A digital clinical nutrition intelligent management method and system

Abstract

The present application discloses a digital clinical nutrition intelligent management method and system, which relates to the field of nutrition processing technology, including: obtaining the body shape data of a target user, obtaining a target data set and target user characteristics from the body shape data; determining the user environment characteristics of the target user according to the target data set and the target user characteristics; filtering the body shape data according to the user environment characteristics to obtain a filtered data set, and determining nutrition configuration parameters based on the filtered data set; obtaining real-time body shape data and historical body shape data, and determining a target feedback state based on a comparison result between the historical body shape data and the real-time body shape data; determining a first compensation variable of a nutrition plan based on the target feedback state, wherein the first compensation variable is at least two data types, and outputting a first compensation variable implementation instruction; the quality and effect of nutrition plan configuration can be improved, and the personalization and participation of the nutrition plan can be improved.

Description

Technical Field

[0001] The present invention relates to the field of nutrition processing technology, and in particular to a digital clinical nutrition intelligent management method and system. Background Art

[0002] With the development of economy and the improvement of living standards, people pay more and more attention to the impact of diet and nutrition on health. Therefore, clinical automatic diagnosis and improving the efficiency of nutritional therapy have gradually become one of the hot research topics in the field of nutrition. Nutritional intervention plays an extremely important role in treating various clinical diseases. Therefore, it is necessary to develop a system with strong functions and good versatility that can complete the diagnosis of common diseases related to nutritional therapy, analysis of causes, determination of treatment plans and recommendation of corresponding foods. It has important social significance and application value.

[0003] The existing clinical nutrition management is to construct a calorie distribution regression model, make accurate dietary distribution according to the calorie distribution regression model, and screen multiple nutritional dietary distribution plans to obtain a target nutritional plan that meets the requirements; however, when attention is focused on calorie distribution, it may lead to insufficient overall nutritional intake and cause other nutritional needs to not be met. Summary of the invention

[0004] The embodiment of the present application provides a digital clinical nutrition intelligent management method and system, which solves the problems in the prior art of insufficient nutrition plan setting and the failure to consider the relationship between compensation variables and abnormal variables in nutrition configuration, improves the quality and efficiency of nutrition configuration, and improves the personalization and participation of nutrition plans.

[0005] The present application embodiment provides a digital clinical nutrition intelligent management method, including:

[0006] Acquire body shape data of a target user, and acquire a target data set and target user characteristics from the body shape data;

[0007] Determine the user environment characteristics of the target user based on the target data set and the target user characteristics;

[0008] According to the user's environmental characteristics, the body data is screened to obtain a screened data set, and the nutritional configuration parameters are determined based on the screened data set;

[0009] Acquire real-time posture data and historical posture data, and determine the target feedback state based on the comparison result between the historical posture data and the real-time posture data;

[0010] Based on the target feedback state, determining a first compensation variable of the nutrition plan, wherein the first compensation variable is at least two data types, and outputting a first compensation variable implementation instruction;

[0011] Implementing instructions based on the first compensation variable, taking the nutrition configuration parameter as input, and determining to obtain a second compensation variable;

[0012] Taking the first compensation variable implementation instruction as input, the second compensation variable as variable, and the user environment characteristic as supplementary variable, obtaining the association topology map according to the target feedback state;

[0013] Based on the association topology graph, the target user's body data is input to obtain an abnormal data set, and the nutritional index is determined according to the abnormal data set.

