Traditional chinese medicine constitution iterative identification method, system and terminal based on feature dynamic embedding

Abstract

The application discloses a traditional Chinese medicine constitution iterative identification method and system based on feature dynamic embedding and a terminal, and relates to the field of artificial intelligence.The technical scheme is as follows: in the case that the quantity of provided constitution features is limited initially, the identified features are dynamically determined according to real-time traditional Chinese medicine constitution identification, the identified features are fused with the existing constitution features, and thus, the traditional Chinese medicine constitution is quickly identified, and the quantity of source data collection is effectively reduced while the accuracy of traditional Chinese medicine constitution identification is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence, more particularly, it relates to a traditional Chinese medicine constitution iterative identification method, system and terminal based on feature dynamic embedding. BACKGROUND

[0002] Traditional Chinese medicine constitution refers to the unique physiological and pathological characteristics formed in the growth and development process under the influence of congenital inheritance and environmental factors. Generally, traditional Chinese medicine divides constitution into the following nine basic types: normal constitution, qi deficiency constitution, yang deficiency constitution, yin deficiency constitution, phlegm-damp constitution, damp-heat constitution, blood stasis constitution, qi depression constitution and special constitution. Through traditional Chinese medicine constitution identification, people can better understand their physical condition and health trend, so as to take more personalized and effective health management measures.

[0003] With the continuous development of artificial intelligence technology, the existing traditional Chinese medicine constitution identification method mainly mines and analyzes a large amount of constitution data through machine learning and deep learning algorithms, mainly considering facial features, tongue features, pulse features and fingerprint features, and some also consider emotional, living habits, eating habits, voice, body shape and other features. However, due to the different feature dimensions exhibited by different traditional Chinese medicine constitutions, some traditional Chinese medicine constitutions can be accurately identified by fewer significant features, while some traditional Chinese medicine constitutions require more features to be accurately identified. In addition, due to the existence of the same or similar features exhibited by different traditional Chinese medicine constitutions, and the influence of system errors brought by feature extraction process, especially in the case of less individual data, it is more likely to misidentify traditional Chinese medicine constitution. On this basis, in order to improve the accuracy of traditional Chinese medicine constitution identification, the number of features required in the traditional Chinese medicine constitution identification process needs to be increased, which not only increases the application difficulty of traditional Chinese medicine constitution identification technology, but also consumes a large amount of network resources, which is not conducive to wide application.

[0004] Therefore, how to research and design a traditional Chinese medicine constitution iterative identification method, system and terminal based on feature dynamic embedding which can overcome the above defects is the problem we need to solve at present. SUMMARY

[0005] In order to solve the problems in the prior art, the purpose of the present application is to provide a traditional Chinese medicine constitution iterative identification method, system and terminal based on feature dynamic embedding, which dynamically determines the to-be-identified features with identification under the condition that the number of constitution features provided initially is limited, and fuses the to-be-identified features with identification with the existing constitution features, so as to realize rapid identification of traditional Chinese medicine constitution, and effectively reduce the data amount of source data collection while ensuring the accuracy of traditional Chinese medicine constitution identification.

[0006] The above technical purpose of the present application is realized by the following technical scheme:

[0007] In a first aspect, a traditional Chinese medicine constitution iterative identification method based on feature dynamic embedding is provided, including the following steps:

[0008] Collecting a facial image, a tongue image and / or a fingerprint image of a target object to obtain a target image;

[0009] Extracting initial constitution features from the target image to obtain a constitution feature set;

[0010] Selecting features exhibited by a single traditional Chinese medicine constitution from the constitution feature set to obtain a sub-feature set corresponding to the traditional Chinese medicine constitution one-to-one;

[0011] Determining at least one to-be-identified feature according to the first N sub-feature sets with the most features and a full feature set corresponding to the traditional Chinese medicine constitutions of the first N sub-feature sets, and generating an information collection strategy according to the detection attribute of the to-be-identified feature;

[0012] Executing the information collection strategy to collect feature information of the to-be-identified feature, and extracting newly added constitution features from the feature information;

[0013] Embedding and fusing the newly added constitution features with the sub-feature sets to obtain updated sub-feature sets;

[0014] Iterating the updated sub-feature sets to embed and fuse the newly added constitution features until the difference between the feature numbers of the first two sub-feature sets with the most features in all the updated sub-feature sets exceeds a feature threshold;

[0015] Taking the traditional Chinese medicine constitution corresponding to the sub-feature set with the most features in the updated sub-feature sets as a traditional Chinese medicine constitution identification result, and outputting the result.

