Diet information recommendation system based on optimal carbon technology

Abstract

The invention relates to the technical field of health, in particular to a diet information recommendation system based on an optimal carbon technology, which comprises a monitoring bracelet, a clustering module, a fitting module and an analysis module, and is characterized in that the monitoring bracelet is used for monitoring inertial data, and the clustering module is used for obtaining various normal inertial data aiming at a monitored main body; the fitting module can identify action categories corresponding to various normal inertial data and abnormal inertial data and construct an association relationship between the abnormal inertial data and the corresponding action categories, and the analysis module can receive the inertial data monitored by the monitoring bracelet in real time to identify whether the abnormal inertial data exists or not; according to the method, the current action type of the monitoring subject is identified by considering the specificity of the action of the monitoring subject and the adaptive selection identification mode, the action type identification accuracy and efficiency are improved, accurate data are provided for diet information recommendation, and the accuracy and the efficiency of diet information recommendation are improved. And recommendation accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of health technologies, and particularly to a diet information recommendation system based on You-carbon technology. Background Art

[0002] With the development of science and technology, personalized diet recommendation has become an emerging research field. It combines wearable devices to obtain and record users' daily exercise conditions, analyze energy consumption, provide diet information that matches the energy consumption, and provide personalized diet records and analyses for users, improving people's quality of life. Related applications and technologies have been taken seriously by people.

[0003] Chinese Patent Publication No.: 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 diet data that conforms to the user's physical health according to the user's body data and establish a healthy diet database for the user; the diet recommendation unit is used to recommend diet data information suitable for the current physical health status of the user according to the user's current body data and the healthy diet database. At the same time, an intelligent diet recommendation method is also disclosed, which can dynamically analyze the obtained user's physical health status data, thereby establishing a unique database for each user and updating it in real time.

[0004] However, the following problems still exist in the prior art.

[0005] In actual situations, some monitoring subjects may have exclusive specific actions when performing different types of actions. Such actions have strong data representativeness. In the prior art, when monitoring the movements of the monitoring subjects, the specificities of the actions of different monitoring subjects are not considered, resulting in a slow speed and poor accuracy in identifying the types of actions of the monitoring subjects. Summary of the Invention

[0006] For this reason, the present invention provides a diet information recommendation system based on You-carbon technology to solve the problems that when monitoring the movements of the monitoring subjects, the specificities of the actions of different monitoring subjects are not considered, resulting in a slow speed and poor accuracy in identifying the types of actions of the monitoring subjects.

[0007] To achieve the above object, the present invention provides a diet information recommendation system based on You-carbon technology, which includes:

[0008] A monitoring bracelet, which includes a bracelet body and an inertial monitoring unit configured on the bracelet body for monitoring inertial data;

[0009] A clustering module, which is connected to the monitoring bracelet, is used to obtain the inertial data monitored by the monitoring bracelet, cluster the inertial data based on the differences in inertial data within different time domain segments, so as to obtain various types of normal inertial data for the monitored subject;

[0010] A fitting module, which is connected to the clustering module, is used to compare various types of normal inertial data with various types of sample inertial data in the sample database, identify the action categories corresponding to various types of normal inertial data, identify abnormal inertial data based on the differences between the normal inertial data and the sample inertial data corresponding to the action categories, construct the association relationship between the abnormal inertial data and the corresponding action categories, and store it in the abnormal feature database for the monitored subject;

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

[0012] The analysis unit responds to the identification result of the pre-identification unit and is used to identify the current action category of the monitored subject, including comparing the abnormal inertial data with the data in the abnormal inertial database to identify the current action category of the monitored subject, or comparing the inertial data with various types of sample inertial data in the sample database to identify the current action category of the monitored subject;

[0013] A recommendation module, which is connected to the analysis module, is used to determine the energy consumption based on the duration of various actions determined by the analysis module, so as to recommend corresponding diet information.

