on the disease type.

[0057] In step S102, the symptom feature vector corresponding to the patient can be obtained by extracting keywords from the medical history text information, and the symptom feature vector can be used to characterize the general symptoms of the current patient, and then determine the type of disease corresponding to the patient. The disease types include ischemic stroke and hemorrhagic stroke, and the ischemic stroke and hemorrhagic stroke can be further classified according to whether the current patient has difficulty swallowing, so as to determine different first rehabilitation diet strategies.

[0058] The first rehabilitation diet strategy includes a first diet formula and a first rehabilitation cycle. The first rehabilitation cycle includes multiple first rehabilitation periods. Each rehabilitation period corresponds to a rehabilitation unit duration, such as 1 day or 2 days. The first diet formula is the same in the same rehabilitation period. Taking the first rehabilitation cycle as 1 month and the first rehabilitation period as 1 day as an example, the first diet formula can be set cyclically in units of weeks. The first diet formula can include any one or more of breakfast combination, lunch combination, and dinner combination.

[0059] For example, for patients with normal swallowing function, the staple food can be a combination of coarse grains and refined grains. For example, brown rice, whole wheat noodles and steamed bread made of refined flour can provide sufficient carbohydrates and increase the intake of dietary fiber, which helps control blood sugar and promote intestinal peristalsis. For protein intake, skinless chicken, lean beef, lean pork, etc. can be cooked by steaming, boiling, stewing, etc., and fried food can be avoided. Vegetables and fruits can be diversified and selected in various colors, such as green spinach and broccoli; red tomatoes and red peppers; orange carrots, pumpkins, etc. For patients with swallowing difficulties, the appropriate food texture can be selected according to the degree of swallowing difficulties. For example, for patients with mild swallowing difficulties, the food can be made into a puree or paste, such as beating meat, vegetables, fruits, etc. into a puree with a blender, and then adding an appropriate amount of soup or rice paste to adjust it to a consistency suitable for swallowing. For patients with moderate to severe swallowing difficulties, thickeners may need to be used to adjust the consistency of the liquid, so that liquids such as water and milk become similar to the consistency of honey or pudding to reduce the risk of swallowing.

[0060] In short, the first rehabilitation diet strategy is the initial rehabilitation diet strategy, which can be obtained by analyzing the rehabilitation diet formulas of multiple patients with different types of symptoms in history and recorded in the historical diet strategy library.

[0061] Step S103: inputting the patient's corresponding age information, dietary preference information and the patient's corresponding disease type into the trained first neural network model, and outputting a first strategy adjustment factor, wherein the first strategy adjustment factor includes a first dietary formula adjustment factor and a first rehabilitation cycle adjustment factor.

[0062] Step S104: adjusting the first diet formula according to the first diet formula adjustment factor and adjusting the first rehabilitation cycle according to the first rehabilitation cycle adjustment factor to obtain a second rehabilitation diet strategy.

[0063] In step S103, due to the differences in the age, dietary preference information and the types of symptoms corresponding to the patients, the first rehabilitation dietary strategy is adjusted according to the needs of different patients. For example, if a patient does not like to eat carrots, the proportion of carrots in all rehabilitation periods can be reduced when matching red vegetables, and pumpkin can be used instead. For another example, if the patient is older, considering the patient's reduced chewing ability, rice paste can be used as the staple food instead of rice.

[0064] In step S104, the second rehabilitation diet strategy includes a second diet formula and a second rehabilitation cycle, the second rehabilitation cycle includes a plurality of second rehabilitation time periods arranged in chronological order, and each second rehabilitation time period corresponds to a set of second diet formulas.

[0065] In short, based on the patient's personalized information, not only the dietary formula is adjusted, but also the intervals of the rehabilitation periods are adjusted. For example, for older patients who do not like particulate matter, assuming that the original dietary formula in the first rehabilitation strategy is staple rice with eggs, and the duration is 2 days, then after adjusting the adjustment factor, considering the patient's age and preferences, the weight of rice substitutes can be increased, that is, the staple rice paste can be replaced with steamed eggs. If the patient's disease type is mild dysphagia, the rehabilitation period corresponding to this dietary formula can be appropriately extended, that is, the first rehabilitation cycle adjustment factor can be set to 1.5, and the rehabilitation period corresponding to the dietary formula after adjustment is set to 3 days.

