Physiological age prediction method, device, electronic device and storage medium

Abstract

The present disclosure provides a physiological age prediction method, device, electronic device and storage medium, which relate to the field of smart medical technology. The method includes: obtaining a physiological age prediction model; obtaining aging data of a subject, the aging data including at least one of the sound characteristics, movement characteristics and cognitive characteristics of the subject; processing the aging data according to the physiological age prediction model to obtain the target physiological age of the subject. The method of processing the aging data of the subject through the physiological age prediction model to predict the target physiological age of the subject can quickly and accurately predict the physiological age of the subject.

Description

Background Art

[0002] As society ages, it becomes increasingly important to detect the physiological age, which is used to indicate the aging rate of an individual. Therefore, how to quickly and accurately predict the physiological age is an urgent problem to be solved.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] The present disclosure provides a physiological age prediction method, device, electronic device and storage medium, and at least provides a solution that can quickly and accurately predict physiological age.

[0005] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0006] According to one aspect of the present disclosure, a physiological age prediction method is provided, comprising: obtaining a physiological age prediction model; obtaining aging data of a subject, the aging data comprising at least one of a sound feature, a movement feature, and a cognitive feature of the subject; and processing the aging data according to the physiological age prediction model to obtain a target physiological age of the subject.

[0007] The physiological age of the subject is predicted by processing the aging data of the subject through the physiological age prediction model, thereby predicting the target physiological age of the subject.

[0008] In one embodiment of the present disclosure, the processing of the aging data according to the physiological age prediction model to obtain the target physiological age of the subject includes: acquiring an aging data generation model; processing the aging data according to the physiological age prediction model to obtain a first physiological age of the subject; processing the first physiological age according to the aging data generation model to obtain first predicted aging data; calculating the similarity between the aging data and the first predicted aging data to obtain a first similarity; when the first similarity is greater than a preset value, using the first physiological age as the target physiological age.

[0009] The method of using the aging data generation model to process the physiological age predicted by the physiological age prediction model, and in turn predicting the predicted aging data corresponding to the physiological age, and comparing the predicted aging data with the actual aging data, provides a technical solution for verifying the accuracy of the predicted physiological age. When the predicted aging data is similar enough to the actual aging data, the physiological age corresponding to the predicted aging data is used as the target physiological age, ensuring that the predicted physiological age has a high degree of accuracy.

[0010] In one embodiment of the present disclosure, it also includes: when the first similarity is not greater than the preset value, adjusting the physiological age prediction model according to the first similarity, and reprocessing the aging data according to the adjusted physiological age prediction model to obtain a second physiological age; processing the second physiological age according to the aging data generation model to obtain second predicted aging data; calculating the similarity between the aging data and the second predicted aging data to obtain a second similarity; when the second similarity is greater than the preset value, using the second physiological age as the target physiological age.

[0011] When the similarity between the predicted aging data predicted based on the physiological age and the actual aging data is lower than a preset value, it can be considered that the physiological age predicted by the current physiological age prediction model is not accurate enough. In this case, the physiological age prediction model is adjusted using the similarity so as to adjust the model parameters of the physiological age prediction model, thereby making the physiological age predicted by the adjusted physiological age prediction model more accurate, until a physiological age with sufficiently high accuracy is predicted.

[0012] In one embodiment of the present disclosure, the aging data includes the sound features, movement features and cognitive features, and obtaining the aging data of the measured object includes: obtaining the sound data, movement data and cognitive data of the measured object; and preprocessing the sound data, movement data and cognitive data to obtain the aging data.

[0013] Using the characteristics of the measured object in multiple dimensions to predict the measured object's physiological age can make the predicted physiological age more accurate.

[0014] In one embodiment of the present disclosure, the sound data includes dynamic sound data and / or static sound data, the dynamic sound data is the data corresponding to the sound emitted by the measured object in a moving state, and the static sound data is the data corresponding to the sound emitted by the measured object in a non-moving state; the cognitive data includes dynamic cognitive data and / or static cognitive data, the dynamic cognitive data is the data generated when the measured object performs a preset human-computer interaction task in a moving state, and the static cognitive data is the data generated when the measured object performs the preset human-computer interaction task in a non-moving state.

