Display method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a display method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: acquiring a flavor improvement instruction of a target detection object; according to a target basic node corresponding to the target attribute data in the target influence node data, a target metabolism node corresponding to the target metabolism data and a target flavor evaluation node corresponding to the target flavor evaluation data, determining an associated variable node; according to the target influence node data, the target flavor evaluation data and a relationship among the target flavor influence node, the associated variable node and the target flavor evaluation node, determining node data of the associated variable node; and outputting and displaying the associated variable node and the node data of the associated variable node. The method is used for improving the effect of adjusting and analyzing the flavor of the food.

Description

Technical Field

[0001] The present application relates to the technical field of food analysis, and in particular to a display method, device, electronic device, storage medium and program product. Background Art

[0002] Food flavor analysis is an important branch of food science and technology, focusing on the study of food flavor characteristics, that is, the comprehensive feeling that food brings to people, including taste, smell, touch and other aspects. The main goal of food flavor analysis is to understand the formation mechanism of food flavor, evaluate and improve the flavor quality of food, so as to meet the needs of consumers. In order to identify the key compound components that affect food flavor, the existing technology includes the following steps: First, obtain the sensory evaluation data and metabolomics data of the food. The sensory evaluation data is obtained through taster or consumer testing, and the metabolomics data is obtained through high-throughput analysis technology (such as GC-MS and LC-MS). Then, multivariate statistical analysis or machine learning methods are used to analyze the correlation between the two sets of data. In this way, compounds that are consistent with the sensory evaluation can be identified, and these compounds are the key factors affecting food flavor.

[0003] However, existing methods have the problem of poor effect in adjusting and analyzing food flavor. Summary of the invention

[0004] The embodiments of the present application provide a display method, device, electronic device, storage medium and program product to improve the effect of adjusting and analyzing food flavor.

[0005] In a first aspect, an embodiment of the present application provides a display method, which is applied to a food flavor analysis system, comprising:

[0006] Acquire a flavor improvement instruction of a target detection object, the flavor improvement instruction including target impact node data and target flavor evaluation data, the target impact node data including at least one of target attribute data and target metabolism data;

[0007] Determine an associated variable node according to a target basic node corresponding to the target attribute data, a target metabolic node corresponding to the target metabolic data, and a target flavor evaluation node corresponding to the target flavor evaluation data in the target influence node data, wherein the associated variable node is a node that has an associated relationship with the target basic node or the target metabolic node and a causal relationship with the target flavor evaluation node;

[0008] Determining node data of an associated variable node according to target influence node data, target flavor evaluation data, and a relationship among a target flavor influence node, an associated variable node, and a target flavor evaluation node;

[0009] Output and display the associated variable nodes and the node data of the associated variable nodes.

[0010] In a possible implementation, obtaining a flavor improvement instruction of a target detection object includes:

[0011] Display the flavor index input interface, which includes a node input area and a node data input area;

[0012] In response to the user's input operation on the node input area and the node data input area in the flavor index input interface, a flavor improvement instruction of the target detection object is obtained.

[0013] In a possible implementation, determining the associated variable node according to the target basic node corresponding to the target attribute data, the target metabolism node corresponding to the target metabolism data, and the target flavor evaluation node corresponding to the target flavor evaluation data in the target influence node data includes:

[0014] Determining a basic node, a metabolic node, and a node relationship between the target flavor evaluation node, the basic node, and the metabolic node in the target detection object that affect the target flavor evaluation node;

[0015] According to the target flavor evaluation node, the node relationship between the basic node and the metabolic node, the target basic node and the target metabolic node, the associated variable node is determined.

[0016] In a possible implementation, determining a base node, a metabolic node, and a node relationship among the target flavor evaluation node, the base node, and the metabolic node in the target detection object that affect the target flavor evaluation node includes:

[0017] Acquire training samples, where the training samples include basic sample data, metabolic sample data, and assessment sample data corresponding to the basic sample data and the metabolic sample data;

[0018] Determine the initial global node relationship of the basic sample node, the assessment sample data node, and the assessment sample node according to the basic sample node corresponding to the basic sample data, the metabolic sample node corresponding to the metabolic sample data, and the assessment sample node corresponding to the assessment sample data;

[0019] According to the basic sample data, the metabolic sample data, and the assessment sample data corresponding to the basic sample data and the metabolic sample data, the initial global node relationship is adjusted to obtain the global node relationship;

[0020] According to the target flavor evaluation node, a basic node and a metabolic node that affect the target flavor evaluation node, and a node relationship among the target flavor evaluation node, the basic node and the metabolic node are determined from the global node relationship.

[0021] In a possible implementation, determining the associated variable node according to the target flavor evaluation node, the node relationship between the base node and the metabolic node, the target base node and the target metabolic node includes:

[0022] According to the target flavor evaluation node, the node relationship between the basic node and the metabolic node, and the target basic node, determining a first associated variable node in the node relationship, the first associated variable node being a node in the metabolic node that has an associated relationship with the target basic node;

[0023] According to the target flavor evaluation node, the node relationship between the basic node and the metabolic node, and the target metabolic node, determining a second associated variable node in the node relationship, the second associated variable node being a node in the metabolic node that has an associated relationship with the target metabolic node, and a node in the basic node that has an associated relationship with the target metabolic node;

[0024] An associated variable node is determined according to the first associated variable node and the second associated variable node.

[0025] In a possible implementation, determining the node data of the associated variable node according to the target influence node data, the target flavor evaluation data, and the relationship between the target flavor influence node, the associated variable node, and the target flavor evaluation node includes:

[0026] According to the relationship between the target flavor influence node, the associated variable node and the target flavor evaluation node, a node relationship equation is constructed;

[0027] According to the target influence node data, the target flavor evaluation data and the node relationship equation, the node data of the associated variable node is obtained.

[0028] In a possible implementation, the flavor improvement instruction of the target detection subject further includes an intervention variable;

[0029] According to the target impact node data, the target flavor evaluation data and the node relationship equation, the node data of the associated variable node is obtained, including:

[0030] According to the target impact node data, the target flavor evaluation data and the node relationship equation, the initial node data of the associated variable node is obtained;

[0031] The node data of the associated variable node is obtained according to the initial node data and the intervention variable of the associated variable node.

[0032] In a possible implementation manner, when there are multiple target flavor evaluation data in the flavor improvement instruction,

[0033] After obtaining the flavor improvement instruction of the target detection object, the method further includes:

[0034] Determine an associated variable node according to a target basic node corresponding to the target attribute data, a target metabolism node corresponding to the target metabolism data, and a target flavor evaluation node corresponding to the target flavor evaluation data in the target influence node data;

[0035] Determining node data of an associated variable node according to target influence node data, target flavor evaluation data, and a relationship among a target flavor influence node, an associated variable node, and a target flavor evaluation node;

[0036] According to the node data of the associated variable node, the global node data of the associated variable node is obtained;

[0037] The global node data of the associated variable node is processed to obtain the optimal solution to obtain the target node data of the associated variable node;

[0038] Output and display the associated variable node and the target node data of the associated variable node.

[0039] In a second aspect, an embodiment of the present application provides a display device, which is applied to a food flavor analysis system, and the device includes:

[0040] an acquisition module, configured to acquire a flavor improvement instruction of a target detection object, wherein the flavor improvement instruction includes target impact node data and target flavor evaluation data, wherein the target impact node data includes at least one of target attribute data and target metabolism data;

[0041] A first determination module is used to determine an associated variable node according to a target basic node corresponding to the target attribute data, a target metabolic node corresponding to the target metabolic data, and a target flavor evaluation node corresponding to the target flavor evaluation data in the target influence node data, wherein the associated variable node is another flavor influence node that has an associated relationship with the target basic node or the target metabolic node and a causal relationship with the target flavor evaluation node;

[0042] a second determination module, for determining node data of an associated variable node according to target influence node data, target flavor evaluation data, and a relationship among the target flavor influence node, the associated variable node, and the target flavor evaluation node;

[0043] The output module is used to output and display the associated variable nodes and the node data of the associated variable nodes.