[0016] Further, the process of selecting features exhibited by a single traditional Chinese medicine constitution from the constitution feature set is specifically as follows:

[0017] Statistically analyzing all constitution features exhibited by a single traditional Chinese medicine constitution from historical data to establish a full feature set;

[0018] Solving the intersection of the full feature set and the constitution feature set to obtain a sub-feature set of the corresponding traditional Chinese medicine constitution;

[0019] If there are two mutually exclusive constitution features in the sub-feature set, the two mutually exclusive constitution features are deleted.

[0020] Further, the determination expression of the to-be-identified feature is specifically as follows:

[0021] Selecting the first N sub-feature sets with the most features from all the sub-feature sets;

[0022] Screening all feature items with the same identified object from the whole feature set of the TCM constitution corresponding to the previous N sub-feature sets to obtain an initial feature item set;

[0023] Deleting the feature items in the initial feature item set contained in any one of the previous N sub-feature sets to obtain a final feature item set;

[0024] Each feature item in the final feature item set is taken as a to-be-identified feature.

[0025] Further, the method further comprises:

[0026] If the number of feature items in the final feature item set is zero, the previous N-1 sub-feature sets with the largest number of feature items are used to replace the previous N sub-feature sets to iteratively determine the final feature item set.

[0027] If the number of feature items in the final feature item set determined by the previous 2 sub-feature sets with the largest number of feature items is zero, one feature item not contained in the corresponding sub-feature set is screened from the whole feature set of the TCM constitution corresponding to the previous 2 sub-feature sets, and the two screened feature items are combined to construct a to-be-identified feature.

[0028] Further, the process of generating an information collection strategy according to the detection attribute of the to-be-identified feature is specifically:

[0029] If the detection attribute of the to-be-identified feature is image detection, the generated information collection strategy includes: controlling the image collection device to start and stop, pre-processing the collected image, and extracting the constitution feature corresponding to the to-be-identified feature from the collected image.

[0030] If the detection attribute of the to-be-identified feature is text detection, the generated information collection strategy includes: simulating to generate a question information corresponding to the to-be-identified feature, receiving an answer information corresponding to the question information, and extracting the constitution feature corresponding to the to-be-identified feature from the answer information.

[0031] Further, the process of embedding and fusing the newly added constitution feature and the sub-feature set is specifically:

[0032] If the newly added constitution feature is contained in the whole feature set corresponding to the corresponding sub-feature set, the newly added constitution feature is written into the corresponding sub-feature set to obtain an updated sub-feature set.

[0033] If the newly added constitution feature is not contained in the whole feature set corresponding to the corresponding sub-feature set, the corresponding sub-feature set is not updated.

[0034] Further, the process of determining the feature threshold is specifically:

[0035] Determine the judgment threshold, standard threshold and the number of real-time features of the Nth sub-feature set with the largest number of features;

[0036] If the number of real-time features is less than or equal to the judgment threshold, the feature threshold is taken as the standard threshold;

[0037] If the number of real-time features is greater than the judgment threshold, the real-time ratio of the number of real-time features to the judgment threshold is calculated, and the feature threshold is calculated as the product of the real-time ratio and the standard threshold;

[0038] Alternatively, the feature threshold adopts a standard threshold.

[0039] Secondly, we provide a TCM constitution iterative identification system based on dynamic feature embedding, including:

[0040] An image acquisition module is used to acquire a facial image, a tongue image, and / or a fingerprint image of a target object to obtain a target image;

[0041] A feature extraction module is used to extract initial physical features from the target image to obtain a physical feature set;

[0042] A feature selection module is used to select the features of a single TCM constitution from the constitution feature set to obtain a sub-feature set corresponding to each TCM constitution;

[0043] A strategy generation module is used to determine at least one feature to be identified based on the top N sub-feature sets with the largest number of features and the full feature set of the TCM constitution corresponding to the top N sub-feature sets, and to generate an information collection strategy based on the detection attributes of the feature to be identified;

[0044] An information collection module, configured to execute an information collection strategy to collect feature information of features to be identified, and extract new physical features from the feature information;

[0045] The feature fusion module is used to embed and fuse the newly added physical features with the sub-feature set to obtain an updated sub-feature set;

[0046] An iterative identification module is used to iterate the updated sub-feature sets to embed and fuse the newly added physical features until the difference in the number of features between the first two sub-feature sets with the largest number of features among all the updated sub-feature sets exceeds a feature threshold;

[0047] The result output module is used to take the TCM constitution corresponding to the updated sub-feature set with the largest number of features as the TCM constitution identification result and output it.