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

[0015] Used to compare the inertial data within different time domain segments and cluster based on the comparison results;

[0016] Among them, the fitting degree between the inertial data within different time domain segments of a single category needs to be greater than a predetermined fitting degree threshold.

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

[0018] Used to determine the average fitting degree between a single type of normal inertial data and various types of sample inertial data in the sample database;

[0019] Used to sort the average fitting degrees and obtain the single type of sample inertial data corresponding to the maximum average fitting degree;

[0020] To determine the action type corresponding to the single-class sample inertial data as the action type corresponding to the single-class normal inertial data;

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

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

[0023] 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] To compare each sub-inertial data with the sample inertial data of the corresponding category in the sample database and solve the fitting degree;

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

[0026] Furthermore, the fitting module is used to construct the association relationship between abnormal inertial data and the corresponding action category, including

[0027] To determine the single-class normal inertial data to which the abnormal inertial data belongs and determine the action type corresponding to the single-class normal inertial data;

[0028] To establish the association relationship between the abnormal inertial data and the action type.

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

[0030] If the recognition result is that there is abnormal inertial data, compare the abnormal inertial data with the data in the abnormal feature database to identify the current action category of the monitoring subject;

[0031] If the recognition result is that there is no abnormal inertial data, compare the inertial data with the data in the sample database to identify the current action category of the monitoring subject.

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

[0033] To compare the abnormal inertial data with each sample abnormal inertial data in the abnormal feature database to determine the fitting degree;

[0034] To determine the sample abnormal inertial data corresponding to the maximum fitting degree;

[0035] To identify the action category associated with the sample abnormal inertial data as the current action category of the monitoring subject.

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

[0037] comparing the inertial data with each sample inertial data in the sample database to determine the fitting degree;

[0038] determining the sample inertial data corresponding to the maximum fitting degree;

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

[0040] wherein, the association relationship between a plurality of sample inertial data and action categories is pre-stored in the sample database.

[0041] Further, the recommended energy consumption per unit time for different action categories and the diet information corresponding to different energy consumption intervals are preset in the recommendation module.

[0042] Further, a display unit is further included, which is arranged on the monitoring bracelet and is used to display the recommended diet 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 normal inertial data for the monitored subject. The fitting module can identify the action categories corresponding to various normal inertial data, identify abnormal inertial data based on the differences between the normal inertial data and the sample inertial data corresponding to the action categories, construct the association relationship between the abnormal inertial data and the 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 according to the identification results to identify the current action category of the monitored subject. The present invention considers the specificity of the actions of the monitored subject, adaptively selects the 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 the recommendation accuracy.

[0044] In particular, in actual situations, the monitored subject has differences in inertial data for different types of actions. 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 within different time domains, clustering and dividing the actions of the monitored subject within a period of time to obtain various normal inertial data of the monitored subject in daily behaviors, providing a data basis for action analysis and diet information recommendation, ensuring the accuracy of monitoring, and improving the pertinence of diet information recommendation.

[0045] In particular, the present invention identifies abnormal inertial data and constructs the correlation between abnormal inertial data and corresponding action categories. In actual situations, there may be abnormal inertial data among various normal inertial data of the monitored subject. For example, when some monitored subjects make walking actions, due to habitual factors, their walking actions may be quite different from those of other monitored subjects or there may be special actions. Correspondingly, this part of the difference will also be reflected in the inertial data and has strong data representativeness. Based on this, the present invention considers identifying abnormal inertial data and constructing the correlation between abnormal inertial data and corresponding action categories. Identifying the abnormal inertial 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, and improves the action calculation efficiency and the pertinence of diet information recommendation.

