Parameter determination method, device and system, computer equipment and storage medium

Abstract

The invention relates to a parameter determination method, device and system, computer equipment and a storage medium. The method comprises the following steps: acquiring a feeding detection result of a target object in a first time period, determining a target time period from the first time period according to the feeding detection result, and determining a current insulin sensitivity coefficient according to a previous insulin sensitivity coefficient and a blood glucose value and insulin information of the target object in the target time period. By adopting the method, the insulin sensitivity coefficient can be accurately determined.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a parameter determination method, apparatus, system, computer equipment and storage medium. Background Art

[0002] Insulin Sensitivity Factor (ISF) is used to indicate the amount by which 1 unit of insulin can lower blood sugar and is an important parameter in the field of diabetes.

[0003] The insulin sensitivity coefficient is easily affected by many factors. Different target subjects have different insulin sensitivity coefficients at different time points in a day. For example, for the same target subject, the insulin sensitivity coefficient in the early morning will be greater than that in the daytime. Therefore, how to accurately determine the insulin sensitivity coefficient is the focus of research for those in this field. Summary of the invention

[0004] Based on this, it is necessary to provide a parameter determination method, device, system, computer equipment and storage medium that can accurately determine the insulin sensitivity coefficient in response to the above technical problems.

[0005] In a first aspect, the present application provides a parameter determination method, the method comprising:

[0006] Obtaining the target object's eating detection result in a first time period; the first time period includes a current time point and a historical time period before the current time point;

[0007] Determine a target time period from the first time period according to the eating detection result;

[0008] The current insulin sensitivity coefficient is determined based on the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

[0009] In one embodiment, determining the target time period from the first time period according to the eating detection result includes:

[0010] If the eating detection result includes that the target subject has an eating behavior within the first time period, the time period in the first time period except the second time period is used as the target time period; the second time period includes a time period of a preset length after the eating time point corresponding to the eating behavior;

[0011] If the eating detection result includes that the target object has no eating behavior within the first time period, the first time period is used as the target time period.

[0012] In one embodiment, the eating detection result further includes food type and / or food amount; the method further includes:

[0013] Determine the preset time duration based on the type of food and / or amount of food.

[0014] In one embodiment, obtaining the target object's eating detection result in the first time period includes:

[0015] Obtain facial vibration detection results corresponding to each time point of the target object in the first time period;

[0016] Determine a vibration matching result according to the facial vibration detection result and the preset vibration result;

[0017] According to the vibration matching result, an eating detection result of the target object in the first time period is obtained.

[0018] In one embodiment, obtaining the target object's eating detection result in the first time period according to the vibration matching result includes:

[0019] When the vibration matching result is a match, a plurality of facial image frames corresponding to the target object at each time point are obtained;

[0020] According to the plurality of facial image frames, an eating detection result of the target object in a first time period is obtained.

[0021] In one embodiment, obtaining a detection result of eating of a target object in a first time period according to a plurality of facial image frames includes:

[0022] determining a facial action detection result based on the plurality of facial image frames;

[0023] In a case where the facial action detection result includes a preset action, determining a food recognition result based on at least one frame of the plurality of facial image frames and a food classification model;

[0024] The target object's eating detection result in the first time period is obtained according to the food recognition result.

[0025] In one embodiment, obtaining the target object's eating detection result in the first time period according to the food recognition result includes:

[0026] When the food recognition result indicates that food is present, the eating detection result is determined to include the target object's eating behavior at a corresponding time point and the eating time point at which the eating behavior occurs.

[0027] In one embodiment, the current insulin sensitivity coefficient is determined based on the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period, including:

[0028] Determine adjustment parameters based on the last insulin sensitivity coefficient and the target subject's blood sugar level and insulin information during the target time period;

[0029] The previous insulin sensitivity coefficient is updated according to the adjustment parameters to obtain the current insulin sensitivity coefficient.

[0030] In one embodiment, the last insulin sensitivity coefficient is updated according to the adjustment parameter to obtain the current insulin sensitivity coefficient and determine the adjustment parameter, including:

[0031] Determine a blood glucose correction value according to the physiological model and the blood glucose value and insulin information of the target subject in the target time period; the blood glucose correction value is used to indicate the difference between the current blood glucose value at the current time point and the theoretical blood glucose value at the current time point;

[0032] The adjustment parameters are determined based on the blood sugar correction value, the last insulin sensitivity coefficient and the preset parameters; the preset parameters include the frequency of obtaining the blood sugar value and the standard basal rate of the target object.

[0033] In a second aspect, the present application further provides a parameter determination device, the device comprising:

[0034] An acquisition module, used to acquire the target object's eating detection result in a first time period; the first time period includes a current time point and a historical time period before the current time point;

[0035] A first determination module, used to determine a target time period from a first time period according to an eating detection result;

[0036] The second determination module is used to determine the current insulin sensitivity coefficient according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

[0037] In a third aspect, the present application also proposes a parameter determination system. The system includes a head-mounted device, a blood glucose sensor, an insulin pump, and a processor;

[0038] A head-mounted device, used to obtain a target object's eating detection result in a first time period; the first time period includes a current time point and a historical time period before the current time point;

[0039] A processor, configured to determine a target time period from the first time period according to the eating detection result;

[0040] A blood glucose sensor, used to obtain the blood glucose value of a target subject during a target time period;

[0041] Insulin pump, used to obtain insulin information of the target subject during the target time period;

[0042] The processor is further used to determine the current insulin sensitivity coefficient according to the previous insulin sensitivity coefficient and the blood glucose value and insulin information of the target subject in the target time period.

[0043] In a fourth aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0044] In a fifth aspect, the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0045] In a sixth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0046] The above parameter determination method, device, system, computer equipment and storage medium obtain the target object's eating detection result in the first time period, and determine the target time period from the first time period according to the eating detection result, and then determine the current insulin sensitivity coefficient according to the last insulin sensitivity coefficient and the target object's blood sugar level and insulin information in the target time period. At present, when determining the insulin sensitivity coefficient, the target object's eating situation is usually ignored, resulting in inaccurate insulin sensitivity coefficient. In this embodiment, since the first time period includes the current time point and the historical time period before the current time point, the eating detection result can reflect the target object's eating situation at the previous time point and the historical time period. Furthermore, since the target time period is determined from the first time period according to the eating detection result, the target time period takes into account the target object's eating situation at the previous time point and the historical time period. In this way, based on the last insulin sensitivity coefficient and the target object's blood sugar level and insulin information in the target time period, a more accurate insulin sensitivity coefficient can be determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is an application environment diagram of the parameter determination method in the embodiment of the present application;

[0048] Figure 2 Schematic diagram of the process of determining parameters in the embodiment of the present application;

[0049] Figure 3 This is a schematic diagram of a process for determining a target time period in an embodiment of the present application;

[0050] Figure 4This is a schematic diagram of a process for obtaining an eating detection result in an embodiment of the present application;

[0051] Figure 5 This is another flow chart of obtaining eating detection results in an embodiment of the present application;

[0052] Figure 6 A schematic diagram of a process of obtaining an eating detection result in one embodiment of the present application;

[0053] Figure 7 This is a schematic diagram of a process for determining an insulin sensitivity coefficient in an embodiment of the present application;

[0054] Figure 8 A schematic diagram of a process for determining adjustment parameters in an embodiment of the present application;

[0055] Fig. 9 A process diagram of a parameter determination method in an embodiment of the present application;

[0056] Fig.10 This is a schematic diagram of the structure of a parameter determination system in an embodiment of the present application;

[0057] Fig.11 It is a structural block diagram of a parameter determination device in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] Figure 1 FIG. 1 is an application environment diagram of the parameter determination method in the embodiment of the present application. In the embodiment of the present application, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 1 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store relevant data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a parameter determination method is implemented.