[0044] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0045] Memory stores computer-executable instructions;

[0046] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0047] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0048] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0049] The display method, device, electronic device, storage medium and program product provided in the embodiments of the present application determine the associated variable node that has an association relationship with the target basic node or the target metabolic node and a causal relationship with the target flavor evaluation node through the flavor improvement instruction of the target detection object and the nodes corresponding to each data in the flavor improvement instruction. According to the causal relationship between the nodes, the node data of the associated variable node is determined, thereby achieving the effect of improving the adjustment and analysis of food flavor. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0051] Figure 1 A schematic diagram of an application scenario of the display method provided in an embodiment of the present application;

[0052] Figure 2 Schematic diagram of the process of the display method provided in the embodiment of the present application Figure 1 ;

[0053] Figure 3 Schematic diagram of the process of the display method provided in the embodiment of the present application Figure 2 ;

[0054] Figure 3a A schematic diagram of the structure of the causal relationship graph model provided in the embodiment of the present application Figure 1 ;

[0055] Figure 3b A schematic diagram of the structure of the causal relationship graph model provided in the embodiment of the present application Figure 2 ;

[0056] Figure 4 Schematic diagram of the process of the display method provided in the embodiment of the present application Figure 2 ;

[0057] Figure 4a A schematic diagram of the structure of the causal relationship graph model provided in the embodiment of the present application Figure 3 ;

[0058] Figure 4b A schematic diagram of the structure of the causal relationship graph model provided in the embodiment of the present application Figure 4 ;

[0059] Figure 5 A schematic diagram of the structure of a display device provided in an embodiment of the present application;

[0060] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0061] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0062] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0063] First, the terms involved in this application are explained:

[0064] Food economics is a discipline that studies food production, distribution, consumption and its economic impact. New flavor development involves food economics because it has a direct impact on the supply and demand relationship, prices, consumer preferences and industry competition in the food market. The success of new flavor products can stimulate market demand, drive sales and economic growth, which in turn affects producers' decisions and resource allocation.

[0065] Coffee flavor is a general term for the sensory characteristics of coffee, including aroma or smell, flavor, aftertaste, acidity, body, body fat, consistency, balance, flaws, sweetness and overall impression; coffee flavor is affected by many factors, such as the variety of coffee beans, origin, processing and storage methods, etc.

[0066] Omics is a method of studying molecular data in organisms (such as genomes, proteomes, metabolomes, etc.), aiming to fully understand the structure, function and dynamic changes of biological systems.

[0067] Sensory evaluation refers to the method of evaluating and measuring the various characteristics of food through human senses (such as vision, smell, taste, touch and hearing); sensory evaluation plays an important role in food science, quality control and new product development.

[0068] Biomarkers in beverages are specific compounds (such as caffeine, chlorogenic acid), genes (regulating the synthesis of caffeine, etc.), etc. that can be used to evaluate beverage quality, health effects and consumption habits.

[0069] Dimensionality reduction refers to mapping high-dimensional data to a low-dimensional space to reduce the number of features while retaining the main information of the data as much as possible. Commonly used dimensionality reduction methods include principal component analysis (PCA) and linear discriminant analysis (LDA).

[0070] Causal discovery methods provide decision makers with a structured model for analyzing and understanding behavioral data.

[0071] Counterfactual reasoning is a method of reasoning that explores the possible outcomes of an event or condition by assuming different changes in the same environment. The counterfactual principle is that for an entity, only factual data can be observed, and other unobserved data is called counterfactual data.

[0072] Food flavor analysis can be used to understand the flavor characteristics of food to ensure product quality, develop new products, improve recipes or meet consumer needs. For example, the flavor characteristics of coffee must meet consumer needs and are the most direct factor affecting consumer preferences. At present, when analyzing the flavor of food, the flavor of food can be evaluated by manual sensory evaluation, that is, a group of professionally trained assessors analyze the food samples. The assessors can keenly perceive and describe the sensory attributes of the food samples such as color, aroma and taste. During the sensory evaluation process, the evaluation results are usually recorded in the form of a score sheet or radar chart to quantify the flavor characteristics of the food samples. However, with the development of scale and group production of food, it is difficult to achieve the purpose of controlling food quality by relying solely on assessors for manual sensory evaluation; at the same time, manual sensory evaluation is easily affected by the subjectivity of the assessors, and factors such as the assessors' work experience, personal preferences, regional differences and olfactory fatigue will directly affect the evaluation results of food quality. With the rapid development of artificial intelligence (AI) technology, an objective model can be obtained based on limited sample learning to assess food quality, which is of great significance for promoting standardized production, structural adjustment and healthy and rapid development of the food industry.

[0073] At present, the existing methods generally use a pre-built analysis model that characterizes sensory evaluation data and metabolome data when performing food flavor improvement analysis. According to the flavor instructions that need to be improved, the metabolome data changes adjusted with the sensory evaluation data are determined from the analysis model, thereby realizing the food flavor improvement analysis. Among them, the construction process of the analysis model may include: obtaining sensory evaluation data and metabolome data of food samples, and the metabolome data can be obtained by, for example, gas chromatography-mass spectrometry (GC-MS) and liquid chromatography-mass spectrometry (LC-MS); obtaining the correlation between the sensory evaluation data and the metabolome data through multivariate statistical analysis or machine learning methods to help understand the flavor formation mechanism of food, thereby obtaining an analysis model.

[0074] However, since the obtained analytical model mainly identifies compound components that are consistent with the sensory evaluation trend based on correlation, the correlation between the sensory evaluation data and the metabolomics data cannot accurately reflect the causal relationship, because correlation is not equal to causality, which may lead to the emergence of pseudo-correlation. For example, both variables may be affected by another common factor (such as altitude), resulting in misleading results. Therefore, the key influencing factors obtained in the above manner are not accurate enough. Therefore, when using this model for analysis, there is a problem of low accuracy.

[0075] Based on the above problems, the present application provides a display method, apparatus, device, storage medium and program product, which can determine, based on the causal relationship between the basic nodes, metabolic nodes and flavor assessment nodes in the target detection object, when receiving a flavor improvement instruction, first determine the associated variable nodes that have an association relationship with the target basic node or the target metabolic node and a causal relationship with the target flavor assessment node according to the target basic node corresponding to the target attribute data, the target metabolic node corresponding to the target metabolic data, and the target flavor assessment data in the instruction, and then determine the node data of the associated variable nodes according to the relationship between the nodes, so that the adjustment strategy of the target detection object can be obtained according to the node data of the associated variable nodes to achieve flavor improvement of the target detection object.

[0076] Figure 1 Schematic diagram of application scenarios of the display method provided in the embodiment of the present application. Figure 1As shown, the application scenario includes: a food flavor analysis system. The food flavor analysis system can be a server, and the server can be a desktop computer, a notebook, a personal digital assistant (PDA), a smart phone, a tablet computer, etc. The embodiment of the present application provides no restriction on the execution subject, as long as the execution subject can execute the flavor improvement instruction of the target detection object, the flavor improvement instruction includes target influence node data and target flavor evaluation data, and the target influence node data includes at least one of target attribute data and target metabolism data; according to the target basic node corresponding to the target attribute data in the target influence node data, the target metabolism node corresponding to the target metabolism data, and the target flavor evaluation data corresponding to the target flavor evaluation data, determine the associated variable node, the associated variable node is a node that has an association relationship with the target basic node or the target metabolism node, and has a causal relationship with the target flavor evaluation node; according to the target influence node data, the target flavor evaluation data, and the relationship between the target flavor influence node, the associated variable node and the target flavor evaluation node, determine the node data of the associated variable node; output and display the associated variable node and the node data of the associated variable node.