[0015] By distinguishing the sound data and cognitive data in static and dynamic states, one type of data can reflect the characteristics of multiple dimensions, thereby better characterizing the object being measured. Using the sound data and cognitive data in static and dynamic states is more conducive to accurately predicting the physiological age of the object being measured.

[0016] In one embodiment of the present disclosure, the motion data includes movement speed and / or body swing angle; the dynamic sound data and the static sound data both include at least one of volume, pitch and speaking speed; the dynamic cognitive data and the static cognitive data both include accuracy and / or average reaction time.

[0017] In one embodiment of the present disclosure, it also includes: obtaining the actual age of the measured object; and issuing a warning notification when the relationship between the target physiological age and the actual age meets a preset condition.

[0018] By issuing a warning notification when the target physiological age is greater than the actual age, the subject can be informed of his or her own aging status in a timely manner, so as to make timely targeted treatment such as seeking medical treatment.

[0019] According to another aspect of the present disclosure, a physiological age prediction device is provided, comprising: a first acquisition module for acquiring a physiological age prediction model; a second acquisition module for acquiring aging data of a measured object, wherein the aging data comprises at least one of a sound feature, a movement feature, and a cognitive feature of the measured object; and a prediction module for processing the aging data according to the physiological age prediction model to obtain a target physiological age of the measured object.

[0020] In one embodiment of the present disclosure, the prediction module is used to obtain an aging data generation model; process the aging data according to the physiological age prediction model to obtain a first physiological age of the subject; process the first physiological age according to the aging data generation model to obtain first predicted aging data; calculate the similarity between the aging data and the first predicted aging data to obtain a first similarity; when the first similarity is greater than a preset value, use the first physiological age as the target physiological age.

[0021] In one embodiment of the present disclosure, the prediction module is further used to adjust the physiological age prediction model according to the first similarity when the first similarity is not greater than the preset value, and re-process the aging data according to the adjusted physiological age prediction model to obtain a second physiological age; process the second physiological age according to the aging data generation model to obtain second predicted aging data; calculate the similarity between the aging data and the second predicted aging data to obtain a second similarity; and use the second physiological age as the target physiological age when the second similarity is greater than the preset value.

[0022] In one embodiment of the present disclosure, the aging data includes the sound features, motion features and cognitive features, and the second acquisition module is used to acquire the sound data, motion data and cognitive data of the subject; and pre-process the sound data, motion data and cognitive data to obtain the aging data.

[0023] In one embodiment of the present disclosure, the device further includes: an early warning module, configured to obtain the actual age of the measured object; and issue an early warning notification when the relationship between the target physiological age and the actual age satisfies a preset condition.

[0024] According to another aspect of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any of the above-mentioned physiological age prediction methods by executing the executable instructions.

[0025] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, any of the above-mentioned physiological age prediction methods is implemented.

[0026] According to another aspect of the present disclosure, a computer program product is provided, the computer program product comprising a computer program or computer instructions, the computer program or the computer instructions being loaded and executed by a processor so that a computer implements any of the physiological age prediction methods described above.

[0027] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0029] Figure 1 A schematic diagram showing a physiological age prediction system in one embodiment of the present disclosure.

[0030] Figure 2 A flow chart of a physiological age prediction method in one embodiment of the present disclosure is shown.

[0031] Figure 3 A schematic diagram showing a physiological age prediction process in one embodiment of the present disclosure.

[0032] Figure 4 A schematic diagram of a physiological age prediction device in one embodiment of the present disclosure is shown.