[0048] In a third aspect, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the feature dynamic embedding-based traditional Chinese medical constitution iterative identification method according to any one of the first aspect when executing the program.

[0049] In a fourth aspect, a computer readable medium is provided, and a computer program is stored on the computer readable medium, and the computer program is executable on a processor to implement the feature dynamic embedding-based traditional Chinese medical constitution iterative identification method according to any one of the first aspect.

[0050] Compared with the prior art, the present application has the following beneficial effects:

[0051] 1. The feature dynamic embedding-based traditional Chinese medical constitution iterative identification method provided by the present application can dynamically determine the to-be-identified features with identification in the case of limited initial provided constitution features, and fuse the to-be-identified features with identification with the existing constitution features, so as to realize rapid identification of traditional Chinese medical constitution, and effectively reduce the data amount of source data collection while ensuring the accuracy of traditional Chinese medical constitution identification.

[0052] 2. In the process of traditional Chinese medical constitution identification, the present application considers the influence of source data error and system error in the feature extraction process, and deletes two mutually exclusive constitution features in the sub-feature set, so as to ensure the accuracy and reliability of traditional Chinese medical constitution identification.

[0053] 3. In the process of determining the to-be-identified features, the present application takes the first N sub-feature sets with the most features as the basis, and screens the features with the same identification object and not contained in any one of the first N sub-feature sets as the to-be-identified features, so as to effectively ensure the identification of the to-be-identified features.

[0054] 4. The present application dynamically determines the size of the feature threshold according to the real-time feature number of the sub-feature set, so as to not reduce the difference requirement of the overall identification in the case of increasing the number of features. BRIEF DESCRIPTION OF DRAWINGS

[0055] The accompanying drawings, which are included to provide a further understanding of the embodiments of the present application and constitute a part of the application, illustrate embodiments of the present application and do not limit the present application. In the drawings:

[0056] Figure 1 is a flowchart in the first embodiment of the present application;

[0057] Figure 2 is a system block diagram in the second embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the objects, technical solutions and advantages of the present application clearer, further detailed description will be given below in combination with embodiments and drawings, and the schematic embodiments and their descriptions are only used to explain the present application, but not to limit the present application.

[0059] Embodiment 1: Traditional Chinese medicine constitution iterative identification method based on feature dynamic embedding, as shown in the following figure, including the following steps: Figure 1

[0060] S1: Collecting facial image, tongue image and / or fingerprint image of a target object to obtain target image;

[0061] S2: Extracting initial constitution features from the target image to obtain constitution feature set;

[0062] S3: Selecting features shown by a single traditional Chinese medicine constitution from the constitution feature set to obtain sub-feature set corresponding to the traditional Chinese medicine constitution one by one;

[0063] S4: Determining at least one to-be-identified feature according to the first N sub-feature sets with the most features and the full feature set of the traditional Chinese medicine constitutions corresponding to the first N sub-feature sets, and generating information collection strategy according to the detection attribute of the to-be-identified feature;

[0064] S5: Executing the information collection strategy to collect feature information of the to-be-identified feature, and extracting new constitution features from the feature information;

[0065] S6: Embedding and fusing the new constitution features with the sub-feature set to obtain updated sub-feature set;

[0066] S7: Iterating the updated sub-feature set to embed and fuse the new constitution features until the difference between the feature numbers of the first two sub-feature sets with the most features in all updated sub-feature sets exceeds the feature threshold;

[0067] S8: Taking the traditional Chinese medicine constitution corresponding to the updated sub-feature set with the most features as the traditional Chinese medicine constitution identification result, and outputting.

[0068] In step S1, considering the convenience of data collection and the rationality of the initially provided constitution features, the present application extracts constitution features by collecting some image information of the target object as source data. The collected image can be at least one of facial image, tongue image and fingerprint image, which is not limited herein.

[0069] In step S2, if there are multiple collected images, all feature items related to traditional Chinese medicine constitution identification are extracted from different images respectively, and each feature item may show different features for different traditional Chinese medicine constitutions.

