Method and system for identifying physique based on big data and electronic equipment

Abstract

The invention discloses a method and system for identifying physique based on big data and electronic equipment, and relates to the technical field of data analysis. The method comprises the following steps: constructing a physique identification model based on big data; collecting tongue coating data and complexion data; respectively inputting the tongue coating data and the complexion data into a constitution identification model to output tongue coating analysis data, a tongue coating constitution analysis result, complexion analysis data and a complexion constitution analysis result; packaging the coated tongue analysis data and the complexion analysis data, inputting the packaged data into a constitution identification model, and outputting a comprehensive constitution analysis result; and performing data analysis on the tongue coating analysis physique result, the complexion analysis physique result and the comprehensive analysis physique result, and outputting a physique identification result. The system and the electronic equipment correspond to the method. According to the invention, the method achieves the reverse verification of the tongue coating analysis physique result and the complexion analysis physique result through the comprehensive analysis physique result, achieves the identification of the physique through comprehensive data, and improves the accuracy, reliability and comprehensiveness of the physique identification result.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, specifically a method, system, and electronic device for identifying physical constitution based on big data. Background Technology

[0002] Body constitution identification is highly valuable for individual health maintenance and medical treatment. However, most existing methods for determining an individual's body constitution type still rely on manual testing. This method, while scientifically sound, suffers from low efficiency, significant human interference, and poor accuracy. Therefore, a scientific and efficient body constitution identification technique is urgently needed. Summary of the Invention

[0003] The purpose of this application is to provide a method, system, and electronic device for identifying physical constitution based on big data, so as to solve the technical problems mentioned in the background art.

[0004] To achieve the above objectives, this application discloses the following technical solutions:

[0005] In a first aspect, this application discloses a method for identifying physical constitution based on big data, the method comprising the following steps:

[0006] A constitution identification model is constructed based on big data. The constitution identification model is constructed by machine learning using tongue coating appearance and / or facial color appearance and corresponding constitution results as keywords.

[0007] Collect users’ tongue coating data and facial color data. The tongue coating data includes tongue color, coating color and tongue appearance. The facial color data includes facial color and eye appearance.

[0008] The user's tongue coating data and complexion data are respectively input into the constitution identification model. The constitution identification model outputs constitution analysis results, which include tongue coating analysis data and tongue coating analysis constitution results, and complexion analysis data and complexion analysis constitution results.

[0009] The tongue coating analysis data and complexion analysis data are packaged and input into the constitution identification model. The constitution identification model outputs the constitution analysis results, which also include comprehensive analysis results.

[0010] The results of the tongue coating analysis, the facial complexion analysis, and the comprehensive analysis of constitution are analyzed. When the comprehensive analysis of constitution is the same as the results of the tongue coating analysis, facial complexion analysis, and comprehensive analysis of constitution, the comprehensive analysis of constitution is taken as the constitution identification result. Otherwise, the results of the tongue coating analysis, facial complexion analysis, and comprehensive analysis of constitution are taken as the constitution identification result.

[0011] Preferably, before inputting the user's tongue coating data and complexion data into the constitution identification model, the method further includes: performing color mean-normalization processing on the tongue coating data and complexion data.

[0012] Preferably, the data analysis of the tongue coating analysis results, the facial complexion analysis results, and the comprehensive analysis results specifically includes:

[0013] Feature descriptions are extracted from the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results, respectively. The obtained feature descriptions are parsed based on natural language understanding technology to obtain a dataset of feature descriptions for the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results.

[0014] Calculate the correlation coefficient Bcw1 between the tongue coating analysis constitution result and the comprehensive analysis constitution result, the correlation coefficient Bcw2 between the complexion analysis constitution result and the comprehensive analysis constitution result, and calculate the correlation coefficient Bcw3 between the tongue coating analysis constitution result, the complexion analysis constitution result and the comprehensive analysis constitution result;

[0015] When Bcw1+Bcw2≥Bcw3, the comprehensive analysis result of constitution is defined to be the same as the tongue coating analysis data and the tongue coating analysis result of constitution, as well as the complexion analysis data and the complexion analysis result of constitution; otherwise, the comprehensive analysis result of constitution is defined to be different from the tongue coating analysis data and the tongue coating analysis result of constitution, as well as the complexion analysis data and the complexion analysis result of constitution.

