A dietary information recommendation system based on Youtan technology

Abstract

The present invention relates to the field of health technology, and in particular to a diet information recommendation system based on Youtan technology. The present invention includes a monitoring bracelet, a clustering module, a fitting module, and an analysis module. The monitoring bracelet is used to monitor inertial data. The clustering module is used to obtain various types of normal inertial data for a monitored subject. The fitting module can identify the action categories corresponding to various types of normal inertial data and identify abnormal inertial data, and establish an association between abnormal inertial data and corresponding action categories. The analysis module can receive the inertial data monitored by the monitoring bracelet in real time to identify whether abnormal inertial data exists, and adaptively select different identification methods to identify the current action category of the monitored subject based on the identification results. The present invention takes into account the specificity of the monitored subject's actions, adaptively selects an identification method to identify the current action category of the monitored subject, improves the accuracy and efficiency of action category identification, provides accurate data for diet information recommendation, and improves recommendation accuracy.

Description

Technical Field

[0001] The present invention relates to the field of health technology, and in particular to a dietary information recommendation system based on UCarbon technology. Background Art

[0002] With the development of science and technology, personalized diet recommendations have become an emerging research field. Combined with wearable devices, they can obtain and record users' daily exercise status, analyze energy consumption, provide diet information that is consistent with energy consumption, and provide users with personalized diet records and analysis, thereby improving people's quality of life. Related applications and technologies are valued by people.

[0003] Chinese patent publication number: CN107633875A, discloses an intelligent diet recommendation system, including a diet database establishment unit and a diet recommendation unit. The diet database establishment unit is used to dynamically calculate and obtain diet data that is consistent with the user's health based on the user's physical data, and establish a healthy diet database for the user; the diet recommendation unit is used to recommend diet data information suitable for the user's current health status based on the user's current physical data and the healthy diet database. At the same time, it also discloses an intelligent diet recommendation method that can dynamically analyze the acquired user health status data, thereby establishing a unique database for each user and updating it in real time.

[0004] However, the prior art still has the following problems:

[0005] In actual situations, some monitored subjects may have exclusive specific movements when performing different types of movements. Such movements have strong data representation. In the existing technology, when performing motion monitoring on the monitored subjects, the specificity of the movements of different monitored subjects is not taken into account, resulting in slow identification of the movement type of the monitored subjects and poor accuracy. Summary of the Invention

[0006] To this end, the present invention provides a dietary information recommendation system based on Youtan technology to solve the problem that when performing exercise monitoring on the monitored subject, the specificity of the actions of different monitored subjects is not taken into account, resulting in slow identification of the monitored subject's action type and poor accuracy.

[0007] To achieve the above objectives, the present invention provides a dietary information recommendation system based on UCarbon technology, which comprises:

[0008] A monitoring wristband comprising a ring body and an inertial monitoring unit configured on the ring body for monitoring inertial data;

[0009] A clustering module, connected to the monitoring bracelet, for obtaining the inertial data monitored by the monitoring bracelet, and clustering the inertial data based on the differences in the inertial data in different time domains to obtain various types of normal inertial data for the monitored subject;

[0010] a fitting module, connected to the clustering module, for comparing various types of normal inertia data with various types of sample inertia data in a sample database, identifying the action categories corresponding to the various types of normal inertia data, identifying abnormal inertia data based on the differences between the normal inertia data and the sample inertia data of the corresponding action categories, establishing an association between the abnormal inertia data and the corresponding action categories, and storing the association in an abnormal feature database for the monitored subject;

[0011] An analysis module, which is connected to the monitoring bracelet and the fitting module respectively, and includes a pre-identification unit and an analysis unit. The pre-identification unit is used to receive the inertial data monitored by the monitoring bracelet in real time to identify whether there is abnormal inertial data;

[0012] The analysis unit is responsive to the recognition result of the pre-recognition unit to identify the current action category of the monitored subject, including comparing the abnormal inertia data with the data in the abnormal feature database to identify the current action category of the monitored subject, or comparing the inertia data with various types of sample inertia data in the sample database to identify the current action category of the monitored subject;

[0013] The recommendation module is connected to the analysis module and is used to determine the energy consumption based on the duration of each type of action determined by the analysis module to recommend corresponding diet information.

[0014] Furthermore, the clustering module is used to cluster the inertial data based on the differences in the inertial data in different time domain segments, including:

[0015] Used to compare inertial data in different time domain segments and perform clustering based on the comparison results;

[0016] The degree of fit between the inertial data in different time domain segments of a single category must be greater than a predetermined degree of fit threshold.