[0060] Those skilled in the art will understand that Figure 1The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0061] This embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers. The server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0062] Figure 2 This is a flow chart of a parameter determination method in an embodiment of the present application. This method can be applied to Figure 1 In the computer device shown, in one embodiment, as Figure 2 As shown, the following steps are included:

[0063] S201, obtaining the target object's eating detection result in a first time period; the first time period includes a current time point and a historical time period before the current time point.

[0064] In this embodiment, the length of the historical time period may be a preset value, which is a number greater than 0, and the unit may be seconds, minutes, or hours. That is, the length of the first time period may be set as required, for example, assuming that the current time is 11 o'clock, the first time period may include the time period corresponding to 8 o'clock to 11 o'clock, or the time period corresponding to 6 o'clock to 11 o'clock.

[0065] Furthermore, the computer device can obtain the target object's eating detection result in the first time period. For example, taking the first time period as 8:00 to 11:00 as an example, the computer device can obtain the target object's eating detection result in the first time period as 8:00 to 11:00.

[0066] The eating detection result is used to indicate the eating situation of the target object in the first time period. The eating detection result may include whether the target object has eating behavior in the first time period, and the eating time point when eating occurs.

[0067] Optionally, the computer device may receive the target object's eating detection result in the first time period sent by other electronic devices, or may determine the target object's eating detection result in the first time period in response to the target object's input operation. In some embodiments, the computer device may also simulate the target object's eating detection result in the first time period based on the target object's historical eating situation.

[0068] S202: Determine a target time period from the first time period according to the eating detection result.

[0069] In this embodiment, since the eating condition will affect the accuracy of determining the insulin sensitivity coefficient, the computer device will determine the target time period from the first time period according to the eating detection result. That is, the target time period is used to indicate the time period of blood sugar value and insulin information required when determining the current insulin sensitivity coefficient.

[0070] Optionally, the computer device may use the time period before the earliest eating time point in the first time period as the target time period according to the eating detection result. For example, assuming that the first time period is 8:00 to 11:00, and the eating detection result indicates that the target object has eating behavior at the earliest at 9:00, the computer device may use 8:00 to 8:59 as the target time period.

[0071] S203, determining the current insulin sensitivity coefficient according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

[0072] In this embodiment, after the computer device determines the target time period from the first time period, it can determine the blood glucose level and insulin information of the target subject in the target time period.

[0073] The target subject's blood glucose level in the target time period may be a sequence that changes over time, or may be an average blood glucose level, a weighted average blood glucose level, etc. The target subject's insulin information in the target time period is similar, wherein the insulin information includes but is not limited to the target subject's insulin intake.

[0074] Taking the target time period of 8:00 to 10:00 as an example, the blood glucose value of the target subject in the target time period may be the target subject's blood glucose value 1 at 8:00, blood glucose value 2 at 8:01, blood glucose value 3 at 8:02, ... blood glucose value 119 at 9:59, and blood glucose value 120 at 10:00. The target subject's insulin information in the target time period may be the target subject's insulin information 1 at 8:00, insulin information 2 at 8:01, insulin information 3 at 8:02, ... insulin information 119 at 9:59, and insulin information 120 at 10:00.

[0075] The last insulin sensitivity coefficient is used to indicate the insulin coefficient determined by the parameter determination method last time. It is understandable that if the insulin coefficient is determined for the first time, the last insulin sensitivity coefficient may be an initial value. The initial value may be a value stored in the computer device in advance, or a value determined in response to an input operation.

[0076] Furthermore, the computer device can determine the current insulin sensitivity coefficient based on the previous insulin sensitivity coefficient and the blood sugar level and insulin information of the target subject in the target time period.

[0077] Optionally, the computer device can train the target model in advance according to the blood glucose level, insulin information and insulin sensitivity coefficient of different time periods, and after completing the training, input the target object's blood glucose level and insulin information in the target time period and the last insulin sensitivity coefficient into the trained target model to obtain the current insulin sensitivity coefficient output by the target model. The target model can be a convolutional neural network (CNN), a recurrent neural network (RNN), or other deep learning networks, machine learning networks, etc.

[0078] For example, assuming that the current time is 6 o'clock and the first time period is from 3 o'clock to 6 o'clock, the computer device calculates the insulin sensitivity coefficient for the first time at this time, and the last insulin sensitivity coefficient is the initial value. Then, the computer device determines the first insulin sensitivity coefficient 1 based on the initial value, the blood sugar value and insulin information of the target object from 3 o'clock to 6 o'clock, and the insulin sensitivity coefficient 1 also indicates the insulin sensitivity coefficient corresponding to the target object at 6 o'clock.

[0079] Afterwards, assuming that the current time is 10 o'clock and the first time period is from 7 o'clock to 10 o'clock, the computer device calculates the insulin sensitivity coefficient for the second time, and the previous insulin sensitivity coefficient is insulin sensitivity coefficient 1. Then, the computer device determines the current insulin sensitivity coefficient 2 based on insulin sensitivity coefficient 1. The target object's blood sugar value and insulin information from 7 o'clock to 10 o'clock, and the insulin sensitivity coefficient 2 also indicates the target object's corresponding insulin sensitivity coefficient at 10 o'clock. Afterwards, the computer device can continuously update the current insulin sensitivity coefficient in this way.

[0080] Further optionally, after the computer device determines the current insulin sensitivity coefficient, it can display the current insulin sensitivity coefficient to provide a reference for the user.

[0081] The parameter determination method provided in this embodiment obtains the target object's eating detection result in the first time period, and determines the target time period from the first time period according to the eating detection result, and then determines the current insulin sensitivity coefficient according to the last insulin sensitivity coefficient and the target object's blood sugar level and insulin information in the target time period. At present, the eating situation of the target object is usually ignored when determining the insulin sensitivity coefficient, resulting in inaccurate determined insulin sensitivity coefficient. In this embodiment, since the first time period includes the current time point and the historical time period before the current time point, the eating detection result can reflect the eating situation of the target object at the previous time point and the historical time period. Furthermore, since the target time period is determined from the first time period according to the eating detection result, the target time period takes into account the eating situation of the target object at the previous time point and the historical time period. In this way, based on the last insulin sensitivity coefficient and the target object's blood sugar level and insulin information in the target time period, a more accurate insulin sensitivity coefficient can be determined.

