Diet adjustment method and system for adjuvant treatment of thrombocytopenia

Abstract

The invention discloses a diet adjustment method and system for adjuvant treatment of thrombocytopenia, and the method comprises the steps: obtaining a diet tendency list of patients, determining a food recommendation index of each patient in the same class, and constructing a patient-recommendation index matrix; complementing the recommendation index of the food, the element value of which is 0, of the specific patient in the patient-recommendation index matrix, and obtaining the final recommendation index # imgabs0 # of each kind of food; based on the final recommendation index # imgabs1 # of each kind of food, the key nutrient content of the food and the energy demand # imgabs2 # of the patient on that day, an optimal diet adjustment scheme is obtained. According to the method, BMI classification, diet tendency, daily energy demand and key nutrient control of patients are comprehensively considered, a personalized diet scheme is customized for each patient, food recommendation is optimized through a matrix decomposition technology, balanced intake of nutrients is ensured, and the problem of malnutrition or excess is effectively avoided.

Description

Technical Field

[0001] The invention belongs to the technical field of information processing, and relates to a diet adjustment method and system for assisting in the treatment of thrombocytopenia. Background Art

[0002] Patients receiving antiplatelet therapy need to strictly control their daily diet, because an inappropriate diet may interfere with the effect of the drug, increase the risk of bleeding, or reduce the efficacy of antiplatelet drugs. Reasonable adjustment of diet and increasing the intake of antiplatelet foods can help patients maintain blood health and reduce the possibility of thrombosis. For example, foods rich in Omega-3 fatty acids, such as deep-sea fish and walnuts, can reduce the adhesion and aggregation of platelets. At the same time, foods rich in vitamin E, such as nuts and green leafy vegetables, help protect the vascular endothelium and reduce platelet activation. Combined with the recommendation algorithm, it is possible to more accurately recommend a diet plan suitable for the patient's health status. In this way, antiplatelet diet adjustment has not only become a part of the treatment, but also an important means to improve the patient's overall health status. The adjustment method of traditional dietary recommendations lacks personalization, cannot fully consider the individual differences of patients, and is prone to ignoring the subjectivity of patients. The direct application of recommendation algorithms in medical diet scenarios may cause the algorithm to be unable to be directly embedded in the current scenario due to constraints such as nutrient ratios. Summary of the invention

[0003] The purpose of the present invention is to solve the problem that the traditional dietary recommendation adjustment method in the prior art lacks personalization, cannot fully consider the individual differences of patients, and easily ignores the subjectivity of patients. By recommending algorithms in medical dietary scenarios, the algorithm may not be directly embedded in the current scenario due to constraints such as nutritional ratios, and a dietary adjustment method and system for auxiliary treatment of thrombocytopenia is provided.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: A dietary adjustment method for assisting the treatment of thrombocytopenia comprises: Collect the types of food in the patient's diet and obtain a list of the patient's dietary preferences; Based on the patient's BMI index, the patients were classified, and based on the patient's dietary preference list, the food recommendation index for each patient in the same category was determined, and then a patient-recommendation index matrix was constructed; Based on the difference between the recommendation index of the current patient and other patients of the same type for each food, a specific index is obtained; Determine the relationship between the normalized specific index and the preset threshold value. If the normalized specific index is greater than the threshold value, the patient is identified as a specific patient. Complete the recommended index of foods with element value 0 in the patient-recommended index matrix for specific patients; Based on the completed patient-recommendation index matrix and the patient's key nutrient weights, the final recommendation index for each food is obtained ; Final recommendation index based on each food , the key nutrient content of food and the patient's daily energy needs , get the best diet adjustment plan.

[0005] A further improvement of the present invention is: Furthermore, the types of food in the patient's diet are collected to obtain the patient's dietary preference list, specifically: Collect the food types in the patient's diet and use The format is represented as follows: It's food , is the element value of food, and its form is as follows: , The patient determines whether the food corresponding to the element is the food that he / she prefers in his / her diet. If so, the value of the element is set to , otherwise keep the default value , transforming the original list of food categories into and The patient's dietary preferences are listed in the following format: .