[0017] Furthermore, the fitting module is used to identify the action categories corresponding to various types of normal inertial data, including:

[0018] To determine the mean value of the fitting between a single type of normal inertial data and various types of sample inertial data in the sample database;

[0019] It is used to sort the mean values ​​of the goodness of fit and obtain the inertia data of a single class of samples corresponding to the maximum mean value of the goodness of fit;

[0020] for determining the action type corresponding to the single type of sample inertia data as the action type corresponding to the single type of normal inertia data;

[0021] Among them, the corresponding relationship between various types of sample inertia data and action types is preset.

[0022] Furthermore, the fitting module is used to identify abnormal inertia data including:

[0023] It is used to divide the single-class normal inertial data in the time domain dimension to obtain sub-inertial data in different sub-time domain segments;

[0024] Comparing each sub-inertial data with the sample inertial data of the corresponding category in the sample database to calculate the degree of fit;

[0025] If the fitting degree corresponding to the sub-inertial data in any sub-time domain segment is less than a predetermined abnormal fitting degree threshold, the sub-inertial data is determined to be abnormal inertial data.

[0026] Furthermore, the fitting module is used to construct an association relationship between abnormal inertia data and corresponding action categories, including:

[0027] To determine whether the abnormal inertia data belongs to a single type of normal inertia data, and to determine the action type corresponding to the single type of normal inertia data;

[0028] Used to establish an association relationship between the abnormal inertia data and the action type.

[0029] Furthermore, the analysis module responds to the recognition result of the pre-recognition unit and includes:

[0030] If the identification result indicates that abnormal inertia data exists, the abnormal inertia data is compared with the data in the abnormal feature database to identify the current action category of the monitored subject;

[0031] If the identification result is that there is no abnormal inertia data, the inertia data is compared with the data in the sample database to identify the current action category of the monitored subject.

[0032] Furthermore, the analysis module is used to compare the abnormal inertia data with the data in the abnormal feature database to identify the current action category of the monitored subject, including:

[0033] Used to compare the abnormal inertia data with the abnormal inertia data of each sample in the abnormal feature database to determine the degree of fit;

[0034] To determine the sample variation inertia data corresponding to the maximum fitting degree;

[0035] Used to identify the action category associated with the sample abnormal inertia data as the current action category of the monitored subject.

[0036] Furthermore, the analysis module is used to compare the inertial data with various types of sample inertial data in the sample database to identify the current action category of the monitored subject, including:

[0037] Used to compare the inertia data with the inertia data of each sample in the sample database to determine the degree of fit;

[0038] To determine the sample inertia data corresponding to the maximum fit;

[0039] for identifying the action category associated with the sample inertial data as the current action category of the monitored subject;

[0040] The sample database pre-stores association relationships between a number of sample inertia data and action categories.

[0041] Furthermore, the recommendation module is pre-set with energy consumption per unit time for different action categories and dietary information corresponding to different energy consumption intervals.

[0042] Furthermore, it also includes a display unit, which is arranged on the monitoring bracelet to display the recommended corresponding dietary information.

[0043] Compared with the prior art, the present invention includes a monitoring bracelet, a clustering module, a fitting module, and an analysis module. The monitoring bracelet is used to monitor inertial data. The clustering module is used to obtain various types of normal inertial data for the monitored subject. The fitting module can identify the action categories corresponding to various types of normal inertial data, identify abnormal inertial data based on the difference between normal inertial data and sample inertial data of the corresponding action category, and establish an association between abnormal inertial data and corresponding action categories. The analysis module can receive the inertial data monitored by the monitoring bracelet in real time to identify whether there is abnormal inertial data, and adaptively select different identification methods to identify the current action category of the monitored subject based on the identification results. The present invention takes into account the specificity of the monitored subject's actions, adaptively selects an identification method to identify the current action category of the monitored subject, improves the accuracy and efficiency of action category identification, provides accurate data for dietary information recommendation, and improves recommendation accuracy.

[0044] In particular, in actual situations, the monitored subject's responses to different types of actions have differences in inertial data. For example, there will be certain differences in the inertial data corresponding to running and walking. Therefore, the present invention considers clustering the inertial data based on the differences in inertial data in different time domain segments, and clustering and dividing the monitored subject's actions over a period of time to obtain various types of normal inertial data for the monitored subject in daily behavior, providing a data basis for action analysis and dietary information recommendations, ensuring the accuracy of monitoring, and improving the pertinence of dietary information recommendations.

