WO2022042205A1

WO2022042205A1 - Disease risk level prediction method and device

Info

Publication number: WO2022042205A1
Application number: PCT/CN2021/109644
Authority: WO
Inventors: 许培达; 周林峰; 李靖
Original assignee: 华为技术有限公司
Priority date: 2020-08-28
Filing date: 2021-07-30
Publication date: 2022-03-03
Also published as: CN114121270A

Abstract

Provided are a disease risk level prediction method and device, relating to the field of data processing, being able to improve the accuracy of diagnosis of a preset disease, and being applicable to a disease risk level prediction system. Said method comprises: acquiring physiological information of a user suffering from a preset disease; then, acquiring a first facial image of the user, and acquiring, on the basis of the first facial image, a first user feature of the user corresponding to a key impact factor of the preset disease; and then, on the basis of the physiological information and the first user feature, predicting a first target risk level of the user suffering from the preset disease. Optionally, after the first target risk level is predicted, by acquiring a second facial image and updating the first facial image, the updating of the target risk level of the user suffering from the preset disease can be realized, such that the diagnosis result better fits the real-time situation of the user, improving the accuracy of diagnosis.

Description

Disease risk level prediction method and device

This application claims the priority of the Chinese patent application with the application number 202010889079.3 and the application name "Disease Risk Level Prediction Method and Device", which was submitted to the State Intellectual Property Office on August 28, 2020, the entire contents of which are incorporated into this application by reference middle.

technical field

The present application relates to the field of data processing, and in particular, to a disease risk level prediction method and device.

Background technique

Obstructive sleep apnea and hypopnea syndrome is a sleep breathing disorder of unknown etiology characterized by nocturnal sleep snoring with apnea and daytime sleepiness. Because apnea can cause nocturnal hypoxia and hypercapnia, which can easily lead to complications such as hypertension, coronary heart disease, diabetes or cerebrovascular disease, and even sudden death at night due to apnea. At present, for the diagnosis of key parameter information of obstructive sleep apnea and hypopnea syndrome, out-of-hospital portable sleep apnea screening equipment is generally used to obtain part of the parameter information, and at the same time, the user enters information based on the application to obtain another part of the parameter information, and then , based on these two parts of parameter information, to diagnose whether the user suffers from obstructive sleep apnea and hypopnea syndrome.

The above technical solution has the following problems: the reliability and integrity of some parameters entered based on the application program are low, resulting in a high misdiagnosis rate for whether the user has obstructive sleep apnea and hypopnea syndrome. Therefore, how to improve the obstructive sleep apnea and hypopnea syndrome? The diagnostic accuracy of sleep apnea and hypopnea syndrome is an urgent technical problem to be solved.

SUMMARY OF THE INVENTION

The embodiments of the present application provide a disease risk level prediction method and device, which can improve the diagnostic accuracy of preset diseases (eg, obstructive sleep apnea and hypoventilation syndrome).

To achieve the above object, the application adopts the following technical solutions:

In a first aspect, a disease risk level prediction method is provided, the prediction method includes: acquiring physiological information that a user suffers from a preset disease, and acquiring a first facial image of the user. Then, based on the first facial image, a first user characteristic of the user corresponding to the key influencing factor of the preset disease is acquired. After that, based on the physiological information and the first user characteristics, a first target risk level of the user suffering from a preset disease is predicted.

Based on the prediction method provided in the first aspect, by acquiring the physiological information of the preset disease of the user, the disease condition of the user can be preliminarily determined. By acquiring the first facial image of the user, the first facial image may be a facial image captured in real time, and then by extracting the first user characteristics of the user corresponding to the key influencing factors of the preset diseases in the first facial image , the key characteristics of the user related to the preset disease can be obtained. Compared with the user input information based on the application program in the prior art, the first user feature extracted by the image has the advantages of convenient acquisition and high integrity, and combined with the physiological information to make a comprehensive judgment, the user's actual situation can be obtained. The judgment of disease risk level can improve the diagnosis rate.

In a possible design, the physiological information related to the preset disease of the user is acquired, and the acquiring method includes: acquiring the physiological information related to the preset disease of the user at least twice within a first preset time period.

The method for predicting a first target risk level of a user suffering from a preset disease based on the physiological information and the first user feature includes: predicting the user based on the obtained physiological information related to the preset disease of the user at least twice and the first user feature. The first target risk level for having a prespecified disease. Or, based on the physiological information obtained each time, predict the first risk level of the user suffering from the preset disease; based on at least two first risk levels and the first user characteristics, predict the first target risk of the user suffering from the preset disease grade.