[0006] Furthermore, based on the patient's dietary preference list, the food recommendation index for each patient in the same category is determined, specifically: The element value of the collection diet tendency list is of food and obtain the types and quantities of key nutrients contained in the food; Based on the number of key nutrients contained in the food obtained and the number of key nutrients required by the patient, obtain the food recommendation index for the current patient; , in, Indicates the recommended index of food for patients; Indicates the number of key nutrients contained in the food; Indicates the number of key nutrients required by the patient, the number of key nutrients contained in the food and the number of key nutrients required by the patient are determined by a nutrition agency; The patient-recommendation index matrix is ​​constructed as follows: For patients belonging to the same category, the element value in the corresponding food preference list is calculated according to the above operation. The recommended index of the food for the patient; After obtaining the food recommendation index of patients of the same type, a patient-recommendation index matrix is ​​constructed; each element in the matrix is ​​the recommended index of the food corresponding to the patient, and the element value that does not generate a recommended index is .

[0007] Furthermore, based on the difference between the recommendation index of each food for the current patient and other patients of the same type, the specific index is obtained. Specifically, the difference between the recommendation index of each food corresponding to the current patient and the recommendation of each same food of other patients of the same type is calculated and accumulated to obtain the specific index of the current patient. The specific formula is: , in, represents the patient-specific index; Indicates the total number of foods in the diet category list; Indicates that the patient Recommended index of each food; Indicates the total number of patients in the patient's category excluding the current patient; Indicates The patient's Recommended index of food.

[0008] Furthermore, the recommendation index of foods with element values ​​of 0 in the patient-recommendation index matrix of specific patients is completed, specifically: a recommendation algorithm based on matrix decomposition is used to obtain a prediction score matrix of the same size as the original matrix; the prediction score matrix contains the prediction scores of foods that have not been scored by specific patients, that is, the food in the original matrix is ​​completed. Element value.

[0009] Furthermore, based on the completed patient-recommendation index matrix and the patient's key nutrient weights, the final recommendation index for each food is obtained. , specifically: , in, Indicates the final recommendation index of the food; Indicates the normalized result value of the food recommendation index; Indicates the number of key nutrients contained in the food; Indicates The weight of each key nutrient is related to the intensity of its impact on the health of anti-platelet patients; Indicates The recommended daily intake limit for 15 key nutrients; Indicates The amount of the key nutrients in the food, per gram of food; Indicates an additional coefficient, only for the patient's dietary preference list Add additional factors to food.

[0010] Furthermore, the patient's daily energy requirement Based on the patient's daily basal metabolic value The patient's activity factor for the day corresponding to the patient's daily activity level The activity coefficient is the different values ​​corresponding to the patient's light activity, moderate activity and heavy activity.

[0011] Further, the final recommendation index based on each food , the key nutrient content of food and the patient's daily energy needs , get the best diet adjustment plan, specifically: The patient chooses the food for the day, and the amount of food is recorded as , OK The key nutrients contained in the food are recorded as and The nutrients in The content of each gram in a food is recorded as , then all food The number of The content formula of key nutrients is as follows: , By The minimum daily intake of each nutrient is recorded as , combined with Get the first The minimum daily intake of each nutrient when converted into food is expressed as follows: , The minimum required The amount of food is enough to satisfy the The intake of nutrients required Food The maximum value needs to be met by the amount of food while also meeting the minimum daily intake of other nutrients.

