Physiological state prediction method and apparatus, electronic device, and storage medium

Abstract

The present disclosure relates to a physiological state prediction method and device, electronic equipment and storage medium. The method comprises obtaining target information and a target physiological signal of a target object; the target information is used to represent information related to the target physiological state recorded in a preset time period, and the target physiological signal is used to represent the physiological signal generated by the target object in the preset time period; based on the target information and the target physiological signal, the target physiological state is predicted to obtain a target prediction result; the target prediction result includes a target time when the target object is in the target physiological state and / or a physiological state performance when the target object is in the target physiological state. The present disclosure can predict the target time when the target object is in the target physiological state and / or the physiological state performance when the target object is in the target physiological state, thereby reducing the inconvenience to the user's life and the damage to the user's health when in the target physiological state, and effectively preventing the target physiological state in advance.

Description

Technical Field

[0001] This disclosure relates to the field of electronic equipment technology, and in particular to a method, apparatus, electronic device, and storage medium for predicting physiological states. Background Technology

[0002] Currently, with changing lifestyles and increasing pressures, some users may experience various health problems that impact their daily lives and harm their physical health. For example, Premenstrual Syndrome (PMS) is a common physiological condition occurring before and after menstruation, with an incidence rate of 20%-40% in women. During PMS, users may experience significant depression, anxiety, and mood instability. In other words, PMS can cause inconvenience in daily life and severely affect a user's mood. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides a method, apparatus, electronic device and storage medium for predicting physiological states.

[0004] According to a first aspect of the present disclosure, a method for predicting physiological states is provided, comprising:

[0005] Acquire target information and target physiological signals of the target object; the target information is used to characterize information related to the target physiological state recorded during a preset time period, and the target physiological signals are used to characterize the physiological signals generated by the target object during the preset time period;

[0006] Based on the target information and the target physiological signals, the target physiological state is predicted to obtain the target prediction result; the target prediction result includes the target time when the target object is in the target physiological state and / or the physiological state performance when in the target physiological state.

[0007] In some embodiments, predicting the target physiological state based on the target information and the target physiological signals to obtain a target prediction result includes:

[0008] Feature extraction is performed on the target physiological signal to obtain the target physiological signal features;

[0009] Periodic features are extracted from the target physiological signal features to obtain target periodic signal features; the target periodic signal features are used to characterize the periodic information of the target physiological signal.

[0010] The target physiological signal features, the target periodic signal features, and the target information are input into the target prediction model, and the target prediction result is output; the target prediction model is used to predict the target time when the target object is in the target physiological state and / or the physiological state performance when it is in the target physiological state.

[0011] In some embodiments, the target prediction model includes multiple prediction networks and a first evaluation network. The prediction networks are used to predict the emotional changes and / or physiological state changes of any object. The prediction content of different prediction networks is different. The first evaluation network is used to predict the duration and / or intensity of any object being in the target physiological state.

[0012] The step of inputting the target physiological signal features, the target periodic signal features, and the target information into the target prediction model and outputting the target prediction result includes:

[0013] For each prediction network, the target physiological signal features, the target periodic signal features, and the target information are input into the prediction network, and a reference prediction result is output.

[0014] The reference prediction results output by each prediction network are input into the first evaluation network to output the target prediction result; the target prediction result includes the target time and / or the intensity of the target object in the target physiological state.

[0015] In some embodiments, the target physiological state includes premenstrual syndrome (PMS), the target prediction model includes a menstrual cycle prediction network, an experience network, and a second evaluation network. The menstrual cycle prediction network is used to predict menstrual information for any subject, the experience network is used to predict a reference time for any subject to be in the PMS, and the second evaluation network is used to predict the duration and / or intensity of any subject to the PMS. The target prediction result includes the target time and / or the intensity of the target subject to the PMS.

[0016] The step of inputting the target physiological signal features, the target periodic signal features, and the target information into the target prediction model and outputting the target prediction result includes:

[0017] The target physiological signal features, the target periodic signal features, and the target information are input into the menstrual cycle prediction network, and the menstrual cycle information of the target object is output.

[0018] The menstrual information is input into the experience network, and the reference time when the target subject is in the premenstrual syndrome is output.

[0019] The target physiological signal characteristics, the target periodic signal characteristics, the target information, the menstrual information, and the reference time are input into the second evaluation network, and the target time and / or the intensity of the target object when it is in the premenstrual syndrome are output.

[0020] In some embodiments, the method further includes:

[0021] The first prompt message is displayed; the first prompt message is used to prompt the target object to confirm the accuracy of the target prediction result;

[0022] In response to the target object's confirmation of the prompt information, the target prediction result is displayed on the screen.

[0023] In some embodiments, the method further includes:

[0024] In response to the target object's correction operation on the target prediction result, the target prediction result is adjusted, and the adjusted target prediction result is displayed on the display screen.

[0025] In some embodiments, the method further includes:

[0026] Based on the physiological signal information of the target object and the target prediction result, a second prompt message is displayed; the second prompt message is used to prompt the behavioral information of the target object.

[0027] In some embodiments, the method further includes:

[0028] Based on the physiological signal information of the target object and the target prediction result, a control signal is sent to the target device so that the target device performs a corresponding operation based on the control signal.

[0029] The third prompt message is displayed; the third prompt message is used to characterize the status of the target device.

[0030] According to a second aspect of the present disclosure, a physiological state prediction device is provided, comprising:

[0031] The acquisition module is configured to acquire target information and target physiological signals of a target object; the target information is used to characterize information related to the target physiological state recorded during a preset time period, and the target physiological signals are used to characterize the physiological signals generated by the target object during the preset time period.

[0032] The determination module is configured to predict the target physiological state based on the target information and the target physiological signal, and obtain a target prediction result; the target prediction result includes the target time when the target object is in the target physiological state and / or the physiological state performance when it is in the target physiological state.

[0033] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0034] processor;

[0035] Memory used to store processor-executable instructions;

[0036] The processor is configured to execute the physiological state prediction method as described in the first aspect of this disclosure.