[0082] Figure 3 This is a flow chart of determining a target time period in an embodiment of the present application, referring to Figure 3 This embodiment relates to an optional implementation method of how to determine the target time period from the first time period. Based on the above embodiment, the above S202, according to the eating detection result, determines the target time period from the first time period, including the following steps:

[0083] S301, if the eating detection result includes that the target object has eating behavior within a first time period, the time period in the first time period except the second time period is used as the target time period; the second time period includes a time period of a preset length after the eating time point corresponding to the eating behavior.

[0084] In this embodiment, if the eating detection result includes that the target object has an eating behavior within the first time period, the computer device can also determine the eating time point corresponding to the eating behavior according to the eating detection result.

[0085] Furthermore, the computer device can determine a second time period of a preset duration after the eating time point, wherein the preset duration may be a value stored in advance in the computer device, and similarly, the preset duration is a number greater than 0, and the unit may be seconds, minutes or hours.

[0086] For example, taking the first time period as 8:00 to 11:00 and the preset duration as 1 hour, the computer device determines that the target object has a meal at 9:00 between 8:00 and 11:00, then the meal time point is 9:00, and the second time period is 1 hour after 9:00. Then, the computer device can use the time period in the first time period except the second time period as the target time period, that is, the time period corresponding to 8:00 to 9:00 and 10:00 and 11:00 as the target time period.

[0087] It is understandable that eating will affect the target object's blood sugar level, and if the insulin sensitivity coefficient is calculated using the blood sugar level during eating, the accuracy of the insulin sensitivity coefficient will be reduced. In this embodiment, since the computer device can use the time period other than the second time period in the first time period as the target time period when the eating detection result includes that the target object has eaten in the first time period, when determining the current insulin sensitivity coefficient later, the blood sugar level and insulin information of the target object in the second time period can be ignored, thereby improving the accuracy of the current insulin sensitivity coefficient.

[0088] S302: If the eating detection result includes that the target object has not eaten in a first time period, the first time period is used as a target time period.

[0089] In this embodiment, if the eating detection result includes that the target object did not eat in the first time period, that is, the target object did not eat in the first time period, the computer device can directly use the first time period as the target time period. For example, if the first time period is 8:00 to 11:00, and the computer device determines that the target object did not eat at 9 o'clock between 8:00 and 11:00, then 8:00 and 11:00 can be used as the target time period.

[0090] Since the eating detection result includes that the target object has not eaten in the first time period, the first time period is used as the target time period. Therefore, when no eating behavior occurs, the blood glucose value and insulin information of the entire first time period can be used to improve the accuracy of the current insulin sensitivity coefficient determined.

[0091] In one embodiment, optionally, the eating detection result also includes food type and / or food amount; the above parameter determination method also includes the following steps:

[0092] Determine the preset time duration based on the type of food and / or amount of food.

[0093] In this embodiment, the eating detection result also includes food types and / or food amounts. The food types include at least one category; the food amount can be a value or a range. For example, the food types can include leafy vegetables, vegetables, fruit and vegetables, grains and oils, fruits, dairy products, etc. The food amount can be less than 10g, 10-20g, ... more than 150g, etc.

[0094] Optionally, the type of food and / or the amount of food may be sent to the computer device by other electronic devices, or may be determined by the computer device in response to an input operation of the target object, or may be simulated by the computer device based on the target object's historical eating habits.

[0095] Furthermore, the computer device can determine the preset duration of the second time period according to the type of food and / or the amount of food.

[0096] Optionally, the computer device may store the correspondence between different food categories and / or food amounts and preset durations. That is, the computer device may store the correspondence between food types and different preset durations, for example, when the food category is fruit, the preset duration may be 0.5 hours. The computer device may also store the correspondence between food amounts and different preset durations, for example, when the food amount is less than 10g, the preset duration is 20 minutes. The computer device may also store the correspondence between different food types, different food amounts and preset durations, for example, when the food type is fruit and the food amount is less than 10g, the preset duration is 10 minutes.

[0097] In this way, the computer device can determine the preset time according to the above correspondence and the type and / or amount of food. Since the preset time is determined according to the type and / or amount of food, the target time period can be flexibly and reasonably set according to the type and / or amount of food. For example, a longer preset time can be set for foods that are difficult to digest, and a shorter preset time can be set for foods that are easy to digest, thereby improving the accuracy of the current insulin sensitivity coefficient.

[0098] Figure 4 This is a flow chart of obtaining the eating detection result in an embodiment of the present application, referring to Figure 4 This embodiment relates to an optional implementation method of how to obtain the eating detection result. Based on the above embodiment, the above S201, obtaining the eating detection result of the target object in the first time period, includes the following steps:

[0099] S401, obtaining facial vibration detection results corresponding to each time point of a target object in a first time period.

[0100] In this embodiment, the facial vibration detection result is used to indicate the muscle vibration of the target object's temple. It can be the result sent to the computer device after other devices measure the facial vibration of the target object, or it can be the result determined by the computer device after obtaining the signal measured by the sensor worn by the target object.

[0101] For example, the target object may wear smart glasses, which are provided with a pressure sensor, which can determine the pressure signal between the target object and the temple, and can convert the pressure signal into an electrical signal according to a certain rule. Then, the pressure sensor sends the electrical signal to the computer device in real time or periodically through the smart glasses, so that the computer device determines the facial vibration detection results corresponding to each time point of the target object in the first time period according to the received electrical signal.

[0102] In one embodiment, the facial vibration detection result may be represented as a curve or a scatter plot that changes with each time point in the first time period.

[0103] S402: Determine a vibration matching result according to the facial vibration detection result and the preset vibration result.

[0104] In this embodiment, after determining the facial vibration detection results corresponding to each time point of the target object in the first time period, the computer device can match the facial vibration detection results with the preset vibration results to obtain a vibration matching result. The vibration matching result may include "match" or "no match".

[0105] The preset vibration result is used to indicate the facial vibration of the target object when eating. For example, the computer device collects facial vibration detection result samples of different objects when chewing and swallowing food in advance, and determines the preset vibration result after post-processing multiple facial vibration detection result samples. The post-processing may include but is not limited to weighted average processing.

[0106] Furthermore, the computer device may calculate the difference between the facial vibration detection result and the preset vibration result, and determine the vibration matching result as "match" if the difference between the facial vibration detection result and the preset vibration result is less than the preset difference, and otherwise determine the vibration matching result as "mismatch". The difference may include but is not limited to the similarity and mean square error between the facial vibration detection result and the preset vibration result.

[0107] In some embodiments, the computer device may also input the facial vibration detection result and the preset vibration result into a trained evaluation model, and the evaluation model outputs a numerical value indicating the degree of matching between the facial vibration detection result and the preset vibration result. When the numerical value output by the rating model is greater than a threshold, the computer device considers the vibration matching result to be a "match", otherwise the vibration matching result is a "mismatch".