[0033] Figure 5 A structural block diagram of an electronic device in one embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0034] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0035] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0036] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0037] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0038] It should be noted that in this specification, before obtaining aging data, the user needs to be authorized first, and the aging data can be obtained only after the user authorizes. If the user refuses to authorize, the user's aging data will not be obtained. If the user first authorizes and then cancels the authorization, all the aging data of the user obtained after the previous user authorization will be deleted.

[0039] Figure 1 A schematic diagram of a physiological age prediction system in an embodiment of the present disclosure is shown, and the system can apply the physiological age prediction method or physiological age prediction device in various embodiments of the present disclosure.

[0040] like Figure 1 As shown, the physiological age prediction system may include: a data collection device 11, a physiological age prediction device 12, and an early warning device 13.

[0041] Among them, the data collection device 11 can collect sound data, motion data and cognitive data. In one embodiment, the data collection device 11 can obtain sound data, motion data and cognitive data through the network; in another embodiment, the data collection device 11 can directly collect the sound data, motion data and cognitive data generated by the object under test, thereby completing the collection of sound data, motion data and cognitive data.

[0042] In one embodiment, the data collection device 11 includes a voice collection device, a speed detection device, a posture detection device, and a human-computer interaction device. The voice data of the object under test (for example, one or more of volume, pitch, and speaking speed) can be collected through the voice collection device. The speed detection device can detect the movement speed of the object under test (a type of motion data). The posture detection device can detect the body swing angle of the object under test during movement (a type of motion data, which can also be called the left and right swing angle). The human-computer interaction device can send a preset human-computer interaction task to the object under test in the form of pictures and / or voice, and record the cognitive data (for example, accuracy and / or average reaction time) generated by the object under test performing the preset human-computer interaction task (for example, what animal is in the green area; for another example, what is 19+27).

[0043] In one embodiment, the voice collection device may be a device such as a microphone for receiving voice. The speed detection device may be any device that can detect the speed of the measured object walking, running, etc. (for example, a speedometer, etc.). The posture detection device has a shooting function, and obtains the body swing angle of the measured object by shooting a video of the measured object in motion and detecting the left and right swing angle of the measured object in the video when the measured object is in motion. The human-computer interaction device may be configured with a display and / or a voice output device, and a preset human-computer interaction task is issued to the measured object through the display and / or the voice output device. The human-computer interaction device may also be configured with an input device so that the measured object can reply to the preset human-computer interaction task through the input device. Among them, the input device may be the above-mentioned voice collection device, or the above-mentioned display, and the display has a touch screen function so that the measured object can reply through the display. In addition, the input device may also be any other device that can be used by the measured object to reply to the preset human-computer interaction task, and the embodiments of the present disclosure are not limited to this.

[0044] The data collection device 11 can also collect the physiological age of the object corresponding to the sound data, motion data and cognitive data. For example, when the sound data, motion data and cognitive data are obtained from the network, the physiological age of the corresponding object is also obtained.

[0045] After the data collection device 11 collects the sound data, motion data, cognitive data, and the corresponding physiological age, it can send the sound data, motion data, cognitive data, and physiological age to the physiological age prediction device 12. The physiological age prediction device 12 can generate aging data based on the sound data, motion data, and cognitive data, and then train the physiological age prediction model and the aging data generation model in combination with the physiological age of the subject corresponding to the aging data. The initial models of the physiological age prediction model and the aging data generation model can be directly constructed in the physiological age prediction device 12, or can be obtained from other devices through the network, and the present disclosure does not limit this.

[0046] After the physiological age prediction device 12 generates aging data based on the sound data, motion data and cognitive data, the physiological age prediction model can be used to directly process the aging data to obtain the physiological age of the subject; or, the physiological age prediction model is used to process the aging data to obtain the physiological age, and then the aging data generation model is used to generate predicted aging data corresponding to the physiological age, and when the similarity between the predicted aging data and the aging data is greater than a preset value, the physiological age predicted by the physiological age prediction model is output as the target physiological age.

[0047] The early warning device 13 can issue an early warning notification when the relationship between the target physiological age and the actual age of the measured object meets the preset condition. For details about the preset condition, please refer to Figure 2 The description of the corresponding embodiments will not be repeated here.