[0014] A digital clinical nutrition intelligent management system, comprising:

[0015] A user status data acquisition module is used to acquire the body data of the target user, and when the amount of body data reaches the quantity required for analysis, it is sent to the environment feature extraction module;

[0016] An environment feature extraction module is used to obtain user environment features of a target user based on a target data set and target user features;

[0017] A feedback state determination module is used to determine the target feedback state according to the comparison result between the historical posture data and the real-time posture data;

[0018] A first compensation module, used for obtaining a first compensation variable of the nutrition scheme in each state according to the target feedback state;

[0019] A second compensation module, used for determining a second compensation variable according to the needs and historical body shape data of the target user;

[0020] An association module, used to determine an association topology map according to the first compensation variable instruction, the second compensation variable, the user environment characteristics, and the target feedback state;

[0021] The abnormal analysis module is used to input the target user's body data based on the association topology map, obtain the abnormal data set, and determine the nutritional index according to the analysis result of the abnormal data set.

[0022] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0023] The present application processes the body data of the target user to obtain the target data set and the target user characteristics; according to the target user characteristics, the nutrition configuration parameters are determined; based on the comparison results of the historical body data and the real-time body data, the target feedback state is determined, based on the target feedback state, the first compensation variable of the nutrition plan is determined, based on the first compensation variable implementation instruction, the nutrition configuration parameters are used as input, and the second compensation variable is determined; the first compensation variable implementation instruction is used as input, the second compensation variable is used as a variable, and the user environment characteristics are used as supplementary variables, and according to the target feedback state, the association topology map is obtained; based on the association topology map, the body data of the target user is input to obtain an abnormal data set, and the nutrition index is determined according to the abnormal data set. The first compensation variable and the second compensation variable obtained can supplement the deficiencies in the nutrition plan, and according to the target feedback state and the user environment characteristics, the obtained plan can be more adaptable to the current environment, and can better highlight the predictability, prevention, personalization and participation of the nutrition plan for the target user. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flowchart of a digital clinical nutrition intelligent management method;

[0025] Figure 2 It is a system schematic diagram of a digital clinical nutrition intelligent management system;

[0026] Figure 3 A flowchart of step S300 of a digital clinical nutrition intelligent management method;

[0027] Figure 4 A flowchart of step S400 of a digital clinical nutrition intelligent management method;

[0028] Figure 5 A flowchart of step S500 of a digital clinical nutrition intelligent management method;

[0029] Figure 6 A flowchart of step S600 of a digital clinical nutrition intelligent management method;

[0030] Figure 7 A flowchart of step S700 of a digital clinical nutrition intelligent management method;

[0031] Figure 8 This is a flowchart of step S800 of a digital clinical nutrition intelligent management method. DETAILED DESCRIPTION

[0032] To facilitate the understanding of the present invention, the present application will be described more comprehensively below with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, but the present invention can be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, the purpose of providing these embodiments is to enable a more thorough and comprehensive understanding of the disclosed content of the present invention.

[0033] It should be noted that the terms “vertical”, “horizontal”, “up”, “down”, “left”, “right” and similar expressions used in this document are only for illustrative purposes and do not represent the only implementation method.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs; the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more related listed items.

[0035] like Figure 1 As shown, a digital clinical nutrition intelligent management method comprises:

[0036] S100, obtaining body data of a target user, and obtaining a target data set and target user features from the body data.

[0037] Among them, the body data refers to the basic physical information of the target user, his own symptoms, time, health status during hospitalization, and the environment information of the target user. The acquired target data set is a data set related to a certain physical feature of the target user, such as data information corresponding to a specific weight. The target user feature is a feature that can have a certain impact on the target user's nutritional plan.

[0038] S200, determining user environment characteristics of the target user according to the target data set and target user characteristics.

[0039] The user environment characteristics refer to the target user's personal environmental information, such as the home environment, the temperature, humidity, pressure of the area where the user is located, and the environment around the user when using the nutritional plan.

[0040] For target user characteristics, obtain the target data set and target user characteristics, select data related to the environment, sort the environmental data, and select the environmental characteristics that have the greatest impact on the nutrition plan after sorting as the output user environmental characteristics.

[0041] S300, screening the body data according to the user environment characteristics to obtain a screening data set, and determining the nutrition configuration parameters based on the screening data set.