In this case, by acquiring the physiological information of the user suffering from the preset disease at least twice within a period of time, it is beneficial to improve the accuracy of acquiring the physiological information, and to improve the prediction of the first risk level obtained according to the physiological information. The accuracy can avoid errors in predicting the first target risk level due to errors in obtaining the user's physiological information. Predicting the first target risk level of the user suffering from a preset disease according to the physiological information obtained multiple times or multiple first risk levels obtained from the physiological information multiple times, and the first user characteristics, is beneficial to reflect the multiple acquisitions. The synthesis of physiological information over this time period.

In a possible design, acquiring the first facial image of the user, the acquiring method includes: acquiring the first facial image of the user when the number of occurrences is greater than or equal to the first preset number of times. Or, in the case that the number of occurrences is greater than or equal to the second preset number of times, and the first risk level of at least two first risk levels greater than or equal to the first preset risk level is continuous occurrence, obtain the first risk level of the user. face image.

It should be noted that the above-mentioned number of occurrences is the number of occurrences of the first risk level that is greater than or equal to the first preset risk level among the at least two first risk levels, and each first risk level is obtained based on the physiological information collected once. .

In this case, it is judged whether to acquire the first facial image based on the rank coefficient of the first risk level, the number of occurrences and whether it occurs continuously, which improves the risk of having a preset disease before acquiring the first facial image. The accuracy of risk judgment, thereby improving the accuracy of subsequent diagnosis of preset diseases.

In a possible design, acquiring the first facial image of the user includes: acquiring at least two images, wherein the at least two images are images of partial regions of the facial image of the user. The at least two images are fused into a first facial image. In this way, the first face image can be obtained from the image with the partial area of the user's face image, which reduces the standard of the user when taking the image and the difficulty of obtaining the first face image. The first facial image makes the first facial image closer to the real situation of the user, which is beneficial to improve the diagnosis accuracy of the preset disease.

In a possible design, based on the first facial image, obtaining the first user feature of the user corresponding to the key influencing factor of the preset disease, including: recognizing the facial feature in the first facial image, and then, based on the facial feature, The identity information of the user corresponding to the key influencing factor of the preset disease is obtained from the information query system. Then, the first user characteristic is determined according to the identity information. In this way, by extracting the identity information related to the key influencing factors of the preset disease from the first facial image, these identity information can be used to revise and judge the validity of the results about the preset disease obtained by the first risk level , update the final result, thereby improving the accuracy and stability of the preset disease diagnosis.

In a possible design, after predicting the first target risk level of the user suffering from a preset disease based on the physiological information and the first user characteristics, the predicting method further includes: acquiring a second facial image of the user, and in the second facial image In the case where the image changes relative to the first facial image, based on the second facial image, the second user feature corresponding to the key influencing factor of the user suffering from the preset disease is acquired. Based on the physiological information and the second user characteristic, a second target risk level of the user suffering from the preset disease is predicted. In this case, by acquiring the second facial image of the user, it is determined whether the second facial image and the first facial image have changed. The acquired second user characteristics are then combined with physiological information for prediction, and the obtained diagnosis result is closer to the real situation of the user, thereby improving the real-time and authenticity of the user's diagnosis of preset diseases.

In a possible design, after predicting the first target risk level of the user suffering from a preset disease based on the physiological information and the first user characteristics, the prediction method further includes: when the first target risk level is greater than or equal to the second target risk level In the case of a preset risk level, a prompt message is output. Wherein, the prompt information includes: a first user characteristic that satisfies a preset condition. Wherein, the first user feature satisfying the preset condition includes: the weight value is greater than or equal to the first user feature corresponding to the preset weight value, or the first user feature corresponding to the first preset number of weight values sorted in descending order of the weight value First User Feature.

In this case, by setting a threshold: the second preset risk level, the severity of the first target risk level is judged, so as to realize a prompt to the user about the preset disease. And by comparing the weight value occupied by each feature in the user feature with the preset weight value, or sorting the weight value occupied by each feature, output each user feature that has a greater impact on causing the preset disease, and prompt the user to achieve Giving accurate and targeted improvement suggestions also makes the improvement suggestions given more in line with the real situation of users.

In a possible design, when the prespecified disease includes obstructive sleep apnea and hypopnea syndrome, the key influencing factors include at least one of gender, age, degree of obesity, deviated nasal septum or craniofacial deformity . In this way, by setting specific key influence factors, it is beneficial to extract specific user characteristics corresponding to the key influence factors from the first facial image or the second facial image.