[0048] The data collection device 11, the physiological age prediction device 12, and the early warning device 13 are connected to each other through a network, and the network can be a wired network or a wireless network.

[0049] The data collection device 11, the physiological age prediction device 12, and the early warning device 13 may be the same device or different devices.

[0050] When the data collection device 11, the physiological age prediction device 12, and the early warning device 13 are different devices, the data collection device 11, the physiological age prediction device 12, and the early warning device 13 can all be any electronic device that can achieve the above-mentioned capabilities. For example, the data collection device 11 is composed of a display and / or a voice data device, an input device, and the physiological age prediction device 12 and the early warning device 13 can both be terminals or servers.

[0051] The present exemplary implementation is described in detail below with reference to the accompanying drawings and embodiments.

[0052] The present disclosure provides a physiological age prediction method, which can be performed by any electronic device with computing and processing capabilities. For example, the device can be a physiological age prediction device.

[0053] Figure 2 A flow chart of a physiological age prediction method in one embodiment of the present disclosure is shown as follows: Figure 2 As shown, the physiological age prediction method provided in the embodiment of the present disclosure includes the following S201 to S203.

[0054] S201, obtaining a physiological age prediction model.

[0055] The embodiments of the present disclosure do not limit the specific model of the physiological age prediction model. For example, the physiological age prediction model can be a support vector machine (SVM), a random forest, a deep neural network, etc.

[0056] In one embodiment, obtaining the physiological age prediction model may include: obtaining the physiological age prediction model from other devices through a network.

[0057] In another embodiment, obtaining a physiological age prediction model may include: obtaining an initial physiological age prediction model; obtaining sample aging data and the corresponding actual age; training the initial physiological age prediction model using the sample aging data and the corresponding actual age to obtain the physiological age prediction model. The method of obtaining the initial physiological age prediction model may include: directly obtaining the initial physiological age prediction model through a network; or directly constructing the initial physiological age prediction model in a physiological age prediction device.

[0058] In one embodiment, sample aging data and the corresponding actual age are obtained, and a plurality of objects under each actual age are sampled, thereby obtaining sample aging data and the corresponding actual age.

[0059] In another embodiment, obtaining sample aging data and the corresponding physiological age may include: sampling multiple objects at each actual age to obtain multiple groups of aging data, each group of aging data corresponding to an actual age; selecting aging data that meets preset conditions from each group of aging data to obtain aging data at each actual age, that is, sample aging data and the corresponding actual age.

[0060] The embodiments of the present disclosure do not limit what the preset condition is. In one embodiment, the preset condition is used to select the aging data of the object that performs better during the test. For example, the preset condition can be aging data that ranks within a preset ranking, or within a preset percentage in a group of aging data. The way to rank the aging data can be to score each or more data in the aging data, so that the score of the aging data can be determined according to the sum of the scores, and the greater the sum of the scores of the data in the aging data, the higher the ranking of the aging data when sorting. How to score each data in the aging data can be set according to experience, and the embodiments of the present disclosure do not limit it. Taking movement speed as an example, movement speed can be positively correlated with the score.

[0061] For example, a set of aging data corresponding to the actual age contains aging data of 500 objects, and the top 100 aging data can be selected as sample aging data.

[0062] S202, obtaining aging data of the measured object, where the aging data includes at least one of a sound feature, a movement feature, and a cognitive feature of the measured object.

[0063] Taking the aging data of the measured object including the sound characteristics, movement characteristics and cognitive characteristics of the measured object as an example, obtaining the aging data of the measured object may include: obtaining the sound data, movement data and cognitive data of the measured object; and preprocessing the sound data, movement data and cognitive data to obtain the aging data.

[0064] Using the characteristics of the measured object in multiple dimensions to predict the measured object's physiological age can make the predicted physiological age more accurate.