[0016] Preferably, the correlation coefficient Bcw1 is calculated using the following formula:

[0017]

[0018] Among them, Q t Q represents the number of feature descriptions in the feature description dataset corresponding to the tongue coating analysis constitution results. COM-T The number of feature descriptions output by the constitution identification model based on tongue coating analysis data in the feature description dataset of the comprehensive analysis of constitution results.

[0019] Preferably, the correlation coefficient Bcw2 is calculated using the following formula:

[0020]

[0021] Among them, Q f Q represents the number of feature descriptions in the feature description dataset corresponding to the complexion analysis results. COM-FThe number of feature descriptions output by the constitution identification model based on facial color analysis data in the feature description dataset of the comprehensive analysis of constitution results.

[0022] Preferably, the correlation coefficient Bcw3 is calculated using the following formula:

[0023]

[0024] Among them, Q t Q represents the number of feature descriptions in the feature description dataset corresponding to the tongue coating analysis constitution results. f Q represents the number of feature descriptions in the feature description dataset corresponding to the complexion analysis results. COM This refers to the total number of feature descriptions in the feature description dataset corresponding to the comprehensive analysis of physical constitution results.

[0025] Secondly, this application discloses a system for identifying physical constitution based on big data, including a data acquisition module, a physical constitution identification model, a result analysis module, and a result output module;

[0026] The data acquisition module is configured to collect the user's tongue coating data and facial color data. The tongue coating data includes tongue color, coating color, and tongue appearance. The facial color data includes facial color and eye appearance.

[0027] The constitution identification model is based on big data to obtain tongue coating appearance, facial complexion appearance, and corresponding constitution results. It is constructed by using tongue coating appearance and / or facial complexion appearance and corresponding constitution results as keywords for machine learning. It is further configured to: use the user's tongue coating data and facial complexion data as input layers, and output constitution analysis results after machine learning. The constitution analysis results include tongue coating analysis data and tongue coating analysis constitution results, and facial complexion analysis data and facial complexion analysis constitution results; and use packaged tongue coating analysis data and facial complexion analysis data as input layers, and output constitution analysis results after machine learning. The constitution analysis results also include comprehensive constitution analysis results.

[0028] The result analysis module is configured to: analyze the results of the tongue coating analysis, the results of the complexion analysis, and the results of the comprehensive analysis; when the results of the comprehensive analysis are the same as the results of the tongue coating analysis, the results of the tongue coating analysis, the results of the complexion analysis, and the results of the complexion analysis, the results of the comprehensive analysis are taken as the results of the constitution identification; otherwise, the results of the tongue coating analysis, the results of the complexion analysis, and the results of the comprehensive analysis are taken as the results of the constitution identification.

[0029] The result output module is configured to display the physical constitution identification results.

[0030] Preferably, the data acquisition module is further configured to perform color mean-reduction and normalization processing on the tongue coating data and the complexion data.

[0031] Preferably, the data analysis of the tongue coating analysis results, the facial complexion analysis results, and the comprehensive analysis results specifically includes:

[0032] Feature descriptions are extracted from the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results, respectively. The obtained feature descriptions are parsed based on natural language understanding technology to obtain a dataset of feature descriptions for the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results.

[0033] Calculate the correlation coefficient Bcw1 between the tongue coating analysis constitution result and the comprehensive analysis constitution result, the correlation coefficient Bcw2 between the complexion analysis constitution result and the comprehensive analysis constitution result, and calculate the correlation coefficient Bcw3 between the tongue coating analysis constitution result, the complexion analysis constitution result and the comprehensive analysis constitution result;

[0034] When Bcw1+Bcw2≥Bcw3, the comprehensive analysis result of constitution is defined to be the same as the tongue coating analysis data and the tongue coating analysis result of constitution, as well as the complexion analysis data and the complexion analysis result of constitution; otherwise, the comprehensive analysis result of constitution is defined to be different from the tongue coating analysis data and the tongue coating analysis result of constitution, as well as the complexion analysis data and the complexion analysis result of constitution.

[0035] Thirdly, this application discloses an electronic device including at least one memory and at least one processor, wherein the memory is communicatively connected to the processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements the method for identifying physical constitution based on big data as described above.