[0066] Step S105: After each of one or more second rehabilitation periods, collect the patient's current second physiological characteristic parameter information, determine the patient's current symptom improvement based on the comparison result of the collected second physiological characteristic parameter information and the first physiological characteristic parameter information, adjust the second dietary formula corresponding to the next second rehabilitation period based on the symptom improvement, obtain a third dietary formula, and use the third dietary formula as the dietary formula corresponding to the next second rehabilitation period.

[0067] Since the second rehabilitation cycle usually lasts for a long time, if the second diet formula corresponding to the second rehabilitation period is not adjusted during this period, it is impossible to track the patient's staged recovery in real time. Therefore, after each one or more second rehabilitation periods, the present application will receive the second physiological characteristic parameter information collected by the patient for evaluation, evaluate the patient's recovery after adopting the current dietary strategy, and then automatically adjust the dietary formula corresponding to the next stage (i.e., the next second rehabilitation period) based on the recovery situation. In addition, the duration of the next second rehabilitation period can also be adjusted in real time based on the improvement of the current patient's symptoms, so that the dietary strategy recommendation is more targeted.

[0068] Step S106: After the second rehabilitation cycle is completed, the second physiological characteristic parameter information of all patients collected during the second rehabilitation period and the corresponding dietary formula are obtained and input into the trained second neural network model, and the rehabilitation report corresponding to the patients in the second rehabilitation cycle is output.

[0069] In step S106, the rehabilitation report includes the improvement of the patient's symptoms after the second rehabilitation cycle. Through the rehabilitation report, the patient's family or medical staff can clearly know the patient's dietary details during the second rehabilitation cycle, as well as the patient's physiological characteristic parameter information after each rehabilitation period, thereby providing strong support for subsequent further rehabilitation treatment.

[0070] Step S107: predicting the patient's future symptom improvement trend after continuing to implement the second rehabilitation diet strategy, and presenting the prediction result in animation form.

[0071] In this embodiment, the trend of symptom improvement can be based on the physiological characteristic parameter information, and a score can be configured based on other indicators. A rehabilitation curve can be obtained based on the score after each second rehabilitation period, and then the trend of symptom improvement in the next rehabilitation period can be predicted. Through animation presentation, the trend of symptom improvement can be made more intuitive, which is convenient for patients to further adhere to the recommended rehabilitation diet strategy.

[0072] In the above technical scheme, the corresponding symptom type is determined by analyzing the patient's medical history text information, and then the first rehabilitation diet strategy corresponding to the patient is determined from the historical diet strategy library based on the symptom type, and the patient's corresponding age information, diet preference information and symptom type are calculated through the first neural network model to obtain the first strategy adjustment factor, and the second rehabilitation diet strategy is obtained based on the first strategy adjustment factor and the first rehabilitation diet strategy. At the same time, based on the patient's symptom improvement in the second rehabilitation period, the dietary formula corresponding to the subsequent second rehabilitation period and the time interval for recommending the use of the dietary formula (i.e., the duration of the next second rehabilitation period) are continuously adjusted, so that the recommendation of stroke rehabilitation diet is more targeted. In addition, after the second rehabilitation cycle, the present application also generates a rehabilitation report by collecting the second physiological characteristic parameter information and the corresponding diet formula of the patient collected in each second rehabilitation period, and predicts the patient's future symptom improvement trend based on the rehabilitation report, which can play a good intervention role.