[0045] In particular, the present invention identifies abnormal inertia data and establishes an association between abnormal inertia data and corresponding action categories. In actual situations, abnormal inertia data may exist in various types of normal inertia data of the monitored subject. For example, due to habitual factors, the walking movements of some monitored subjects may be quite different from those of other monitored subjects or have special movements. Correspondingly, these differences will also be reflected in the inertia data and have strong data characterization. Based on this, the present invention considers identifying abnormal inertia data and establishing an association between abnormal inertia data and corresponding action categories. Identifying the abnormal inertia data of the monitored subject facilitates the subsequent rapid determination of the corresponding action category, improves the accuracy of the judgment of the monitored subject's behavior, improves the efficiency of action calculation, and improves the pertinence of dietary information recommendations.

[0046] In particular, the present invention determines whether there is abnormal inertia data to identify the current behavior of the monitored subject. In actual situations, if there is abnormal inertia data, it is only necessary to compare the abnormal inertia data. Comparing the abnormal inertia data with the data in the abnormal feature database reduces the number of comparisons in the system and the amount of data calculation. Due to the specificity of the abnormal inertia data, the data representation is strong. Under the premise of ensuring reliability, the action type of the monitored subject can be quickly and accurately determined. In this case, the energy consumption can be determined based on the duration of each type of action to recommend corresponding dietary information, thereby improving the accuracy and efficiency of dietary information recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a structural diagram of a dietary information recommendation system based on UCarbon technology according to an embodiment of the invention;

[0048] Figure 2 A logic block diagram of an embodiment of the present invention in response to a recognition result of a pre-recognition unit;

[0049] Figure 3 A logic block diagram for determining whether inertial data should be clustered according to an embodiment of the present invention;

[0050] Figure 4 This is a logic block diagram for determining whether sub-inertial data is abnormal inertial data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0052] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0053] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0054] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the term "connection" should be understood in a broad sense. For example, it can mean a fixed connection, a detachable connection, or an integral connection; it can mean a mechanical connection or an electrical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0055] See also Figures 1-4 As shown, Figure 1 This is a structural diagram of a dietary information recommendation system based on UCarbon technology according to an embodiment of the invention. Figure 2 This is a logic block diagram of an embodiment of the invention in response to the recognition result of the pre-recognition unit. Figure 3 This is a logic block diagram for determining whether inertial data should be clustered according to an embodiment of the present invention. Figure 4 This is a logic block diagram of determining whether sub-inertia data is abnormal inertia data according to an embodiment of the invention. A dietary information recommendation system based on UCarbon technology according to the present invention includes:

[0056] A monitoring wristband comprising a ring body and an inertial monitoring unit configured on the ring body for monitoring inertial data;

[0057] A clustering module, connected to the monitoring bracelet, for obtaining the inertial data monitored by the monitoring bracelet, and clustering the inertial data based on the differences in the inertial data in different time domains to obtain various types of normal inertial data for the monitored subject;

[0058] a fitting module, connected to the clustering module, for comparing various types of normal inertia data with various types of sample inertia data in a sample database, identifying the action categories corresponding to the various types of normal inertia data, identifying abnormal inertia data based on the differences between the normal inertia data and the sample inertia data of the corresponding action categories, establishing an association between the abnormal inertia data and the corresponding action categories, and storing the association in an abnormal feature database for the monitored subject;

[0059] An analysis module, which is connected to the monitoring bracelet and the fitting module respectively, and includes a pre-identification unit and an analysis unit. The pre-identification unit is used to receive the inertial data monitored by the monitoring bracelet in real time to identify whether there is abnormal inertial data;

[0060] The analysis unit is responsive to the recognition result of the pre-recognition unit to identify the current action category of the monitored subject, including comparing the abnormal inertia data with the data in the abnormal feature database to identify the current action category of the monitored subject, or comparing the inertia data with various types of sample inertia data in the sample database to identify the current action category of the monitored subject;

[0061] The recommendation module is connected to the analysis module and is used to determine the energy consumption based on the duration of each type of action determined by the analysis module to recommend corresponding diet information.

[0062] Specifically, there is no limitation on the specific structure of the inertial monitoring unit. For example, it can be an inertial sensor that only needs to be able to monitor inertial data. This is an existing technology and will not be described in detail.

[0063] Specifically, there is no limitation on the location of the inertial monitoring unit, which may be located inside the ring body or on the ring body and directly connected to the ring body, which will not be elaborated herein.