[0037] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the physiological state prediction method as described in the first aspect of the present disclosure.

[0038] The above-described method of this disclosure has the following beneficial effects: The method provided by the embodiments of this disclosure can predict the target time and / or the physiological state performance of the target object when it is in the target physiological state, thereby reducing the inconvenience to the user's life and the damage to the user's health when in the target physiological state, and effectively preventing the target physiological state in advance.

[0039] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0041] Figure 1 This is a flowchart illustrating a physiological state prediction method according to an exemplary embodiment.

[0042] Figure 2 This is a flowchart illustrating a physiological state prediction method according to an exemplary embodiment.

[0043] Figure 3 This is a schematic diagram illustrating a physiological state prediction method according to an exemplary embodiment.

[0044] Figure 4 This is a flowchart illustrating a physiological state prediction method according to an exemplary embodiment.

[0045] Figure 5 This is a schematic diagram illustrating a physiological state prediction method according to an exemplary embodiment.

[0046] Figure 6 This is a flowchart illustrating a physiological state prediction method according to an exemplary embodiment.

[0047] Figure 7 This is a schematic diagram illustrating a physiological state prediction method according to an exemplary embodiment.

[0048] Figure 8 This is a schematic diagram illustrating an interactive guidance process according to an exemplary embodiment.

[0049] Figure 9A This is a schematic diagram illustrating a sleep reminder message according to an exemplary embodiment.

[0050] Figure 9B This is a schematic diagram illustrating a motion prompt message according to an exemplary embodiment.

[0051] Figure 9C This is a schematic diagram illustrating an emotional cue message according to an exemplary embodiment.

[0052] Figure 10A This is a schematic diagram illustrating the state of a water dispenser according to an exemplary embodiment.

[0053] Figure 10B This is a schematic diagram illustrating the state of an air conditioner according to an exemplary embodiment.

[0054] Figure 10C This is a schematic diagram illustrating the state of an audio system according to an exemplary embodiment.

[0055] Figure 11 This is a flowchart illustrating a physiological state prediction method according to an exemplary embodiment.

[0056] Figure 12 This is a block diagram illustrating a physiological state prediction device according to an exemplary embodiment.

[0057] Figure 13 This is a block diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0058] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0059] Currently, with changing lifestyles and increasing pressures, some users may experience various health problems that impact their daily lives and harm their physical health. For example, premenstrual syndrome (PMS) is a common physiological condition that occurs before and after menstruation, with an incidence rate of 20%-40% in women. During PMS, users may experience significant depression, anxiety, and mood instability. In other words, PMS can cause inconvenience to users' daily lives and severely affect their emotions.

[0060] To address the aforementioned problems, this disclosure provides a method for predicting physiological states. This method can acquire target information and target physiological signals of a target object. The target information characterizes information related to the target physiological state recorded within a preset time period, and the target physiological signals characterize the physiological signals generated by the target object during the preset time period. Based on the target information and target physiological signals, the target physiological state is predicted to obtain a prediction result. The prediction result includes the target time when the target object is in the target physiological state and / or the physiological state performance while in the target physiological state. The method provided in this disclosure can predict the target time when a target object is in the target physiological state and / or the physiological state performance while in the target physiological state, thereby reducing the inconvenience and harm to the user's health caused by being in the target physiological state, and effectively preventing the target physiological state in advance.

[0061] The physiological state prediction method provided in this disclosure is executed by an electronic device, which may specifically be a mobile phone, tablet computer, laptop, smart robot, smart wearable device, or other smart device. In addition, the electronic device is equipped with various hardware resources and an energy storage device that provides power for the operation of these hardware resources.

[0062] Figure 1 This is a flowchart illustrating a physiological state prediction method according to an exemplary embodiment, executed by an electronic device, see [link to flowchart]. Figure 1 The method includes the following steps:

[0063] Step S101: Obtain target information and target physiological signals of the target object; the target information is used to characterize the information related to the target physiological state recorded in the preset time period, and the target physiological signals are used to characterize the physiological signals generated by the target object in the preset time period.

[0064] Physiological states can be used to characterize certain physiological symptoms. For example, target physiological states may include premenstrual syndrome, menopausal syndrome, postpartum syndrome (such as postpartum depression), etc.

[0065] In some embodiments, the size of the preset time period can be selected based on actual needs; for example, the preset time period can be a week or a month.

[0066] In some embodiments, target information can be determined based on the type of target physiological state, and the target information related to different types of physiological states may differ. Optionally, target information may include the target object's emotional information, mental state information, and dietary information within a preset time period. The target object's emotional information may include sadness, happiness, anger, etc.; the target object's mental state information may include calmness, anxiety, etc.; and the target object's dietary information may include the target object's dietary composition and calorie intake, etc.

[0067] It should be noted that when the target physiological state includes premenstrual syndrome, the target information may also include the target subject's menstrual information.

[0068] Physiological signals can refer to the physiological signals generated by the physiological activities of the target object. Target physiological signals can include physiological signals such as body temperature, heart rate, sleep, movement information, blood flow information, and skin conductance information of the target object within a preset time period. Among them, sleep can include sleep duration, sleep onset time, and sleep end time, and blood flow information can include blood flow velocity and blood flow rate. Optionally, target physiological signals can be physiological signals collected by wearable devices worn by the target object.

[0069] In one example, the target user can proactively record target information, such as by filling out a questionnaire or document to record such information. Alternatively, the electronic device can periodically guide the target user to record target information based on their needs, for example, by pushing a questionnaire or document to the target user to prompt them to fill it out. In another example, the electronic device can automatically detect and record information related to the target's physiological state, with the user's permission.

[0070] In some embodiments, during the process of recording target information, the target object can manually input the aforementioned target information. For example, for the target object's emotional information, the target object can manually input "happy". Alternatively, the target object can select the corresponding option from multiple options provided by the electronic device. For example, for the target object's emotional information, the electronic device can provide multiple options such as "happy", "anxious", "sad", "angry", and "fear" and display these options on the screen. The target object can select from multiple options based on its own actual situation. For example, if the target object's actual emotion is anxiety, the target object can select the "anxious" option from multiple options.