[0046] In particular, the present invention determines whether there is abnormal inertial data to identify the current behavior of the monitored subject. In actual situations, for the existence of abnormal inertial data, only the abnormal inertial data needs to be compared. The abnormal inertial data is compared with the data in the abnormal feature database, reducing the number of comparisons in the system and lowering the data operation volume. Due to the specificity of the abnormal inertial data and its strong data representativeness, the action type of the monitored subject can be quickly and accurately judged under the premise of ensuring reliability. In this case, based on the duration of various actions, the energy consumption can be determined to recommend corresponding diet information, improving the accuracy and efficiency of diet information recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic structural diagram of a diet information recommendation system based on the Youtan technology according to an embodiment of the invention;

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

[0049] Figure 3 It is a logic block diagram for determining whether inertial data is clustered according to an embodiment of the invention;

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

[0051] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

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

[0053] It should be noted that in the description of the present invention, the terms indicating the direction or positional relationship such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the direction or positional relationship shown in the 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 should not be construed as a limitation to the present invention.

[0054] In addition, it should also be noted that in the description of the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present invention can be understood according to specific situations.

[0055] Please refer to Figures 1-4 as shown Figure 1 a schematic structural diagram of a diet information recommendation system based on the Youtan technology according to an embodiment of the invention, Figure 2 a logic block diagram in response to the recognition result of the pre-recognition unit according to an embodiment of the invention, Figure 3 a logic block diagram for determining whether to cluster inertial data according to an embodiment of the invention, Figure 4 a logic block diagram for determining whether sub-inertial data is abnormal inertial data according to an embodiment of the invention. A diet information recommendation system based on the Youtan technology of the present invention includes:

[0056] a monitoring bracelet, which includes a bracelet body and an inertial monitoring unit configured on the bracelet body for monitoring inertial data;

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

[0058] a fitting module, which is connected to the clustering module, used to compare various types of normal inertial data with various types of sample inertial data in the sample database, identify the action categories corresponding to various types of normal inertial data, identify abnormal inertial data based on the differences between the normal inertial data and the sample inertial data corresponding to the action categories, construct the association relationship between the abnormal inertial data and the corresponding action categories, and store it in the abnormal feature database for the monitored subject;

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

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

[0061] A recommendation module, connected to the analysis module, is used to determine the energy consumption based on the duration of various actions determined by the analysis module and recommend corresponding diet information.

[0062] Specifically, the specific structure of the inertial monitoring unit is not limited. For example, it can be an inertial sensor, as long as it can monitor inertial data. This is prior art and will not be elaborated further.

[0063] Specifically, the installation position of the inertial monitoring unit is not limited. It can be installed inside the bracelet body or directly connected to the bracelet body on the bracelet body. This will not be elaborated further.

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

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

[0066] comparing the inertial data in different time domain segments and clustering based on the comparison results;

[0067] Among them, the fitting degree between the inertial data in different time domain segments of a single category needs to be greater than a predetermined fitting degree threshold.

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

[0069] The method for solving the fitting degree between inertial data is not limited. For example, if the inertial data includes acceleration data, a time domain change curve of the acceleration in the time domain dimension can be constructed, and the fitting degree between inertial data can be the fitting degree between the corresponding time domain change curves;

[0070] The method for determining the fitting degree between time-domain change curves is not limited. For example, the cosine similarity between two time-domain curves can be calculated, and the cosine similarity is determined as the fitting degree between the time-domain change curves.

[0071] Specifically, in actual situations, the monitoring subject has differences in inertial data for different types of actions. For example, there are certain differences in the inertial data corresponding to running and walking. Therefore, the present invention considers clustering inertial data based on the differences in inertial data within different time-domain segments, clustering and dividing the actions of the monitoring subject within a period of time to obtain various normal inertial data of the monitoring subject in daily behaviors, providing a data basis for action analysis and diet information recommendation, ensuring the accuracy of monitoring, and improving the pertinence of diet information recommendation.

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

[0073] used to determine the average fitting degree between a single type of normal inertial data and various sample inertial data in the sample database;

[0074] used to sort the average fitting degrees to obtain the single type of sample inertial data corresponding to the maximum average fitting degree;

[0075] used to determine the action type corresponding to the single type of sample inertial data as the action type corresponding to the single type of normal inertial data;

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

[0077] Specifically, the sample inertial data is pre-collected. Among them, the inertial data of different monitoring subjects performing different types of actions is obtained through big data, and the corresponding relationship is synchronously constructed and stored in the sample database. Each type of sample inertial data and action type are in one-to-one correspondence.