[0012] A dietary adjustment system for assisting in the treatment of thrombocytopenia, comprising: A collection module, wherein the collection module collects food types in the patient's diet and obtains the patient's dietary preference list; A construction module, wherein the construction module classifies the patients based on their BMI index, and determines the food recommendation index for each patient in the same category based on the patient's dietary preference list, thereby constructing a patient-recommendation index matrix; A first acquisition module, which acquires a specific index based on a difference between a current patient and other patients of the same type regarding a recommendation index for each food; A judgment module, wherein the judgment module judges the relationship between the normalized specific index and a preset threshold value, and if the normalized specific index is greater than the threshold value, the patient is identified as a specific patient; A completion module, wherein the completion module completes the recommended index of the food of the specific patient whose element value is 0 in the patient-recommended index matrix; The second acquisition module obtains the final recommendation index of each food based on the completed patient-recommendation index matrix and the patient's key nutrient weights. ; The third acquisition module is based on the final recommendation index of each food. , the key nutrient content of food and the patient's daily energy needs , get the best diet adjustment plan.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention tailors a personalized diet plan for each patient by comprehensively considering the patient's BMI classification, dietary preferences, daily energy requirements, and control of key nutrients. At the same time, through accurate recommendation index and specific index analysis, it can provide more appropriate dietary recommendations for the unique needs of different patients. Food recommendations are optimized through matrix decomposition technology to ensure a balanced intake of nutrients and effectively avoid the problem of malnutrition or overnutrition. By dynamically updating the recommendation index matrix and flexibly adjusting food intake, the goal of both meeting treatment needs and promoting long-term health is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 This is a schematic flow chart of the dietary adjustment method for assisting in the treatment of thrombocytopenia of the present invention; Figure 2 This is a schematic structural diagram of the diet adjustment system for assisting in the treatment of thrombocytopenia according to the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0017] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0019] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0020] In addition, if the term "horizontal" appears, it does not mean that the component is required to be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0021] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] The present invention is further described in detail below in conjunction with the accompanying drawings: See also Figure 1The present invention discloses a dietary adjustment method for assisting the treatment of thrombocytopenia, comprising: S101, collecting food types in the patient's diet and obtaining a list of the patient's dietary preferences; Collect the food types in the patient's diet and use The format is represented as follows: It's food , is the element value of food, and its form is as follows: , The patient determines whether the food corresponding to the element is the food that he / she prefers in his / her diet. If so, the value of the element is set to , otherwise keep the default value , transforming the original list of food categories into and The patient's dietary preferences are listed in the following format: .

[0023] S102, classifying the patients based on their BMI index, and determining a food recommendation index for each patient in the same category based on their dietary preference list, thereby constructing a patient-recommendation index matrix; Patients are classified by calculating their BMI index. The BMI index is the body mass index. The calculation of the BMI index requires the patient's weight and height. The index classifies patients into the following categories: malnutrition, standard weight, overweight, mild obesity, and severe obesity, in order.

[0024] , Based on the patient's dietary tendency list, determine the food recommendation index for each patient in the same category, specifically: The element value of the collection diet tendency list is of food and obtain the types and quantities of key nutrients contained in the food; Based on the number of key nutrients contained in the food obtained and the number of key nutrients required by the patient, obtain the food recommendation index for the current patient; , in, Indicates the recommended index of food for patients; Indicates the number of key nutrients contained in the food; Indicates the number of key nutrients required by the patient, the number of key nutrients contained in the food and the number of key nutrients required by the patient are determined by a nutrition agency; The patient-recommendation index matrix is ​​constructed as follows: For patients belonging to the same category, the element value in the corresponding food preference list is calculated according to the above operation. The recommended index of the food for the patient; After obtaining the food recommendation index of patients of the same type, a patient-recommendation index matrix is ​​constructed; each element in the matrix is ​​the recommended index of the food corresponding to the patient, and the element value that does not generate a recommended index is .

[0025] S103, obtaining a specific index based on the difference between the recommendation index of each food for the current patient and other patients of the same type; The recommended index of each food corresponding to the current patient is calculated and added up with the recommended index of each same food of other patients of the same type to obtain the specific index of the current patient. The specific formula is: , in, represents the patient-specific index; Indicates the total number of foods in the diet category list; Indicates that the patient Recommended index of each food; Indicates the total number of patients in the patient's category excluding the current patient; Indicates The patient's Recommended index of food.

[0026] After obtaining the patient's specific index, patients with a higher specific index have the following tendencies: The first point is that there are foods with recommended indexes. The recommended index of foods for this patient is significantly different from that of other patients in the same category, indicating that the current food is more special for the patient. Special refers to more suitable or less suitable. Because the absolute value is involved in the comparison of parameters, too large or too small will cause the deviation of the specific index to increase. The second point is that the number of foods that patients prefer tends to be too small, because if there are too many elements in the patient's dietary preference list with a value of When comparing foods, large deviations in each comparison will accumulate, resulting in a higher specificity index.

[0027] S104, determining the relationship between the normalized specific index and a preset threshold value, and if the normalized specific index is greater than the threshold value, the patient is identified as a specific patient; Normalize the specific index of patients of the same type and set the normalized index greater than the threshold The patients were defined as specific patients, and the threshold T was set to 0.9. The patient was considered to be a special patient.