[0042] Further, if Figure 3 As shown, step S300 includes:

[0043] S301, generating a preliminary nutrition plan based on the screened data set.

[0044] S302, determining a nutrition setting process for the preliminary nutrition plan according to the user's environmental characteristics.

[0045] S303, obtaining nutrition configuration parameters of each nutrition setting process according to the nutrition allocation index in each nutrition setting process.

[0046] Specifically, according to the filtered data set, the nutrition plan is determined for the user environment characteristics of the target user; the user environment characteristics are used to determine the characteristic information of the corresponding environment according to the environmental information of each user, so as to facilitate the screening of target users related to the environment. The nutrition setting process is the way to use the nutrition plan within different time ranges. The nutrition allocation index is the nutrition amount that each nutrition plan needs to meet, and the nutrition configuration parameter is the specific allocation amount.

[0047] For the obtained nutrition configuration parameters, the adaptability of multiple environmental variables in the screening data set to the nutrition plan is analyzed to obtain the corresponding nutrition setting process. In the nutrition setting process that meets the environmental changes, the relevant nutrition allocation indicators are selected and the nutrition configuration parameters are compared, so as to output some nutrition configuration parameters that meet the current conditions. According to the obtained nutrition configuration parameters, the nutrition powder used in the nutrition plan is adjusted.

[0048] Further, the historical body shape data of the preliminary nutrition plan is compared, and regression calculation is performed on the preliminary nutrition plan to obtain the target nutrition plan;

[0049] According to the setting weight of the target nutrition scheme, the environmental characteristics during configuration are determined, the target nutrition scheme with the largest weight is used as the first output scheme, and the target nutrition scheme with the average weight value is used as the second output scheme;

[0050] Based on the first output scheme and the second output scheme, the scheme comfort level is extracted, and according to the scheme comfort level, the nutritional configuration parameters of the final output are determined.

[0051] S400, acquiring real-time posture data and historical posture data, and determining a target feedback state based on a comparison result between the historical posture data and the real-time posture data.

[0052] Among them, the real-time posture data is compared with the historical posture data. The purpose of the comparison is to find out the differences and change trends between the historical posture data and the real-time data. Nutritional configuration parameters refer to specific indicators or rules related to the body shape data of the target user. For different target users, the differences and change trends of body shape data are analyzed, and the body shape of the target user can be judged in combination with the nutritional configuration parameters.

[0053] Specifically, Figure 4 As shown, for step S400, it also includes:

[0054] S401, determining nutrition configuration parameters related to body shape data according to nutrition requirements and target user characteristics.

[0055] S402, based on the comparison result between the real-time posture data and the historical posture data, perform state judgment and output an initial state set.

[0056] S403, based on the initial state set, obtain N target state features under N states; based on the loss of the N target state features, determine to obtain N state indexes; wherein N is the result value after state category clustering of the target user.

[0057] For the target state feature, select N states as the initial cluster centers, compare the distance between the state center and the target state feature, and select the closest N target state features. Then calculate the square root of the sum of the squares of the distance differences, and use it as the evaluation value of the initial cluster center. Select the initial cluster center closest to the evaluation value as the cluster center, and determine the value of N according to the numerical value of the cluster center.

[0058] The obtained N target state features, N states, and N state indexes correspond one to one.

[0059] S404, setting the largest state index among the N state indexes as the first state index, taking the first state index as an advantage, and outputting the state index that best matches the target user as the target feedback state.

[0060] S500, based on the target feedback state, determining a first compensation variable of the nutrition plan, wherein the first compensation variable has at least two data types, and outputting a first compensation variable implementation instruction.

[0061] In this step, the part that needs to be supplemented in the nutrition plan is determined based on the target feedback state, and the first compensation variable is selected according to the target feedback state; the first compensation variable is the variable most relevant to the current state after the target state is clustered; the first compensation variable includes at least two data types, such as value, ratio, percentage, etc.