[0108] Further optionally, in order to improve efficiency and accuracy, the computer device can divide the facial vibration detection results into sub-detection results, and use the sub-detection results and the preset vibration results to determine the vibration matching results corresponding to each sub-detection result. Exemplarily, if the first time period is from 8:00 to 11:00, the computer device can obtain sub-detection result 1 from 8:00 to 8:05, and determine the eating detection result corresponding to 8:05 to 8:05 based on sub-detection result 1 and the preset vibration result. Similarly, the computer device can obtain sub-detection result 2 from 8:05 to 8:10, and determine the eating detection result corresponding to 8:05 to 8:10 based on sub-detection result 2 and the preset vibration result, and so on.

[0109] S403: Obtaining an eating detection result of the target object in the first time period according to the vibration matching result.

[0110] In this embodiment, after determining the vibration matching result, the computer device can obtain the eating detection result of the target object in the first time period according to the vibration matching result.

[0111] Optionally, when the vibration matching result is a match, the computer device may determine that the target object has an eating behavior in the first time period, and select a time point from each time point in the first time period as the eating time point. For example, the computer device may use the first time point in the time period in which the eating behavior exists as the eating time point, or may use the time point in the time period in which the facial vibration detection result signal is the strongest as the eating time point.

[0112] This embodiment obtains the facial vibration detection results corresponding to each time point of the target object in the first time period. Since the vibration matching results can be determined based on the facial vibration detection results and the preset vibration results, and then the eating detection results of the target object in the first time period are obtained based on the vibration matching results, this embodiment can automatically determine the eating detection results of the target object in the first time period without the target object manually sending the situation to the computer device when eating, thereby improving the efficiency of determining the eating detection results.

[0113] Figure 5 This is another flow chart of obtaining the eating detection result in the embodiment of the present application, referring to Figure 5This embodiment relates to an optional implementation method of how to obtain the eating detection result. Based on the above embodiment, the above S403, according to the vibration matching result, obtains the eating detection result of the target object in the first time period, including the following steps:

[0114] S501 : when the vibration matching result is a match, obtaining a plurality of facial image frames corresponding to the target object at each time point.

[0115] In this embodiment, the vibration matching result is used to assist the computer device in determining the eating detection result. When the vibration matching result is a match, the computer device still needs to obtain multiple facial image frames corresponding to the target object at each time point, and obtain the eating detection result of the target object in the first time period based on the facial image frames.

[0116] The computer device may obtain multiple facial image frames through a visual sensor. For example, the target object may wear smart glasses, which are provided with a visual sensor, and the visual sensor may determine and obtain multiple facial image frames corresponding to the target object at each time point.

[0117] Continuing with the above example, assuming that the computer device determines that the eating detection results corresponding to 8:00 to 8:05 are a match, the computer device continues to acquire multiple facial image frames corresponding to 8:00 to 8:05.

[0118] S502: Acquire a detection result of the target object eating in a first time period according to the multiple facial image frames.

[0119] Furthermore, the computer device may obtain the target object's eating detection result in the first time period based on the multiple facial image frames. For example, the computer device may input the multiple facial image frames into a trained action recognition model, and the action recognition model outputs the target object's eating detection result in the first time period.

[0120] In this embodiment, when the vibration matching result is a match, multiple facial image frames corresponding to the target object at each time point are obtained, and the eating detection result of the target object in the first time period is obtained based on the multiple facial image frames. The accuracy of the eating detection result is improved by using both vibration and facial methods.

[0121] Figure 6 Schematic diagram of a process for obtaining eating detection results in the embodiments of the present application, refer to Figure 6 This embodiment relates to an optional implementation method of how to obtain the eating detection result. Based on the above embodiment, the above S502, based on multiple facial image frames, obtains the eating detection result of the target object in the first time period, including the following steps:

[0122] S601, determining a facial action detection result according to a plurality of facial image frames.

[0123] In this embodiment, the computer device determines the facial action detection result based on the multiple facial image frames. Optionally, the computer device can use facial action capture to determine the facial action detection result based on the multiple facial image frames.

[0124] The facial action detection result is used to indicate the facial action of the target object. For example, the facial action detection result includes but is not limited to one of laughing, being silent, sleeping, and chewing.

[0125] In some embodiments, optionally, the visual sensor may include a camera and a reflective marker ball. The camera may emit light of a specific wavelength. After being projected by the reflective marker ball, each camera may correspond to the two-dimensional coordinates of the reflective marker ball.

[0126] Then, the computer device can determine the two-dimensional coordinates of the corresponding reflective marker ball according to the facial image frame. Furthermore, after the computer device performs a 3D reconstruction algorithm on multiple facial image frames, it can determine the three-dimensional coordinates corresponding to the facial image frames.

[0127] Afterwards, the computer device calculates the corresponding speed, acceleration vector and six-degree-of-freedom posture information of the rigid body according to the three-dimensional coordinates. Finally, the computer device can determine the facial action detection result based on the above speed, acceleration vector and six-degree-of-freedom posture information of the rigid body. For example, the computer device imports the above speed, acceleration vector and six-degree-of-freedom posture information of the rigid body into MotionBuilder (3D character animation software) for repair processing, and then imports the repaired result into 3dMax (three-dimensional animation rendering and production software) and Unreal (3D engine), and then the facial action detection result can be determined.

[0128] S602: When the facial action detection result includes a preset action, determine a food recognition result according to at least one frame of the plurality of facial image frames and a food classification model.

[0129] Furthermore, in order to detect the eating behavior, the preset action can be set to chewing. Then, when the facial action detection result includes chewing, the computer device can continue to identify the food according to at least one frame of the multiple facial image frames.

[0130] The computer device may input at least one of the multiple facial image frames into the food classification model to determine the food recognition result. For example, the computer device may input any one of the multiple facial image frames corresponding to the preset action when the facial action detection result is the preset action into the food classification model to obtain the food recognition result.

[0131] The food classification model can be a convolutional neural network (CNN), a recurrent neural network (RNN), or other deep learning networks, machine learning networks, etc.

[0132] Further optionally, the food classification model is a region-based convolutional neural network (R-CNN), in which the first stage identifies a subset of regions in the facial image frame that may contain food; and the second stage classifies the food in each subset of regions that may contain food. In other words, the food recognition result includes not only whether there is food, but also, if there is food, the type of food and / or the amount of food.

[0133] S603: Obtaining a detection result of the target object eating in the first time period according to the food recognition result.

[0134] In this embodiment, after determining the food recognition result, the computer device can obtain the target object's eating detection result in the first time period according to the food recognition result.

[0135] In one embodiment, optionally, the above S603, obtaining the target object's eating detection result in the first time period according to the food recognition result, can be implemented in the following manner:

[0136] When the food recognition result indicates that food exists, the eating detection result is determined to include the eating behavior of the target object at the corresponding time point and the eating time point at which the eating behavior occurs. In this way, the target time period can be determined from the first time period according to the eating detection result.

[0137] In some embodiments, when the food recognition result indicates that food exists, the computer device can not only determine the target object's eating behavior at the corresponding time point and the eating time point at which the eating behavior occurs, but also determine the type of food and / or the amount of food. In this way, the computer device can determine the preset time according to the type of food and / or the amount of food.