[0078] It can be understood that the obtained inertial data can be inertial data within a time-domain segment. For the convenience 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] used to divide a single type of normal inertial data in the time-domain dimension to obtain sub-inertial data within different sub-time-domain segments;

[0081] used to compare each sub-inertial data with the sample inertial data of the corresponding category in the sample database to solve the fitting degree. It can be understood that for the convenience of comparison, the sample inertial data can be segmented in the time-domain dimension to correspond to the sub-time-domain segments;

[0082] If the fitting degree corresponding to the sub-inertial data within any sub-time domain segment is less than the predetermined abnormal change fitting degree threshold, it is determined that the sub-inertial data is abnormal change inertial data.

[0083] Specifically, the predetermined abnormal change fitting degree threshold is calculated in advance. A number of inertial data of the same action type are obtained in advance as samples, and the average value of the fitting degree between the inertial data is solved. To reflect the difference, the predetermined abnormal change fitting degree threshold is set between 0.3 times and 0.6 times the average value of the fitting degree between the inertial data.

[0084] It can be understood that when the monitored subject makes an action, there may be an abnormal change action. For example, due to habitual factors, there is a periodic abnormal arm swing when walking, but the current action is still walking. The inertial data corresponding to the abnormal arm swing is abnormal change inertial data.

[0085] Specifically, the present invention identifies abnormal change inertial data and constructs an association relationship between the abnormal change inertial data and the corresponding action category. In actual situations, there may be abnormal change inertial data among various normal state inertial data of the monitored subject. For example, when some monitored subjects make a walking action, due to habitual factors, their walking actions may be quite different from those of other monitored subjects or there may be special actions. Correspondingly, this part of the difference will also be reflected in the inertial data and has strong data representativeness. Based on this, the present invention considers identifying abnormal change inertial data and constructing an association relationship between the abnormal change inertial data and the corresponding action category. Identifying the abnormal change inertial data of the monitored subject facilitates quickly determining the corresponding action category subsequently, improving the accuracy of the judgment of the behavior of the monitored subject, improving the action calculation efficiency, and the pertinence of the diet information recommendation.

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

[0087] To determine the single-category normal state inertial data to which the abnormal change inertial data belongs and determine the action type corresponding to the single-category normal state inertial data;

[0088] To establish the association relationship between the abnormal change inertial data and the action type.

[0089] Specifically, the analysis module's response to the recognition result of the pre-recognition unit includes

[0090] If the recognition result is that there is abnormal change inertial data, the abnormal change inertial data is compared with the data in the abnormal change feature database to identify the current action category of the monitored subject;

[0091] If the recognition result is that there is no abnormal change inertial data, the inertial 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 to respond to the recognition result of the pre-recognition unit, the amount of data in the mutation feature database should be sufficient. Preferably, the sample mutation inertia data stored in the mutation feature database is not less than the reference quantity, and the reference quantity should be set to be greater than 100 when it is set.

[0093] Specifically, the present invention determines whether there is mutation inertia data to identify the current behavior of the monitored subject. In actual situations, for the existence of mutation inertia data, it is only necessary to compare the mutation inertia data. By comparing the mutation inertia data with the data in the mutation feature database, the comparison times of the system are reduced, and the data operation amount is decreased. Due to the specificity of the mutation inertia data and its strong data representativeness, the action type of the monitored subject can be quickly and accurately determined on the premise of ensuring reliability. In this case, based on the duration of various actions, the energy consumption can be determined to recommend corresponding diet information, improving the accuracy and efficiency of diet information recommendation.