[0062] Specifically, the first compensation variable can be the component of nutrition intake for the target user. For example, when the user's physical condition lacks hygienic elements, the first compensation variable is the vitamins mainly taken in for the current illness; when the user's own white blood cells or other human body components are too high, the first compensation variable is the medicine that cures or reduces the excessive human body components.

[0063] For step S500, Figure 5 The processing is as follows:

[0064] S501, selecting a nutrition plan that matches the target feedback state from a preset nutrition plan library.

[0065] S502, performing feature recognition on the nutrition plan, and identifying a state interval that is greater than the target feedback state.

[0066] S503, marking the state interval in real time, and selecting the value with the largest difference between the target feedback state and the state interval as the determined first compensation variable.

[0067] S504, inputting the first compensation variable into the state association model to determine the output first compensation variable.

[0068] For determining the first compensation variable, the user environment feature and the target feature corresponding to each first compensation variable are compared, and the first compensation variable is determined by comparing the part with the smallest difference between the target feature and the user environment feature.

[0069] S505: Generate a corresponding first compensation variable implementation instruction based on the first compensation variable.

[0070] Among them, a nutrition plan that meets the requirements is obtained from a preset nutrition plan library, feature identification is performed in the nutrition plan, and compared with the target feedback state, and the value with the largest difference is selected as the output state interval. The state interval is obtained based on the set of outputs after comparing the target feedback state with multiple nutrition plans; then the value in the state interval with the largest difference is selected as the first compensation variable, and the adaptability of the first compensation variable is determined according to the set state association model, and the first compensation variable with the highest adaptability is output.

[0071] In detail, the higher the adaptability, the more the nutritional plan obtained according to the first compensation variable is closer to people's daily life and the dietary plan needed to solve physical problems. The lower the adaptability, the worse the effect of the plan obtained according to the first compensation variable.

[0072] For example, according to the target feedback state, two data-type variables are selected as the first compensation variables; these two variables are the nutritional configuration parameters that are desired to be changed or adjusted, such as the amount of protein (g) and the amount of fat (g) ingested.

[0073] The output first compensation variable implementation instruction is: increase protein intake to the target value of X grams, and reduce fat intake to the target value of Y grams. The first compensation variable implementation instruction obtained at this time is used to adjust the intake of protein and fat.

[0074] S600, executing instructions based on the first compensation variable, taking the nutrition configuration parameter as input, and determining to obtain a second compensation variable.

[0075] The second compensation variable is selected according to the change of the current body shape data. The second compensation variable is selected based on the first compensation variable and is a relatively prominent variable in the change of the body shape data.

[0076] Specifically, the second compensation variable means that after the human body composition is processed by the first compensation variable, if there is still a certain human body risk or the first compensation variable used cannot completely solve the problem caused by too high or too low human body composition, the second compensation variable is used to assist the first compensation variable to solve the problem.

[0077] For example, the first compensating variable is protein intake and fat intake, and the second compensating variable is weight change;

[0078] Increasing protein intake provides more amino acids that aid in muscle repair and growth, which may lead to an increase in muscle mass, weight gain, or a decrease in fat mass.

[0079] Reducing fat intake can reduce energy intake and thus contribute to weight loss or a decrease in fat mass.

[0080] The first compensation variable will cause the second compensation variable to increase or decrease. Adaptive adjustment of the first compensation variable and the second compensation variable can improve the treatment effect of the nutrition plan.

[0081] Specifically, Figure 6 As shown, the implementation of step S600 is as follows:

[0082] S601, determining nutrition configuration parameters for each group according to the needs of target users and characteristics of the nutrition plan;

[0083] S602, taking the first compensation variable implementation instruction as input, and making corresponding adjustments according to the information in the implementation instruction;

[0084] S603, determining the association between the nutrition configuration parameter and the first compensation variable in combination with the needs and historical body shape data of the target user;

[0085] S604: Determine a second compensation variable based on the analysis result of the nutrition configuration parameter and the first compensation variable.