[0138] The above example is based on first determining the facial vibration detection result, then performing the facial action detection result and the food recognition result. In some embodiments, the computer device may also only obtain multiple facial image frames corresponding to each time point of the target object in the first time period, and when the facial action detection result includes a preset action, determine the food recognition result based on at least one frame of the multiple facial image frames and the food classification model, and then determine the target object's eating behavior at the corresponding time point and the eating time point when the eating behavior occurs when the food recognition result is that food exists.

[0139] In some embodiments, the computer device may also first perform facial action detection results and food recognition results, and then use facial vibration detection results to assist in determining eating detection results. That is, the computer device may also obtain multiple facial image frames corresponding to the target object at each time point in the first time period, and when the facial action detection results include a preset action, determine the food recognition result based on at least one frame of the multiple facial image frames and the food classification model, and then, when the food recognition result is that food exists, continue to obtain the facial vibration detection results corresponding to the target object at each time point in the first time period, and determine the vibration matching result based on the facial vibration detection results and the preset vibration results. Afterwards, when the food recognition result is that food exists and the vibration matching result is a match, it is determined that the target object has an eating behavior at the corresponding time point and the eating time point at which the eating behavior occurs.

[0140] Figure 7 This is a schematic diagram of a process for determining the insulin sensitivity coefficient in an embodiment of the present application, referring to Figure 7 This embodiment relates to an optional implementation method of how to determine the current insulin sensitivity coefficient. Based on the above embodiment, the above S203, according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target object in the target time period, determines the current insulin sensitivity coefficient, including the following steps:

[0141] S701, determining adjustment parameters according to the last insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

[0142] S702: Update the insulin sensitivity coefficient of the previous time according to the adjustment parameter to obtain the insulin sensitivity coefficient of the current time.

[0143] In this embodiment, in order to obtain the current insulin sensitivity coefficient, the computer device first needs to determine the adjustment parameter ratio according to the previous insulin sensitivity coefficient and the blood glucose value and insulin information of the target object in the target time period. i . Where i is an integer greater than or equal to 1, ratio i This means the adjustment parameter for the i-th time. For example, when the current time is the first time, the adjustment parameter ratio is determined 1 , when the current time is the second time, determine the adjustment parameter ratio 2 , and so on.

[0144] Optionally, the computer device may input the last insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period into a trained adjustment model, so that the adjustment model outputs the adjustment parameters.

[0145] Furthermore, after the adjustment parameters are determined, the computer device can update the insulin sensitivity coefficient of the previous time according to the adjustment parameters to obtain the insulin sensitivity coefficient of the current time.

[0146] Optionally, the computer device can determine the current insulin sensitivity coefficient based on the quotient of the last insulin sensitivity coefficient and the adjustment parameter. For example, the insulin sensitivity coefficient of the ith time is denoted as ISF i , then ISF i =ISF i-1 / ratio i It can be understood that when i=1, ISF 0 Indicates the initial value corresponding to the insulin sensitivity coefficient.

[0147] In this embodiment, the adjustment parameter is first determined based on the last insulin sensitivity coefficient and the blood sugar level and insulin information of the target object in the target time period, and then the last insulin sensitivity coefficient is updated based on the adjustment parameter to obtain the current insulin sensitivity coefficient. Therefore, after considering the target object's eating situation in the first time period, a more accurate adjustment parameter can be determined, and then the last insulin sensitivity coefficient can be updated based on the adjustment parameter, and the last insulin sensitivity coefficient can be corrected to improve the accuracy of the current insulin sensitivity coefficient.

[0148] Figure 8 This is a flow chart of determining adjustment parameters in an embodiment of the present application, referring to Figure 8 This embodiment relates to an optional implementation method of how to determine the adjustment parameter. Based on the above embodiment, the above S701 determines the adjustment parameter according to the last insulin sensitivity coefficient and the blood glucose level and insulin information of the target object in the target time period, including the following steps:

[0149] S801, determining a blood glucose correction value based on a physiological model and the blood glucose value and insulin information of a target subject during a target time period; the blood glucose correction value is used to indicate the difference between a current blood glucose value at a current time point and a theoretical blood glucose value at a current time point.

[0150] In this embodiment, the physiological model includes the conversion relationship between insulin and blood glucose of the target object, which can be other models stored in the computer device, or a model obtained by the computer device based on the blood glucose values ​​and insulin information analysis of multiple target objects in historical time periods.

[0151] Furthermore, the computer device can determine the target subject's theoretical blood sugar value at the current time point based on the target subject's blood sugar value and insulin information during the target time period and the physiological model. Afterwards, the difference between the target subject's current blood sugar value at the current time point and the theoretical blood sugar value can be determined to determine the blood sugar correction value delta.

[0152] S802, determining adjustment parameters according to the blood glucose correction value, the last insulin sensitivity coefficient and preset parameters; the preset parameters include the frequency of obtaining the blood glucose value and the standard basal rate of the target object.

[0153] In this embodiment, the preset parameters include the frequency of obtaining the blood glucose value and the standard basal rate of the target object, which may be parameters stored in the computer device in advance or parameters requested from other electronic devices when needed.

[0154] The preset parameters include the acquisition frequency of the blood glucose value and the standard basal rate of the target object. Among them, the acquisition frequency m of the blood glucose value is used to indicate the interval between two adjacent blood glucose values. If the computer device receives the blood glucose value from the blood glucose sensor, the acquisition frequency can be the minimum interval time between the blood glucose values ​​received by the computer device from the blood glucose sensor, in minutes. The standard basal rate basal of the target object is in U / h (unit per hour).

[0155] Furthermore, the computer device can determine the adjustment parameter ratio according to the blood sugar correction value, the last insulin sensitivity coefficient and the preset parameters. i For example, the computer device may determine the adjustment parameter ratio according to the following formula: i .

[0156] ratio i =[delta / ISF i-1 +basal / (60 / m)] / (basal / (60 / m))

[0157] This embodiment determines the blood glucose correction value based on the physiological model and the blood glucose value and insulin information of the target object in the target time period, and determines the adjustment parameter based on the blood glucose correction value, the last insulin sensitivity coefficient and the preset parameters. Since the preset parameters include the acquisition frequency of the blood glucose value and the standard basal rate of the target object, the blood glucose correction value is used to indicate the difference between the current blood glucose value at the current time point and the theoretical blood glucose value at the current time point, so it is possible to calculate a more accurate adjustment parameter in combination with the preset parameters.

[0158] In order to more clearly introduce the parameter determination method of the present application, Fig. 9 Provide explanation. Fig. 9 Schematic diagram of a parameter determination method in an embodiment of the present application. Fig. 9As shown, the computer device can execute the above parameter determination method according to the following process.

[0159] S901, obtaining facial vibration detection results corresponding to each time point of a target object in a first time period.

[0160] S902: Determine a vibration matching result according to the facial vibration detection result and the preset vibration result.