[0028] S105, completing the recommended index of the food of the specific patient whose element value is 0 in the patient-recommended index matrix; Based on the matrix decomposition recommendation algorithm, a prediction score matrix of the same size as the original matrix is ​​obtained; the prediction score matrix contains the prediction scores of the unrated foods of specific patients, that is, the scores in the original matrix are completed. Element value.

[0029] A patient-recommendation index matrix between users and foods is constructed, in which the known recommendation index is filled in the matrix, and the values ​​of the unrated elements are 0. By randomly initializing two low-rank matrices, namely the user matrix and the food matrix, the objective function is optimized using the gradient descent method. The objective function minimizes the difference between the original patient-recommendation index matrix and the predicted score matrix. The elements in the user matrix and the food matrix are iteratively updated until the loss function converges. Once the two low-rank matrices are optimized, the predicted score matrix can be generated by matrix multiplication. The scale of the predicted score matrix is ​​the same as that of the patient-recommendation index matrix, and it contains the predicted scores for foods that have not been rated by specific patients, that is, the 0 element values ​​in the original matrix are completed.

[0030] S106, based on the completed patient-recommendation index matrix and the patient's key nutrient weights, obtain the final recommendation index for each food ; Based on the completed patient-recommendation index matrix and the patient's key nutrient weights, the final recommendation index for each food is obtained , specifically: , in, Indicates the final recommendation index of the food; Indicates the normalized result value of the food recommendation index; Indicates the number of key nutrients contained in the food; Indicates The weight of each key nutrient is related to the intensity of its impact on the health of anti-platelet patients; Indicates The recommended daily intake limit for 15 key nutrients; Indicates The amount of the key nutrients in the food, per gram of food; Indicates an additional coefficient, only for the patient's dietary preference list Add additional factors to food. The value of .

[0031] Indicates the normalized result value of the food recommendation index. The larger the value, the more worthy it is to be included in the recommended adjustment plan for patients. The part that is concerned with the key nutrients in the food is a measure of the The ratio of the nutrient content to its safe upper limit of intake. The greater the ratio, the greater the final recommended index of the food. Then multiply it by the weight of the nutrient to get the result value of this part. After cumulative multiplication, the recommended index Make an impact and get the final recommended index of food .

[0032] The design and description of the key nutrients considered and the corresponding weights of the nutrients are described as follows: Vitamins Directly affects coagulation function, needs to be strictly controlled, and given weight ; High sodium intake may affect blood circulation and drug effects, so it is given weight Potassium has a positive effect on blood pressure and blood circulation, but it needs to be balanced and given weight. ; Saturated fatty acids may increase the risk of platelet aggregation and need to be appropriately restricted and given weight ; Fatty acids help to resist platelets, and their weight is negative. The formula also adds points, giving them weight. ; Folic acid helps red blood cell production, but the weight is low, so it is a bonus item and is given weight ; Vitamins , a natural antioxidant that assists in antiplatelet function, giving weight .

[0033] S107, Final recommendation index based on each food , the key nutrient content of food and the patient's daily energy needs , get the best diet adjustment plan.

[0034] The patient's daily energy requirement Based on the patient's daily basal metabolic value The patient's activity factor for the day corresponding to the patient's daily activity level The activity coefficient is the different values ​​corresponding to the patient's light activity, moderate activity and heavy activity.

[0035] Estimate the patient's daily basal metabolic value , adjust the patient's activity coefficient for the day according to the patient's daily activity level, and the activity coefficient is recorded as , usually (Light activity), (moderate activity), (heavy activity), thus obtaining the patient's energy requirement for the day, recorded as , there are the following relations between the parameters: , At this point, the patient's daily energy needs are obtained.

[0036] Final recommendation index based on each food , the key nutrient content of food and the patient's daily energy needs , get the best diet adjustment plan, specifically: The patient chooses the food for the day, and the amount of food is recorded as , OK The key nutrients contained in the food are recorded as and The nutrients in The content of each gram in a food is recorded as , then all food The number of The content formula of key nutrients is as follows: , By The minimum daily intake of each nutrient is recorded as , combined with Get the first The minimum daily intake of each nutrient when converted into food is expressed as follows: , The minimum required The amount of food is enough to satisfy the The intake of nutrients required Food The maximum value needs to be met by the amount of food while also meeting the minimum daily intake of other nutrients.

[0037] For example, the patient chooses foods that contain vitamins and Fatty acids, calculated as a minimum Foods to meet vitamin Intake requires at least Food to satisfy Fatty acid intake, then set the food amount to It satisfies the vitamin The intake needs of Fatty acid intake requirements.