[0073] In some embodiments, Figure 2 As shown, the method also includes:

[0074] Step S201: Calculate a score according to the improvement of the patient's symptoms after the second rehabilitation cycle, and determine a second strategy adjustment factor according to the calculated score, wherein the second strategy adjustment factor includes a second diet formula adjustment factor and a second rehabilitation cycle adjustment factor;

[0075] Step S202: updating the first diet formula recorded in the historical diet strategy library according to the second diet formula adjustment factor, and adjusting the first rehabilitation cycle recorded in the historical diet strategy library according to the second rehabilitation cycle adjustment factor to obtain an updated first rehabilitation diet strategy.

[0076] In short, since the dietary formula adopted by each patient is adjusted during different rehabilitation periods, the dietary formula adopted by patients of each type of symptoms in the rehabilitation report is not exactly the same as the dietary formula originally recorded in the historical dietary strategy library. In order to make the dietary formula in the historical dietary strategy library more in line with reality, it is necessary to update it. The present application determines the influencing factor based on the improvement of symptoms of different patients, and adjusts the first rehabilitation dietary strategy in the historical dietary strategy library according to the influencing factor. Specifically, the higher the improvement of symptoms and the higher the score, the greater the corresponding influencing factor, and the higher the weight of replacing the dietary formula in the historical dietary strategy library with the dietary formula finally adopted by the current patient.

[0077] In some embodiments, the method further comprises:

[0078] After each of one or more second rehabilitation periods, the monitoring risk level of the current patient is determined based on the collected second physiological characteristic parameter information of the patient, and the duration of the next second rehabilitation period is adjusted according to the monitoring risk level. Further, when the monitoring risk level is higher than the preset risk level, a second prompt message is sent to the preset terminal.

[0079] In short, after each rehabilitation period, if it is found that the abnormal fluctuation amplitude of the patient's current second physiological characteristic parameter is greater than the preset amplitude, the corresponding monitoring risk level of the current patient will be increased accordingly. The higher the monitoring risk level, the shorter the duration of the next second rehabilitation period corresponding to the patient. And if the risk level is high, a second prompt message will also be sent to the preset terminal. The preset terminal can be a terminal device controlled by the patient's family or medical staff. The second prompt message can also include sound prompts, light prompts, vibration prompts, or text and graphics on the display interface of the display device. When the second prompt message is text and graphics on the display interface of the display device, the second prompt message can also include precautions corresponding to the current monitoring risk level.

[0080] In some embodiments, Figure 3 As shown, the method also includes:

[0081] Step S301: generating a corresponding diet data table based on the second diet formula and the second rehabilitation cycle, and generating an interactive animation according to the diet data table.

[0082] Preferably, the diet data table records the diet type and quantity corresponding to each second rehabilitation period, and the interactive animation can be presented in the form of VR or interactive video.

[0083] Step S302: In each of the second rehabilitation periods, receiving interaction data between the user and the interactive animation, determining the completion percentage of the current patient's dietary formula in the current second rehabilitation period based on the interaction data, and issuing a first prompt message when the completion percentage is lower than a preset completion percentage.

[0084] If the patient is conscious, the interactive data can be input through the patient and the interactive animation. If the patient is conscious, the interactive data can be input by medical staff or the patient's family. Through the interactive data, the completion status of the patient's recuperation according to the second rehabilitation diet strategy up to now can be analyzed in time. If the completion status is low, the system will promptly issue the first prompt information to prompt.

[0085] In some embodiments, Figure 4 As shown, the method also includes:

[0086] Step S401: determining a first rehabilitation exercise strategy corresponding to the patient from a historical exercise strategy library based on the disease type, wherein the first rehabilitation exercise strategy includes a plurality of preset action sequences corresponding to action rehabilitation periods;

[0087] Step S402: Receive the patient's motion data uploaded during each motion rehabilitation period, compare the collected motion data with the preset motion sequence, determine the difference between the two according to the comparison result, output motion correction suggestions based on the difference, and adjust the preset motion sequence corresponding to the next motion rehabilitation period according to the size of the difference.