In a second aspect, a disease risk level prediction device is provided.

In a possible design, the disease risk level prediction apparatus is used to execute a disease risk level prediction method provided in the first aspect above. According to the method provided in the above-mentioned first aspect, the present application can divide the functional modules of the disease risk level prediction device. For example, each function module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. Exemplarily, the present application may divide the disease risk level prediction device into an information acquisition module, an image acquisition module, a feature acquisition module, a prediction module, and the like according to functions. For descriptions of possible technical solutions and beneficial effects performed by each of the above-divided functional modules, reference may be made to the technical solutions provided by the first aspect or its corresponding possible designs, which will not be repeated here.

In another possible design, the disease risk level prediction device includes: a memory and one or more processors, the memory and the processor being coupled. The memory is used for storing computer instructions, and the processor is used for invoking the computer instructions to perform any one of the methods provided by the first aspect and any possible design manners thereof.

In a third aspect, the present application provides a computer readable storage medium, such as a computer non-transitory readable storage medium. A computer program (or instruction) is stored thereon, and when the computer program (or instruction) runs on the disease risk level prediction device, the disease risk level prediction device is made to execute any one of the possible implementations of the first aspect. any method.

In a fourth aspect, the present application provides a computer program product that, when run on a computer, enables any one of the methods provided by any one of the possible implementations of the first aspect to be executed.

In a fifth aspect, the present application provides a chip system, including: a processor, where the processor is configured to call and run a computer program stored in the memory from a memory, and execute any one of the methods provided in the implementation manner of the first aspect.

In a sixth aspect, the present application provides a disease risk level prediction system, including: a first terminal and a second terminal. The first terminal is used to collect physiological information, and the second terminal processes the collected physiological information to predict disease risk levels. Alternatively, the disease risk level prediction system includes a third terminal, and the third terminal is configured to execute any one of the methods provided by the implementation manner in the first aspect.

It can be understood that any disease risk level prediction device, computer storage medium, computer program product or disease risk level prediction system provided above can be applied to the corresponding method provided above, therefore, it can achieve For the beneficial effects, reference may be made to the beneficial effects in the corresponding method, which will not be repeated here.

In this application, the names of the above-mentioned disease risk level prediction apparatus do not limit the devices or functional modules themselves, and in actual implementation, these devices or functional modules may appear in other names. As long as the functions of each device or functional module are similar to those of the present application, they fall within the scope of the claims of the present application and their equivalents.

These and other aspects of the present application will be more clearly understood from the following description.

Description of drawings

1 is one of the schematic diagrams of the architecture of a disease risk level prediction system provided by an embodiment of the present application;

FIG. 2 is the second schematic diagram of the architecture of the disease risk level prediction system provided by the embodiment of the present application;

3 is a schematic structural diagram of the connection between one of the disease risk level prediction systems provided by the embodiment of the present application and an information query system;

FIG. 4 is a schematic structural diagram of a terminal device provided by an embodiment of the present application;

FIG. 5 is one of the schematic flowcharts of the method for predicting disease risk level provided by the embodiment of the present application;

FIG. 6 is the second schematic flow chart of the method for predicting disease risk level provided by the embodiment of the present application;

FIG. 7 is a schematic diagram of a display interface of a second terminal of the disease risk level prediction method provided by the embodiment of the present application;

FIG. 8 is a schematic diagram of a disease risk level prediction device provided by an embodiment of the present application;

FIG. 9 is a schematic structural diagram of a chip system provided by an embodiment of the present application;

FIG. 10 is a conceptual partial view of a computer program product provided by an embodiment of the present application.

detailed description

The technical solutions in the present application will be described below with reference to the accompanying drawings.

1) Obstructive sleep apnea and hypopnea syndrome

Obstructive sleep apnea and hypopnea syndrome (OSAHS) is a sleep breathing disorder of unknown etiology characterized by nocturnal sleep snoring with apnea and daytime sleepiness. Repeated nocturnal hypoxia and hypercapnia caused by apnea can lead to complications such as hypertension, coronary heart disease, diabetes and cerebrovascular disease, traffic accidents, and even sudden death at night. Therefore OSAHS is a potentially fatal sleep breathing disorder.

2), nasal septum curvature

Deviated nasal septum is a structural deformity caused by the influence of certain factors during the development of the nasal septum. The shape is skewed to one or both sides, or partially protruded, which can affect the physiological function of the nasal cavity and cause a series of pathological changes. If the nasal septum is sharply protruding, it is called spinous process or calcaroid process; if it is elongated, it is called crista; In fact, the nasal septum is rarely completely straight, and often has different degrees of deviation, and the above-mentioned various forms can exist at the same time.