[0077] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0078] Figure 2 Schematic diagram of the process of the display method provided in the embodiment of the present application Figure 1 ,like Figure 2 As shown, the execution subject of the method may be a food flavor analysis system, and the method may include:

[0079] S201. Obtain a flavor improvement instruction for a target detection object, where the flavor improvement instruction includes target influencing node data and target flavor evaluation data, and the target influencing node data includes at least one of target attribute data and target metabolism data.

[0080] The target detection object may refer to a detection object that needs to be analyzed for food flavor improvement, and the detection object may be any food, such as coffee, chocolate, spices, nuts, and tea.

[0081] The flavor improvement instruction may refer to an instruction sent directly by a user to the food flavor analysis system, or may refer to an instruction sent indirectly by a user to the food flavor analysis system through other clients. The instruction is used to instruct the food flavor analysis system to perform an improved analysis of the food flavor of the target detection object.

[0082] The target influencing node data may refer to data that influences the target flavor rating data, and the data may be part of all data that influences the target flavor rating data.

[0083] In the embodiment of the present application, the data that affects the target flavor evaluation data can be divided into target attribute data and target metabolism data according to their types, wherein the target attribute data can represent the data involved in the process from planting to picking, processing, etc. of the target detection object, and the target metabolism data can represent the component data of the target detection object itself.

[0084] In an embodiment of the present application, when the target influencing node data includes target attribute data, the target attribute data may refer to the data of the target attribute, and the target attribute may refer to the basic attribute selected from the basic attributes of the target detection object. Among them, the basic attributes may include the origin, altitude, etc. of the target detection object in the planting stage, the picking strategy in the picking stage, the washing and honey treatment in the primary processing stage, the shallow, medium and deep baking in the deep processing stage, and the storage link, etc., which affect the attributes of the flavor of the target detection object. For example, when the target detection object is coffee beans, the target attribute may include the following basic attributes: genotype, variety, origin, light, temperature, humidity, altitude, UV (Ultraviolet), field management (fertilizer, irrigation or pruning), picking period (fruit maturity or fruit color), processing method (dry fermentation, wet fermentation, honey treatment, or barrel fermentation), baking method, baking degree, storage time, storage method, grinding degree, extraction method, formula, ratio, etc. At least one basic attribute. The target attribute data may be parameter data corresponding to the target attribute.

[0085] When the target influencing node data includes target metabolic data, the target metabolic data may refer to the data of the target metabolic components within the target detection object, and the target metabolic components may be selected from the metabolic components of the target detection object. Among them, the metabolic components of the target detection object may be detected by a chemical detector (FID or MS), thereby obtaining the odor characteristic original data composed of chromatographic and mass spectrometric original data (i.e., the chromatographic and mass spectrometric data of the content and chemical structure of each volatile component of the target detection object). For example, when the target detection object is coffee beans, the target metabolic components of the target detection object may refer to compounds including caffeine, harringtonine, chlorogenic acid, sucrose and lipids that are regulated by genotype and significantly affected by environmental conditions and processing. The target metabolic data of the target metabolic components may refer to parameter data such as the content of the target metabolic components.

[0086] The target flavor evaluation data may refer to data obtained through sensory evaluation and used to describe the desired flavor characteristics, such as aroma, taste, mouthfeel, etc. In some embodiments, the target flavor evaluation data may be obtained by evaluation by professional sensory evaluators, or may refer to data obtained after analysis based on metabolic data. In the embodiments of the present application, the target flavor evaluation data may refer to the required data for a certain flavor evaluation dimension of the target detection object. For example, when the target impact node data is the data corresponding to the target detection object when the aroma level is 5, the target flavor evaluation data may represent the data for increasing the aroma level to 7.

[0087] In this embodiment of the present application, the method for obtaining the flavor improvement instruction of the target detection object may include:

[0088] Display the flavor index input interface, which includes a node input area and a node data input area;

[0089] In response to the user's input operation on the node input area and the node data input area in the flavor index input interface, a flavor improvement instruction of the target detection object is obtained.

[0090] The flavor index input interface may refer to an interface in a display screen of the food analysis system, which is used to interact with a user. The user may input an operation on the flavor index input interface to enable the food analysis system to obtain a flavor improvement instruction for the target detection object.

[0091] The flavor index input interface may include a node input area and a node data input area, wherein:

[0092] The node input area can be used to select and specify the corresponding target attributes, target metabolites, and target flavor evaluation dimensions. For example, when the target detection object is coffee beans: the target attribute can be selected from the basic attributes such as genotype, variety, origin, light, temperature, humidity, altitude, UV, field management, picking period, processing method, roasting method, roasting degree, storage time, storage method, grinding degree, extraction method, formula, and ratio. The target metabolite can be selected from the target metabolites that characterize each metabolite. The dimension of the target flavor evaluation can include dimensional data such as aroma and taste.

[0093] The node data input area can be used to input the corresponding target attribute data, target metabolism data and target flavor evaluation data. Therefore, the user can input specific values ​​in the node data input area so that the system can accurately obtain and process these data. For example:

[0094] The target attributes determined by the user in the node input area may include: variety, origin, picking period, roasting method, storage time, and then the user enters the following in the node data input area corresponding to each node input area: variety type data, origin data, picking period data, roasting method data, and storage time data.

[0095] After the target metabolic components determined by the user in the node input area may include: caffeine, chlorogenic acid and 2-methylbutanal, the node data input area corresponding to each node input area enters: the percentage content of caffeine, the percentage content of chlorogenic acid and the percentage content of 2-methylbutanal.

[0096] The target flavor evaluation dimensions determined by the user in the node input area may include: fruity aroma, acidity; and the following are input in the node data input area corresponding to each node input area: fruity aroma level 5, acidity level 3.

[0097] Therefore, through the design of the flavor index input interface, users can easily input and adjust various flavor-related data, thereby helping the food analysis system to improve and optimize the flavor more accurately.

[0098] S202. Determine an associated variable node according to a target basic node corresponding to the target attribute data, a target metabolic node corresponding to the target metabolic data, and a target flavor assessment node corresponding to the target flavor assessment data in the target influence node data. The associated variable node is a node that has an associated relationship with the target basic node or the target metabolic node and a causal relationship with the target flavor assessment node.

[0099] Among them, the target basic node may refer to the node corresponding to the target attribute data in the pre-built food analysis model, the target metabolic node may refer to the node corresponding to the target metabolic data in the pre-built food analysis model, and the target flavor evaluation node may refer to the node corresponding to the target flavor evaluation data in the pre-built food analysis model. The node can represent the data type of each data, that is, the target basic node can represent the target attribute, the target metabolic node can represent the target metabolic component, and the target flavor evaluation node can represent the dimension of the target flavor evaluation. The relationship between each node in the target detection object can be determined through the food analysis model.

[0100] In the embodiment of the present application, the food analysis model can be presented in the form of a node graph, the nodes in the node graph represent the basic nodes of each basic attribute in the target detection object, the metabolic nodes of the metabolic components, and the flavor evaluation nodes of the flavor evaluation dimension, and the edges in the node graph can represent the relationship between the nodes. The food analysis model can be obtained by model training.