[0086] A data model related to the nutrition configuration parameter is established according to the second compensation variable, the nutrition configuration parameter is input into the state association model, and the value or setting of the second compensation variable is determined according to the calculation and prediction results of the model.

[0087] The nutrition plan generated at this time has at least two or more compensation values, making the nutrition plan easier to modify and implement.

[0088] S700, taking the first compensation variable implementation instruction as input, the second compensation variable as a variable, and the user environment characteristic as a supplementary variable, and obtaining a correlation topology map according to a target feedback state.

[0089] Specifically, in order to make the acquired body data more suitable for the implementation requirements, such as Figure 7 As shown, step S700 is performed as follows:

[0090] S701, obtaining feedback status and user environment feature data of a target user;

[0091] S702, determining the specific definition and range of the first compensation variable implementation instruction and the second compensation variable;

[0092] S703, using the first compensation variable implementation instruction, the second compensation variable and the user environment feature as nodes to establish a correlation topology graph;

[0093] S704, inputting the real-time body condition data into the association topology map, and adding related nodes and edges to the association topology map;

[0094] S705, analyzing the constructed association topology graphs, and comparing the associations and impact paths between the association topology graphs.

[0095] Specifically, the first compensation variable implementation instruction and the second compensation variable are analyzed according to the user environment characteristics, and the relationship between these data is used to establish a corresponding association topology diagram. The association topology diagram is used to display the relevant information between different data, and the weight distribution between each variable is determined according to the distance between each node; the user environment characteristics corresponding to the target user are used as input information, and the first compensation variable implementation instruction and the second compensation variable that are closest to the target user are selected, so as to determine the first compensation implementation quality and the second compensation variable adopted by the nutrition plan.

[0096] Afterwards, the distances between multiple input user environment features are judged, and the user environment feature with the largest weight value is selected as the final basis for selecting a nutrition plan, and the nutrition plan is pushed to the user.

[0097] In this step, instructions are implemented for the first compensation variable and the second compensation variable determines the human body components that need to be processed, such as processing protein intake, the treatment method for leukopenia, determining the relationship between body shape data and different compensation variables, what form of components will be missing when the body shape data increases, and comparing the associations and influence paths between the association topology diagrams based on these mutually influential relationships.

[0098] In one embodiment of the present invention, the abnormal information existing in the association topology diagram is determined according to the input variables, and the final generated nutrition plan is determined according to the specific situation of the abnormal information, such as Figure 8 The specific implementation is as follows:

[0099] S800, based on the association topology map, input the body shape data of the target user, obtain the abnormal data set, and determine the nutrition index according to the abnormal data set;

[0100] S801, input all relevant variables into the association topology map, perform anomaly identification on the output result of the association topology map according to preset indicators, and obtain an abnormal data set.

[0101] Among them, the abnormal identification of the associated topology diagram includes:

[0102] Defining Preset Indicators,First, the preset indicators for anomaly identification are determined, which can be attributes or parameters related to the topological graph, such as the degree of nodes, the weight of edges, and the distance between nodes.

[0103] Build a normal data set, using a known normal data set, calculate the value of each indicator, and use these indicators for the benchmark under normal conditions.

[0104] Obtain an abnormal data set, and determine the value of the indicator after the abnormal data is input according to the association between the abnormal data set and the associated topology graph.

[0105] Feature extraction, taking the values ​​of preset indicators extracted from each associated topological graph as features.

[0106] Anomaly recognition model training, using normal data sets and abnormal data sets to build an anomaly recognition model; using the extracted features as input, marking normal data as category 1 and abnormal data as category 0, and performing model training.

[0107] Anomaly identification: Use the trained model to identify anomalies in new topology data. Extract the features of new data and use the model to make predictions; based on the output of the model, record the data that is judged to be abnormal.