[0036] Beneficial Effects: The method, system, and electronic device for identifying body constitution based on big data in this application construct a body constitution identification model based on big data. Using collected tongue coating and facial color data as input layers, the model outputs corresponding tongue coating analysis data and body constitution analysis results, as well as facial color analysis data and body constitution analysis results. Then, using the combined data of tongue coating and facial color analysis as input layers, the model outputs corresponding comprehensive body constitution analysis results. Finally, through data analysis of the tongue coating, facial color, and comprehensive body constitution analysis results, the body constitution identification result is obtained. This approach achieves the goal of using comprehensive body constitution analysis results to verify the tongue coating and facial color analysis results, improving the accuracy of body constitution identification results. Simultaneously, it achieves the goal of identifying body constitution using comprehensive data, thereby improving the reliability and comprehensiveness of the body constitution identification results. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A flowchart illustrating a method for identifying physical constitution based on big data, as provided in an embodiment of this application. Detailed Implementation

[0039] The technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0040] In this document, the term "comprising" is intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0041] In a first aspect, this embodiment discloses as follows Figure 1 The method shown is based on big data to identify physical constitution. The method includes the following steps:

[0042] A constitution identification model is constructed based on big data. The constitution identification model is constructed by machine learning using tongue coating appearance and / or facial color appearance and corresponding constitution results as keywords.

[0043] Collect users’ tongue coating data and facial color data. The tongue coating data includes tongue color, coating color and tongue appearance. The facial color data includes facial color and eye appearance.

[0044] The user's tongue coating data and complexion data are respectively input into the constitution identification model. The constitution identification model outputs constitution analysis results, which include tongue coating analysis data and tongue coating analysis constitution results, and complexion analysis data and complexion analysis constitution results.

[0045] The tongue coating analysis data and complexion analysis data are packaged and input into the constitution identification model. The constitution identification model outputs the constitution analysis results, which also include comprehensive analysis results.

[0046] The results of the tongue coating analysis, the facial complexion analysis, and the comprehensive analysis of constitution are analyzed. When the comprehensive analysis of constitution is the same as the results of the tongue coating analysis, facial complexion analysis, and comprehensive analysis of constitution, the comprehensive analysis of constitution is taken as the constitution identification result. Otherwise, the results of the tongue coating analysis, facial complexion analysis, and comprehensive analysis of constitution are taken as the constitution identification result.

[0047] Constitution identification is a crucial step in Traditional Chinese Medicine (TCM) diagnosis. Based on constitution, it comprehensively assesses a person's health status through observation, auscultation, inquiry, and palpation. Therefore, TCM techniques can be used to identify a person's constitution. This application constructs a constitution identification model based on big data. Using collected tongue coating and facial color data as input layers, the model outputs corresponding tongue coating analysis data and constitution analysis results, as well as facial color analysis data and constitution analysis results. Then, using the combined data from the tongue coating and facial color analysis as input layers, the model outputs a comprehensive constitution analysis result. Finally, through data analysis of the tongue coating, facial color, and comprehensive constitution analysis results, the final constitution identification result is obtained. This approach achieves the goal of using the comprehensive constitution analysis result to verify the tongue coating and facial color analysis results, improving the accuracy of the constitution identification results. Simultaneously, it achieves the goal of identifying constitution using comprehensive data, thereby enhancing the reliability and comprehensiveness of the constitution identification results.

[0048] In this embodiment, before inputting the user's tongue coating data and complexion data into the constitution identification model, the method further includes: performing color mean removal and normalization processing on the tongue coating data and complexion data. The advantage of this is that it reduces the computational burden on the constitution identification model when recognizing data, improving data processing efficiency and accuracy.

[0049] In this embodiment, the data analysis of the tongue coating analysis results, the facial complexion analysis results, and the comprehensive analysis results specifically includes:

[0050] Feature descriptions are extracted from the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results, respectively. The obtained feature descriptions are parsed based on natural language understanding technology to obtain a dataset of feature descriptions for the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results.

[0051] Calculate the correlation coefficient Bcw1 between the tongue coating analysis constitution result and the comprehensive analysis constitution result, the correlation coefficient Bcw2 between the complexion analysis constitution result and the comprehensive analysis constitution result, and calculate the correlation coefficient Bcw3 between the tongue coating analysis constitution result, the complexion analysis constitution result and the comprehensive analysis constitution result;

[0052] When Bcw1+Bcw2≥Bcw3, the comprehensive analysis result of constitution is defined to be the same as the tongue coating analysis data and the tongue coating analysis result of constitution, as well as the complexion analysis data and the complexion analysis result of constitution; otherwise, the comprehensive analysis result of constitution is defined to be different from the tongue coating analysis data and the tongue coating analysis result of constitution, as well as the complexion analysis data and the complexion analysis result of constitution.