[0101] The associated variable node may refer to a node determined from the food analysis model that has an associated relationship with the target base node or the target metabolic node and a causal relationship with the target flavor evaluation node. The associated relationship may refer to a statistical correlation with the target base node or the target metabolic node, that is, a connection between the change of one node and the change of another node, for example, when the storage time increases, the content of compound 1 will also increase. The causal relationship may refer to a direct causal relationship with the target flavor evaluation node, that is, a change in one node can directly lead to a change in another node, and this effect is predictable and consistent, for example, when the content of compound 1 increases, the acidity will increase.

[0102] In some embodiments, when the target detection object is coffee beans, if the target influencing node data includes roasting time data and storage time data representing the target attribute data, and the target flavor evaluation data includes aroma level data, then the corresponding target basic nodes can be determined to be the roasting node and the storage node, and the aroma node corresponding to the aroma level data; and thus, the initial target metabolic node having an associated relationship with the roasting node and the storage node, and other target basic nodes having an associated relationship with the initial target metabolic node can be determined from the food analysis model, and the associated variable nodes that affect the aroma node are determined from the initial target metabolic node and the other target basic nodes.

[0103] In some embodiments, when the target detection object is coffee beans, if the target influencing node data includes storage time data representing the target attribute data and compound 1 content data representing the target metabolic data, and the target flavor evaluation data includes aroma level data, then the corresponding target basic node can be determined to be the roasting node and the corresponding target metabolic node is the compound 1 node, and the aroma level data corresponds to the aroma node; and thus, the initial target metabolic node having an association relationship with the roasting node and the compound 1 node, as well as other target basic nodes with the initial target metabolic node can be determined from the food analysis model, and the associated variable node that affects the aroma node is determined from the initial target metabolic node and the other target basic nodes.

[0104] S203: Determine node data of the associated variable node according to the target influence node data, the target flavor evaluation data, and the relationship among the target flavor influence node, the associated variable node, and the target flavor evaluation node.

[0105] The target flavor influencing node may include a node corresponding to the target influencing node data, and the node may include a target basic node and a target metabolic node.

[0106] The relationship between the target flavor impact node, the associated variable node, and the target flavor evaluation node may include an edge relationship between the nodes in the node graph representing the food analysis model. For example, when the associated variable node is compound 1 having an edge relationship with the aroma dimension, and the target basic nodes corresponding to the roasting time, altitude, and storage time, the relationship may be represented as:

[0107] Compound 1 = 5*baking time + 0.2*altitude - 2*storage time + 5.

[0108] Among them, 5, 0.2, and -2 can be represented as edge relationships between nodes.

[0109] After the relationship among the target flavor influence node, the associated variable node, and the target flavor rating node is determined, the node data of the associated variable node may be determined according to the target influence node data and the target flavor rating data.

[0110] S204: Output and display the associated variable nodes and the node data of the associated variable nodes.

[0111] Among them, after determining the associated variable node and the node data of the associated variable node, the food flavor analysis system can display the associated variable node and the node data of the associated variable node on the display screen, and can also play the associated variable node and the node data of the associated variable node through voice broadcast.

[0112] The display method provided in the embodiment of the present application can, based on the causal relationship among the basic nodes, metabolic nodes and flavor assessment nodes in the target detection object, when receiving a flavor improvement instruction, first determine the associated variable nodes that have an association relationship with the target basic node or the target metabolic node and a causal relationship with the target flavor assessment node according to the target basic node corresponding to the target attribute data, the target metabolic node corresponding to the target metabolic data, and the target flavor assessment node corresponding to the target flavor assessment data in the instruction, and then determine the node data of the associated variable nodes according to the relationship between the nodes, so that the adjustment strategy of the target detection object can be obtained according to the node data of the associated variable nodes to achieve flavor improvement of the target detection object.

[0113] Figure 3 Schematic diagram of the process of the display method provided in the embodiment of the present application Figure 2 ,like Figure 3 As shown, in this embodiment Figure 2 Based on the embodiment, a method for determining an associated variable node according to a target basic node corresponding to target attribute data in target influence node data, a target metabolic node corresponding to target metabolic data, and a target flavor evaluation node corresponding to target flavor evaluation data is described in detail. The method includes:

[0114] S301 . Obtain training samples, where the training samples include basic sample data, metabolic sample data, and assessment sample data corresponding to the basic sample data and the metabolic sample data.

[0115] The training sample may refer to a data set used to construct a flavor causal mechanism that affects the target detection object, and the data set may include basic sample data, metabolic sample data, and evaluation sample data. The basic sample data may refer to sample attribute data corresponding to each basic attribute node. The metabolic sample data may refer to sample data corresponding to each metabolic node, and the evaluation sample data may refer to sample data corresponding to a flavor evaluation node.

[0116] In an embodiment of the present application, when the target detection object is coffee beans, the method for obtaining training samples may include:

[0117] Determine the sample of the target detection object;

[0118] Determine basic sample data based on the sample of the target detection object, wherein the basic sample data may include at least one of the following attribute parameters: genotype, variety, origin, light, temperature, humidity, altitude, UV, field management, picking period, processing method, roasting method, roasting degree, storage time, storage method, grinding degree, extraction method, formula, ratio, etc.;

[0119] The sample of the target object is sent to GC (Gas Chromatography). After separation by the capillary column, the outflow components are divided into two paths by the diversion valve. One path enters the chemical detector to obtain the odor characteristic raw data composed of chromatographic and mass spectrometric raw data;

[0120] Based on the original data of odor characteristics, the metabolic sample data and the evaluation sample data are determined. For example, the biochemical components in coffee beans may include caffeine, harringtonine, chlorogenic acid, sucrose and lipids. For example, the evaluation sample data can be obtained by analyzing the metabolic sample data. For example, by analyzing the metabolism of flavor substances in coffee beans, the effects of seed processing and storage on the accumulation of these flavor substances can be understood, thereby identifying the evaluation sample data that determines coffee.

[0121] According to the basic sample data, the metabolic sample data and the evaluation sample data, the training samples are obtained. For example, the training samples can be shown in Table 1:

[0122]

[0123] Among them, bean variety, origin, altitude, picking, roasting, storage method, and storage time are basic sample data, compounds 1 to 2000 are metabolic sample data, and acidity and alcohol content are evaluation sample data.

[0124] After obtaining the training samples, each data in the training samples may be preprocessed to improve the quality of each data and make it more suitable for use in subsequent methods.

[0125] The preprocessing of each data in the training sample may include:

[0126] For data with physical meaning of progressive characteristics, each data can be encoded according to the progressive characteristics. For example, the roasting method "light / medium / roasted" can be encoded as "1 / 2 / 3" or "3 / 2 / 1". In this way, the data in the training samples, such as light intensity and picking height, can be converted into numerical values ​​for subsequent processing.

[0127] Scale data with a larger feature scale range to the same scale range to prevent large differences in feature values ​​from causing difficulties in subsequent training. For example, perform a log() conversion on the data.

[0128] In addition, since the flavor of coffee changes over time, it is necessary to fill in the metabolic sample data and the evaluation sample data. The system can display the data to the user and fill in the data by the user. For example, the "storage time" can be used as the timestamp to fill in the data according to the time series data. When filling, you can use the linear interpolation method, that is, use the data before and after the missing value for linear interpolation. You can also use the polynomial interpolation method, that is, use the polynomial function to interpolate the missing value. You can also use the moving average method, that is, use the mean value in the front and back windows for filling.

[0129] In the embodiment of the present application, when the features (feature dimensions) in the data set are much larger than the number of samples, data analysis and modeling will become more complicated, which may lead to problems such as overfitting of the model and low computational efficiency. Therefore, multiple data tables can be split based on each score. The split data tables can be shown in Table 2 and Table 3.