[0064] Specifically, inertial data includes acceleration data. In actual applications, when performing different types of actions, there will be differences in the acceleration data in the time domain dimension. Based on this, it can be used to identify the type of action.

[0065] Specifically, the clustering module is used to cluster the inertial data based on the differences in inertial data in different time domain segments, including:

[0066] Used to compare inertial data in different time domain segments and perform clustering based on the comparison results;

[0067] The degree of fit between the inertial data in different time domain segments of a single category must be greater than a predetermined degree of fit threshold.

[0068] It can be understood that the purpose of clustering is to distinguish the inertial data corresponding to different action types.

[0069] There is no limitation on the method for calculating the degree of fit between inertial data. For example, if the inertial data includes acceleration data, a time domain variation curve of acceleration in the time domain dimension can be constructed, and the degree of fit between the inertial data can be the degree of fit between the corresponding time domain variation curves.

[0070] There is no limitation on the method for determining the degree of fit between the time domain change curves. For example, the cosine similarity between two time domain curves may be calculated and the cosine similarity may be determined as the degree of fit between the time domain change curves.

[0071] Specifically, in actual situations, the monitored subject's responses to different types of actions have differences in inertial data. For example, there will be certain differences in the inertial data corresponding to running and walking. Therefore, the present invention considers clustering the inertial data based on the differences in inertial data in different time domain segments, and clustering and dividing the actions of the monitored subject over a period of time to obtain various types of normal inertial data for the monitored subject in daily behavior, providing a data basis for action analysis and dietary information recommendations, ensuring the accuracy of monitoring, and improving the pertinence of dietary information recommendations.

[0072] Specifically, the fitting module is used to identify the action categories corresponding to various types of normal inertial data, including:

[0073] To determine the mean value of the fitting between a single type of normal inertial data and various types of sample inertial data in the sample database;

[0074] It is used to sort the mean values ​​of the goodness of fit and obtain the inertia data of a single class of samples corresponding to the maximum mean value of the goodness of fit;

[0075] for determining the action type corresponding to the single type of sample inertia data as the action type corresponding to the single type of normal inertia data;

[0076] Among them, the corresponding relationship between various types of sample inertia data and action types is preset.

[0077] Specifically, the sample inertia data is collected in advance, wherein the inertia data of different monitoring subjects when performing different types of actions is obtained through big data, and the corresponding relationship needs to be synchronously constructed and stored in the sample database, and each type of sample inertia data corresponds one-to-one to the action type.

[0078] It is understandable that the acquired inertial data may be inertial data within a time domain segment. For ease of comparison, the normal inertial data is also inertial data within a time domain segment.

[0079] Specifically, the fitting module is used to identify abnormal inertial data including:

[0080] It is used to divide the single-class normal inertial data in the time domain dimension to obtain sub-inertial data in different sub-time domain segments;

[0081] Comparing each sub-inertial data with the sample inertial data of the corresponding category in the sample database to calculate the degree of fit. It is understandable that, to facilitate comparison, the sample inertial data can be divided in the time domain dimension to correspond to the sub-time domain segments;

[0082] If the fitting degree corresponding to the sub-inertial data in any sub-time domain segment is less than a predetermined abnormal fitting degree threshold, the sub-inertial data is determined to be abnormal inertial data.

[0083] Specifically, the predetermined anomaly fitting threshold is calculated in advance. Several inertial data of the same action type are obtained in advance as samples, and the mean fitting value between the inertial data is solved. In order to reflect the difference, the predetermined anomaly fitting threshold is set to between 0.3 and 0.6 times the mean fitting value between the inertial data.

[0084] It is understandable that when the monitored subject moves, there may be abnormal movements. For example, due to habitual factors, the arms may swing abnormally periodically while walking, but the movement at this moment is still walking. The inertial data corresponding to the abnormal arm swing is abnormal inertial data.

[0085] Specifically, the present invention identifies abnormal inertia data and establishes an association between abnormal inertia data and corresponding action categories. In actual situations, abnormal inertia data may exist in various types of normal inertia data of the monitored subject. For example, due to habitual factors, the walking movements of some monitored subjects may be quite different from those of other monitored subjects or have special movements. Correspondingly, these differences will also be reflected in the inertia data and have strong data characterization. Based on this, the present invention considers identifying abnormal inertia data and establishing an association between abnormal inertia data and corresponding action categories. Identifying the abnormal inertia data of the monitored subject facilitates the subsequent rapid determination of the corresponding action category, improves the accuracy of the judgment of the monitored subject's behavior, improves the efficiency of action calculation, and improves the pertinence of dietary information recommendations.