[0038] By obtaining the method of obtaining the minimum daily food amount, the maximum daily food amount is obtained, and thus the food amount range of the day can be obtained, in grams, which means that the amount of food the patient consumes on the day needs to be kept between the minimum food amount and the maximum food amount. Thus, a constraint based on the key nutrient content is completed.

[0039] Similar to the above method, the minimum and maximum food amounts obtained by quadratically constraining food calories can be obtained. The actual meaning is the same as the minimum and maximum food amount intervals obtained by key nutrients, so it will not be repeated here. At this time, two intervals are obtained. Solving the intersection of the two food amount intervals can obtain the patient's food amount range for the day. After that, the corresponding food amounts of food can be freely matched within the food amount range, and the higher the final recommendation index, the greater the proportion of food amount.

[0040] See also Figure 2 The present invention discloses a diet adjustment system for assisting in the treatment of thrombocytopenia, comprising: A collection module, wherein the collection module collects food types in the patient's diet and obtains the patient's dietary preference list; A construction module, wherein the construction module classifies the patients based on their BMI index, and determines the food recommendation index for each patient in the same category based on the patient's dietary preference list, thereby constructing a patient-recommendation index matrix; A first acquisition module, which acquires a specific index based on a difference between a current patient and other patients of the same type regarding a recommendation index for each food; A judgment module, wherein the judgment module judges the relationship between the normalized specific index and a preset threshold value, and if the normalized specific index is greater than the threshold value, the patient is identified as a specific patient; A completion module, wherein the completion module completes the recommended index of the food of the specific patient whose element value is 0 in the patient-recommended index matrix; The second acquisition module obtains the final recommendation index of each food based on the completed patient-recommendation index matrix and the patient's key nutrient weights. ; The third acquisition module is based on the final recommendation index of each food. , the key nutrient content of food and the patient's daily energy needs , get the best diet adjustment plan.

[0041] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A dietary adjustment method for assisting the treatment of thrombocytopenia, characterized in that: include: Collect the types of food in the patient's diet and obtain a list of the patient's dietary preferences; Based on the patient's BMI index, the patients were classified, and based on the patient's dietary preference list, the food recommendation index for each patient in the same category was determined, and then a patient-recommendation index matrix was constructed; Patients are graded by calculating their BMI index; BMI index is body mass index. The calculation of BMI index requires the patient's weight and height. The index classifies patients; the specific classifications are as follows, in order: malnutrition, standard weight, overweight, mild obesity, and severe obesity; ， Based on the difference between the recommendation index of the current patient and other patients of the same type for each food, a specific index is obtained; Determine the relationship between the normalized specific index and the preset threshold value. If the normalized specific index is greater than the threshold value, the patient is identified as a specific patient. Complete the recommended index of foods with element value 0 in the patient-recommended index matrix for specific patients; Based on the completed patient-recommendation index matrix and the patient's key nutrient weights, the final recommendation index for each food is obtained ; Final recommendation index based on each food , the key nutrient content of food and the patient's daily energy needs , get the best diet adjustment plan.

2. The dietary adjustment method for assisting the treatment of thrombocytopenia according to claim 1, characterized in that: The method of collecting the food types in the patient's diet and obtaining the patient's dietary preference list is specifically as follows: Collect the food types in the patient's diet and use The format is represented as follows: It's food , is the element value of food, and its form is as follows: ， The patient determines whether the food corresponding to the element is the food that he / she prefers in his / her diet. If so, the value of the element is set to , otherwise keep the default value , transforming the original list of food categories into and The patient's dietary preferences are listed in the following format: 。 3. The dietary adjustment method for assisting the treatment of thrombocytopenia according to claim 2, characterized in that: The food recommendation index for each patient in the same category is determined based on the patient's dietary preference list, specifically: The element value of the collection diet tendency list is of food and obtain the types and quantities of key nutrients contained in the food; Based on the number of key nutrients contained in the food obtained and the number of key nutrients required by the patient, obtain the food recommendation index for the current patient; ， in, Indicates the recommended index of food for patients; Indicates the number of key nutrients contained in the food; Indicates the number of key nutrients required by the patient, the number of key nutrients contained in the food and the number of key nutrients required by the patient are determined by a nutrition agency; The patient-recommendation index matrix is ​​constructed as follows: For patients belonging to the same category, the element value in the corresponding food preference list is calculated according to the above operation. The recommended index of the food for the patient; After obtaining the food recommendation index of patients of the same type, a patient-recommendation index matrix is ​​constructed; each element in the matrix is ​​the recommended index of the food corresponding to the patient, and the element value that does not generate a recommended index is .