[0065] For details on how to obtain the sound data, motion data, and cognitive data of the measured object, please refer to Figure 1 The corresponding embodiments of the physiological age prediction system are not described in detail here.

[0066] In one embodiment, preprocessing the sound data, motion data, and cognitive data may include: cleaning, normalizing, and feature extracting the sound data, motion data, and cognitive data in sequence to obtain aging data.

[0067] In one embodiment, the sound data includes dynamic sound data and / or static sound data, the dynamic sound data is the data corresponding to the sound emitted by the measured object in motion, and the static sound data is the data corresponding to the sound emitted by the measured object in a non-motion state. The cognitive data includes dynamic cognitive data and / or static cognitive data, the dynamic cognitive data is the data generated by the measured object performing a preset human-computer interaction task in a motion state, and the static cognitive data is the data generated by the measured object performing a preset human-computer interaction task in a non-motion state.

[0068] By distinguishing the sound data and cognitive data in static and dynamic states, one type of data can reflect the characteristics of multiple dimensions, thereby better characterizing the object being measured. Using the sound data and cognitive data in static and dynamic states to predict the physiological age is more conducive to accurately predicting the physiological age of the object being measured.

[0069] In one embodiment, the object under test may be considered to be in motion when it generates motion data. In another embodiment, the object under test may be considered to be in motion when the motion speed of the object under test is not zero.

[0070] In one embodiment, the motion data includes motion speed and / or body swing angle; the dynamic sound data and the static sound data both include at least one of volume, pitch and speaking speed; the dynamic cognitive data and the static cognitive data both include accuracy and / or average reaction time.

[0071] Take the example that motion data includes motion speed and body swing angle, dynamic sound data and static sound data both include volume, pitch and speaking speed, and dynamic cognitive data and static cognitive data both include accuracy and average reaction time. Each type of data (for example, motion speed, dynamic volume, static speaking speed) corresponds to a vector. The embodiments of the present disclosure do not limit how to determine the vector corresponding to each type of data. For example, the mapping rules between each type of data and vectors can be designed in advance, and then the vector corresponding to any specific data in the data type can be determined according to the mapping rules corresponding to the data type.

[0072] In one embodiment, the lengths of vectors corresponding to different types of data are the same, and a matrix obtained by merging the vectors corresponding to each type of data is the aging data; or, a vector obtained by concatenating the vectors corresponding to each type of data is the aging data.

[0073] In another embodiment, the lengths of vectors corresponding to different types of data may be the same or different, and a vector obtained by concatenating the vectors corresponding to the different types of data is the aging data.

[0074] In yet another embodiment, the combination of vectors corresponding to various types of data is aging data.

[0075] It should be noted that if the aging data only includes sound features but does not include motion features and cognitive features, then when acquiring the data, only the sound data can be acquired without acquiring cognitive data and motion data. Accordingly, the sound data can be preprocessed to obtain the aging data. If the aging data only includes motion features but does not include sound features and cognitive features, then when acquiring the data, only the motion data can be acquired without acquiring cognitive data and sound data. Accordingly, the motion data can be preprocessed to obtain the aging data. If the aging data only includes cognitive features but does not include motion features and sound features, then when acquiring the data, only the cognitive data can be acquired without acquiring sound data and motion data. Accordingly, the cognitive data can be preprocessed to obtain the aging data.

[0076] S203, processing the aging data according to the physiological age prediction model to obtain the target physiological age of the subject.

[0077] In one embodiment, the aging data is input into a physiological age prediction model, and the physiological age prediction model is used to process the aging data, thereby outputting the physiological age of the subject, and the output physiological age is used as the target physiological age.

[0078] The physiological age of the subject is predicted by processing the aging data of the subject through the physiological age prediction model, thereby predicting the target physiological age of the subject.