[0053] Specifically, the correlation coefficient Bcw1 is calculated using the following formula:

[0054]

[0055] Among them, Q t Q represents the number of feature descriptions in the feature description dataset corresponding to the tongue coating analysis constitution results. COM-T The number of feature descriptions output by the constitution identification model based on tongue coating analysis data in the feature description dataset of the comprehensive analysis of constitution results.

[0056] Specifically, the correlation coefficient Bcw2 is calculated using the following formula:

[0057]

[0058] Among them, Q fQ represents the number of feature descriptions in the feature description dataset corresponding to the complexion analysis results. COM-F The number of feature descriptions output by the constitution identification model based on facial color analysis data in the feature description dataset of the comprehensive analysis of constitution results.

[0059] Specifically, the correlation coefficient Bcw3 is calculated using the following formula:

[0060]

[0061] Among them, Q t Q represents the number of feature descriptions in the feature description dataset corresponding to the tongue coating analysis constitution results. f Q represents the number of feature descriptions in the feature description dataset corresponding to the complexion analysis results. COM This refers to the total number of feature descriptions in the feature description dataset corresponding to the comprehensive analysis of physical constitution results.

[0062] In the complex and reliable theories of Traditional Chinese Medicine, different morphological manifestations can exhibit different symptoms / manifestations. Therefore, in the calculation of the correlation coefficient, it is understandable that Q... COM With Q COM-F and Q COM-T There is an uncertain relationship between them, that is, there may be a Q. COM =Q COM-F +Q COM-T Q COM >Q COM-F +Q COM-T And Q COM <Q COM-F +Q COM-T Therefore, in these three cases, the correlation coefficients Bcw1 and Bcw2 cannot be relied upon alone to obtain the final constitution identification result. This application, however, uses a comprehensive analysis of constitution data obtained by integrating tongue coating analysis data and facial complexion analysis data, and further uses this comprehensive analysis result to verify the tongue coating analysis and facial complexion analysis results, thus improving the accuracy, reliability, and comprehensiveness of the constitution identification result.

[0063] Secondly, this embodiment discloses a system for identifying body constitution based on big data, including a data acquisition module, a body constitution identification model, a result analysis module, and a result output module.

[0064] Specifically, the data acquisition module is configured to: collect the user's tongue coating data and facial color data, wherein the tongue coating data includes tongue color, coating color and tongue appearance, and the facial color data includes facial color and eye appearance;

[0065] The constitution identification model is based on big data to obtain tongue coating appearance, facial complexion appearance, and corresponding constitution results. It is constructed by using tongue coating appearance and / or facial complexion appearance and corresponding constitution results as keywords for machine learning. It is further configured to: use the user's tongue coating data and facial complexion data as input layers, and output constitution analysis results after machine learning. The constitution analysis results include tongue coating analysis data and tongue coating analysis constitution results, and facial complexion analysis data and facial complexion analysis constitution results; and use packaged tongue coating analysis data and facial complexion analysis data as input layers, and output constitution analysis results after machine learning. The constitution analysis results also include comprehensive constitution analysis results.

[0066] The result analysis module is configured to: analyze the results of the tongue coating analysis, the results of the complexion analysis, and the results of the comprehensive analysis; when the results of the comprehensive analysis are the same as the results of the tongue coating analysis, the results of the tongue coating analysis, the results of the complexion analysis, and the results of the complexion analysis, the results of the comprehensive analysis are taken as the results of the constitution identification; otherwise, the results of the tongue coating analysis, the results of the complexion analysis, and the results of the comprehensive analysis are taken as the results of the constitution identification.

[0067] The result output module is configured to display the physical constitution identification results.

[0068] In this embodiment, the data acquisition module is further configured to perform color mean-reduction and normalization processing on the tongue coating data and the facial color data.

[0069] In this embodiment, the data analysis of the tongue coating analysis results, the facial complexion analysis results, and the comprehensive analysis results specifically includes:

[0070] Feature descriptions are extracted from the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results, respectively. The obtained feature descriptions are parsed based on natural language understanding technology to obtain a dataset of feature descriptions for the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results.

[0071] Calculate the correlation coefficient Bcw1 between the tongue coating analysis constitution result and the comprehensive analysis constitution result, the correlation coefficient Bcw2 between the complexion analysis constitution result and the comprehensive analysis constitution result, and calculate the correlation coefficient Bcw3 between the tongue coating analysis constitution result, the complexion analysis constitution result and the comprehensive analysis constitution result;

[0072] When Bcw1 + Bcw2 ≥ Bcw3, the comprehensive constitution analysis result is defined as being the same as the tongue coating analysis data and the tongue coating analysis constitution result, as well as the complexion analysis data and the complexion analysis constitution result; otherwise, the comprehensive constitution analysis result is defined as being different from the tongue coating analysis data and the tongue coating analysis constitution result, as well as the complexion analysis data and the complexion analysis constitution result.