3), other terms

In the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations or illustrations. Any embodiments or designs described in the embodiments of the present application as "exemplary" or "such as" should not be construed as preferred or advantageous over other embodiments or designs. Rather, use of words such as "exemplary" or "such as" is intended to present the related concepts in a specific manner.

In the embodiments of the present application, the terms "first" and "second" are only used for description purposes, and cannot be understood as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature defined as "first" or "second" may expressly or implicitly include one or more of that feature.

In the description of this application, unless stated otherwise, "plurality" means two or more. The term "at least one" in this application means one or more.

It is to be understood that the terminology used in describing the various described examples herein is for the purpose of describing particular examples and is not intended to be limiting. As used in the description of the various described examples and the appended claims, the singular forms "a", "an")" and "the" are intended to include the plural forms as well, unless the context dictates otherwise. clearly instructed.

It will also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. The term "and/or" is an association relationship that describes an associated object, indicating that there can be three kinds of relationships, for example, A and/or B, which can mean that A exists alone, A and B exist simultaneously, and B exists alone. a situation. In addition, the character "/" in this application generally indicates that the related objects are an "or" relationship.

It should also be understood that, in each embodiment of the present application, the size of the sequence number of each process does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not be used in the embodiment of the present application. Implementation constitutes any limitation.

It should be understood that determining B according to A does not mean that B is only determined according to A, and B may also be determined according to A and/or other information.

It will also be understood that the term "includes" (also referred to as "includes", "including", "comprises" and/or "comprising") when used in this specification designates the presence of stated features, integers, steps, operations, elements , and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groupings thereof.

It should also be understood that the term "if" may be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting." Similarly, depending on the context, the phrases "if it is determined..." or "if a [statement or event] is detected" can be interpreted to mean "when determining..." or "in response to determining... ” or “on detection of [recited condition or event]” or “in response to detection of [recited condition or event]”.

It should be understood that references throughout the specification to "one embodiment," "an embodiment," and "one possible implementation" mean that a particular feature, structure, or characteristic related to the embodiment or implementation is included in the present application at least one embodiment of . Thus, appearances of "in one embodiment" or "in an embodiment" or "one possible implementation" in various places throughout this specification are not necessarily necessarily referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments.

Referring to FIG. 1 , FIG. 1 is one of the schematic diagrams of the architecture of the disease risk level prediction system provided by the embodiment of the present application. As shown in FIG. 1 , the disease risk level prediction system includes a first terminal 11 and a second terminal 12 .

As shown in FIG. 1 , the first terminal 11 is configured to collect physiological information related to a preset disease of the user, and then send the collected physiological information to the second terminal 12 . Physiological information includes, but is not limited to: pulse information, brain wave information, sound information, electrocardiogram information, oral and nasal airflow information, blood oxygen information or breathing information.

The first terminal 11 in this embodiment may include a smart watch with a function of acquiring physiological information, a smart bracelet, an eye patch, an oral bite device, a heart implantable device, an oral and nasal airflow sensor, a blood oxygen sensor, a bio-radar, a recording One or more of device, optical sensor, pulse wave sensor, heart rate sensor, acceleration sensor, gyroscope.

The second terminal 12 is configured to receive the physiological information of the user sent by the first terminal 11, acquire the first facial image of the user, and based on the first facial image, acquire the user's biological information corresponding to the key influencing factors of the preset diseases The first user characteristic, and then based on the first user characteristic and the physiological information, a first target risk level of the user suffering from the preset disease is predicted.

The second terminal 12 in this embodiment may be a smart bracelet, a smart watch, or a smart phone, etc., which has a photographing function and is installed with an APP that can predict a preset disease risk level.

Referring to FIG. 2 , FIG. 2 is the second schematic diagram of the architecture of the disease risk level prediction system provided by the embodiment of the present application. As shown in FIG. 2 , the disease risk level prediction system includes a third terminal 13 .

The third terminal 13 is configured to collect the physiological information of the user, obtain the first facial image of the user, and based on the first facial image, obtain the first user characteristic of the user corresponding to the key influencing factor of the preset disease, and then Based on the first user characteristics and physiological information, a first target risk level of the user suffering from a preset disease is predicted.