[0130] Table 2:

[0131]

[0132] Table 3:

[0133]

[0134] In the embodiments of the present application, "supervised dimensionality reduction" can be performed for each data table. For example, PLS-DA (Partial Least Squares Discriminant Analysis) is a supervised discriminant analysis statistical method. PLS-DA can be used to establish a relationship model between metabolite expression and flavor evaluation to predict the flavor of the sample. The influence and explanatory power of the expression pattern of each metabolite on the classification and discrimination of each group of samples can be measured by calculating the variable projection importance (Variable Importance for the Projection, VIP), thereby assisting the screening of marker metabolites (usually VIP value>1.0 is used as the screening criterion).

[0135] In some embodiments, the performance evaluation of dimensionality reduction is affected by factors such as the number of principal components in PLS. The optimal dimensionality reduction latitude in PLS can be determined based on the prediction accuracy of the data set after dimensionality reduction in discriminant analysis. For example, from the preprocessing interface, an accuracy specification is received, and the data after dimensionality reduction needs to reach 90% accuracy of the original sensory evaluation data.

[0136] S302, determining the initial global node relationship of the basic sample node, the assessment sample data node, and the assessment sample node according to the basic sample node corresponding to the basic sample data, the metabolic sample node corresponding to the metabolic sample data, and the assessment sample node corresponding to the assessment sample data.

[0137] The initial global node relationship can represent the initial model between the constructed basic sample nodes, metabolic sample nodes and assessment sample nodes. For example, a node relationship graph is constructed with the basic sample nodes, metabolic sample nodes and assessment sample nodes. The edges in the node relationship graph connected between the basic sample nodes and the metabolic sample nodes, between the metabolic sample nodes and the assessment sample nodes, and between the basic sample nodes and the assessment sample nodes can represent the initial global node relationship.

[0138] S303 . Adjust the initial global node relationship according to the basic sample data, the metabolic sample data, and the assessment sample data corresponding to the basic sample data and the metabolic sample data to obtain the global node relationship.

[0139] The global node relationship can represent the model obtained after adjusting the parameters of the initial model. In some embodiments, after determining the node relationship graph, the weight corresponding to each edge can be determined by the basic sample data, the metabolic sample data, and the assessment sample data, and the global node relationship can be determined by the weight.

[0140] For example, building a causal graph model that represents global node relationships may include:

[0141] Determine the sample data that characterizes the flavor variable (outcome variable), for example, the flavor characteristics of coffee (such as acidity, bitterness, aroma intensity).

[0142] Determine the basic sample data that characterizes the environmental variables (causal variables): Altitude: the altitude at which the coffee is grown. Roasting method: the degree of roasting of the coffee beans (such as light roasting, medium roasting, and dark roasting).

[0143] Determine the metabolic sample data that characterizes metabolome variables (mediating variables): compound components in coffee beans, such as: organic acids (such as malic acid, citric acid, chlorogenic acid), aroma compounds (such as guaiacol: one of the sources of vanilla flavor); bitter compounds (such as caffeine);

[0144] Among them, since the relationship between variables may be affected by some unobserved or random disturbance factors, the introduction of exogenous noise nodes (N1, ..., N m ) represents these unobserved factors to supplement the completeness of the model.

[0145] After determining the variables in the model, use expert knowledge to define the prior constraints in the model. For example, if you know that node A is the ancestor node of node B (that is, the causal effect of A will be transmitted to B), you can add this constraint to the model during the model design phase. This can be achieved by manually setting or modifying the structure of the causal graph. For example, the impact of altitude and roasting method on metabolome variables (compound components), the impact of metabolome variables on flavor variables, and environmental variables (altitude, roasting method) directly affect flavor variables and indirectly affect flavor variables through metabolome variables.

[0146] Thus, the relationships between certain edges or nodes are fixed in the model to ensure that the network structure conforms to expert knowledge. For example, the causal relationship between compounds can be enforced when building the model.

[0147] After determining the relationship between the variables in the model, a causal graph model can be constructed. In some embodiments, causal discovery technology can be used to automatically explore potential patterns from a given data set, wherein the causal discovery technology may include but is not limited to: Peter-Clark Algorithm (PC) algorithm, Greedy Equivalent Search (GES), Linear non-Gaussian Model (LiNGAM), or Causal Additive Model (CAM), etc. In an embodiment of the present application, a model can be constructed based on a Bayesian network, which can identify the direct and indirect causes of a target and can be used to draw causal conclusions by implying causal relationships.

[0148] For example, we can first perform a conditional independence test: determine the conditional independence between variables through statistical tests. Then build a preliminary causal graph: build a preliminary directed acyclic graph (DAG) based on the conditional independence test results. Then learn the model: adjust the causal graph structure, remove false causal relationships, and optimize the direction of the edges. Finally, verify the model: check the accuracy of the model on the verification data and perform a conditional independence test. Exogenous noise nodes (N1, ..., N m ) can be obtained by the residual (yy) between the true observation and the model prediction. pred ), and obtain y represents the true observed value, y pred It is obtained by the predicted value of its cause node; finally, based on the expert knowledge in the field, multiple local causal discoveries can be performed and merged into a complete causal discovery network as needed.

[0149] Figure 3a A schematic diagram of the structure of the causal relationship graph model provided in the embodiment of the present application Figure 1 ,like Figure 3a As shown, the causal graph model representing the global node relationship can be displayed in the form of a graph, where the nodes in the graph represent variables and the edges (directed arrows) represent the direction of the causal relationship. For example, a DAG can show the direct impact of variable A on variable B, and the direct impact of variable B on variable C (i.e., the initial global node relationship).

[0150] After determining the causal structure of each node in the graph, the causal effect can also be quantitatively estimated, such as the regression coefficient, the size of the causal effect, etc. The causal relationship between variables is determined by quantitative estimation. For example, the causal effect of variable A on variable B is estimated to be 0.5, which means that for every unit increase in A, B will increase by 0.5 units.

[0151] Finally, the model goodness of fit index is calculated through the model prediction value and the actual observation value. For example, the comparative fit index CFI (Comparative Fit Index), the non-standardized fit index TLI (Tucker-Lewis Index), the error-based fit index RMSEA (Root Mean Square Error of Approximation) and the standardized residual-based fit index SRMR (Standardized Root Mean Square Residual) are commonly used goodness of fit indicators (i.e. global node relationships) in structural equation modeling (SEM).

[0152] In order to improve the accuracy of the model, counterfactual reasoning can be performed on the model during the model training process to determine the noise value of each node. That is, based on the current overall causal model and the current flavor value of the new sample, the exogenous noise nodes (N1, ..., N m ) from the original probability distribution to a specific value. For example, compound 1 = 5*baking + 0.2*altitude - 2*storage time + N1, N1 can be determined by residual calculation, and now it is assumed to be N1~Norm(10,5 2 ). Substitute the current flavor of the new sample into the above formula. Thus, N1 can be obtained. Thus, the noise value corresponding to each node can be determined.

[0153] Figure 3b A schematic diagram of the structure of the causal relationship graph model provided in the embodiment of the present application Figure 2 ,like Figure 3b As shown, the noise value of the node corresponding to compound 1 in the model is 5, the noise value of the node corresponding to compound 2 is 21, the noise value of the node corresponding to compound 3 is -2, the noise value of the node corresponding to alcohol content is 11, the noise value of the node corresponding to acidity is 9, and the noise value of the node corresponding to aftertaste is 1.

[0154] S304 , according to the target flavor evaluation node, determine from the global node relationship the basic node and the metabolic node that affect the target flavor evaluation node, and the node relationship between the target flavor evaluation node, the basic node and the metabolic node.

[0155] After determining the global node relationship between nodes, the metabolic nodes having edge relationships with the target flavor evaluation node and the basic nodes having edge relationships with the metabolic nodes can be determined according to the target flavor evaluation node, and the relationship between these nodes can be determined accordingly.