[0070] ​1. Taking facial images as an example, the feature items related to TCM constitution contained in facial images include but are not limited to complexion, skin texture, facial luster, eyelid puffiness, facial shape, eyebrow thickness, and lip thickness.

[0071] Specifically, (1) changes in facial color can reflect the state of the body's Qi and blood. For example, a pale complexion may be related to Qi and blood deficiency, a sallow complexion may be related to spleen and stomach weakness, a dark complexion may be related to kidney deficiency or blood stasis, a bluish-purple complexion may be related to Qi and blood stasis, and a red complexion may be related to heat syndrome or Yin deficiency. (2) Changes in skin texture, such as the number and distribution of wrinkles, can also reflect the state of the body constitution. For example, people with Yin deficiency constitution tend to have dry skin and are prone to wrinkles. (3) The glossiness of the face can reflect the state of the body's spirit. Good glossiness usually indicates sufficient Qi and blood, while a dull complexion may indicate insufficient Qi and blood or other health problems. (4) Swollen eyelids may be related to poor kidney function or internal water retention. (5) Facial shape, such as the fatness or thinness of the face, can also reflect the body constitution. For example, facial obesity may be related to phlegm-damp constitution. (6) The thickness and shape of the eyebrows may be related to the release of liver Qi. (7) The thickness and color of the lips can reflect the health of the spleen and stomach.

[0072] Furthermore, facial image features can include facial muscle state and facial temperature. The tension or relaxation of facial muscles can also provide information about physical constitution. Facial temperature distribution may be related to qi and blood circulation and the function of internal organs.

[0073] 2. Taking tongue images as an example, the feature items related to TCM constitution contained in tongue images include but are not limited to tongue color, tongue coating, tongue shape, tongue quality, tooth marks, sublingual veins and tongue body dynamics.

[0074] Specifically, (1) changes in tongue color can reflect the state of Qi and blood. For example, a pale tongue may be associated with Qi and blood deficiency, a red tongue may be associated with heat syndrome or Yin deficiency, and a purple tongue may be associated with Qi and blood stasis. (2) The color and thickness of the tongue coating can reflect the state of dampness, heat, cold and dampness in the body. For example, a white coating may be associated with cold syndrome or superficial syndrome, a yellow coating may be associated with heat syndrome, a thick coating may be associated with phlegm dampness or food accumulation, and a thin coating may be associated with Yin deficiency or superficial syndrome. (3) The shape of the tongue, such as fat, thin, or cracked, can also reflect the state of the body constitution. For example, a fat tongue may be associated with phlegm dampness constitution, and a thin tongue may be associated with Yin deficiency or Qi and blood deficiency. (4) The moistness and elasticity of the tongue can reflect the sufficiency of body fluids and Qi and blood. A dry tongue may be associated with Yin deficiency or heat syndrome, and a moist tongue may be associated with internal water retention. (5) Tooth marks on the edge of the tongue can reflect spleen deficiency or internal water retention. (6) The fullness and color of the sublingual veins can reflect the state of blood circulation and blood stasis. (7) The movement and extension of the tongue can reflect the functional state of the nervous system.

[0075] III. Taking a fingerprint image as an example, the feature items related to the TCM constitution contained in the fingerprint image include, but are not limited to, the texture, morphology and distribution of the fingerprint and the like.

[0076] The constitution features extracted from each source data are combined to form a constitution feature set.

[0077] In step S3, the process of selecting the features exhibited by a single TCM constitution from the constitution feature set is specifically as follows: all the constitution features exhibited by a single TCM constitution are statistically analyzed from the historical data to establish a full feature set; the intersection of the full feature set and the constitution feature set is solved to obtain a sub-feature set of the corresponding TCM constitution; wherein, if there are two mutually exclusive constitution features in the sub-feature set, the two mutually exclusive constitution features are deleted.

[0078] For example, if the constitution feature set contains 11 constitution features {a, b, c, d, e, f, g, h, I, j, k} in total, and the full feature set of yin deficiency constitution is {a, b, f, j, k, m, q, s, …}, then the sub-feature set corresponding to the yin deficiency constitution selected from the constitution feature set is {a, b, f, j, k}.

[0079] In the process of identifying the TCM constitution, the present application takes into account the influence of source data errors and system errors in the feature extraction process, and deletes two mutually exclusive constitution features in the sub-feature set, so as to ensure the accuracy and reliability of the identification of the TCM constitution.