[0071] Step S102: Based on the target information and target physiological signals, predict the target physiological state to obtain the target prediction result; the target prediction result includes the target time when the target object is in the target physiological state and / or the physiological state performance when in the target physiological state.

[0072] Physiological state performance refers to the different performance when in the target physiological state compared to when in the normal physiological state. Physiological state performance can be presented in terms of intensity, which can be the intensity of any performance related to the target physiological state, such as the intensity of emotional changes, the intensity of physiological state changes, or the combined intensity of multiple intensities.

[0073] In some embodiments, the target physiological state can be predicted using a target prediction model to obtain the target prediction result. The target prediction model can be a pre-trained prediction model, and the training data for the target prediction model can include information and physiological signals of multiple objects, as well as the time and / or physiological state performance corresponding to the information and physiological signals in the target physiological state.

[0074] In some embodiments, target information and target physiological signals can be input into a target prediction model to output target prediction results.

[0075] In some embodiments, the electronic device may display the target prediction result and, based on the target prediction result, display a preset prompt message. The preset prompt message may prompt the target object to take preventive measures against the target physiological state so as to take appropriate measures before the target physiological state occurs, thereby reducing the risks and damages caused by the target physiological state.

[0076] Additionally, it should be noted that some electronic devices, such as wearable devices, have limited processing power and cannot execute the processing procedures shown in steps S101-S102. Therefore, electronic devices lacking processing power can collect the target physiological information and target information of the target object, and send the target information and target physiological signals to an electronic device with processing power connected to it. The electronic device with processing power can perform processing based on the target information and target physiological signals of the target object, determine the target prediction result, and feed back the target prediction result to the electronic device lacking processing power. The electronic device lacking processing power can receive and display the target prediction result. The interaction process between electronic devices with and without processing power will not be described in detail here.

[0077] The method provided in this disclosure can predict the target time and / or the physiological state performance of a target object when it is in a target physiological state, thereby reducing the inconvenience to the user's life and the damage to the user's health when in a target physiological state, and effectively preventing the target physiological state in advance.

[0078] In some embodiments, signal features can be extracted from the target physiological signal, and a target prediction result can be obtained based on the extracted features, target information, and target prediction model. Feature extraction can extract information from the raw data that is helpful for model learning and prediction. The following describes... Figure 2 The illustrated example explains the process of determining the target prediction result.

[0079] Figure 2 This is a flowchart illustrating a physiological state prediction method according to an exemplary embodiment, executed by an electronic device, see [link to flowchart]. Figure 2 The method includes the following steps:

[0080] Step S201: Extract features from the target physiological signal to obtain the target physiological signal features.

[0081] In some embodiments, feature extraction can be performed on the target physiological signal according to a preset signal duration to obtain target physiological signal features; the preset signal duration includes at least one of seconds, minutes, hours, and days, and the target physiological signal features include physiological signal features of physiological signals of different preset signal durations in the target physiological signal. For example, signal features per second of the target physiological signal can be extracted according to a signal duration of seconds.

[0082] It should be noted that the embodiments disclosed herein do not limit the specific method of feature extraction of the target physiological signal. Optionally, the feature extraction method may include any one of the following methods: principal component analysis, linear discriminant analysis, deep learning feature extraction method, etc. The feature extraction process will not be described in detail here.

[0083] Step S202: Periodic feature extraction is performed on the target physiological signal features to obtain the target periodic signal features; the target periodic signal features are used to characterize the periodic information of the target physiological signal.

[0084] The periodic information of the target physiological signal can include menstrual cycle, daily cycle, weekly cycle, monthly cycle, quarterly cycle, annual cycle, etc.

[0085] In some embodiments, periodic analysis can be performed on the target physiological signal features, and periodic features of the target physiological signal features can be extracted to obtain the target periodic signal features. This disclosure does not limit the specific method of periodic analysis; optionally, periodic analysis of the target physiological signal features can be performed using methods such as correlation analysis, Fourier transform, autocorrelation analysis, and time-frequency analysis.

[0086] To make the process of periodic analysis clearer, the following explanation uses correlation analysis as an example to illustrate the process of periodic analysis of target physiological signal characteristics.

[0087] When the target physiological signal feature is periodic, there is a time lag relationship between the target physiological signal feature Xt and Xt+k, and the period T = k. By setting different time lag values ​​and calculating the correlation between the physiological signal feature Xt+k and the target physiological signal feature Xt, the time lag value corresponding to the maximum correlation can be determined. This time lag value can then be defined as the period.

[0088] In one example, the menstrual cycle can be characterized by the trend of body temperature changes over multiple consecutive days. For instance, when a similar trend of body temperature changes reappears, the time interval between the date corresponding to that trend and the date corresponding to the current trend can be determined as the menstrual cycle. The daily cycle can be characterized by the time of falling asleep and waking up over multiple consecutive days, and the weekly cycle can be characterized by the duration of sleep over multiple consecutive days.

[0089] Step S203: Input the target physiological signal features, target periodic signal features and target information into the target prediction model and output the target prediction result.

[0090] Among them, the target prediction model is used to predict the target time when the target object is in the target physiological state and / or the physiological state performance when it is in the target physiological state.

[0091] In some embodiments, the training data of the target prediction model may include physiological signal features, periodic signal features and information of multiple objects, as well as prediction results corresponding to the above input information.

[0092] Additionally, it should be noted that target information and target physiological signals can also be input into the target prediction model, where feature extraction of the target physiological signals can be performed to obtain target physiological signal features. Furthermore, periodic feature extraction of the target physiological signal features can be performed within the target prediction model to obtain target periodic signal features. Subsequently, based on the target physiological signal features, target periodic signal features, and target information, the target physiological state is predicted, and the target prediction result is output.

[0093] The method provided in this disclosure can extract features and periodic features from physiological signals to obtain target physiological signal features and target periodic signal characteristics. In this way, the target physiological state can be predicted from multiple aspects, resulting in more accurate target prediction results.