[0073] It should be noted that the system for identifying physical constitution based on big data in this embodiment is applicable to the aforementioned method for identifying physical constitution based on big data. Therefore, the technical effects of the system for identifying physical constitution based on big data disclosed in this embodiment are the same as those of the aforementioned method for identifying physical constitution based on big data, and will not be repeated here. Furthermore, for any technical means not disclosed in this system for identifying physical constitution based on big data, please refer to the relevant descriptions in the aforementioned method for identifying physical constitution based on big data, and will not be repeated here.

[0074] Thirdly, this embodiment discloses an electronic device, including at least one memory and at least one processor, wherein the memory is communicatively connected to the processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, the method for identifying physical constitution based on big data as described above is implemented.

[0075] Similarly, the electronic device in this embodiment corresponds to the aforementioned method for identifying physical constitution based on big data. Therefore, the technical effects of the electronic device disclosed in this embodiment are the same as those of the aforementioned method for identifying physical constitution based on big data, and will not be repeated here.

[0076] In this embodiment, for software implementation, some or all of the processes of the embodiment can be implemented by a computer program instructing related hardware. During implementation, the program can be stored in a computer-readable storage medium or transmitted as one or more instructions or code on a computer-readable storage medium. Specifically, the computer-readable storage medium includes computer storage media and communication media, wherein the communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium that a computer can access. Computer-readable storage media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code having the form of instructions or data structures and accessible by a computer.

[0077] Finally, it should be noted that the above description is only a preferred embodiment of this application and is not intended to limit this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for identifying body constitution based on big data, characterized in that, The method includes the following steps: A constitution identification model is constructed based on big data. The constitution identification model is constructed by machine learning using tongue coating appearance and / or facial color appearance and corresponding constitution results as keywords. Collect users’ tongue coating data and facial color data. The tongue coating data includes tongue color, coating color and tongue appearance. The facial color data includes facial color and eye appearance. The user's tongue coating data and complexion data are respectively input into the constitution identification model. The constitution identification model outputs constitution analysis results, which include tongue coating analysis data and tongue coating analysis constitution results, and complexion analysis data and complexion analysis constitution results. The tongue coating analysis data and complexion analysis data are packaged and input into the constitution identification model. The constitution identification model outputs the constitution analysis results, which also include comprehensive analysis results. The results of the tongue coating analysis, the facial complexion analysis, and the comprehensive analysis of constitution are analyzed. When the comprehensive analysis of constitution is the same as the results of the tongue coating analysis, facial complexion analysis, and comprehensive analysis of constitution, the comprehensive analysis of constitution is taken as the constitution identification result. Otherwise, the results of the tongue coating analysis, facial complexion analysis, and comprehensive analysis of constitution are taken as the constitution identification result.

2. The method for identifying physical constitution based on big data according to claim 1, characterized in that, Before inputting the user's tongue coating data and complexion data into the constitution identification model, the method further includes: performing color mean-reduction and normalization processing on the tongue coating data and the complexion data.

3. The method for identifying physical constitution based on big data according to claim 1, characterized in that, The data analysis of the tongue coating analysis results, the facial complexion analysis results, and the comprehensive analysis results specifically includes: Feature descriptions are extracted from the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results, respectively. The obtained feature descriptions are parsed based on natural language understanding technology to obtain a dataset of feature descriptions for the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results. Calculate the correlation coefficient Bcw1 between the tongue coating analysis constitution result and the comprehensive analysis constitution result, the correlation coefficient Bcw2 between the complexion analysis constitution result and the comprehensive analysis constitution result, and calculate the correlation coefficient Bcw3 between the tongue coating analysis constitution result, the complexion analysis constitution result and the comprehensive analysis constitution result; When Bcw1+Bcw2≥Bcw3, the comprehensive analysis result of constitution is defined to be the same as the tongue coating analysis data and the tongue coating analysis result of constitution, as well as the complexion analysis data and the complexion analysis result of constitution; otherwise, the comprehensive analysis result of constitution is defined to be different from the tongue coating analysis data and the tongue coating analysis result of constitution, as well as the complexion analysis data and the complexion analysis result of constitution.