The third terminal 13 in this embodiment may be a smart bracelet, a smart watch, or a smart phone, etc., which has a function of acquiring physiological information, a function of taking a picture, and an APP that can predict a preset disease risk level.

Referring to FIG. 3 , FIG. 3 is a schematic structural diagram of the connection between one of the disease risk level prediction systems provided by the embodiment of the present application and the information query system. In this embodiment, the second disease risk level prediction system shown in FIG. 2 can also be used to connect with the information query system, and its effect is the same as that of the schematic structural diagram shown in FIG. It is not limited that a specific disease risk level prediction system is connected to the information query system.

As shown in FIG. 3 , the second terminal 12 in the disease risk level prediction system is connected to the information query system, specifically, the second terminal 12 (or the third terminal 13 ) is connected to the public security system 14 or the medical system 15 to realize information exchange , the information query system may include the public security system 14 or the medical system 15 .

The public security system 14 is used to store the user's identity information. The user feature extraction module in the second terminal 12 determines the user's facial features by using the acquired first facial image of the user. Then, based on the user's facial features, the user's identity information is obtained from the public security system 14, and then the user's first user characteristics are determined through the identity information. The first user characteristics obtained from the public security system 14 include, but are not limited to, first user characteristics such as gender, age, or weight.

The medical system 15 is configured to store the user's identity information, and the second terminal 12 determines the user's facial features from the user's first facial image obtained. Then, based on the user's facial features, the user's identity information is obtained from the medical system 15 , and then the user's first user characteristics are obtained from the medical system 15 through the identity information. The first user characteristics acquired from the medical system 15 include, but are not limited to: gender, age, weight, whether the nasal septum is deviated, whether there is a craniofacial deformity, and other first user characteristics.

Referring to FIG. 4 , FIG. 4 is a schematic structural diagram of a terminal device provided by an embodiment of the present application. The terminal device 30 may be the first terminal 11 or the second terminal 12 in FIG. 1 , or may be the third terminal 13 in FIG. 2 .

As shown in FIG. 4 , the terminal device 30 may include a processor 31 , a memory 32 , a communication interface 33 and a bus 34 . The processor 31 , the memory 32 and the communication interface 33 may be connected through a bus 34 .

The processor 31 is the control center of the terminal device 30, and may be a general-purpose central processing unit (central processing unit, CPU) or other general-purpose processors. Wherein, the general-purpose processor may be a microprocessor or any conventional processor.

As an example, processor 31 may include one or more CPUs, such as CPU0 and CPU1 shown in FIG. 4 .

The memory 32 may be read-only memory (ROM) or other type of static storage device that can store static information and instructions, random access memory (RAM) or other type of static storage device that can store information and instructions A dynamic storage device that can also be an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium, or other magnetic storage device, or can be used to carry or store instructions or data structures with in the form of desired program code and any other medium that can be accessed by a computer, but is not limited thereto.

In a possible implementation, the memory 32 may exist independently of the processor 31 . The memory 32 may be connected to the processor 31 through a bus 34 for storing data, instructions or program codes. When the processor 31 calls and executes the instructions or program codes stored in the memory 32, the prediction method provided by the embodiments of the present application can be implemented.

In another possible implementation manner, the memory 32 may also be integrated with the processor 31 .

The communication interface 33 is used for connecting the terminal device 30 with other devices (such as servers, etc.) through a communication network, and the communication network can be an Ethernet, a radio access network (RAN), a wireless local area network (wireless local area networks, WLAN), etc. The communication interface 33 may include a receiving unit for receiving data, and a transmitting unit for transmitting data.

The bus 34 can be an industry standard architecture (Industry Standard Architecture, ISA) bus, a peripheral device interconnect (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus and the like. The bus can be divided into address bus, data bus, control bus and so on. For ease of presentation, only one thick line is used in FIG. 4, but it does not mean that there is only one bus or one type of bus.

It should be pointed out that the structure shown in FIG. 4 does not constitute a limitation on the terminal device 30. In addition to the components shown in FIG. 4, the terminal device 30 may include more or less components than those shown in the figure, or Combining certain components, or different component arrangements.

The embodiments of the present application provide a disease risk level prediction method and apparatus, and the method can be applied to the first terminal 11 or the second terminal 12 shown in FIG. 1 or the third terminal 13 shown in FIG. 2 . Specifically, the method can be applied to the terminal device 30 shown in FIG. 4 . When the method is applied to the terminal device 30 shown in FIG. 4 , the processor 31 can execute the program instructions in the memory 32 to realize the implementation of the present application. Examples of disease risk level prediction methods provided. By executing the disease risk level prediction method provided in the embodiment of the present application, the risk level of the user suffering from a preset disease can be more accurately predicted.