[0094] In some embodiments, the electronic device includes a feature extraction module, which can input target physiological signals to achieve feature extraction of the target physiological signals. The electronic device also includes a periodic feature extraction module, which can input target physiological signal features to the periodic feature extraction module and output target periodic signal features. The following describes... Figure 3 The diagram illustrates a physiological state prediction method, explaining the process. First, the target physiological signals and information of the target object are acquired. Then, the target physiological signals are input into a feature extraction module, which outputs target physiological signal features. Next, the target physiological signal features are input into a periodic feature extraction module, which outputs target periodic signal features. Finally, the target periodic signal features, target physiological signal features, and target information are input into a target prediction model, outputting the target prediction result.

[0095] In some embodiments, the target prediction model can be a single model or a combination of multiple networks and logic. Furthermore, when a target is in a target physiological state, its hormone levels, neurotransmitter balance, stress levels, anxiety levels, and emotions are affected by this physiological state. Therefore, by observing changes in the target's emotions and physiological state, the duration of the target's state and / or its physiological manifestations while in the target physiological state can be predicted.

[0096] In one example, the target prediction model includes multiple prediction networks and a first evaluation network. The prediction networks predict changes in the emotional state and / or physiological state of any object. The predictions of different prediction networks differ. The first evaluation network predicts the duration and / or intensity of any object's target physiological state. The following will illustrate this... Figure 4 The illustrated example explains the process of determining the target prediction result.

[0097] Figure 4 This is a flowchart illustrating a physiological state prediction method according to an exemplary embodiment, executed by an electronic device, see [link to flowchart]. Figure 4 The method includes the following steps:

[0098] Step S401: For each prediction network, the target physiological signal features, target periodic signal features, and target information are input into the prediction network, and the reference prediction result is output.

[0099] The content predicted by the prediction network can be set and selected based on actual needs. Emotional changes can include the intensity of emotional changes, and physiological state changes can include the intensity of physiological state changes; the intensity of changes can be expressed in numerical form. That is, the output reference prediction result can be expressed in numerical form.

[0100] In some embodiments, the target physiological signal features, target periodic signal features, and target information can be input into the prediction network respectively, and the reference prediction result corresponding to each prediction network can be output.

[0101] In one example, the target prediction model may include three prediction networks (a first prediction network, a second prediction network, and a third prediction network, respectively). The first prediction network represents the intensity of the happiness-sadness change, the second prediction network represents the intensity of the wakefulness-fatigue change, and the third prediction network represents the intensity of the calmness-tension change. Specifically, the happiness-sadness change intensity can be the intensity of the emotional change when the target's emotional state changes from happiness to sadness; the wakefulness-fatigue change intensity can be the intensity of the physiological change when the target's physiological state changes from wakefulness to fatigue; and the calmness-tension change intensity can be the intensity of the physiological change when the target's physiological state changes from calmness to tension.

[0102] Correspondingly, the target physiological signal characteristics, target periodic signal characteristics, and target information can be input into the first prediction network, the second prediction network, and the third prediction network, respectively. The first prediction network can output the intensity of the happiness-sadness change corresponding to the input information, the second prediction network can output the intensity of the wakefulness-fatigue change corresponding to the input information, and the third prediction network can output the intensity of the calmness-tension change corresponding to the input information.

[0103] It should be noted that the greater the intensity value of the change, the more drastic the change.

[0104] Step S402: Input the reference prediction results output by each prediction network into the first evaluation network and output the target prediction results.

[0105] The target prediction results include the target time and / or the intensity of the target physiological state when the target object is in the target physiological state.

[0106] In some embodiments, the first evaluation network can comprehensively evaluate the reference prediction results output by each prediction network to obtain the target prediction result.

[0107] In some embodiments, the first evaluation network includes weight values ​​of the outputs of different prediction networks. Thus, the target prediction result can be comprehensively determined based on the weight values ​​in the first evaluation network. In one example, the intensity of the target object's physiological state can be obtained through comprehensive evaluation based on these weight values. For instance, if the weight of the first prediction network is 0.5, the weight of the second prediction network is 0.2, and the weight of the third prediction network is 0.3, and the intensity of the happiness-sadness change is 50, the intensity of the wakefulness-fatigue change is 40, and the intensity of the calmness-tension change is 50, then the intensity of the target object's physiological state can be 48.

[0108] In some embodiments, the first evaluation network can predict the target time when the target object is in the target physiological state based on the reference prediction results output by each prediction network. In one example, the intensity of change when the target object is in the target physiological state differs from the intensity of change when the target object is not in the target physiological state. Furthermore, the intensity of change represented by the reference prediction results is proportional to the distance between the preset time period and the target time; that is, the closer the preset time period is to the target time, the stronger the intensity of change represented by the reference prediction results. Therefore, the first evaluation network can determine the target time based on the intensity of change represented by the reference prediction results.

[0109] It should be noted that the target object may exhibit the target physiological state for several consecutive days, and correspondingly, the target time can be the target time period.

[0110] The following is based on Figure 5 The process of determining the target prediction result is explained using a schematic diagram of a physiological state prediction method shown below. Figure 5The schematic diagram shows a first prediction network, a second prediction network, a third prediction network, and a first evaluation network. First, input information, including target physiological signal characteristics, target periodic signal characteristics, and target information, is fed into the first, second, and third prediction networks, respectively. These prediction networks then output a first reference prediction result, a second reference prediction result, and a third reference prediction result, respectively. Next, these three prediction results are input into the first evaluation network, which outputs the target time and / or intensity (the target time and / or intensity of the target object in the target physiological state).

[0111] The method provided in this disclosure can divide the target prediction model into multiple prediction networks. In this way, the target time and / or intensity of the target object in the target physiological state can be predicted from multiple perspectives, resulting in a more accurate target time and / or intensity. This makes it easier for users to prevent the target physiological state and reduce the impact of the target physiological state when the target object is in the target physiological state.