4. The method for identifying physical constitution based on big data according to claim 3, characterized in that, The correlation coefficient Bcw1 is calculated using the following formula: Among them, Q t Q represents the number of feature descriptions in the feature description dataset corresponding to the tongue coating analysis constitution results. COM-T The number of feature descriptions output by the constitution identification model based on tongue coating analysis data in the feature description dataset of the comprehensive analysis of constitution results.

5. The method for identifying physical constitution based on big data according to claim 3, characterized in that, The correlation coefficient Bcw2 is calculated using the following formula: Among them, Q f Q represents the number of feature descriptions in the feature description dataset corresponding to the complexion analysis results. COM-F The number of feature descriptions output by the constitution identification model based on facial color analysis data in the feature description dataset of the comprehensive analysis of constitution results.

6. The method for identifying physical constitution based on big data according to claim 3, characterized in that, The correlation coefficient Bcw3 is calculated using the following formula: Among them, Q t Q represents the number of feature descriptions in the feature description dataset corresponding to the tongue coating analysis constitution results. f Q represents the number of feature descriptions in the feature description dataset corresponding to the complexion analysis results. COM This refers to the total number of feature descriptions in the feature description dataset corresponding to the comprehensive analysis of physical constitution results.

7. A system for identifying physical constitution based on big data, characterized in that, It includes a data acquisition module, a physical constitution identification model, a result analysis module, and a result output module; The data acquisition module is configured to collect the user's tongue coating data and facial color data. The tongue coating data includes tongue color, coating color, and tongue appearance. The facial color data includes facial color and eye appearance. The constitution identification model is based on big data to obtain tongue coating appearance, facial complexion appearance, and corresponding constitution results. It is constructed by using tongue coating appearance and / or facial complexion appearance and corresponding constitution results as keywords for machine learning. It is further configured to: use the user's tongue coating data and facial complexion data as input layers, and output constitution analysis results after machine learning. The constitution analysis results include tongue coating analysis data and tongue coating analysis constitution results, and facial complexion analysis data and facial complexion analysis constitution results; and use packaged tongue coating analysis data and facial complexion analysis data as input layers, and output constitution analysis results after machine learning. The constitution analysis results also include comprehensive constitution analysis results. The result analysis module is configured to: analyze the results of the tongue coating analysis, the results of the complexion analysis, and the results of the comprehensive analysis; when the results of the comprehensive analysis are the same as the results of the tongue coating analysis, the results of the tongue coating analysis, the results of the complexion analysis, and the results of the complexion analysis, the results of the comprehensive analysis are taken as the results of the constitution identification; otherwise, the results of the tongue coating analysis, the results of the complexion analysis, and the results of the comprehensive analysis are taken as the results of the constitution identification. The result output module is configured to display the physical constitution identification results.

8. The system for identifying physical constitution based on big data according to claim 7, characterized in that, The data acquisition module is further configured to perform color mean-reduction and normalization processing on the tongue coating data and the complexion data.

9. The system for identifying physical constitution based on big data according to claim 7, characterized in that, The data analysis of the tongue coating analysis results, the facial complexion analysis results, and the comprehensive analysis results specifically includes: Feature descriptions are extracted from the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results, respectively. The obtained feature descriptions are parsed based on natural language understanding technology to obtain a dataset of feature descriptions for the tongue coating analysis results, the complexion analysis results, and the comprehensive analysis results. Calculate the correlation coefficient Bcw1 between the tongue coating analysis constitution result and the comprehensive analysis constitution result, the correlation coefficient Bcw2 between the complexion analysis constitution result and the comprehensive analysis constitution result, and calculate the correlation coefficient Bcw3 between the tongue coating analysis constitution result, the complexion analysis constitution result and the comprehensive analysis constitution result; When Bcw1+Bcw2≥Bcw3, the comprehensive analysis result of constitution is defined to be the same as the tongue coating analysis data and the tongue coating analysis result of constitution, as well as the complexion analysis data and the complexion analysis result of constitution; otherwise, the comprehensive analysis result of constitution is defined to be different from the tongue coating analysis data and the tongue coating analysis result of constitution, as well as the complexion analysis data and the complexion analysis result of constitution.

10. An electronic device, characterized in that, It includes at least one memory and at least one processor, the memory being communicatively connected to the processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements the method for identifying physical constitution based on big data as described in any one of claims 1-6.

Images