[0156] In the embodiment of the present application, since there are many types of compounds corresponding to the metabolic nodes, the key nodes can also be determined by performing a graph analysis on the global node relationship, wherein the method may include:

[0157] Determine the flavor dimensions that need to be improved based on the target flavor evaluation node;

[0158] According to the flavor dimension that needs to be improved, all ancestor nodes that affect the flavor dimension that needs to be improved are determined, wherein the ancestor node may refer to all nodes that are located before a certain node on the path and affect the node.

[0159] After determining the causal effects of all ancestral nodes, the causal effects are sorted, where the causal effects can be calculated based on individual treatment effects (ITE), for example, by the formula:

[0160]

[0161] Among them, i represents the individual sample, represents the individual causal effect of adding one unit of treatment to sample i, It represents the individual causal effect of reducing the treatment of sample i by one unit;

[0162] X t Indicates intervention on the item (such as baking method, compound, etc.), X i represents the specific observed value of sample i at present, and Y represents the target sensory evaluation;

[0163] E[Y|do(X t =t+1),X i ] can refer to predicting the outcome of a one-unit increase in treatment for an individual based on the individual's environmental variables, metabolome data, and overall model;

[0164] E[Y|do(X t =t),X i ] can refer to the observation results under the current treatment.

[0165] Finally, the key nodes are determined based on the order of causal effects.

[0166] For example, take Gesha from a certain origin;

[0167] The current flavors of the new samples are shown in Table 4:

[0168] Bean seeds altitude Baking Storage time Compound 1 … Compound 100 acidity Body Gesha 1300m Shallow = 1 10 days 380 … 365512 9 7

[0169] The new flavors of the new samples are shown in Table 5:

[0170] Bean seeds altitude Baking Storage time Compound 1 … Compound 100 acidity Body Gesha 1300m Shallow = 1 10 days 380 … 365512 9 8

[0171] When alcohol content is the cause node that characterizes the target flavor evaluation node, Figure 3b As shown, the basic nodes and metabolic nodes that can be determined to affect the target flavor evaluation node include: bean species, altitude, roasting, storage time, compound 1 and compound 2. After the bean species, altitude, roasting, storage time, compound 1 and compound 2 are determined, the causal effects of bean species, altitude, roasting, storage time, compound 1 and compound 2 are ranked, wherein, when the causal effect of roasting is higher than the causal effect of compound 2, the causal effect of compound 2 is higher than the causal effect of compound 1, the causal effect of compound 1 is higher than the causal effect of storage time, the causal effect of storage time is higher than the causal effect of altitude, and the causal effect of altitude is higher than the causal effect of bean species, the metabolic nodes corresponding to the top three causal effects are taken as key influencing factors, and then the important compound components can be obtained: roasting, compound 2, compound 1.

[0172] When there are multiple flavor dimensions that need to be improved, the formula can be used:

[0173]

[0174] Linearly weight each node involved in the k flavor dimensions Thus, the weighted causal effects of each node can be obtained. And according to the ranking results of the weighted causal effects, the metabolic nodes corresponding to the key influencing factors can be determined. Thus, the corresponding metabolic nodes can be quickly selected.

[0175] In the embodiment of the present application, according to the target flavor evaluation node, the node relationship between the basic node and the metabolic node, the target basic node and the target metabolic node, the method for determining the associated variable node may include:

[0176] According to the target flavor evaluation node, the node relationship between the basic node and the metabolic node, and the target basic node, determining a first associated variable node in the node relationship, the first associated variable node being a node in the metabolic node that has an associated relationship with the target basic node;

[0177] According to the target flavor evaluation node, the node relationship between the basic node and the metabolic node, and the target metabolic node, determining a second associated variable node in the node relationship, the second associated variable node being a node in the metabolic node that has an associated relationship with the target metabolic node, and a node in the basic node that has an associated relationship with the target metabolic node;

[0178] An associated variable node is determined according to the first associated variable node and the second associated variable node.

[0179] After all nodes that affect the target flavor evaluation node are determined, a first associated variable node associated with the target base node may be determined based on the target base node, and after all nodes that affect the target flavor evaluation node are determined, a second associated variable node associated with the target base node may be determined based on the target metabolism node. Finally, an associated variable node is determined based on the first associated variable node and the second associated variable node.

[0180] For example, Figure 3b As shown, when the target flavor evaluation node is alcohol content, the metabolic nodes having an edge relationship with the target flavor evaluation node are the node corresponding to compound 1 and the node corresponding to compound 2, and the basic nodes having an edge relationship with compound 1 are the node corresponding to altitude, the node corresponding to roasting, and the node corresponding to storage time, and the basic nodes having an edge relationship with compound 2 are the node corresponding to bean species, the node corresponding to altitude, and the node corresponding to roasting. After determining the above nodes, the relationship between the above nodes can be obtained. When the target basic node is the node corresponding to storage time, the first associated variable node can include the node corresponding to compound 1. When the target metabolic node is the node corresponding to compound 1, the second associated variable node can include the node corresponding to bean species and the node corresponding to altitude. Therefore, the associated variable node can be determined according to the first associated variable node and the second associated variable node.

[0181] The display method provided in the embodiment of the present application constructs a global node relationship representing the causal relationship between the basic node, the metabolic node, and the flavor evaluation node through training samples, and determines the associated variable node having an associated relationship and a causal relationship with the target basic node, the target metabolic node, and the target flavor evaluation node from the relationship, thereby more accurately determining the associated variable node. In addition, the constructed global node relationship representing the causal relationship between the basic node, the metabolic node, and the flavor evaluation node can also make the determination of the node data of the associated variable node more accurate.

[0182] Figure 4 Schematic diagram of the process of the display method provided in the embodiment of the present application Figure 2 ,like Figure 4 As shown, in this embodiment Figure 2 Based on the embodiment, a method for determining node data of an associated variable node according to target influence node data, target flavor evaluation data, and the relationship between the target flavor influence node, the associated variable node, and the target flavor evaluation node is described in detail. The method includes:

[0183] S401, constructing a node relationship equation according to the relationship between the target flavor influencing node, the associated variable node and the target flavor evaluation node;

[0184] S402: Obtain node data of associated variable nodes according to target influence node data, target flavor evaluation data and node relationship equations.

[0185] The node relationship equation may include a causal relationship equation between the associated variable node and the target flavor impact node, and a causal relationship equation between the associated variable node and the target flavor evaluation node. In the embodiment of the present application, the node relationship equation may be constructed based on the edge relationship between the nodes represented in the analysis model.

[0186] After the node relationship equation is determined, the node relationship equation is solved according to the target impact node data and the target flavor evaluation data, thereby obtaining the node data of the associated variable node.

[0187] for example, Figure 4a A schematic diagram of the structure of the causal relationship graph model provided in the embodiment of the present application Figure 3 ,like Figure 4a As shown, when the target flavor evaluation data is to change the aroma corresponding to the target flavor evaluation node from level 7 to level 9, the target influence node data includes the roasting and storage time corresponding to the target base node, and the associated variable node includes compound 1 and compound 2 corresponding to the target metabolism node, the node relationship equation may include:

[0188] X1=N1,X2=N2;

[0189] X3=(X1) 2 -(X2-7)2+N3;

[0190] X4=10*Sin(X1)-|X2-3|+X3+N4;

[0191] Y=log(X3)+2*X2+N3.

[0192] Therefore, after determining that the specific exogenous noise variables are N1, ..., N4, the value corresponding to X3 of compound 1 and the value corresponding to X4 of compound 2 that characterize the associated variable node can be determined.