[0112] In some embodiments, the target physiological state includes premenstrual syndrome (PMS), and the target prediction model includes a menstrual cycle prediction network, an experience network, and a second evaluation network. The menstrual cycle prediction network is used to predict menstrual information for any subject, the experience network is used to predict the reference time for any subject to experience PMS, and the second evaluation network is used to predict the duration and / or intensity of any subject's PMS. The target prediction result includes the target time and / or the intensity of the target subject's PMS. The following describes... Figure 6 The illustrated example explains the process of determining the target prediction result.

[0113] Figure 6 This is a flowchart illustrating a physiological state prediction method according to an exemplary embodiment, executed by an electronic device, see [link to flowchart]. Figure 6 The method includes the following steps:

[0114] Step S601: Input the target physiological signal characteristics, target periodic signal characteristics and target information into the menstrual prediction network, and output the menstrual information of the target object.

[0115] The menstrual information may include menstrual period, ovulation time, follicular phase, luteal phase, etc.

[0116] In some embodiments, the menstrual cycle prediction network can be a pre-trained network whose training data may include physiological signal features, periodic signal features, target information, and menstrual information corresponding to the above information for multiple objects.

[0117] Step S602: Input menstrual information into the experience network and output the reference time when the target subject is in premenstrual syndrome.

[0118] The reference time can be used to characterize the approximate duration of premenstrual syndrome in the individual.

[0119] In some embodiments, the experience network can be a pre-trained network whose training data may include menstrual period information of multiple subjects and a reference time for premenstrual syndrome (PMS) corresponding to each menstrual period. Alternatively, in some embodiments, the experience network can be an empirical formula, such as the period 3-5 days before menstruation being the time of PMS.

[0120] Step S603: Input the target physiological signal characteristics, target periodic signal characteristics, target information, menstrual information and reference time into the second evaluation network, and output the target time and / or intensity of the target subject when in premenstrual syndrome.

[0121] To more accurately pinpoint the timing and intensity of premenstrual syndrome (PMS) in the target individual, target physiological signal characteristics, target periodic signal characteristics, target information, menstrual information, and reference time can be input into a second evaluation network, which then outputs the target time and / or intensity. The second evaluation network can be a pre-trained network whose training data includes physiological signal characteristics, periodic signal characteristics, target information, menstrual information, reference time, and the corresponding time and / or intensity for multiple individuals.

[0122] The following is based on Figure 7 The process of determining the target prediction result is explained using a schematic diagram of a physiological state prediction method shown below. Figure 7 The diagram illustrates a menstrual cycle prediction network, an experience network, and a second evaluation network. First, input information is fed into the menstrual cycle prediction network, which outputs menstrual cycle information. This input information includes target physiological signal characteristics, target periodic signal characteristics, and target information. Then, the menstrual cycle information is input into the experience network, which outputs a reference time. Next, the input information, menstrual cycle information, and reference time are input into the second evaluation network, which outputs the target time and / or the intensity of premenstrual syndrome (PMS) for the target individual. Similarly, the target time can be a target time period, which will not be elaborated further here.

[0123] The method provided in this disclosure divides the target prediction model into a menstrual cycle prediction network, an experience network, and an evaluation network. The menstrual cycle prediction network and the experience network determine the approximate time of onset of premenstrual syndrome (PMS), while the evaluation network determines the target time and / or intensity of PMS in the target individual. This allows for more accurate prediction of the target time and / or intensity, thereby helping users effectively prevent PMS.

[0124] Optionally, after determining the target prediction result, the electronic device can directly display the target prediction result on the display screen. For example, when the electronic device is a mobile phone, tablet, or other device, it can display the target prediction result at a preset location on its display screen, which may include the control bar, desktop, application interface, etc.; or, when the electronic device is a wearable device, such as a smartwatch, it can display the target prediction result on the watch face; or, when the electronic device is an electronic device without processing capabilities, it can receive the target prediction result sent by an electronic device with processing capabilities and display the target prediction result on its display screen.

[0125] Optionally, after determining the target prediction result, the electronic device can prompt the target object to confirm whether the target prediction result is accurate, and perform corresponding operations in response to the user's operation. For example, if the user confirms that the target prediction result is accurate, the target prediction result can be displayed; or, if the user confirms that the target prediction result is inaccurate, the target prediction result can be updated.

[0126] In some embodiments, the electronic device may display a first prompt message; in response to the target object's confirmation operation of the prompt message, display the target prediction result on the display screen; or, in response to the target object's correction operation of the target prediction result, adjust the target prediction result and display the adjusted target prediction result on the display screen. The electronic device may be a device without processing capabilities or a device with processing capabilities, and the first prompt message is used to prompt the target object to confirm the accuracy of the prediction result.

[0127] In other words, when the target object determines that the prediction result is accurate, the prediction result is displayed on the screen; conversely, when the target object corrects the prediction result, it indicates that there is a deviation in the prediction result. At this time, the electronic device can respond to the correction operation of the target object, adjust the prediction result based on the correction operation, and display the adjusted prediction result on the screen. In this way, the accuracy of the prediction result displayed on the screen can be guaranteed.

[0128] Additionally, it should be noted that when the electronic device is a mobile phone, tablet, or similar device, the target prediction result can be simultaneously displayed on the wearable device that has established a communication connection with the mobile phone, tablet, or similar device. Similarly, when the electronic device is a wearable device, the target prediction result can be simultaneously displayed on other electronic devices connected to the wearable device.

[0129] The method provided in this disclosure can directly display the target prediction result on a display screen for user viewing. Alternatively, it can display a first prompt message, and then display the target prediction result on the display screen only after the user confirms that the target prediction result is correct or after correcting the target prediction result. In this way, the target prediction result can be confirmed or corrected based on external input information, thereby ensuring the accuracy of the target prediction result.

[0130] In some embodiments, such as Figure 8 The diagram illustrates an interactive guidance process. An electronic device can monitor the physiological signal information of a target object in real time and execute interactive guidance logic based on the target object's physiological signal information and the target prediction result. The physiological signal information can be the target object's real-time physiological signal information or the target object's physiological signal information within a preset time period (i.e., the target physiological signal). The target prediction result can include the target time and / or intensity. Furthermore, the physiological signal information can be information from a specific moment or sequence information.