[0079] In another embodiment, processing the aging data according to the physiological age prediction model to obtain the target physiological age of the subject under test may include: acquiring an aging data generation model; processing the aging data according to the physiological age prediction model to obtain a first physiological age of the subject under test; processing the first physiological age according to the aging data generation model to obtain first predicted aging data; calculating the similarity between the aging data and the first predicted aging data to obtain a first similarity; and when the first similarity is greater than a preset value, using the first physiological age as the target physiological age.

[0080] The embodiments of the present disclosure do not limit the specific implementation method of obtaining the aging data generation model, and reference may be made to the implementation method of obtaining the physiological age prediction model in S201 above.

[0081] The embodiments of the present disclosure do not limit the method for calculating the similarity between the aging data and the first predicted aging data. For example, the similarity between the aging data and the first predicted aging data may be calculated by using a cosine distance, a Euclidean distance, or the like. It should be noted that the method for calculating the similarity below may be the same as the method for calculating the similarity between the aging data and the first predicted aging data, and will not be described in detail below.

[0082] The method of using the aging data generation model to process the physiological age predicted by the physiological age prediction model, and in turn predicting the predicted aging data corresponding to the physiological age, and comparing the predicted aging data with the actual aging data, provides a technical solution for verifying the accuracy of the predicted physiological age. When the predicted aging data is similar enough to the actual aging data, the physiological age corresponding to the predicted aging data is used as the target physiological age, ensuring that the predicted physiological age has a high degree of accuracy.

[0083] In addition, when the first similarity is not greater than a preset value, the physiological age prediction model can be adjusted according to the first similarity, and the aging data can be reprocessed according to the adjusted physiological age prediction model to obtain a second physiological age; the second physiological age can be processed according to the aging data generation model to obtain second predicted aging data; the similarity between the aging data and the second predicted aging data can be calculated to obtain a second similarity; when the second similarity is greater than a preset value, the second physiological age can be used as the target physiological age.

[0084] When the similarity between the predicted aging data predicted based on the physiological age and the actual aging data is lower than a preset value, it can be considered that the physiological age predicted by the current physiological age prediction model is not accurate enough. In this case, the physiological age prediction model is adjusted using the similarity so as to adjust the model parameters of the physiological age prediction model, thereby making the physiological age predicted by the adjusted physiological age prediction model more accurate, until a physiological age with sufficiently high accuracy is predicted.

[0085] If the second similarity is still not greater than the preset value, continue to use the second similarity to adjust the physiological age prediction model, and cyclically predict the physiological age of the subject until the similarity between the predicted aging data generated in reverse based on the predicted physiological age and the aging data is greater than the preset value, and then output the physiological age as the target physiological age.

[0086] The embodiments of the present disclosure do not limit the specific value of the preset value, and can be set based on experience, for example, the preset value is 0.95, or 0.9, or 0.85.

[0087] The embodiments of the present disclosure do not limit the specific model of the aging data generation model. For example, the aging data generation model can be an autoencoder, or a generative adversarial network (GANs), or a variational autoencoder (VAEs), or a word embedding inversion model, etc.

[0088] To facilitate understanding of the process of physiological age prediction model and aging data prediction model working together to predict the physiological age of the subject, the following will combine Figure 3 Provide explanation.

[0089] like Figure 3As shown, first, the aging data is input into the physiological age prediction model, and the physiological age prediction model processes the aging data to obtain the preliminary physiological age. Then, the preliminary physiological age is input into the aging data generation model, and the aging data generation model processes the preliminary physiological age to obtain the predicted aging data. Then, the similarity between the predicted aging data and the aging data is calculated, and when the similarity is greater than the preset value, the preliminary physiological age is used as the target physiological age. When the similarity is not greater than the preset value, the loss value of the physiological age prediction model is adjusted by the similarity, and the model parameters of the physiological age prediction model are adjusted according to the adjusted loss value to complete the adjustment of the physiological age prediction model. Afterwards, the aging data is reprocessed using the adjusted physiological age prediction model to obtain a new preliminary physiological age, and the aging data generation model is re-used to judge the new preliminary physiological age, until the similarity corresponding to the final preliminary physiological age (the similarity between the predicted aging data corresponding to the preliminary physiological age and the aging data) is greater than the preset value, and the final preliminary physiological age is used as the target physiological age.