[0088] In short, in order for patients to recover as soon as possible, in addition to daily nutritional therapy through dietary strategies, stroke patients usually need to maintain a certain amount of exercise every day, such as regular arm movements or turning over, etc. Therefore, this application also teaches by setting up multiple sets of different rehabilitation movement videos, and can receive movement data uploaded by patients for comparison. If there is a large difference from the preset movement sequence in the standard rehabilitation movement video, movement correction suggestions will be made based on the difference between the two, thereby promoting faster and better recovery of patients.

[0089] In some embodiments, Figure 5 As shown, the first neural network model is trained according to the following method:

[0090] Step S501: obtaining first sample data, wherein the first sample data includes sample age information, sample dietary preference information, and sample rehabilitation dietary strategy;

[0091] Step S502: input the first sample data into a first neural network model to be trained, iteratively update relevant parameters of the first neural network model, and obtain a trained first neural network model.

[0092] In some embodiments, Figure 6 As shown, the second neural network model is trained according to the following method:

[0093] Step S601: Acquire second sample data, wherein the second sample data includes multiple groups of sample recovery periods and sample dietary formulas;

[0094] Step S602: input the second sample data into a second neural network model to be trained, iteratively update relevant parameters of the second neural network model, and obtain a trained second neural network model.

[0095] Preferably, the first neural network model and the second neural network model can be a convolutional neural network (CNN) or a recurrent neural network (RNN) and their variants (such as LSTM, GRU).

[0096] In a second aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for recommending dietary strategies for stroke rehabilitation as described in the first aspect of the present invention is implemented.

[0097] The computer-readable storage medium may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories.

[0098] The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD ROM); the magnetic surface memory can be a disk memory or a tape memory.

[0099] The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), direct memory bus random access memory (DRRAM). The computer-readable storage medium described in the embodiments of the present invention is intended to include these and any other suitable types of memory.

[0100] like Figure 7 As shown, in a third aspect, the present invention provides an electronic device 10, comprising a processor 101 and a storage medium 102, wherein a computer program is stored on the storage medium, and when the computer program is executed by the processor, the method for recommending dietary strategies for stroke rehabilitation as described in the first aspect of the present invention is implemented.

[0101] In some embodiments, the processor can be implemented by software, hardware, firmware or a combination thereof, and can use circuits, single or multiple application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), central processing units (CPU), controllers, microcontrollers, and at least one of microprocessors, so that the processor can execute some or all of the steps or any combination of the steps in the method for recommending dietary strategies for stroke rehabilitation described in the various embodiments of the present application.

[0102] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of the present invention, the patent protection scope of the present invention cannot be limited thereby. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of the present invention and using the contents recorded in the specification and drawings of the present invention, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. A method for recommending dietary strategies for stroke rehabilitation, characterized in that: include: Acquiring patient information, the patient information including user name, user identification information, age information, medical history text information, first physiological characteristic parameter information, and dietary preference information; Performing semantic analysis on the medical history text information to obtain a symptom feature vector corresponding to the patient, determining a symptom type corresponding to the patient according to the symptom feature vector, and determining a first rehabilitation diet strategy corresponding to the patient from a historical diet strategy library based on the symptom type, wherein the first rehabilitation diet strategy includes a first diet formula and a first rehabilitation cycle; Inputting the patient's corresponding age information, dietary preference information and the type of disease corresponding to the patient into the trained first neural network model, outputting a first strategy adjustment factor, wherein the first strategy adjustment factor includes a first dietary formula adjustment factor and a first rehabilitation cycle adjustment factor, adjusting the first dietary formula according to the first dietary formula adjustment factor and adjusting the first rehabilitation cycle according to the first rehabilitation cycle adjustment factor, to obtain a second rehabilitation dietary strategy, wherein the second rehabilitation dietary strategy includes a second dietary formula and a second rehabilitation cycle, wherein the second rehabilitation cycle includes a plurality of second rehabilitation periods arranged in chronological order, and each second rehabilitation period corresponds to a set of second dietary formulas; After each of one or more second rehabilitation periods, the patient's current second physiological characteristic parameter information is collected, and the improvement of the patient's current condition is determined according to a comparison result of the collected second physiological characteristic parameter information and the first physiological characteristic parameter information, and the second dietary formula corresponding to the next second rehabilitation period is adjusted based on the improvement of the condition to obtain a third dietary formula, and the third dietary formula is used as the dietary formula corresponding to the next second rehabilitation period; After the second rehabilitation cycle is over, the second physiological characteristic parameter information of all patients collected during the second rehabilitation period and the corresponding dietary formula are obtained and input into the trained second neural network model, and a rehabilitation report corresponding to the patients in the second rehabilitation cycle is output. The rehabilitation report includes the improvement of the patient's symptoms after the second rehabilitation cycle, and predicts the future improvement trend of the patient's symptoms after continuing to implement the second rehabilitation dietary strategy, and the prediction results are presented in the form of animation.