[0131] Additionally, it should be noted that the above interactive guidance logic can be applied at any time. For example, it can be applied to any time other than the target time when the target physiological state is in progress. For instance, when the target physiological state is premenstrual syndrome, the interactive guidance logic can be applied to the target time when premenstrual syndrome is in progress, or it can be applied to the menstrual period when premenstrual syndrome is not in progress.

[0132] Interactive guidance logic can be used to guide a target object or other objects to perform preset behaviors, thereby guiding the target object to prevent the effects and discomfort caused by the target's physiological state. Alternatively, interactive guidance logic can control the usage status of other devices, thereby combining with other devices to adjust the environment in which the target object is located, thereby providing a more comfortable environment for the target object and reducing the discomfort caused by the target's physiological state.

[0133] In some embodiments, the electronic device may display a second prompt based on the physiological signal information of the target object and the target prediction result. The physiological signal information may include sleep information, movement information, heart rate information, etc.; sleep information may include sleep duration, sleep onset time, sleep end time, deep sleep duration, etc.; movement information may include movement duration, movement intensity, movement type, etc.; the second prompt is used to prompt the target object's behavioral information, which may include the target object's current behavioral information and / or the behavioral information the target object is about to perform.

[0134] Furthermore, based on the target prediction results, the current time period of the target object can be determined. For example, if the current time falls within the target time period, the target object can be identified as being in the target physiological state. Correspondingly, the target object's current time period can be added to the second prompt message, further encouraging the target object to pay closer attention to themselves. In this way, the target object can take corresponding actions based on the second prompt message, thereby reducing discomfort and improving the user experience.

[0135] In addition, the second prompt may also include adjustments to the electronic device's color tone, subject, font, brightness, volume, and other settings, which will not be elaborated here.

[0136] In one example, the second cue information can be sleep cue information, exercise cue information, or mood cue information. Among them, sleep cue information can include sleep duration, sleep regularity (cycle disorder, late bedtime, early wake-up, sleep efficiency), sleep stage results, etc.; exercise cue information can include exercise duration, exercise type, exercise frequency, calorie consumption, exercise heart rate, exercise body temperature, sweating amount, etc.

[0137] like Figure 9A The diagram shows a sleep prompt message that can be displayed on the watch face of an electronic device to remind the target to adjust their sleep schedule.

[0138] like Figure 9B The diagram shows a motion prompt message that can be displayed on the dial of an electronic device to prompt the target object to increase its movement.

[0139] like Figure 9C The diagram shows an example of an emotion prompt message that can be displayed on the dial of an electronic device to prompt the target to adjust their emotions.

[0140] The method provided in this disclosure can prompt the user with information about their current or previous behavior and provide the user with information about behaviors to be performed, thereby helping the user adjust their own state before a target time, during a target time period, or at any time, so as to optimize the user's state and health, thereby reducing physical discomfort caused by the target physiological state or other reasons.

[0141] In some embodiments, based on the physiological signal information of the target object and the target prediction result, a control signal is sent to the target device to enable the target device to perform corresponding operations based on the control signal; a third prompt message is displayed; the third prompt message is used to characterize the state of the target device. The physiological signal information and the target prediction result will not be described in detail here.

[0142] Furthermore, based on the target prediction results, the current period of the target object can be determined. For example, if the current time falls within the target time period, the target object can be identified as being in the target physiological state. Accordingly, the target object's current period can be added to the third prompt information to further encourage the target object to pay more attention to itself.

[0143] In some embodiments, the target device can be a device with a communication connection to the electronic device, such as an air conditioner, audio system, water dispenser, curtains, television, refrigerator, smart light, etc. Correspondingly, the electronic device can send control signals to the target device via the communication connection; the target device can receive and execute the operation corresponding to the control signal, and send feedback information to the electronic device after execution; the feedback information indicates that the target device has successfully executed the operation corresponding to the control signal; after receiving the feedback information, the electronic device can display a third prompt message.

[0144] like Figure 10A The diagram shown illustrates the status of a water dispenser, which can display the current period and status of the water dispenser on the dial of an electronic device.

[0145] like Figure 10B The diagram shown illustrates the status of an air conditioner, which can display the current period and status of the air conditioner on the dial of an electronic device.

[0146] like Figure 10C The diagram shown illustrates the status of an audio device, which can display the current period and audio status of the target object on the dial of an electronic device.

[0147] The method provided in this disclosure can be combined with smart devices to adjust the surrounding environment of the target object, such as adjusting the water temperature of a water dispenser, adjusting the indoor temperature, adjusting the sound, adjusting the lighting, etc., thereby providing users with a comfortable living environment and reducing physical discomfort caused by the target's physiological state or other reasons.

[0148] In some embodiments, a fourth prompt message can also be sent to other devices; these other devices can be devices belonging to family members of the target object. The fourth prompt message is used to inform the family members of the target object's status so that the family members can guide the target object's behavior. The family members can be selected by the target object itself.

[0149] The method provided in this disclosure can send the status of a target object to a family member, thereby notifying the family member so that the family member can guide the user's behavior, thereby increasing care for the user, reducing user discomfort, and protecting the user's personal safety.

[0150] Figure 11 This is a flowchart illustrating a physiological state prediction method according to an exemplary embodiment, executed by an electronic device, see [link to flowchart]. Figure 11 The method includes the following steps:

[0151] Step S1101: Obtain target information and target physiological signals of the target object.

[0152] Step S1102: Extract features from the target physiological signal according to the preset signal time length to obtain the target physiological signal features.

[0153] Step S1103: Periodic feature extraction is performed on the target physiological signal features to obtain the target periodic signal features.

[0154] Depending on the structure of the target prediction model, steps S1104-S1105 can be executed according to the actual results of the target prediction model, or steps S1106-S1108 can be executed.

[0155] Step S1104: The target prediction model includes multiple prediction networks and a first evaluation network. For each prediction network, the target physiological signal characteristics, target periodic signal characteristics, and target information are input into the prediction network, and a reference prediction result is output.