[0193] for example, Figure 4b A schematic diagram of the structure of the causal relationship graph model provided in the embodiment of the present application Figure 4 ,like Figure 4b As shown, when the target flavor evaluation data is to change the aroma corresponding to the target flavor evaluation node from level 7 to level 9, the target influence node data includes the storage time corresponding to the target base node and the compound 1 corresponding to the target metabolism node, and the associated variable node includes the roasting corresponding to the target base node and the compound 2 corresponding to the target metabolism node, the node relationship equation may include:

[0194] X1=1, X3=100;

[0195] X4=10*Sin(X1)-|X2-3|+X3+N4;

[0196] Y=log(X3)+2*X2+N3.

[0197] Therefore, after determining that the specific exogenous noise variables are N1, ..., N4, the value corresponding to X4 of compound 2 representing the associated variable node can be determined.

[0198] The flavor improvement instruction of the target detection object also includes an intervention variable; in the embodiment of the present application, the node data of the associated variable node is obtained according to the target impact node data, the target flavor evaluation data and the node relationship equation, including:

[0199] According to the target impact node data, the target flavor evaluation data and the node relationship equation, the initial node data of the associated variable node is obtained;

[0200] The node data of the associated variable node is obtained according to the initial node data and the intervention variable of the associated variable node.

[0201] The intervention variable may refer to a constraint condition for intervening in node data cost.

[0202] The initial node data may refer to data of associated variable nodes obtained through a node relationship equation, and the data may represent data within a certain range.

[0203] In the embodiment of the present application, after determining the node data of the associated variable node, in order to meet the cost and other conditions, the node data of the associated variable node can be supplemented with constraint conditions so that the node data of the associated variable node is more in line with the actual needs. For example, as shown in Table 6:

[0204]

[0205]

[0206] Here, +n / -n represents a continuous change of n units, and accordingly, the intervention cost also changes by n units.

[0207] Objective function 1: maximization / minimization

[0208]

[0209] stC(X I )≤B;

[0210] x I ∈[x I,min ,xI,max ], for each x I ∈X I .

[0211] Objective function 2: not less than a certain value α

[0212]

[0213] stE[Y|do(X I =x I )]≥α;

[0214] C(X I )≤B;

[0215] x I ∈[x I,min ,x I,max ], for each x I ∈X I .

[0216] Therefore, by solving the initial node data of the associated variable node by objective function 1 and objective function 2, the node data of the associated variable node under the constraint condition of the intervention cost can be determined.

[0217] Wherein, when there are multiple target flavor evaluation data in the flavor improvement instruction, in the embodiment of the present application, after obtaining the flavor improvement instruction of the target detection object, the method further includes:

[0218] Determine an associated variable node according to a target basic node corresponding to the target attribute data, a target metabolism node corresponding to the target metabolism data, and a target flavor evaluation node corresponding to the target flavor evaluation data in the target influence node data;

[0219] Determining node data of an associated variable node according to target influence node data, target flavor evaluation data, and a relationship among a target flavor influence node, an associated variable node, and a target flavor evaluation node;

[0220] According to the node data of the associated variable node, the global node data of the associated variable node is obtained;

[0221] The global node data of the associated variable node is processed to obtain the optimal solution to obtain the target node data of the associated variable node;

[0222] Output and display the associated variable node and the target node data of the associated variable node.

[0223] When there are multiple target flavor evaluation data, the node data of the associated variable node corresponding to each target flavor evaluation data can be determined in turn, and then the global node data of the associated variable node can be obtained according to the node data of the associated variable node corresponding to each target flavor evaluation data. The global node data of the associated variable node is processed to obtain the optimal solution to obtain the target node data that meets the requirements of all target flavor evaluation data.

[0224] Among them, when there are multiple groups of targets affecting node data When the target influence node data, the target flavor evaluation data and the node relationship equation are used, the step of obtaining the node data of the associated variable node can be repeated multiple times.

[0225]

[0226] stC(X I )≤B;

[0227] x I ∈[x I,min ,x I,max ], for each x I ∈X I .

[0228] When there are multiple improvement targets, weighted average can be used to convert multiple targets into single target optimization. For example, linear weighted average can be used to calculate K optimization targets.

[0229] Figure 5 A schematic diagram of the structure of the display device provided in the embodiment of the present application, such as Figure 5 As shown, the display device 50 provided in this embodiment includes:

[0230] An acquisition module 501 is used to acquire a flavor improvement instruction of a target detection object, the flavor improvement instruction includes target impact node data and target flavor evaluation data, the target impact node data includes at least one of target attribute data and target metabolism data;

[0231] A first determination module 502 is used to determine an associated variable node according to a target basic node corresponding to the target attribute data, a target metabolic node corresponding to the target metabolic data, and a target flavor evaluation node corresponding to the target flavor evaluation data in the target influence node data, wherein the associated variable node is another flavor influence node that has an associated relationship with the target basic node or the target metabolic node and a causal relationship with the target flavor evaluation node;

[0232] A second determination module 503, for determining node data of an associated variable node according to the target influence node data, the target flavor evaluation data, and the relationship between the target flavor influence node, the associated variable node, and the target flavor evaluation node;

[0233] The output module 504 is used to output and display the associated variable nodes and the node data of the associated variable nodes.

[0234] In a possible implementation, the acquisition module 501 is further specifically configured to:

[0235] Display the flavor index input interface, which includes a node input area and a node data input area;

[0236] In response to the user's input operation on the node input area and the node data input area in the flavor index input interface, a flavor improvement instruction of the target detection object is obtained.

[0237] In a possible implementation manner, the first determining module 502 is further specifically configured to:

[0238] Determining a basic node, a metabolic node, and a node relationship between the target flavor evaluation node, the basic node, and the metabolic node in the target detection object that affect the target flavor evaluation node;

[0239] According to the target flavor evaluation node, the node relationship between the basic node and the metabolic node, the target basic node and the target metabolic node, the associated variable node is determined.

[0240] In a possible implementation manner, the first determining module 502 is further specifically configured to:

[0241] Acquire training samples, where the training samples include basic sample data, metabolic sample data, and assessment sample data corresponding to the basic sample data and the metabolic sample data;

[0242] Determine the initial global node relationship of the basic sample node, the assessment sample data node, and the assessment sample node according to the basic sample node corresponding to the basic sample data, the metabolic sample node corresponding to the metabolic sample data, and the assessment sample node corresponding to the assessment sample data;

[0243] According to the basic sample data, the metabolic sample data, and the assessment sample data corresponding to the basic sample data and the metabolic sample data, the initial global node relationship is adjusted to obtain the global node relationship;

[0244] According to the target flavor evaluation node, a basic node and a metabolic node that affect the target flavor evaluation node, and a node relationship among the target flavor evaluation node, the basic node and the metabolic node are determined from the global node relationship.

[0245] In a possible implementation manner, the first determining module 502 is further specifically configured to:

[0246] According to the target flavor evaluation node, the node relationship between the basic node and the metabolic node, and the target basic node, determining a first associated variable node in the node relationship, the first associated variable node being a node in the metabolic node that has an associated relationship with the target basic node;

[0247] According to the target flavor evaluation node, the node relationship between the basic node and the metabolic node, and the target metabolic node, determining a second associated variable node in the node relationship, the second associated variable node being a node in the metabolic node that has an associated relationship with the target metabolic node, and a node in the basic node that has an associated relationship with the target metabolic node;

[0248] An associated variable node is determined according to the first associated variable node and the second associated variable node.

[0249] In a possible implementation manner, the second determining module 503 is further specifically configured to:

[0250] According to the relationship between the target flavor influence node, the associated variable node and the target flavor evaluation node, a node relationship equation is constructed;

[0251] According to the target influence node data, the target flavor evaluation data and the node relationship equation, the node data of the associated variable node is obtained.