[0161] S903: When the vibration matching result is a match, a plurality of facial image frames corresponding to the target object at each time point are obtained.

[0162] S904: Determine a facial action detection result according to the multiple facial image frames.

[0163] S905: When the facial action detection result includes a preset action, determine a food recognition result according to at least one frame of the plurality of facial image frames and a food classification model.

[0164] S906, when the food recognition result is that food exists, determine that the eating detection result includes the target object eating behavior at the corresponding time point, the eating time point when the eating behavior occurs, the type of food, and the amount of food.

[0165] S907, determining a preset time duration according to the type of food and / or the amount of food.

[0166] S908, if the eating detection result includes that the target object has eaten in the first time period, the time period in the first time period except the second time period is used as the target time period; the second time period includes a time period of a preset length after the eating time point corresponding to the eating behavior.

[0167] S909: If the eating detection result includes that the target object has not eaten in the first time period, the first time period is used as the target time period.

[0168] S910, determining a blood glucose correction value based on the physiological model and the blood glucose value and insulin information of the target subject in the target time period; the blood glucose correction value is used to indicate the difference between the current blood glucose value at the current time point and the theoretical blood glucose value at the current time point.

[0169] S911, determining adjustment parameters according to the blood glucose correction value, the last insulin sensitivity coefficient and preset parameters; the preset parameters include the frequency of obtaining blood glucose values ​​and the standard basal rate of the target object.

[0170] S912: Update the previous insulin sensitivity coefficient according to the adjustment parameter to obtain the current insulin sensitivity coefficient.

[0171] The steps of S901 to S912 may refer to the above embodiment and will not be described in detail here.

[0172] Fig.10 Schematic diagram of a parameter determination system in an embodiment of the present application. Fig.10 As shown, in one embodiment, optionally, the parameter determination system 1000 includes a head-mounted device 1002, a blood glucose sensor 1003, an insulin pump 1004 and a processor 1005, and the head-mounted device 1002, the blood glucose sensor 1003 and the insulin pump 1004 are worn by the target object 1001.

[0173] Among them, the head-mounted device 1002 may include but is not limited to smart glasses. The blood glucose sensor 1003 includes but is not limited to a blood glucose monitoring device (Continuous Glucose Monitoring, CGM). The processor 1005 can communicate with the head-mounted device 1002, the blood glucose sensor 1003 and the insulin pump 1004 respectively, and the communication method may include a wireless communication method and a wired communication method. The wireless communication method may be based on but is not limited to at least one of Bluetooth (BlueTooth), wireless communication technology (WIFI), ZigBee protocol (ZigBee), long-range radio (Long Range Radio, LoRA), active radio frequency identification (RFID) or ultra-wide band (Ultra Wide Band, UWB).

[0174] It should be noted that Fig.10 Taking the processor 1005 as a smart phone as an example, the processor 1005 can also be a personal computer, a laptop, a smart phone, a tablet computer, etc. Of course, the processor 1005 can also be set inside at least one of the head-mounted device 1002, the blood glucose sensor 1003 or the insulin pump 1004, and implemented by at least one of a central processing unit (CPU), a digital signal processor (DSP), a field programmable gate array (FPGA) or other programmable logic devices.

[0175] Furthermore, the head mounted device 1002 is used to obtain the target object's eating detection result in a first time period; the first time period includes a current time point and a historical time period before the current time point.

[0176] Processor 1005 is used to determine a target time period from the first time period according to the eating detection result.

[0177] The blood glucose sensor 1003 is used to obtain the blood glucose value of the target subject in the target time period.

[0178] The insulin pump 1004 is used to obtain insulin information of the target subject in the target time period.

[0179] The processor 1005 is further configured to determine the current insulin sensitivity coefficient according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

[0180] Optionally, processor 1005 is also used to, if the eating detection result includes that the target object has eaten within a first time period, use the time period in the first time period except the second time period as the target time period; the second time period includes a time period of a preset length after the eating time point corresponding to the eating behavior; if the eating detection result includes that the target object has not eaten within the first time period, use the first time period as the target time period.

[0181] Optionally, the eating detection result also includes the type of food and / or the amount of food; the processor 1005 is further used to determine the preset time duration based on the type of food and / or the amount of food.

[0182] Optionally, the head-mounted device 1002 also includes a pressure sensor, and the processor 1005 is also used to obtain facial vibration detection results corresponding to the target object at each time point in the first time period through a visual sensor; determine a vibration matching result based on the facial vibration detection result and a preset vibration result; and obtain an eating detection result of the target object in the first time period based on the vibration matching result.

[0183] Optionally, processor 1005 is further used to obtain, when the vibration matching result is a match, a plurality of facial image frames corresponding to the target object at each time point through a visual sensor; and obtain an eating detection result of the target object in a first time period based on the plurality of facial image frames.

[0184] Optionally, processor 1005 is further used to determine facial action detection results based on multiple facial image frames; when the facial action detection results include preset actions, determine food recognition results based on at least one frame of the multiple facial image frames and a food classification model; and obtain eating detection results of the target object in the first time period based on the food recognition results.

[0185] Optionally, the processor 1005 is further used to determine, when the food recognition result is that food is present, that the eating detection result includes the target object's eating behavior at a corresponding time point and the eating time point at which the eating behavior occurs.

[0186] Optionally, processor 1005 is further used to determine adjustment parameters based on the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period; update the previous insulin sensitivity coefficient according to the adjustment parameters to obtain the current insulin sensitivity coefficient.

[0187] Optionally, processor 1005 is further used to determine a blood glucose correction value based on the physiological model and the blood glucose value and insulin information of the target object in the target time period; the blood glucose correction value is used to indicate the difference between the current blood glucose value at the current time point and the theoretical blood glucose value at the current time point; the adjustment parameters are determined based on the blood glucose correction value, the last insulin sensitivity coefficient and preset parameters; the preset parameters include the frequency of obtaining the blood glucose value and the standard basal rate of the target object.

[0188] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0189] Based on the same inventive concept, the embodiment of the present application also provides a parameter determination device for implementing the parameter determination method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more parameter determination device embodiments provided below can refer to the limitations of the parameter determination method above, and will not be repeated here.

[0190] Fig.11 is a structural block diagram of a parameter determination device in an embodiment of the present application, such as Fig.11 As shown, in an embodiment of the present application, a parameter determination device 1100 is provided, including: an acquisition module 1101, a first determination module 1102 and a second determination module 1103, wherein:

[0191] The acquisition module 1101 is used to acquire the eating detection result of the target object in the first time period; the first time period includes the current time point and the historical time period before the current time point.

[0192] The first determination module 1102 is used to determine a target time period from the first time period according to the eating detection result.