[0080] For example, if constitution feature a and constitution feature b do not exist simultaneously in the yin deficiency constitution, then constitution feature a and constitution feature b can be deleted from the sub-feature set at the same time, and the final sub-feature set is {f, j, k}.

[0081] In step S4, the determination expression of the to-be-identified features is specifically as follows: the first N sub-feature sets with the most features are selected from all the sub-feature sets; all the feature items with the same identification object are selected from the full feature sets of the TCM constitutions corresponding to the first N sub-feature sets to obtain an initial feature item set; the feature items contained in any one of the first N sub-feature sets in the initial feature item set are deleted to obtain a final feature item set; each feature item in the final feature item set is taken as a to-be-identified feature.

[0082] For example, the first three sub-feature sets with the most features are selected as follows: the phlegm-damp constitution {a, f, g, h, I, j}, the damp-heat constitution {a, b, e, f, k} and the yin deficiency constitution {f, j, k}.

[0083] And the full feature set of phlegm-dampness constitution is {a, f, g, h, I, j, r, y, z, s,...}, the full feature set of damp-heat constitution is {a, b, e, f, k, g, z, x, s,...}, the full feature set of yin deficiency constitution is {a, b, f, j, k, m, q, s,...}, and the feature items corresponding to a and s are screened out as all feature items with the same identification object, since a is in the above sub-feature set, the final feature item set is {S}, wherein S is the feature item corresponding to s.

[0084] In addition, if the number of feature items in the final feature item set is zero, the first N-1 sub-feature sets with the most feature items are used to replace the first N sub-feature sets with the most feature items to iteratively determine the final feature item set. If the number of feature items in the final feature item set determined by the first 2 sub-feature sets with the most feature items is zero, one feature item not included in the corresponding sub-feature set is screened out from the full feature set of the corresponding constitution of traditional Chinese medicine of the first 2 sub-feature sets, and the two screened feature items are combined to construct a to-be-identified feature.

[0085] The process of generating an information collection strategy according to the detection attribute of the to-be-identified feature is as follows: if the detection attribute of the to-be-identified feature is image detection, the generated information collection strategy includes: controlling the start and stop of the image collection device, preprocessing the collected image, and extracting the constitution feature corresponding to the to-be-identified feature from the collected image; if the detection attribute of the to-be-identified feature is text detection, the generated information collection strategy includes: simulating the generation of question information corresponding to the to-be-identified feature, receiving answer information corresponding to the question information, and extracting the constitution feature corresponding to the to-be-identified feature from the answer information.

[0086] In step S5, assuming that the to-be-identified feature is eating habits and the detection attribute is text detection, the information collection strategy can be executed in two ways: voice questioning and text questioning. Therefore, a series of question information can be generated using an artificial voice template, such as: "Do you like spicy food?", "Do you like greasy food?", etc.

[0087] In the process of executing the information collection strategy, it also includes controlling the start of devices such as voice players and sound collectors to realize automatic information collection.

[0088] In step S6, the process of embedding and fusing the added constitution feature and the sub-feature set is as follows: if the added constitution feature is included in the full feature set corresponding to the corresponding sub-feature set, the added constitution feature is written into the corresponding sub-feature set to obtain an updated sub-feature set; if the added constitution feature is not included in the full feature set corresponding to the corresponding sub-feature set, the corresponding sub-feature set is not updated.

[0089] If the added constitution feature is s, the updated sub-feature set is {f, j, k, s}.

[0090] In step S7, after each update, it is determined whether the difference between the number of features of the first two sub-feature sets with the largest number of features in the current iteration exceeds the feature threshold. If not, the iteration continues; if so, the recognition process terminates.

[0091] As an optional embodiment, the feature threshold can be set as a fixed standard threshold according to historical data.

[0092] As another optional embodiment, the determination process of the feature threshold is as follows: determining the judgment threshold, the standard threshold and the real-time feature quantity of the Nth sub-feature set with the largest number of features; if the real-time feature quantity is less than or equal to the judgment threshold, the feature threshold is set as the standard threshold; if the real-time feature quantity is greater than the judgment threshold, the real-time ratio of the real-time feature quantity to the judgment threshold is calculated, and the product of the real-time ratio and the standard threshold is calculated to obtain the feature threshold.

[0093] According to the real-time feature quantity of the sub-feature set, the size of the feature threshold is dynamically determined, and the difference requirement of the overall recognition is not reduced in the case of increasing the number of features.