[0086] Specifically, the fitting module is used to construct the association between the abnormal inertia data and the corresponding action category, including:

[0087] To determine whether the abnormal inertia data belongs to a single type of normal inertia data, and to determine the action type corresponding to the single type of normal inertia data;

[0088] Used to establish an association relationship between the abnormal inertia data and the action type.

[0089] Specifically, the analysis module responds to the recognition result of the pre-recognition unit including:

[0090] If the identification result indicates that abnormal inertia data exists, the abnormal inertia data is compared with the data in the abnormal feature database to identify the current action category of the monitored subject;

[0091] If the identification result is that there is no abnormal inertia data, the inertia data is compared with the data in the sample database to identify the current action category of the monitored subject.

[0092] It is understandable that before the analysis module starts responding to the recognition result of the pre-recognition unit, the amount of data in the abnormal feature database should be sufficient. Preferably, the sample abnormal inertia data stored in the abnormal feature database is not less than the reference number, and the reference number needs to be greater than 100 when set.

[0093] Specifically, the present invention determines whether there is abnormal inertia data to identify the current behavior of the monitored subject. In actual situations, if there is abnormal inertia data, it is only necessary to compare the abnormal inertia data. Comparing the abnormal inertia data with the data in the abnormal feature database reduces the number of comparisons in the system and the amount of data calculation. Due to the specificity of the abnormal inertia data, the data representation is strong. Under the premise of ensuring reliability, the action type of the monitored subject can be quickly and accurately determined. In this case, the energy consumption can be determined based on the duration of each type of action to recommend corresponding dietary information, thereby improving the accuracy and efficiency of dietary information recommendations.

[0094] Specifically, the analysis module is used to compare the abnormal inertia data with the data in the abnormal feature database to identify the current action category of the monitored subject, including:

[0095] Used to compare the abnormal inertia data with the abnormal inertia data of each sample in the abnormal feature database to determine the degree of fit;

[0096] To determine the sample variation inertia data corresponding to the maximum fitting degree;

[0097] Used to identify the action category associated with the sample abnormal inertia data as the current action category of the monitored subject.

[0098] It is understandable that the sample abnormal inertia data is pre-stored by the fitting module, which will not be described in detail.

[0099] Specifically, the analysis module is used to compare the inertial data with various types of sample inertial data in the sample database to identify the current action category of the monitored subject, including:

[0100] Used to compare the inertia data with the inertia data of each sample in the sample database to determine the degree of fit;

[0101] To determine the sample inertia data corresponding to the maximum fit;

[0102] for identifying the action category associated with the sample inertial data as the current action category of the monitored subject;

[0103] The sample database pre-stores association relationships between a number of sample inertia data and action categories, that is, the sample inertia data is associated with the corresponding action type.

[0104] Specifically, the recommendation module is pre-set with the energy consumption per unit time of different action categories, as well as the dietary information corresponding to different energy consumption intervals.

[0105] It can be understood that after determining the duration of each type of action, the total energy consumption can be obtained based on the energy consumption per unit time;

[0106] It is understandable that by monitoring the energy consumption interval corresponding to the total energy consumption of the subject, the corresponding dietary information can be determined, and the dietary information includes the name and quantity of food that needs to be consumed.

[0107] Those skilled in the art can pre-set the dietary information corresponding to the energy consumption interval. Usually, it is set based on the corresponding relationship between energies. The energy supplemented by the food corresponding to the dietary information is within the corresponding energy consumption interval. This will not be repeated here.

[0108] Specifically, it also includes a display unit, which is arranged on the monitoring bracelet to display the recommended corresponding dietary information.

[0109] Specifically, there is no limitation on the specific structure of the display unit. For example, it can be an LCD screen or a touch screen. It only needs to be able to display the recommended corresponding dietary information, which will not be elaborated here.