[0193] The second determination module 1103 is used to determine the current insulin sensitivity coefficient according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

[0194] The parameter determination device provided in this embodiment obtains the target object's eating detection result in the first time period, and determines the target time period from the first time period according to the eating detection result, and then determines the current insulin sensitivity coefficient according to the last insulin sensitivity coefficient and the target object's blood sugar level and insulin information in the target time period. At present, the eating situation of the target object is usually ignored when determining the insulin sensitivity coefficient, resulting in inaccurate determined insulin sensitivity coefficient. In this embodiment, since the first time period includes the current time point and the historical time period before the current time point, the eating detection result can reflect the eating situation of the target object at the previous time point and the historical time period. Furthermore, since the target time period is determined from the first time period according to the eating detection result, the target time period takes into account the eating situation of the target object at the previous time point and the historical time period. In this way, based on the last insulin sensitivity coefficient and the target object's blood sugar level and insulin information in the target time period, a more accurate insulin sensitivity coefficient can be determined.

[0195] Optionally, the first determining module 1102 includes:

[0196] The first determination unit is used to use the time period in the first time period except the second time period as the target time period if the eating detection result includes that the target object has eating behavior within the first time period; the second time period includes a time period of a preset length after the eating time point corresponding to the eating behavior.

[0197] The second determining unit is configured to use the first time period as the target time period if the eating detection result includes that the target object has not eaten within the first time period.

[0198] Optionally, the eating detection result further includes food type and / or food amount; the parameter determination device 1100 further includes:

[0199] The third determination module is used to determine the preset time according to the food type and / or food amount.

[0200] Optionally, the acquisition module 1101 includes:

[0201] A first acquisition unit is used to acquire facial vibration detection results corresponding to each time point of the target object in a first time period;

[0202] A third determining unit, configured to determine a vibration matching result according to the facial vibration detection result and the preset vibration result;

[0203] The second acquisition unit is used to acquire the eating detection result of the target object in the first time period according to the vibration matching result.

[0204] Optionally, the second acquiring unit includes:

[0205] A first acquisition subunit is used to acquire a plurality of facial image frames corresponding to the target object at each time point when the vibration matching result is a match;

[0206] The second acquisition subunit is used to acquire the eating detection result of the target object in the first time period according to the multiple facial image frames.

[0207] Optionally, the second acquisition subunit is further used to determine facial action detection results based on multiple facial image frames; when the facial action detection results include preset actions, determine food recognition results based on at least one frame of the multiple facial image frames and a food classification model; and obtain eating detection results of the target object in the first time period based on the food recognition results.

[0208] Optionally, the second acquisition subunit is further used to determine, when the food identification result is the presence of food, that the eating detection result includes the target object's eating behavior at a corresponding time point and the eating time point at which the eating behavior occurs.

[0209] Optionally, the second determining module 1103 includes:

[0210] The fourth determining unit is used to determine the adjustment parameter according to the last insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

[0211] The updating unit is used to update the insulin sensitivity coefficient of the previous time according to the adjustment parameter to obtain the insulin sensitivity coefficient of the current time.

[0212] Optionally, the fourth determining unit includes:

[0213] The first determination subunit is used to determine a blood glucose correction value based on a physiological model and the blood glucose value and insulin information of the target subject in a target time period; the blood glucose correction value is used to indicate the difference between the current blood glucose value at the current time point and the theoretical blood glucose value at the current time point.

[0214] The second determination subunit is used to determine the adjustment parameters according to the blood glucose correction value, the last insulin sensitivity coefficient and the preset parameters; the preset parameters include the frequency of obtaining the blood glucose value and the standard basal rate of the target object.

[0215] Each module in the above parameter determination device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0216] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0217] Obtaining a target object's eating detection result in a first time period; the first time period includes a current time point and a historical time period before the current time point;

[0218] determining a target time period from the first time period according to the eating detection result;

[0219] The current insulin sensitivity coefficient is determined according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

[0220] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0221] If the eating detection result includes that the target object has eaten within the first time period, the time period in the first time period except the second time period is used as the target time period; the second time period includes a time period of a preset length after the eating time point corresponding to the eating behavior; if the eating detection result includes that the target object has not eaten within the first time period, the first time period is used as the target time period.

[0222] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0223] The preset time duration is determined according to the food type and / or food amount.

[0224] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0225] Obtain facial vibration detection results corresponding to each time point of the target object in the first time period; determine a vibration matching result according to the facial vibration detection results and a preset vibration result; and obtain an eating detection result of the target object in the first time period according to the vibration matching result.

[0226] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0227] When the vibration matching result is a match, a plurality of facial image frames corresponding to the target object at each of the time points are obtained; and based on the plurality of facial image frames, an eating detection result of the target object in a first time period is obtained.

[0228] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0229] Facial action detection results are determined based on the multiple facial image frames; when the facial action detection results include preset actions, food recognition results are determined based on at least one frame of the multiple facial image frames and a food classification model; and eating detection results of the target object in the first time period are obtained based on the food recognition results.

[0230] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0231] In the case where the food identification result is that food exists, the eating detection result is determined to include the eating behavior of the target object at the corresponding time point and the eating time point at which the eating behavior occurs.

[0232] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0233] According to the last insulin sensitivity coefficient and the blood sugar level and insulin information of the target object in the target time period, an adjustment parameter is determined; according to the adjustment parameter, the last insulin sensitivity coefficient is updated to obtain the current insulin sensitivity coefficient.

[0234] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0235] A blood glucose correction value is determined based on the physiological model and the blood glucose value and insulin information of the target object in the target time period; the blood glucose correction value is used to indicate the difference between the current blood glucose value at the current time point and the theoretical blood glucose value at the current time point; the adjustment parameter is determined based on the blood glucose correction value, the previous insulin sensitivity coefficient and preset parameters; the preset parameters include the frequency of obtaining the blood glucose value and the standard basal rate of the target object.

[0236] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0237] Obtaining a target object's eating detection result in a first time period; the first time period includes a current time point and a historical time period before the current time point;

[0238] determining a target time period from the first time period according to the eating detection result;

[0239] The current insulin sensitivity coefficient is determined according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

[0240] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0241] If the eating detection result includes that the target object has eaten within the first time period, the time period in the first time period except the second time period is used as the target time period; the second time period includes a time period of a preset length after the eating time point corresponding to the eating behavior; if the eating detection result includes that the target object has not eaten within the first time period, the first time period is used as the target time period.

[0242] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0243] The preset time duration is determined according to the food type and / or food amount.

[0244] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0245] Obtain facial vibration detection results corresponding to each time point of the target object in the first time period; determine a vibration matching result according to the facial vibration detection results and a preset vibration result; and obtain an eating detection result of the target object in the first time period according to the vibration matching result.

[0246] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0247] When the vibration matching result is a match, a plurality of facial image frames corresponding to the target object at each of the time points are obtained; and based on the plurality of facial image frames, an eating detection result of the target object in a first time period is obtained.

[0248] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0249] Facial action detection results are determined based on the multiple facial image frames; when the facial action detection results include preset actions, food recognition results are determined based on at least one frame of the multiple facial image frames and a food classification model; and eating detection results of the target object in the first time period are obtained based on the food recognition results.

[0250] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0251] In the case where the food identification result is that food exists, the eating detection result is determined to include the eating behavior of the target object at the corresponding time point and the eating time point at which the eating behavior occurs.