2. The method for recommending dietary strategies for stroke rehabilitation according to claim 1, characterized in that: The method further comprises: Calculate a score according to the improvement of the patient's symptoms after the second rehabilitation cycle, and determine a second strategy adjustment factor according to the calculated score, wherein the second strategy adjustment factor includes a second diet formula adjustment factor and a second rehabilitation cycle adjustment factor; The first diet formula recorded in the historical diet strategy library is updated according to the second diet formula adjustment factor, and the first rehabilitation cycle recorded in the historical diet strategy library is adjusted according to the second rehabilitation cycle adjustment factor to obtain an updated first rehabilitation diet strategy.

3. The method for recommending dietary strategies for stroke rehabilitation according to claim 1, characterized in that: The method further comprises: After each one or more second rehabilitation periods, the monitoring risk level of the current patient is determined based on the collected second physiological characteristic parameter information of the patient, and the duration of the next second rehabilitation period is adjusted according to the monitoring risk level. The higher the monitoring risk level, the shorter the duration of the next second rehabilitation period corresponding to the patient.

4. The method for recommending dietary strategies for stroke rehabilitation according to claim 3, characterized in that: The method comprises: When the monitored risk level is higher than the preset risk level, a second prompt message is sent to a preset terminal.

5. The method for recommending dietary strategies for stroke rehabilitation according to claim 1, characterized in that: The method further comprises: generating a corresponding diet data table based on the second diet formula and the second rehabilitation period, and generating an interactive animation according to the diet data table; During each of the second rehabilitation periods, interaction data between the user and the interactive animation is received, and the completion percentage of the current patient's dietary formula during the current second rehabilitation period is determined based on the interaction data, and a first prompt message is issued when the completion percentage is lower than a preset completion percentage.

6. The method for recommending dietary strategies for stroke rehabilitation according to claim 1, characterized in that: The method further comprises: Determining a first rehabilitation exercise strategy corresponding to the patient from a historical exercise strategy library based on the disease type, wherein the first rehabilitation exercise strategy includes a plurality of preset action sequences corresponding to action rehabilitation periods; Receive the patient's motion data uploaded during each motion rehabilitation period, compare the collected motion data with the preset motion sequence, determine the difference between the two according to the comparison result, output motion correction suggestions based on the difference, and adjust the preset motion sequence corresponding to the next motion rehabilitation period according to the size of the difference.

7. The method for recommending dietary strategies for stroke rehabilitation according to claim 1, characterized in that: The first neural network model is trained according to the following method: Acquire first sample data, wherein the first sample data includes sample age information, sample dietary preference information, and sample rehabilitation dietary strategy; The first sample data is input into a first neural network model to be trained, and relevant parameters of the first neural network model are iteratively updated to obtain a trained first neural network model.

8. The method for recommending dietary strategies for stroke rehabilitation according to claim 1, characterized in that: The second neural network model is trained according to the following method: Acquiring second sample data, the second sample data comprising a plurality of groups of sample recovery periods and sample dietary formulas; The second sample data is input into a second neural network model to be trained, and relevant parameters of the second neural network model are iteratively updated to obtain a trained second neural network model.

9. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions implement the method of any one of claims 1 to 8 when executed by a processor.

10. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 8.

Images