[0108] Construct anomaly data set: Based on the results of anomaly identification, the associated topological map data that is judged to be abnormal is recorded to form an anomaly data set.

[0109] In order to make the data obtained from the abnormal data set more accurate, the abnormal data set is divided into the first abnormal variable and the second abnormal variable, and the difference between the two abnormal variables is compared to obtain clearer abnormal features. Specifically, as shown below:

[0110] S802, determining whether the current abnormal data set is two types of outputs, if the abnormal data set is two types of outputs, determining the environmental abnormality variable according to the user environment characteristics.

[0111] S803, determining a first abnormal variable and a second abnormal variable according to the environmental abnormal variable, wherein the first abnormal variable refers to an output of one type of the environmental abnormal variable, and the second abnormal variable refers to an environmental abnormal variable other than the first abnormal variable.

[0112] S804: Extract an abnormal difference set using the first abnormal variable and the second abnormal variable.

[0113] The abnormal difference set is used to obtain abnormal variables with different values ​​between the first abnormal variable and the second abnormal variable, thereby reducing the time complexity of the acquisition and being able to more accurately obtain the time when the abnormal data occurs;

[0114] Furthermore, the acquired abnormal data set is compared with the nutritional parameters configured in real time to determine the optimized nutritional configuration parameters.

[0115] S805, obtaining real-time nutrition configuration parameters and predicted nutrition configuration parameters; based on the abnormal difference set, screening the real-time nutrition configuration parameters and predicted nutrition configuration parameters, and outputting nutrition control indicators; wherein the nutrition control indicators are indicators output after excluding the parameters related to the point abnormal difference set.

[0116] S806, optimizing the association topology map based on the nutrition control index; obtaining the nutrition superposition index of each nutrition configuration process in the association topology map.

[0117] S807, based on the nutrition superposition index, compare the preset adaptation value, and output the compared nutrition superposition index as the nutrition index of the nutrition plan.

[0118] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0119] The present application processes the body data of the target user to obtain the target data set and the target user characteristics; according to the target user characteristics, the nutrition configuration parameters are determined; based on the comparison results of the historical body data and the real-time body data, the target feedback state is determined, based on the target feedback state, the first compensation variable of the nutrition plan is determined, based on the first compensation variable implementation instruction, the nutrition configuration parameters are used as input, and the second compensation variable is determined; the first compensation variable implementation instruction is used as input, the second compensation variable is used as a variable, and the user environment characteristics are used as supplementary variables, and according to the target feedback state, the association topology map is obtained; based on the association topology map, the body data of the target user is input to obtain an abnormal data set, and the nutrition index is determined according to the abnormal data set. The first compensation variable and the second compensation variable obtained can supplement the deficiencies in the nutrition plan, and according to the target feedback state and the user environment characteristics, the obtained plan can be more adaptable to the current environment, and can better highlight the predictability, prevention, personalization and participation of the nutrition plan for the target user.

[0120] like Figure 2 As shown, a digital clinical nutrition intelligent management system includes:

[0121] A user status data acquisition module is used to acquire the body data of the target user, and when the amount of body data reaches the quantity required for analysis, it is sent to the environment feature extraction module;

[0122] An environment feature extraction module is used to obtain user environment features of a target user based on a target data set and target user features;

[0123] A feedback state determination module is used to determine the target feedback state according to the comparison result between the historical posture data and the real-time posture data;

[0124] A first compensation module, used for obtaining a first compensation variable of the nutrition scheme in each state according to the target feedback state;

[0125] A second compensation module, used for determining a second compensation variable according to the needs and historical body shape data of the target user;

[0126] An association module, used to determine an association topology map according to the first compensation variable instruction, the second compensation variable, the user environment characteristics, and the target feedback state;

[0127] The abnormal analysis module is used to input the target user's body data based on the association topology map, obtain the abnormal data set, and determine the nutritional index according to the analysis result of the abnormal data set.