4. The dietary adjustment method for assisting the treatment of thrombocytopenia according to claim 3, characterized in that: The specific index is obtained based on the difference between the recommendation index of each food of the current patient and other patients of the same type. Specifically, the recommendation index of each food corresponding to the current patient is calculated and accumulated with the recommendation of each same food of other patients of the same type to obtain the specific index of the current patient. The specific formula is: ， in, represents the patient-specific index; Indicates the total number of foods in the diet category list; Indicates that the patient Recommended index of each food; Indicates the total number of patients in the patient's category excluding the current patient; Indicates The patient's Recommended index of food.

5. The dietary adjustment method for assisting the treatment of thrombocytopenia according to claim 4, characterized in that: The method of completing the recommendation index of foods with element values ​​of 0 in the patient-recommendation index matrix for specific patients is specifically as follows: a recommendation algorithm based on matrix decomposition is used to obtain a prediction score matrix with the same size as the original matrix; the prediction score matrix includes the prediction scores of foods that have not been scored by specific patients, that is, the prediction scores of foods in the original matrix are completed. Element value.

6. The dietary adjustment method for assisting the treatment of thrombocytopenia according to claim 5, characterized in that: The final recommendation index for each food is obtained based on the completed patient-recommendation index matrix and the patient's key nutrient weights. , specifically: ， in, Indicates the final recommendation index of the food; Indicates the normalized result value of the food recommendation index; Indicates the number of key nutrients contained in the food; Indicates The weight of each key nutrient is related to the intensity of its impact on the health of anti-platelet patients; Indicates The recommended daily intake limit for 10 key nutrients; Indicates The amount of the key nutrients in the food, per gram of food; Indicates an additional coefficient, only for the patient's dietary preference list Add additional factors to food.

7. The dietary adjustment method for assisting the treatment of thrombocytopenia according to claim 6, characterized in that: The patient's daily energy requirement Based on the patient's daily basal metabolic value The patient's activity coefficient for the day corresponding to the patient's daily activity level The activity coefficient is the different values ​​corresponding to the patient's light activity, moderate activity and heavy activity.

8. The dietary adjustment method for assisting the treatment of thrombocytopenia according to claim 7, characterized in that: The final recommendation index based on each food , the key nutrient content of food and the patient's daily energy needs , get the best diet adjustment plan, specifically: The patient chooses the food for the day, and the amount of food is recorded as , OK The key nutrients contained in the food are recorded as and The nutrients in The content of each gram in a food is recorded as , then all food The number of The content formula of key nutrients is as follows: ， By The minimum daily intake of each nutrient is recorded as , combined with Get the first The minimum daily intake of each nutrient when converted into food is expressed as follows: ， The minimum required The amount of food is enough to satisfy the The intake of nutrients required Food The maximum value needs to be met by the amount of food while also meeting the minimum daily intake of other nutrients.

9. A dietary adjustment system for assisting the treatment of thrombocytopenia, characterized in that: include: A collection module, wherein the collection module collects food types in the patient's diet and obtains a list of the patient's dietary preferences; A construction module, wherein the construction module classifies the patients based on their BMI index, and determines the food recommendation index for each patient in the same category based on the patient's dietary preference list, thereby constructing a patient-recommendation index matrix; A first acquisition module, which acquires a specific index based on a difference between a current patient and other patients of the same type regarding a recommendation index for each food; A judgment module, wherein the judgment module judges the relationship between the normalized specific index and a preset threshold value, and if the normalized specific index is greater than the threshold value, the patient is identified as a specific patient; A completion module, wherein the completion module completes the recommended index of the food of the specific patient whose element value is 0 in the patient-recommended index matrix; The second acquisition module obtains the final recommendation index of each food based on the completed patient-recommendation index matrix and the patient's key nutrient weights. ; The third acquisition module is based on the final recommendation index of each food. , the key nutrient content of food and the patient's daily energy needs , get the best diet adjustment plan.

Images