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

[0095] comparing the mutation inertia data with each sample mutation inertia data in the mutation feature database to determine the fitting degree;

[0096] determining the sample mutation inertia data corresponding to the maximum fitting degree;

[0097] identifying the action category associated with the sample mutation inertia data as the current action category of the monitored subject.

[0098] It is understandable that the sample mutation inertia data is pre-stored by the fitting module and will not be elaborated here.

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

[0100] comparing the inertia data with each sample inertia data in the sample database to determine the fitting degree;

[0101] determining the sample inertia data corresponding to the maximum fitting degree;

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

[0103] Among them, the sample database pre-stores the association relationships between several sample inertia data and action categories, that is, there is an association between the sample inertia data and the corresponding action types.

[0104] Specifically, different energy consumptions of different action categories per unit time and the corresponding diet information for different energy consumption ranges are preset in the recommendation module.

[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 can be understood that by monitoring the energy consumption range in which the total energy consumption of the subject is located, the corresponding diet information can be determined, and the diet information includes the names and quantities of the foods to be consumed.

[0107] Those skilled in the art can preset the diet information corresponding to the energy consumption range. Generally, it is set according to the corresponding relationship between energies. The energy supplemented by the foods corresponding to the diet information is within the corresponding energy consumption range, which will not be elaborated here.

[0108] Specifically, it further includes a display unit, which is arranged on the monitoring bracelet and used to display the recommended corresponding diet information.

[0109] Specifically, no limitation is imposed on the specific structure of the display unit. For example, it can be a liquid crystal screen or a touch screen, as long as it can display the recommended corresponding diet information, which will not be elaborated here.

[0110] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A dietary information recommendation system based on UCarbon technology, characterized in that: include: A monitoring bracelet, comprising a ring body and an inertial monitoring unit configured on the ring body for monitoring inertial data; A clustering module, which is connected to the monitoring bracelet and is used to obtain the inertial data monitored by the monitoring bracelet, and cluster the inertial data based on the difference of the inertial data in different time domains to obtain various types of normal inertial data for the monitored subject; A fitting module, which is connected to the clustering module, is used to compare various types of normal inertia data with various types of sample inertia data in the sample database, identify the action categories corresponding to various types of normal inertia data, identify abnormal inertia data based on the difference between the normal inertia data and the sample inertia data of the corresponding action category, build an association relationship between the abnormal inertia data and the corresponding action category, and store it in the 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-recognition unit and an analysis unit, wherein the pre-recognition 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 inertia 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; 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 dietary information.

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 difference of inertial data in different time domain segments, including: It is used to compare the inertial data in different time domains 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 is characterized in that: 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 fitting degree and obtain the single-class sample inertia data corresponding to the maximum mean value of the fitting degree; Determining the action type corresponding to the single type of sample inertial data as the action type corresponding to the single type of normal inertial data; Among them, the corresponding relationship between various types of sample inertia data and action types is preset.

4. The dietary information recommendation system based on UCarbon technology according to claim 3 is characterized in that: The fitting module is used to identify abnormal inertial data, including: It is used to divide a single type of normal inertial data in the time domain dimension to obtain sub-inertial data in different sub-time domain segments; for comparing each sub-inertia data with the sample inertia 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.

5. The dietary information recommendation system based on UCarbon technology according to claim 4 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 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.

6. 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 including: If the identification result is 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 inertial data, the inertial data is compared with the data in the sample database to identify the current action category of the monitored subject.

7. The dietary information recommendation system based on UCarbon technology according to claim 6 is 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: 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 fit; Used to identify the action category associated with the sample abnormal inertial data as the current action category of the monitored subject.

8. The dietary information recommendation system based on UCarbon technology according to claim 1 is characterized in that: The analysis module is used to compare the inertial data with the data in the sample database to identify the current action category of the monitored subject, including: 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 monitoring subject; The sample database pre-stores associations between a number of sample inertia data and action categories.

9. The dietary information recommendation system based on UCarbon technology according to claim 1, characterized in that: 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.

10. 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