The disease risk level prediction method provided by the embodiments of the present application will be described below with reference to the accompanying drawings.

Example 1

The disease risk level prediction method adopted in this embodiment may be applied to the disease risk level prediction system shown in FIG. 1 . Please refer to FIG. 5 , which shows a schematic flowchart of a method for predicting a disease risk level provided by an embodiment of the present application. The method may include the following steps:

S101 , the first terminal 11 acquires the physiological information of the user, and transmits it to the second terminal 12 .

As shown in FIG. 1 , the physiological information of the user is acquired through the first terminal 11 .

Physiological information includes, but is not limited to: one or more of brain wave information, sound information, electrocardiogram information, mouth and nose airflow information, blood oxygen information, breathing information, sleep time, body motion information or pulse information. The example does not impose specific restrictions on this.

The embodiments of the present application are described by taking the first terminal 11 as a smart watch having a function of acquiring physiological information as an example.

The smart watch obtains the user's physiological information, such as blood oxygen information or breathing information, and determines the user's sleep time and sleep end time, and calculates the user's sleep time according to the user's sleep time and sleep end time. Then, the smart watch determines the number of apnea times of the user during the sleep period by combining the obtained blood oxygen information or breathing information and combining with the user's sleep time. Then, all the data obtained by the smart watch is transmitted to the second terminal 12. The transmission method can be data line transmission, Bluetooth transmission, network transmission or other transmission methods. This embodiment does not limit the specific transmission method.

S102. The second terminal 12 predicts, based on the physiological information of the user, a first risk level of the user suffering from a preset disease.

The embodiments of the present application are described by taking as an example that the second terminal 12 is a smart phone with a camera function and an APP that can predict a preset disease risk level is installed.

After receiving the physiological information obtained by the smart watch, the second terminal 12 determines the first risk level of the user suffering from a preset disease according to the blood oxygen information, breathing information, sleep time and the number of apnea of the user. For a specific implementation manner, reference may be made to the prior art.

S103. The second terminal 12 acquires the first facial image of the user.

After acquiring the first risk level of the user suffering from the preset disease, the second terminal 12 may directly perform the operation of acquiring the first facial image of the user.

Alternatively, after acquiring the first risk level of the user suffering from the preset disease, the second terminal 12 may determine whether it is necessary to acquire the first risk level of the user according to the level of the first risk level and/or the occurrence number of the first risk level. a face image.

Optionally, the second terminal 12 may determine whether to acquire the user's first facial image according to the following conditions.

Manner 1: within a first preset time period, obtain at least two first risk levels of the user suffering from a preset disease; determine a first risk greater than or equal to the first preset risk level among the at least two first risk levels The number of occurrences of the level; when the number of occurrences is greater than or equal to the first preset number of times, the first facial image of the user is acquired.

It should be noted that, the first preset time period in this embodiment can be determined according to the number of times of obtaining physiological information and the frequency of obtaining physiological information. The first preset time period may be set to three days; if five acquisitions are required and the acquisition frequency remains unchanged, the first preset time period may be set to five days. The first preset number of times in this embodiment may be determined according to experience or corresponding medical statistical rules. If physiological information needs to be acquired three times in total within the first preset time period, the first preset number of times may be set to one or two times; if the physiological information needs to be acquired five times in total within the first preset time period, the first preset number of times may be set to three times. The specific settings of the first preset time period and the first preset number of times are not specifically limited in this embodiment of the present application.

Exemplarily, the first terminal 11 acquires the physiological information of the user at least twice within the first preset time period, and then transmits the acquired physiological information each time to the smartphone. The second terminal 12 analyzes the received physiological information each time, and predicts the first risk level of the user suffering from a preset disease. For example, the smart watch obtains the user's physiological information three times within three days, and each time it obtains the physiological information and transmits it to the smartphone, the smartphone obtains a total of three first-risk results.

After the number of occurrences of the first risk level within the first preset time period is determined, the level situation of each occurrence of the first risk level is also determined. Therefore, a first preset risk level is set, and the first preset risk level may be a specific threshold for determining the level of the first risk level that occurs each time. For example, the first risk level is greater than or equal to the first risk level. The preset risk level is a high risk level; the first risk level is lower than the first preset risk level and is a low risk level.