[0128] In one embodiment of the present invention, a digital clinical nutrition intelligent management system further includes: a nutrition distribution unit and a state selection unit.

[0129] A nutrition allocation unit, used to select corresponding nutrition configuration parameters according to the nutrition setting process;

[0130] The state selection unit is used to determine the state index according to the target state characteristics of the target user, and set the largest state index among the state indexes as the first state index.

[0131] In one embodiment of the present invention, a digital clinical nutrition intelligent management system also includes: a state association unit, an abnormality identification unit, and a nutrition superposition unit.

[0132] A state association unit, configured to identify a state interval in the nutrition plan that is greater than the target feedback state according to the target feedback state, and select a first compensation variable based on the state interval;

[0133] An anomaly identification unit, used to identify anomalies on the output results of the association topology map and obtain an anomaly data set;

[0134] The nutrition superposition unit is used to obtain the nutrition superposition index of each nutrition configuration process in the associated topology diagram based on the nutrition control index.

[0135] The above description is only a preferred embodiment of the present invention and is 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 digital clinical nutrition intelligent management method, characterized in that: include: Acquire body shape data of a target user, and acquire a target data set and target user characteristics from the body shape data; The target data set consists of data related to the physical characteristics of the target user; Determine the user environment characteristics of the target user based on the target data set and the target user characteristics; According to the user's environmental characteristics, the body data is screened to obtain a screened data set, and the nutritional configuration parameters are determined based on the screened data set; Acquire real-time posture data and historical posture data, and determine the target feedback state based on the comparison result between the historical posture data and the real-time posture data; Based on the target feedback state, determining a first compensation variable of the nutrition plan, wherein the first compensation variable is at least two data types, and outputting a first compensation variable implementation instruction; Implementing instructions based on the first compensation variable, taking the nutrition configuration parameter as input, and determining to obtain a second compensation variable; Taking the first compensation variable implementation instruction as input, the second compensation variable as variable, and the user environment characteristic as supplementary variable, obtaining the association topology map according to the target feedback state; Based on the association topology graph, the target user's body data is input to obtain an abnormal data set, and the nutritional index is determined according to the abnormal data set; Wherein, determining the nutrition configuration parameters based on the screening data set includes: Generating a preliminary nutrition plan based on the screening data set; Determine the nutrition setting process of the preliminary nutrition plan according to the user's environmental characteristics; According to the nutrition allocation index in each nutrition setting process, the nutrition configuration parameters of each nutrition setting process are obtained; The step of determining a first compensation variable of the nutrition plan based on the target feedback state and outputting a first compensation variable implementation instruction comprises: From the preset nutrition plan library, select the nutrition plan that matches the target feedback status; Characterize the nutrition plan and identify the state interval that is greater than the target feedback state; Mark the state interval in real time, and select the value with the largest difference between the target feedback state and the state interval as the first compensation variable to be determined; Inputting the first compensation variable into the state association model to determine the output first compensation variable; Based on the output first compensation variable, generating a corresponding first compensation variable implementation instruction; The step of executing the instruction based on the first compensation variable, taking the nutrition configuration parameter as input, and determining to obtain the second compensation variable comprises: Determine the nutritional configuration parameters for each group based on the needs of the target users and the characteristics of the nutritional program; Taking the first compensation variable implementation instruction as input, and making corresponding adjustments according to the information in the implementation instruction; Determine the association between the nutrition configuration parameter and the first compensation variable in combination with the needs and historical body shape data of the target user; Determining a second compensation variable based on the analysis results of the nutrition configuration parameter and the first compensation variable; The association topology diagram is represented as follows: Obtain target user’s feedback status and user environment feature data; Determine the specific definition and range of the first compensation variable implementation instruction and the second compensation variable; Taking the first compensation variable implementation instruction, the second compensation variable and the user environment characteristics as nodes, establishing a correlation topology graph; Input the real-time body posture data into the association topology graph, and add the relevant nodes and edges to the association topology graph; Analyze the constructed association topology graphs and compare the associations and impact paths between the association topology graphs; The step of inputting the body data of the target user and obtaining the abnormal data set includes: All relevant variables are input into the association topology map, and the output results of the association topology map are identified as abnormal according to preset indicators to obtain the abnormal data set.