[0090] In one embodiment, after obtaining the target physiological age, the method further includes: obtaining the actual age of the subject; and issuing a warning notification when the relationship between the target physiological age and the actual age meets a preset condition.

[0091] The embodiments of the present disclosure do not limit what the preset condition is. For example, the preset condition may be that the target physiological age is greater than the actual age; or the preset condition may be that the target physiological age is greater than the actual age, and the age difference between the target physiological age and the actual age is greater than a preset age difference.

[0092] The embodiments of the present disclosure do not limit the specific value of the preset age difference. For example, the preset age difference is 1 year, 2 years, 3 years, etc.

[0093] Based on the same inventive concept, the present disclosure also provides a physiological age prediction device, as described in the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0094] Figure 4 A schematic diagram of a physiological age prediction device in one embodiment of the present disclosure is shown. Figure 4 As shown, the device includes: a first acquisition module 41, used to obtain a physiological age prediction model; a second acquisition module 42, used to obtain aging data of the object under test, the aging data including at least one of the sound characteristics, movement characteristics and cognitive characteristics of the object under test; a prediction module 43, used to process the aging data according to the physiological age prediction model to obtain the target physiological age of the object under test.

[0095] In one embodiment of the present disclosure, the prediction module 43 is used to obtain an aging data generation model; process the aging data according to the physiological age prediction model to obtain a first physiological age of the subject; process the first physiological age according to the aging data generation model to obtain first predicted aging data; calculate the similarity between the aging data and the first predicted aging data to obtain a first similarity; when the first similarity is greater than a preset value, use the first physiological age as the target physiological age.

[0096] In one embodiment of the present disclosure, the prediction module 43 is also used to adjust the physiological age prediction model according to the first similarity when the first similarity is not greater than a preset value, and re-process the aging data according to the adjusted physiological age prediction model to obtain a second physiological age; process the second physiological age according to the aging data generation model to obtain second predicted aging data; calculate the similarity between the aging data and the second predicted aging data to obtain a second similarity; and use the second physiological age as the target physiological age when the second similarity is greater than a preset value.

[0097] In one embodiment of the present disclosure, the aging data includes sound features, motion features and cognitive features. The second acquisition module 42 is used to acquire the sound data, motion data and cognitive data of the object under test; and pre-process the sound data, motion data and cognitive data to obtain the aging data.

[0098] In one embodiment of the present disclosure, the device further includes: an early warning module 44, which is used to obtain the actual age of the measured object; and issue an early warning notification when the relationship between the target physiological age and the actual age meets a preset condition.

[0099] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0100] Refer to the following Figure 5 The electronic device 500 according to this embodiment of the present disclosure is described. Figure 5 The electronic device 500 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0101] like Figure 5As shown, the electronic device 500 is in the form of a general computing device. The components of the electronic device 500 may include but are not limited to: at least one processing unit 510, at least one storage unit 520, and a bus 530 connecting different system components (including the storage unit 520 and the processing unit 510).

[0102] The storage unit stores program codes, which can be executed by the processing unit 510, so that the processing unit 510 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Specific Implementation Methods” section of this specification.

[0103] The storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 5201 and / or a cache storage unit 5202 , and may further include a read-only storage unit (ROM) 5203 .

[0104] The storage unit 520 may also include a program / utility 5204 having a set (at least one) of program modules 5205, such program modules 5205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0105] Bus 530 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0106] The electronic device 500 may also communicate with one or more external devices 540 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 500, and / or any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 550. Furthermore, the electronic device 500 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 560. Figure 5 As shown, the network adapter 560 communicates with other modules of the electronic device 500 via the bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0107] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0108] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the above-mentioned method of the present disclosure is stored thereon. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Specific Implementation Methods” section of this specification.