It should be noted that, the first preset risk level in this embodiment may be determined according to an apnea-hypopnea index (Apnea-hypopnea index, AHI) or a respiratory disturbance index (Respiratory disturbance index, RDI), or according to experience It is determined that the apnea-hypopnea index and the respiratory disorder index are indexes in the existing medicine, which will not be repeated here.

When the three first risk levels obtained by the smartphone are respectively a high risk level, a low risk level and a high risk level, it means that two of the three first risk levels obtained by the smartphone have the first risk level greater than or Equal to the case of the first preset level. When the first preset number of times is 2, it means that the number of occurrences of the first risk level greater than or equal to the first preset level is greater than or equal to the first preset number of times, and at this time, the second terminal 12 is triggered to acquire the first facial image conditions of.

The second terminal 12 acquires the first face of the user when the occurrence number of the first risk level of the at least two first risk levels that is greater than or equal to the first preset risk level is greater than or equal to the first preset number of times The image can avoid the first risk level prediction error caused by the user's physiological information acquisition error, thereby causing the user's first target risk level to suffer from a preset disease. The accuracy of the first target level.

Mode 2: within a first preset time period, obtain at least two first risk levels of the user suffering from a preset disease; determine a first risk greater than or equal to the first preset risk level among the at least two first risk levels The number of occurrences of the level; when the number of occurrences of the first risk level greater than or equal to the first preset level is greater than or equal to the second preset number of times, and the first risk level is greater than or equal to the first preset level, it is a continuous occurrence, Get the first face image of the user.

Exemplarily, when the smartphone obtains three results of the first risk level, and the first risk levels obtained three times are respectively a low risk level, a high risk level, and a high risk level. And when the second preset number of times is 2, it means that the number of occurrences of the first risk level greater than or equal to the first preset level is greater than or equal to the second preset number of times, and the first risk level is greater than or equal to the first preset number The level is continuous, at which time the smartphone acquires the user's first face image.

The acquisition is triggered only when the number of occurrences of the first risk level greater than or equal to the first preset risk level is greater than or equal to the second preset number, and the first risk level greater than or equal to the first preset risk level is a continuous occurrence The condition of the user's first facial image can realize that the user's first risk level is not erroneously predicted, thereby improving the prediction accuracy of the first risk level, and further improving the first target level of predicting that the user suffers from a preset disease. accuracy.

It should be noted that, in addition to acquiring the first facial image of the user, a full-body image of the user, a partial image of the user, etc. can also be acquired, and then the first facial image of the user can be acquired from the full-body image or the partial image of the user, This embodiment of the present application does not specifically limit this. In addition, other physiological information of the user can also be obtained through the whole body image or the partial image of the user. For example, the degree of obesity of the user cannot be identified only by acquiring the first facial image of the user, and the degree of obesity of the user can be determined by acquiring the whole body image of the user.

Method 3: The second terminal 12 obtains the first risk level of the user suffering from a preset disease, and then compares it with the first preset risk level, and if the first risk level is greater than or equal to the first preset risk level, obtains the user first facial image.

By setting the first preset risk level as a threshold, it is determined whether the first risk level is a high-risk level or a low-risk level, so as to determine whether to acquire the user's first facial image, which realizes the necessity of acquiring the user's first facial image. It can be realized that the first face image of the user is not acquired when the first risk level is a low risk level.

For S103, it can be implemented in the following ways:

Manner 1: When the second terminal 12 determines that the conditions for obtaining the user's first facial image (such as but not limited to any of the conditions provided above) are currently met, output prompt information; receive the user's operation, and based on This operation captures a first face image of the user.

For example, prompt information for obtaining the user's first facial image is popped up on the display interface of the second terminal 12; a touch operation of the user on the prompt information is received, and the touch operation is to instruct the second terminal 12 to obtain the user's first facial image. case, take a first face image of the user.

As shown in FIG. 7 , the user performs a touch operation on the prompt information in the display interface, and when the second terminal 12 receives the user's touch operation to instruct the second terminal 12 to obtain the user's first face image, call the The photographing device of the second terminal 12 photographs the first facial image of the user.

For another example, the prompt information is output in the form of voice. After the user receives the prompt voice, the user performs a touch operation on the display interface, and the second terminal 12 receives the user's touch operation to instruct the second terminal 12 to obtain the user's first face. In the case of an image, the photographing device of the second terminal 12 is called to photograph the first facial image of the user.

In this embodiment, the prompt information can also be output in other forms, and the user's operation can also be fed back to the second terminal 12 in the form of keys. This embodiment does not limit the specific output form of the prompt information and the specific form of receiving user operation feedback .