[0110] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A dietary information recommendation system based on UCarbon technology, characterized in that: include: A monitoring wristband comprising a ring body and an inertial monitoring unit configured on the ring body for monitoring inertial data; A clustering module, connected to the monitoring bracelet, for obtaining the inertial data monitored by the monitoring bracelet, and clustering the inertial data based on the differences in the inertial data in different time domains to obtain various types of normal inertial data for the monitored subject; a fitting module, connected to the clustering module, for comparing various types of normal inertia data with various types of sample inertia data in a sample database, identifying the action categories corresponding to the various types of normal inertia data, identifying abnormal inertia data based on the differences between the normal inertia data and the sample inertia data of the corresponding action categories, establishing an association between the abnormal inertia data and the corresponding action categories, and storing the association in an abnormal feature database for the monitored subject; An analysis module, which is connected to the monitoring bracelet and the fitting module respectively, and includes a pre-identification unit and an analysis unit. The pre-identification unit is used to receive the inertial data monitored by the monitoring bracelet in real time to identify whether there is abnormal inertial data; The analysis unit is responsive to the recognition result of the pre-recognition unit to identify the current action category of the monitored subject, including comparing the abnormal inertia data with the data in the abnormal feature database to identify the current action category of the monitored subject, or comparing the inertia data with various types of sample inertia data in the sample database to identify the current action category of the monitored subject; a recommendation module, connected to the analysis module, for determining energy consumption based on the duration of each type of action determined by the analysis module, so as to recommend corresponding dietary information; The fitting module is used to identify the action categories corresponding to various types of normal inertial data, including: To determine the mean value of the fitting between a single type of normal inertial data and various types of sample inertial data in the sample database; It is used to sort the mean values ​​of the goodness of fit and obtain the inertia data of a single class of samples corresponding to the maximum mean value of the goodness of fit; for determining the action type corresponding to the single type of sample inertia data as the action type corresponding to the single type of normal inertia data; Among them, the corresponding relationship between various types of sample inertia data and action types is preset.

2. The dietary information recommendation system based on UCarbon technology according to claim 1, characterized in that: The clustering module is used to cluster the inertial data based on the differences in the inertial data in different time domain segments, including: Used to compare inertial data in different time domain segments and perform clustering based on the comparison results; The degree of fit between the inertial data in different time domain segments of a single category must be greater than a predetermined degree of fit threshold.

3. The dietary information recommendation system based on UCarbon technology according to claim 1, characterized in that: The fitting module is used to identify abnormal inertia data, including: It is used to divide the single-class normal inertial data in the time domain dimension to obtain sub-inertial data in different sub-time domain segments; Comparing each sub-inertial data with the sample inertial data of the corresponding category in the sample database to calculate the degree of fit; If the fitting degree corresponding to the sub-inertial data in any sub-time domain segment is less than a predetermined abnormal fitting degree threshold, the sub-inertial data is determined to be abnormal inertial data.

4. The dietary information recommendation system based on UCarbon technology according to claim 3 is characterized in that: The fitting module is used to construct the association relationship between the abnormal inertia data and the corresponding action category, including: To determine whether the abnormal inertia data belongs to a single type of normal inertia data, and to determine the action type corresponding to the single type of normal inertia data; Used to establish an association relationship between the abnormal inertia data and the action type.

5. The dietary information recommendation system based on UCarbon technology according to claim 1, characterized in that: The analysis module responds to the recognition result of the pre-recognition unit by: If the identification result indicates that abnormal inertia data exists, the abnormal inertia data is compared with the data in the abnormal feature database to identify the current action category of the monitored subject; If the identification result is that there is no abnormal inertia data, the inertia data is compared with the data in the sample database to identify the current action category of the monitored subject.

6. The dietary information recommendation system based on UCarbon technology according to claim 5, characterized in that: The analysis module is used to compare the abnormal inertia data with the data in the abnormal feature database to identify the current action category of the monitored subject, including: Used to compare the abnormal inertia data with the abnormal inertia data of each sample in the abnormal feature database to determine the degree of fit; To determine the sample variation inertia data corresponding to the maximum fitting degree; Used to identify the action category associated with the sample abnormal inertia data as the current action category of the monitored subject.

7. The dietary information recommendation system based on UCarbon technology according to claim 1, characterized in that: The analysis module is used to compare the inertial data with various types of sample inertial data in the sample database to identify the current action category of the monitored subject, including: Used to compare the inertia data with the inertia data of each sample in the sample database to determine the degree of fit; To determine the sample inertia data corresponding to the maximum fit; for identifying the action category associated with the sample inertial data as the current action category of the monitored subject; The sample database pre-stores association relationships between a number of sample inertia data and action categories.

8. The dietary information recommendation system based on UCarbon technology according to claim 1, characterized in that: The recommendation module is pre-set with the energy consumption of different action categories per unit time and the dietary information corresponding to different energy consumption intervals.

9. The dietary information recommendation system based on UCarbon technology according to claim 1, characterized in that: It also includes a display unit, which is arranged on the monitoring bracelet and is used to display the recommended corresponding dietary information.

Images