[0252] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0253] According to the last insulin sensitivity coefficient and the blood sugar level and insulin information of the target object in the target time period, an adjustment parameter is determined; according to the adjustment parameter, the last insulin sensitivity coefficient is updated to obtain the current insulin sensitivity coefficient.

[0254] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0255] A blood glucose correction value is determined based on the physiological model and the blood glucose value and insulin information of the target object in the target time period; the blood glucose correction value is used to indicate the difference between the current blood glucose value at the current time point and the theoretical blood glucose value at the current time point; the adjustment parameter is determined based on the blood glucose correction value, the previous insulin sensitivity coefficient and preset parameters; the preset parameters include the frequency of obtaining the blood glucose value and the standard basal rate of the target object.

[0256] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0257] Obtaining a target object's eating detection result in a first time period; the first time period includes a current time point and a historical time period before the current time point;

[0258] determining a target time period from the first time period according to the eating detection result;

[0259] The current insulin sensitivity coefficient is determined according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

[0260] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0261] If the eating detection result includes that the target object has eaten within the first time period, the time period in the first time period except the second time period is used as the target time period; the second time period includes a time period of a preset length after the eating time point corresponding to the eating behavior; if the eating detection result includes that the target object has not eaten within the first time period, the first time period is used as the target time period.

[0262] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0263] The preset time duration is determined according to the food type and / or food amount.

[0264] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0265] Obtain facial vibration detection results corresponding to each time point of the target object in the first time period; determine a vibration matching result according to the facial vibration detection results and a preset vibration result; and obtain an eating detection result of the target object in the first time period according to the vibration matching result.

[0266] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0267] When the vibration matching result is a match, a plurality of facial image frames corresponding to the target object at each of the time points are obtained; and based on the plurality of facial image frames, an eating detection result of the target object in a first time period is obtained.

[0268] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0269] Facial action detection results are determined based on the multiple facial image frames; when the facial action detection results include preset actions, food recognition results are determined based on at least one frame of the multiple facial image frames and a food classification model; and eating detection results of the target object in the first time period are obtained based on the food recognition results.

[0270] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0271] In the case where the food identification result is that food exists, the eating detection result is determined to include the eating behavior of the target object at the corresponding time point and the eating time point at which the eating behavior occurs.

[0272] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0273] According to the last insulin sensitivity coefficient and the blood sugar level and insulin information of the target object in the target time period, an adjustment parameter is determined; according to the adjustment parameter, the last insulin sensitivity coefficient is updated to obtain the current insulin sensitivity coefficient.

[0274] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0275] A blood glucose correction value is determined based on the physiological model and the blood glucose value and insulin information of the target object in the target time period; the blood glucose correction value is used to indicate the difference between the current blood glucose value at the current time point and the theoretical blood glucose value at the current time point; the adjustment parameter is determined based on the blood glucose correction value, the previous insulin sensitivity coefficient and preset parameters; the preset parameters include the frequency of obtaining the blood glucose value and the standard basal rate of the target object.

[0276] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0277] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0278] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0279] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A parameter determination method, characterized in that: The method comprises: Obtaining a target object's eating detection result in a first time period; the first time period includes a current time point and a historical time period before the current time point; determining a target time period from the first time period according to the eating detection result; The current insulin sensitivity coefficient is determined according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

2. The method according to claim 1, characterized in that Determining a target time period from the first time period according to the eating detection result includes: If the eating detection result includes that the target object has eaten in the first time period, the time period in the first time period except the second time period is used as the target time period; the second time period includes a time period of a preset length after the eating time point corresponding to the eating behavior; If the eating detection result includes that the target object has not eaten during the first time period, the first time period is used as the target time period.

3. The method according to claim 2, characterized in that The eating detection result also includes food type and / or food amount; the method also includes: The preset time duration is determined according to the food type and / or food amount.

4. The method according to any one of claims 1 to 3, characterized in that: The step of obtaining the target object's eating detection result in the first time period includes: Obtaining facial vibration detection results corresponding to each time point of the target object in the first time period; Determining a vibration matching result according to the facial vibration detection result and the preset vibration result; According to the vibration matching result, an eating detection result of the target object in a first time period is obtained.

5. The method according to claim 4, characterized in that The step of obtaining the target object's eating detection result in the first time period according to the vibration matching result includes: When the vibration matching result is a match, obtaining a plurality of facial image frames corresponding to the target object at each of the time points; Acquire, according to the plurality of facial image frames, an eating detection result of the target object in a first time period.

6. The method according to claim 5, characterized in that The step of obtaining, according to the plurality of facial image frames, an eating detection result of the target object in a first time period includes: determining a facial action detection result based on the plurality of facial image frames; In a case where the facial action detection result includes a preset action, determining a food recognition result according to at least one frame of the plurality of facial image frames and a food classification model; The target object's eating detection result in the first time period is obtained according to the food recognition result.

7. The method according to claim 6, characterized in that The step of obtaining the target object's eating detection result in the first time period according to the food recognition result includes: In the case where the food identification result is that food exists, the eating detection result is determined to include the eating behavior of the target object at the corresponding time point and the eating time point at which the eating behavior occurs.

8. The method according to any one of claims 1 to 3, characterized in that: The step of determining the current insulin sensitivity coefficient according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period includes: Determining adjustment parameters according to the last insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period; The insulin sensitivity coefficient of the previous time is updated according to the adjustment parameter to obtain the insulin sensitivity coefficient of the current time.

9. The method according to claim 8, characterized in that The updating of the insulin sensitivity coefficient of the previous time according to the adjustment parameter to obtain the insulin sensitivity coefficient of the current time and determining the adjustment parameter includes: Determine a blood glucose correction value according to the physiological model and the blood glucose value and insulin information of the target subject in the target time period; the blood glucose correction value is used to indicate the difference between the current blood glucose value at the current time point and the theoretical blood glucose value at the current time point; The adjustment parameter is determined according to the blood glucose correction value, the previous insulin sensitivity coefficient and preset parameters; the preset parameters include the acquisition frequency of the blood glucose value and the standard basal rate of the target object.

10. A parameter determination device, characterized in that: The device comprises: An acquisition module, used to acquire a target object's eating detection result in a first time period; the first time period includes a current time point and a historical time period before the current time point; A first determination module, configured to determine a target time period from the first time period according to the eating detection result; The second determination module is used to determine the current insulin sensitivity coefficient according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

11. A parameter determination system, characterized in that: The system includes a head mounted device, a blood glucose sensor, an insulin pump and a processor; The head mounted device is used to obtain a detection result of an eating of a target object in a first time period; the first time period includes a current time point and a historical time period before the current time point; The processor is used to determine a target time period from the first time period according to the eating detection result; The blood glucose sensor is used to obtain the blood glucose value of the target subject during the target time period; The insulin pump is used to obtain insulin information of the target subject during the target time period; The processor is further used to determine the current insulin sensitivity coefficient according to the previous insulin sensitivity coefficient and the blood glucose level and insulin information of the target subject in the target time period.

12. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images