2. A digital clinical nutrition intelligent management method as claimed in claim 1, characterized in that: The step of acquiring the real-time posture data and the historical posture data, and determining the target feedback state based on the comparison result between the historical posture data and the real-time posture data, includes: Determine the nutritional configuration parameters related to body shape data according to nutritional needs and target user characteristics; Based on the comparison results of real-time posture data and historical posture data, the state is judged and the initial state set is output; Based on the initial state set, N target state features under N states are obtained; based on the loss of the N target state features, N state indexes are determined; wherein N is the result value after the state category of the target user is clustered; The largest state index among the N state indexes is set as the first state index, the first state index is used as the advantage, and the state index that best matches the target user is output as the target feedback state.

3. A digital clinical nutrition intelligent management method as claimed in claim 1, characterized in that: Determining the nutritional index according to the abnormal data set includes: Determine whether the current abnormal data set is two types of output. If the abnormal data set is two types of output, determine the environmental abnormal variables according to the user environment characteristics; According to the environmental abnormal variable, a first abnormal variable and a second abnormal variable are determined; Extracting an abnormal difference set using the first abnormal variable and the second abnormal variable; Obtain real-time nutrition configuration parameters and predicted nutrition configuration parameters; based on the abnormal difference set, screen the real-time nutrition configuration parameters and predicted nutrition configuration parameters, and output nutrition control indicators; Based on the nutrition control index, the association topology map is optimized; the nutrition superposition index of each nutrition configuration process in the association topology map is obtained; Based on the nutrition superposition index, the preset adaptation value is compared, and the compared nutrition superposition index is output as the nutrition index of the nutrition plan.

4. A digital clinical nutrition intelligent management system, applied to the digital clinical nutrition intelligent management method as described in any one of claims 1 to 3, characterized in that: include: A user status data acquisition module is used to acquire the body data of the target user, and when the amount of body data reaches the quantity required for analysis, it is sent to the environment feature extraction module; An environment feature extraction module is used to obtain user environment features of a target user based on a target data set and target user features; A feedback state determination module is used to determine the target feedback state according to the comparison result between the historical posture data and the real-time posture data; A first compensation module, used for obtaining a first compensation variable of the nutrition scheme in each state according to the target feedback state; A second compensation module, used for determining a second compensation variable according to the needs and historical body shape data of the target user; An association module, used to determine an association topology map according to the first compensation variable instruction, the second compensation variable, the user environment characteristics, and the target feedback state; The abnormal analysis module is used to input the target user's body data based on the association topology map, obtain the abnormal data set, and determine the nutritional index according to the analysis result of the abnormal data set.

5. A digital clinical nutrition intelligent management system as claimed in claim 4, characterized in that: Also includes: Nutrition allocation unit, state selection unit; A nutrition allocation unit, used to select corresponding nutrition configuration parameters according to the nutrition setting process; The state selection unit is used to determine the state index according to the target state characteristics of the target user, and set the largest state index among the state indexes as the first state index.

6. A digital clinical nutrition intelligent management system as claimed in claim 5, characterized in that: Also includes: State association unit, abnormality identification unit, and nutrition superposition unit; A state association unit, configured to identify a state interval in the nutrition plan that is greater than the target feedback state according to the target feedback state, and select a first compensation variable based on the state interval; An anomaly identification unit, used to identify anomalies on the output results of the association topology map and obtain an anomaly data set; The nutrition superposition unit is used to obtain the nutrition superposition index of each nutrition configuration process in the associated topology diagram based on the nutrition control index.

Images