[0156] Step S1105: Input the reference prediction results output by each prediction network into the first evaluation network and output the target prediction results.

[0157] Step S1106: The target physiological state includes premenstrual syndrome. The target prediction model includes a menstrual prediction network, an experience network, and a second evaluation network. The target physiological signal characteristics, target periodic signal characteristics, and target information are input into the menstrual prediction network, and the menstrual information of the target object is output.

[0158] Step S1107: Input menstrual information into the experience network and output the reference time when the target subject is in premenstrual syndrome.

[0159] Step S1108: Input the target physiological signal characteristics, target periodic signal characteristics, target information, menstrual information and reference time into the second evaluation network, and output the target time and / or intensity of the target subject when in premenstrual syndrome.

[0160] Step S1109: Display the first prompt message.

[0161] Depending on the operation performed on the target object, the corresponding step can be selected from steps S1110 and S1111 for execution. When the operation on the target object is a confirmation operation, step S1110 is executed; when the operation on the target object is a correction operation, step S1111 is executed.

[0162] In step S1110, in response to the target object's confirmation of the prompt information, the target prediction result is displayed on the screen.

[0163] Step S1111: In response to the target object's correction operation on the target prediction result, the prediction result is adjusted and the adjusted target prediction result is displayed on the display screen.

[0164] Figure 12 This is a block diagram illustrating a physiological state prediction device according to an exemplary embodiment, configured in an electronic device, see [link to relevant documentation]. Figure 12 The device includes:

[0165] The acquisition module 1201 is configured to acquire target information and target physiological signals of the target object; the target information is used to characterize information related to the target physiological state recorded in a preset time period, and the target physiological signals are used to characterize the physiological signals generated by the target object in the preset time period.

[0166] The determination module 1202 is configured to predict the target physiological state based on target information and target physiological signals, and obtain the target prediction result; the target prediction result includes the target time when the target object is in the target physiological state and / or the physiological state performance when it is in the target physiological state.

[0167] In some embodiments, the determining module 1202 is configured to:

[0168] Feature extraction is performed on the target physiological signal to obtain the target physiological signal features;

[0169] Periodic features are extracted from the target physiological signal characteristics to obtain the target periodic signal features; the target periodic signal features are used to characterize the periodic information of the target physiological signal.

[0170] The target physiological signal characteristics, target periodic signal characteristics, and target information are input into the target prediction model, and the target prediction results are output. The target prediction model is used to predict the target time when the target object is in the target physiological state and / or the physiological state performance when it is in the target physiological state.

[0171] In some embodiments, the target prediction model includes multiple prediction networks and a first evaluation network. The prediction networks are used to predict the emotional changes and / or physiological state changes of any object. The prediction content of different prediction networks is different. The first evaluation network is used to predict the duration and / or intensity of any object being in the target physiological state.

[0172] Module 1202 is configured as follows:

[0173] For each prediction network, the target physiological signal characteristics, target periodic signal characteristics, and target information are input into the prediction network, and the reference prediction result is output.

[0174] The reference prediction results output by each prediction network are input into the first evaluation network to output the target prediction results; the target prediction results include the target time and / or the intensity of the target object in the target physiological state.

[0175] In some embodiments, the target physiological state includes premenstrual syndrome (PMS), the target prediction model includes a menstrual prediction network, an experience network, and a second evaluation network. The menstrual prediction network is used to predict menstrual information for any subject, the experience network is used to predict the reference time for any subject to be in PMS, and the second evaluation network is used to predict the duration and / or intensity of any subject to PMS. The target prediction result includes the target time for the target subject to be in PMS and / or the intensity of the target subject to PMS.

[0176] Module 1202 is configured as follows:

[0177] The target physiological signal characteristics, target periodic signal characteristics, and target information are input into the menstrual cycle prediction network, and the menstrual cycle information of the target object is output.

[0178] Menstrual cycle information is input into an experience network, and the reference time for the target subject to be in premenstrual syndrome is output.

[0179] The target physiological signal characteristics, target periodic signal characteristics, target information, menstrual information, and reference time are input into the second evaluation network, which outputs the target time and / or the intensity of the target subject's premenstrual syndrome.

[0180] In some embodiments, the physiological state prediction device further includes a display module, which is configured to:

[0181] Display the first prompt message; the first prompt message is used to prompt the target object to confirm the accuracy of the target prediction result;

[0182] In response to the target object's confirmation of the prompt, the target prediction result is displayed on the screen.

[0183] In some embodiments, the display module is configured to:

[0184] In response to the target object's correction operation on the target prediction result, the target prediction result is adjusted and displayed on the display screen.

[0185] In some embodiments, the display module is configured to:

[0186] Based on the physiological signal information of the target object and the target prediction results, a second prompt message is displayed; the second prompt message is used to prompt the target object's behavioral information.

[0187] In some embodiments, the display module is configured to:

[0188] Based on the physiological signal information of the target object and the target prediction results, control signals are sent to the target device so that the target device can perform corresponding operations based on the control signals.

[0189] The third prompt message is displayed; the third prompt message is used to characterize the status of the target device.

[0190] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0191] This disclosure also provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the physiological state prediction method in the above embodiments.

[0192] Figure 13 This is a block diagram of an electronic device 1300 according to an exemplary embodiment.

[0193] Reference Figure 13The electronic device 1300 may include one or more of the following components: a processing component 1302, a memory 1304, a power supply component 1306, a multimedia component 1308, an audio component 1310, an input / output (I / O) interface 1312, a sensor component 1314, and a communication component 1316.

[0194] Processing component 1302 typically controls the overall operation of electronic device 1300, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 1302 may include one or more processors 1320 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 1302 may include one or more modules to facilitate interaction between processing component 1302 and other components. For example, processing component 1302 may include a multimedia module to facilitate interaction between multimedia component 1308 and processing component 1302.

[0195] Memory 1304 is configured to store various types of data to support the operation of electronic device 1300. Examples of such data include instructions for any application or method operating on electronic device 1300, contact data, phonebook data, messages, pictures, videos, etc. Memory 1304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0196] Power supply component 1306 provides power to various components of electronic device 1300. Power supply component 1306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 1300.