[0252] In a possible implementation manner, the flavor improvement instruction of the target detection object further includes an intervention variable; and the second determination module 503 is further specifically configured to:

[0253] According to the target impact node data, the target flavor evaluation data and the node relationship equation, the initial node data of the associated variable node is obtained;

[0254] The node data of the associated variable node is obtained according to the initial node data and the intervention variable of the associated variable node.

[0255] In a possible implementation manner, when there are multiple target flavor assessment data in the flavor improvement instruction, the second determining module 503 is further specifically configured to:

[0256] Determine an associated variable node according to a target basic node corresponding to the target attribute data, a target metabolism node corresponding to the target metabolism data, and a target flavor evaluation node corresponding to the target flavor evaluation data in the target influence node data;

[0257] Determining node data of an associated variable node according to target influence node data, target flavor evaluation data, and a relationship among a target flavor influence node, an associated variable node, and a target flavor evaluation node;

[0258] According to the node data of the associated variable node, the global node data of the associated variable node is obtained;

[0259] The global node data of the associated variable node is processed to obtain the optimal solution to obtain the target node data of the associated variable node;

[0260] Output and display the associated variable node and the target node data of the associated variable node.

[0261] The display device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0262] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes: at least one processor 601 and a memory 602. Optionally, the device 60 also includes a communication component 603. The processor 601, the memory 602 and the communication component 603 are connected via a bus 604.

[0263] In a specific implementation process, at least one processor 601 executes the computer execution instructions stored in the memory 602, so that at least one processor 601 executes the above method.

[0264] The specific implementation process of the processor 601 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0265] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0266] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0267] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0268] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0269] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0270] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0271] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0272] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0273] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0274] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0275] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0276] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0277] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A display method, characterized in that: Applied to food flavor analysis systems, including: Obtaining a flavor improvement instruction of a target detection object, the flavor improvement instruction including target influence node data and target flavor evaluation data, the target influence node data including at least one of target attribute data and target metabolism data; determining an associated variable node according to a target base node corresponding to the target attribute data in the target influence node data, a target metabolism node corresponding to the target metabolism data, and a target flavor evaluation node corresponding to the target flavor evaluation data, the associated variable node being a node that has an associated relationship with the target base node or the target metabolism node and a causal relationship with the target flavor evaluation node; determining node data of the associated variable node according to the target influence node data, the target flavor evaluation data, and a relationship among the target flavor influence node, the associated variable node, and the target flavor evaluation node; The associated variable node and the node data of the associated variable node are output and displayed.

2. The method according to claim 1, characterized in that: The step of obtaining the flavor improvement instruction of the target detection object includes: Displaying a flavor index input interface, wherein the flavor index input interface includes a node input area and a node data input area; In response to the user's input operation on the node input area and the node data input area in the flavor index input interface, a flavor improvement instruction of the target detection object is obtained.

3. The method according to claim 1, characterized in that The determining of the associated variable node according to the target basic node corresponding to the target attribute data in the target influence node data, the target metabolism node corresponding to the target metabolism data, and the target flavor evaluation node corresponding to the target flavor evaluation data comprises: Determining a basic node, a metabolic node, and a node relationship among the target flavor evaluation node, the basic node, and the metabolic node in the target detection object that affect the target flavor evaluation node; The associated variable node is determined according to the target flavor evaluation node, the node relationship between the base node and the metabolic node, the target base node, and the target metabolic node.

4. The method according to claim 3, characterized in that: The determining of the basic node and the metabolic node in the target detection object that affect the target flavor evaluation node, and the node relationship between the target flavor evaluation node, the basic node and the metabolic node, comprises: Acquire a training sample, wherein the training sample includes basic sample data, metabolic sample data, and assessment sample data corresponding to the basic sample data and the metabolic sample data; Determining an initial global node relationship among the basic sample node, the assessment sample data node, and the assessment sample node according to the basic sample node corresponding to the basic sample data, the metabolic sample node corresponding to the metabolic sample data, and the assessment sample node corresponding to the assessment sample data; According to the basic sample data, the metabolic sample data, and the assessment sample data corresponding to the basic sample data and the metabolic sample data, the initial global node relationship is adjusted to obtain a global node relationship; According to the target flavor evaluation node, a base node and a metabolic node that affect the target flavor evaluation node, and a node relationship between the target flavor evaluation node, the base node and the metabolic node are determined from the global node relationship.

5. The method according to claim 3, characterized in that: The determining the associated variable node according to the target flavor evaluation node, the node relationship between the base node and the metabolic node, the target base node and the target metabolic node comprises: Determining a first associated variable node in the node relationship according to the target flavor evaluation node, the node relationship between the base node and the metabolic node, and the target base node, wherein the first associated variable node is a node in the metabolic node that has an associated relationship with the target base node; Determining a second associated variable node in the node relationship according to the target flavor evaluation node, the node relationship between the base node and the metabolic node, and the target metabolic node, wherein the second associated variable node is a node in the metabolic node that has an associated relationship with the target metabolic node, and a node in the base node that has an associated relationship with the target metabolic node; The associated variable node is determined according to the first associated variable node and the second associated variable node.

6. The method according to claim 1, characterized in that The determining of the node data of the associated variable node according to the target influence node data, the target flavor evaluation data, and the relationship among the target flavor influence node, the associated variable node, and the target flavor evaluation node comprises: constructing a node relationship equation according to the relationship between the target flavor influence node, the associated variable node and the target flavor evaluation node; The node data of the associated variable node is obtained according to the target influence node data, the target flavor rating data and the node relationship equation.

7. The method according to claim 6, characterized in that The flavor improvement instructions for the target detection subject also include an intervention variable; The step of obtaining the node data of the associated variable node according to the target influence node data, the target flavor evaluation data and the node relationship equation includes: Obtaining initial node data of the associated variable node according to the target impact node data, the target flavor evaluation data and the node relationship equation; The node data of the associated variable node is obtained according to the initial node data of the associated variable node and the intervention variable.

8. The method according to claim 1, characterized in that: When there are multiple target flavor evaluation data in the flavor improvement instruction, After acquiring the flavor improvement instruction of the target detection object, the method further includes: Determining an associated variable node according to a target basic node corresponding to the target attribute data in the target influencing node data, a target metabolism node corresponding to the target metabolism data, and a target flavor evaluation node corresponding to the target flavor evaluation data; determining node data of the associated variable node according to the target influence node data, the target flavor evaluation data, and the relationship among the target flavor influence node, the associated variable node, and the target flavor evaluation node; Obtaining global node data of the associated variable node according to the node data of the associated variable node; Performing optimal solution processing on the global node data of the associated variable node to obtain the target node data of the associated variable node; The associated variable node and the target node data of the associated variable node are output and displayed.

9. A display device, characterized in that: Applied to a food flavor analysis system, the device comprises: an acquisition module, configured to acquire a flavor improvement instruction of a target detection object, wherein the flavor improvement instruction includes target impact node data and target flavor evaluation data, wherein the target impact node data includes at least one of target attribute data and target metabolism data; A first determination module is used to determine an associated variable node according to a target basic node corresponding to target attribute data in the target influencing node data, a target metabolic node corresponding to the target metabolic data, and a target flavor evaluation node corresponding to the target flavor evaluation data, wherein the associated variable node is another flavor influencing node that has an associated relationship with the target basic node or the target metabolic node and a causal relationship with the target flavor evaluation node; a second determination module, configured to determine the node data of the associated variable node according to the target influence node data, the target flavor evaluation data, and the relationship among the target flavor influence node, the associated variable node, and the target flavor evaluation node; The output module is used to output and display the associated variable node and the node data of the associated variable node.

10. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed by a processor.

12. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images