[0109] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0110] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0111] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0112] In specific implementation, the program code for performing the operation of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0113] In an exemplary embodiment of the present disclosure, a computer program product is also provided, which includes a computer program or computer instructions, and the computer program or computer instructions are loaded and executed by a processor to enable a computer to implement the steps of various exemplary embodiments of the present disclosure described in the above "Specific Implementation" section of this specification.

[0114] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0115] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0116] Through the description of the above implementation modes, it is easy for those skilled in the art to understand that the example implementation modes described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation mode of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation mode of the present disclosure.

[0117] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The description and examples are to be regarded as exemplary only, and the true scope of the present disclosure is indicated by the appended claims.

Claims

1. A method for predicting physiological age, characterized in that: include: Obtain a physiological age prediction model; Acquiring aging data of the subject, the aging data comprising at least one of a sound feature, a movement feature, and a cognitive feature of the subject; Processing the aging data according to the physiological age prediction model to obtain the target physiological age of the subject; The processing of the aging data according to the physiological age prediction model to obtain the target physiological age of the subject includes: acquiring an aging data generation model; processing the aging data according to the physiological age prediction model to obtain a first physiological age of the subject; processing the first physiological age according to the aging data generation model to obtain first predicted aging data; calculating the similarity between the aging data and the first predicted aging data to obtain a first similarity; and when the first similarity is greater than a preset value, using the first physiological age as the target physiological age.

2. The method according to claim 1, characterized in that Also includes: When the first similarity is not greater than the preset value, adjusting the physiological age prediction model according to the first similarity, and reprocessing the aging data according to the adjusted physiological age prediction model to obtain a second physiological age; Processing the second physiological age according to the aging data generation model to obtain second predicted aging data; calculating the similarity between the aging data and the second predicted aging data to obtain a second similarity; When the second similarity is greater than the preset value, the second physiological age is used as the target physiological age.

3. The method according to claim 1, characterized in that The aging data includes the sound features, movement features and cognitive features, and the step of obtaining the aging data of the subject includes: Acquiring sound data, movement data, and cognitive data of the measured object; The sound data, movement data and cognitive data are preprocessed to obtain the aging data.

4. The method according to claim 3, characterized in that The sound data includes dynamic sound data and / or static sound data, wherein the dynamic sound data is data corresponding to the sound emitted by the measured object in a moving state, and the static sound data is data corresponding to the sound emitted by the measured object in a non-moving state; The cognitive data includes dynamic cognitive data and / or static cognitive data. The dynamic cognitive data is data generated when the measured object performs a preset human-computer interaction task in a moving state, and the static cognitive data is data generated when the measured object performs the preset human-computer interaction task in a non-moving state.

5. The method according to claim 4, characterized in that The motion data includes motion speed and / or body swing angle; The dynamic sound data and the static sound data each include at least one of volume, pitch and speech speed; The dynamic cognitive data and the static cognitive data both include accuracy and / or average reaction time.

6. The method according to any one of claims 1 to 5, characterized in that: Also includes: Obtaining the actual age of the subject; When the relationship between the target physiological age and the actual age meets a preset condition, a warning notification is issued.

7. A physiological age prediction device, characterized in that: include: A first acquisition module is used to acquire a physiological age prediction model; A second acquisition module is used to acquire aging data of the subject, wherein the aging data includes at least one of a sound feature, a movement feature, and a cognitive feature of the subject; A prediction module, used for processing the aging data according to the physiological age prediction model to obtain the target physiological age of the subject; The prediction module is used to obtain an aging data generation model; Processing the aging data according to the physiological age prediction model to obtain a first physiological age of the subject; processing the first physiological age according to the aging data generation model to obtain first predicted aging data; calculating the similarity between the aging data and the first predicted aging data to obtain a first similarity; When the first similarity is greater than a preset value, the first physiological age is used as the target physiological age.

8. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the physiological age prediction method according to any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the physiological age prediction method according to any one of claims 1 to 6 is implemented.

Images