[0197] Multimedia component 1308 includes a screen that provides an output interface between the electronic device 1300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 1308 includes a front-facing camera and / or a rear-facing camera. When the electronic device 1300 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0198] Audio component 1310 is configured to output and / or input audio signals. For example, audio component 1310 includes a microphone (MIC) configured to receive external audio signals when electronic device 1300 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 1304 or transmitted via communication component 1316. In some embodiments, audio component 1310 also includes a speaker for outputting audio signals.

[0199] I / O interface 1312 provides an interface between processing component 1302 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0200] Sensor assembly 1314 includes one or more sensors for providing state assessments of various aspects of electronic device 1300. For example, sensor assembly 1314 may detect the on / off state of electronic device 1300, the relative positioning of components such as the display and keypad of electronic device 1300, changes in position of electronic device 1300 or a component of electronic device 1300, the presence or absence of user contact with electronic device 1300, the orientation or acceleration / deceleration of electronic device 1300, and temperature changes of electronic device 1300. Sensor assembly 1314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 1314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 1314 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0201] Communication component 1316 is configured to facilitate wired or wireless communication between electronic device 1300 and other devices. Electronic device 1300 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 1316 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 1316 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0202] In an exemplary embodiment, the electronic device 1300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0203] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1304 including instructions, which can be executed by a processor 1320 of an electronic device 1300 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0204] A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the physiological state prediction method provided by an exemplary embodiment of this disclosure.

[0205] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0206] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for predicting physiological states, characterized in that, include: Acquire target information and physiological signals of the target object; The target information is used to characterize information related to the target physiological state recorded during a preset time period, and the target physiological signal is used to characterize the physiological signal generated by the target object during the preset time period. Based on the target information and the target physiological signals, the target physiological state is predicted to obtain the target prediction result; the target prediction result includes the target time when the target object is in the target physiological state and / or the physiological state performance when in the target physiological state.

2. The physiological state prediction method according to claim 1, characterized in that, The step of predicting the target's physiological state based on the target information and the target's physiological signals to obtain a target prediction result includes: Feature extraction is performed on the target physiological signal to obtain the target physiological signal features; Periodic features are extracted from the target physiological signal features to obtain target periodic signal features; the target periodic signal features are used to characterize the periodic information of the target physiological signal. The target physiological signal features, the target periodic signal features, and the target information are input into the target prediction model, and the target prediction result is output; the target prediction model is used to predict the target time when the target object is in the target physiological state and / or the physiological state performance when it is in the target physiological state.

3. The physiological state prediction method according to claim 2, characterized in that, The target prediction model includes multiple prediction networks and a first evaluation network. The prediction networks are used to predict the emotional changes and / or physiological state changes of any object. The prediction content of different prediction networks is different. The first evaluation network is used to predict the duration and / or intensity of any object being in the target physiological state. The step of inputting the target physiological signal features, the target periodic signal features, and the target information into the target prediction model and outputting the target prediction result includes: For each prediction network, the target physiological signal features, the target periodic signal features, and the target information are input into the prediction network, and a reference prediction result is output. The reference prediction results output by each prediction network are input into the first evaluation network to output the target prediction result; the target prediction result includes the target time and / or the intensity of the target object in the target physiological state.

4. The physiological state prediction method according to claim 2, characterized in that, The target physiological state includes premenstrual syndrome (PMS). The target prediction model includes a menstrual cycle prediction network, an experience network, and a second evaluation network. The menstrual cycle prediction network is used to predict the menstrual cycle information of any subject. The experience network is used to predict the reference time when any subject is in the PMS. The second evaluation network is used to predict the duration and / or intensity of any subject's PMS. The target prediction result includes the target time when the target subject is in the PMS and / or the intensity of the PMS. The step of inputting the target physiological signal features, the target periodic signal features, and the target information into the target prediction model and outputting the target prediction result includes: The target physiological signal features, the target periodic signal features, and the target information are input into the menstrual cycle prediction network, and the menstrual cycle information of the target object is output. The menstrual information is input into the experience network, and the reference time when the target subject is in the premenstrual syndrome is output. The target physiological signal characteristics, the target periodic signal characteristics, the target information, the menstrual information, and the reference time are input into the second evaluation network, and the target time and / or the intensity of the target object when it is in the premenstrual syndrome are output.

5. The physiological state prediction method according to claim 1, characterized in that, The method further includes: The first prompt message is displayed; the first prompt message is used to prompt the target object to confirm the accuracy of the target prediction result; In response to the target object's confirmation of the prompt information, the target prediction result is displayed on the screen.

6. The physiological state prediction method according to claim 5, characterized in that, The method further includes: In response to the target object's correction operation on the target prediction result, the target prediction result is adjusted, and the adjusted target prediction result is displayed on the display screen.

7. The physiological state prediction method according to claim 1, characterized in that, The method further includes: Based on the physiological signal information of the target object and the target prediction result, a second prompt message is displayed; the second prompt message is used to prompt the behavioral information of the target object.

8. The physiological state prediction method according to claim 1, characterized in that, The method further includes: Based on the physiological signal information of the target object and the target prediction result, a control signal is sent to the target device so that the target device performs a corresponding operation based on the control signal. The third prompt message is displayed; the third prompt message is used to characterize the status of the target device.

9. A physiological state prediction device, characterized in that, include: The acquisition module is configured to acquire target information and target physiological signals of the target object. The target information is used to characterize information related to the target physiological state recorded during a preset time period, and the target physiological signal is used to characterize the physiological signal generated by the target object during the preset time period. The determination module is configured to predict the target physiological state based on the target information and the target physiological signal, and obtain a target prediction result; the target prediction result includes the target time when the target object is in the target physiological state and / or the physiological state performance when it is in the target physiological state.

10. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to perform the physiological state prediction method as described in any one of claims 1-8.

11. A non-transitory computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the physiological state prediction method as described in any one of claims 1-8.

Images