[0094] In step S8, the traditional Chinese constitution recognition result can be printed by a printing device, or connected to other electronic devices, terminals, software apps, etc. to remotely transmit the traditional Chinese constitution recognition result, which is not limited here.

[0095] Embodiment 2: A traditional Chinese constitution iterative recognition system based on dynamic feature embedding, which is used to realize the traditional Chinese constitution iterative recognition method based on dynamic feature embedding as described in embodiment 1, as shown in the following figure, including an image acquisition module, a feature extraction module, a feature selection module, a strategy generation module, an information acquisition module, a feature fusion module, an iterative recognition module and a result output module. Figure 2

[0096] ​Among them, the image acquisition module is used to collect the facial image, tongue image and / or fingerprint image of the target object to obtain the target image; the feature extraction module is used to extract the initial physical characteristics from the target image to obtain the physical characteristic set; the feature selection module is used to select the characteristics of a single traditional Chinese medicine constitution from the physical characteristic set to obtain a sub-feature set corresponding to the traditional Chinese medicine constitution; the strategy generation module is used to determine at least one feature to be identified based on the top N sub-feature sets with the largest number of features and the full feature set of the traditional Chinese medicine constitution corresponding to the top N sub-feature sets, and generate an information acquisition strategy based on the detection attributes of the feature to be identified; the information The acquisition module is used to execute the information acquisition strategy to collect the feature information of the features to be identified, and extract the newly added physical features from the feature information; the feature fusion module is used to embed and fuse the newly added physical features with the sub-feature set to obtain an updated sub-feature set; the iterative identification module is used to iterate the updated sub-feature set to embed and fuse the newly added physical features until the difference in the number of features of the first two sub-feature sets with the largest number of features in all the updated sub-feature sets exceeds the feature threshold; the result output module is used to use the traditional Chinese medicine constitution corresponding to the updated sub-feature set with the largest number of features as the traditional Chinese medicine constitution identification result, and output it.

[0097] The present invention also records a computer terminal, which includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, it implements the iterative identification method of TCM constitution based on dynamic feature embedding as described in Example 1.

[0098] The present invention also records a computer-readable medium on which a computer program is stored. When the computer program is executed by a processor, it can implement the iterative identification method of TCM constitution based on dynamic feature embedding as described in Example 1.

[0099] Working principle: When the number of initially provided physical characteristics is limited, the present invention dynamically determines the identifiable features to be identified based on the real-time TCM physical characteristics identification situation, and integrates the identifiable features to be identified with the previously existing physical characteristics, thereby realizing the rapid identification of TCM physical characteristics, and effectively reducing the amount of source data collected while ensuring the accuracy of TCM physical characteristics identification.

[0100] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0101] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0102] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0103] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0104] The above description is only specific implementation of the present application, and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. The iterative identification method of TCM constitution based on dynamic feature embedding is characterized by: The following steps are involved: Collecting a facial image, a tongue image, and / or a fingerprint image of a target object to obtain a target image; Extracting initial physical features from the target image to obtain a physical feature set; Select the characteristics of a single TCM constitution from the constitution characteristic set to obtain a sub-feature set corresponding to each TCM constitution; Determine at least one feature to be identified based on the top N sub-feature sets with the largest number of features and the full feature set of the TCM constitution corresponding to the top N sub-feature sets, and generate an information collection strategy based on the detection attributes of the feature to be identified; Executing an information collection strategy to collect feature information of the feature to be identified, and extracting new physical features from the feature information; The newly added physical features are embedded and fused with the sub-feature set to obtain the updated sub-feature set; The updated sub-feature sets are iterated to embed and fuse the newly added physical features until the difference in the number of features between the first two sub-feature sets with the largest number of features among all the updated sub-feature sets exceeds the feature threshold; The TCM constitution corresponding to the updated sub-feature set with the largest number of features is taken as the TCM constitution identification result and output.

2. The iterative identification method for TCM constitution based on dynamic feature embedding according to claim 1 is characterized in that: The process of selecting the characteristics of a single TCM constitution from the constitution characteristic set is specifically as follows: Statistically analyze all the constitutional characteristics of a single TCM constitution from historical data and establish a complete characteristic set; Solve the intersection of the full feature set and the constitution feature set to obtain the sub-feature set of the corresponding TCM constitution; If there are two mutually exclusive physical features in the sub-feature set, the two mutually exclusive physical features are deleted.

3. The iterative identification method for TCM constitution based on dynamic feature embedding according to claim 1 is characterized in that: The specific expression for determining the feature to be identified is: Filter out the top N sub-feature sets with the largest number of features from all sub-feature sets; From the full feature set of TCM constitutions corresponding to the first N sub-feature sets, all feature items with the same identification object are screened out to obtain the initial feature item set; Delete the feature items in any of the first N sub-feature sets in the initial feature item set to obtain the final feature item set; Each feature item in the final feature item set is used as a feature to be identified.

4. The iterative identification method for TCM constitution based on dynamic feature embedding according to claim 3 is characterized in that: The method further includes: If the number of feature items in the final feature item set is zero, the first N-1 sub-feature sets with the largest number of features are used to replace the first N sub-feature sets with the largest number of features to iterate and determine the final feature item set; If the number of feature items in the final feature item set determined by the first two sub-feature sets with the largest number of features is zero, then one feature item that is not included in the corresponding sub-feature set is screened out from the full feature set of the TCM constitution corresponding to the first two sub-feature sets, and the two screened feature items are combined to construct a feature to be identified.

5. The iterative identification method of TCM constitution based on dynamic feature embedding according to claim 1 is characterized in that: The process of generating an information collection strategy based on the detection attributes of the feature to be identified is specifically as follows: If the detection attribute of the feature to be identified is image detection, the generated information collection strategy includes: controlling the image acquisition device to start and stop, pre-processing the acquired image, and extracting the physical characteristics corresponding to the feature to be identified from the acquired image; If the detection attribute of the feature to be identified is text detection, the generated information collection strategy includes: simulating and generating question information corresponding to the feature to be identified, receiving answer information corresponding to the question information, and extracting the physical characteristics corresponding to the feature to be identified from the answer information.

6. The iterative identification method for TCM constitution based on dynamic feature embedding according to claim 1 is characterized in that: The process of embedding and fusing the newly added physical features with the sub-feature set is specifically as follows: If the newly added physical feature is included in the full feature set corresponding to the corresponding sub-feature set, the newly added physical feature is written into the corresponding sub-feature set to obtain an updated sub-feature set; If the newly added physical feature is not included in the full feature set corresponding to the corresponding sub-feature set, the corresponding sub-feature set will not be updated.

7. The iterative identification method for TCM constitution based on dynamic feature embedding according to claim 1 is characterized in that: The process of determining the characteristic threshold is specifically as follows: Determine the judgment threshold, standard threshold and the number of real-time features of the Nth sub-feature set with the largest number of features; If the number of real-time features is less than or equal to the judgment threshold, the feature threshold is taken as the standard threshold; If the number of real-time features is greater than the judgment threshold, the real-time ratio of the number of real-time features to the judgment threshold is calculated, and the feature threshold is calculated as the product of the real-time ratio and the standard threshold; Alternatively, the feature threshold adopts a standard threshold.

8. The TCM constitution iterative identification system based on dynamic feature embedding is characterized by: include: An image acquisition module is used to acquire a facial image, a tongue image, and / or a fingerprint image of a target object to obtain a target image; A feature extraction module is used to extract initial physical features from the target image to obtain a physical feature set; A feature selection module is used to select the features of a single TCM constitution from the constitution feature set to obtain a sub-feature set corresponding to each TCM constitution; A strategy generation module is used to determine at least one feature to be identified based on the top N sub-feature sets with the largest number of features and the full feature set of the TCM constitution corresponding to the top N sub-feature sets, and to generate an information collection strategy based on the detection attributes of the feature to be identified; An information collection module, configured to execute an information collection strategy to collect feature information of features to be identified, and extract new physical features from the feature information; The feature fusion module is used to embed and fuse the newly added physical features with the sub-feature set to obtain an updated sub-feature set; An iterative identification module is used to iterate the updated sub-feature sets to embed and fuse the newly added physical features until the difference in the number of features between the first two sub-feature sets with the largest number of features among all the updated sub-feature sets exceeds a feature threshold; The result output module is used to take the TCM constitution corresponding to the updated sub-feature set with the largest number of features as the TCM constitution identification result and output it.

9. A computer terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the iterative identification method of TCM constitution based on dynamic feature embedding as described in any one of claims 1 to 7 is implemented.

10. A computer-readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the TCM constitution iterative identification method based on dynamic feature embedding as described in any one of claims 1 to 7.

Images