Manner 2: When the second terminal 12 detects the user, acquire the first facial image of the user.

For example, when the user views the interface of the second terminal 12, the user's first facial image is directly photographed. In this manner, there is no need to prompt the user to perform an operation to capture the first face image, and in the case of detecting the user, the first face image is captured to achieve sensorless shooting.

Manner 3: Acquire at least two images, and fuse the at least two images into a first facial image.

The first face images of the user are captured multiple times. Since the obtained at least two first face images may be partial images in which only partial faces of the user are captured, the at least two partial images may be fused into the first face of the user. part image.

By fusing the at least two partial images into the first facial image, the first facial image can include as many facial features of the user as possible, thereby realizing the accuracy of predicting the first target risk level of the user suffering from a preset disease. The first facial image fused into at least two partial images may not contain all the facial features of the user. In order to further improve the accuracy of predicting the first target risk level of the user suffering from a preset disease, the Until the first facial image fused from multiple partial images contains all facial features.

S104. The second terminal 12 acquires, based on the first facial image, the first user characteristic of the user corresponding to the key influencing factor of the preset disease.

In this embodiment, when the preset disease includes obstructive sleep apnea and hypopnea syndrome, the key influencing factors include at least one of gender, age, degree of obesity, whether the nasal septum is deviated or whether it is craniofacial deformity. The default disease is obstructive sleep apnea and hypopnea syndrome as an example to illustrate.

Exemplarily, the key influencing factors of the preset disease are determined, the first facial image and the key influencing factors of the preset disease are used as input data, and are input into the first prediction model, from the first facial image, based on the preset The key influencing factors of diseases, and the first user characteristics of users are obtained.

In one example, when the key influencing factors include gender, age, degree of obesity, whether there is a deviated septum or whether there is a craniomaxillofacial deformity, the acquired first user characteristics are: male, 46 years old, obese, with deviated nasal septum and Craniomaxillofacial deformities are present.

Obtaining the first user characteristics of the user corresponding to the key influencing factor of the preset disease may specifically include:

Facial features in the first facial image are identified, wherein the facial features include but are not limited to at least one of the following: eyes, nose, mouth, eyebrows, or facial features such as whether there is a beard. The age of the user can be determined based on the facial features of the eyes, and the gender of the user can be determined based on the facial features of whether there is a beard. Through image recognition technology, identify whether the facial features in the first facial image contain a curvature of the nasal septum or whether it is a craniomaxillofacial deformity. The identified feature is used as the first user feature of the user corresponding to the key influencing factor of the preset disease.

For S104, it may specifically include: recognizing the facial features of the first facial image, based on the facial features, acquiring the identity information of the user corresponding to the key influencing factor of the preset disease from the information query system, and determining the first user feature based on the identity information .

It should be noted that the information query system may include the public security system 14 or the medical system 15 .

In one example, the information query system is the public security system 14, which recognizes the facial features of the first facial image, and queries the identity information of the corresponding user from the information query system according to the facial features. The public security system 14 stores the identity information of the corresponding user. It should be noted that the identity information includes but is not limited to: age, weight, gender, home address or educational background and other identity information.

Obtaining the identity information corresponding to the key influencing factors of the preset disease in the identity information, and determining the part of the identity information as part of the first user characteristics of the user. For example, the identity information such as gender, weight, and age in the user's identity information is obtained as part of the first user characteristics. For other first user characteristics of the user, the first facial image needs to be identified after image recognition, for example: through the image A first user characteristic is identified that determines whether the nasal septum is deviated or whether a craniomaxillofacial deformity is present in the first facial image of the user.

The public security system 14 is used to determine some of the first user characteristics of the user. Since the image recognition technology may cause deviations or inaccurate identification of the first user characteristics of the user, the public security system 14 determines some of the first user characteristics of the user, so that the The accuracy of the obtained first user feature is higher.

In another example, the information query system is the medical system 15, which identifies the facial features of the first facial image, and from the medical system 15, obtains the user's family genetic history of a predetermined disease, whether the nasal septum is deviated, or whether the user is craniofacial or not. Deformity and other identification information. Some of the first user characteristics are determined based on the user's identity information such as the user's family genetic history of a preset disease, whether the nasal septum is deviated or whether there is a craniofacial deformity, and the user's age, gender, weight and other information are obtained based on image recognition.

It should be noted that, when the medical system 15 is included in the embodiment, the key influencing factors of the preset disease also include the family genetic history of the preset disease.

Using the medical system 15 to determine part of the first user characteristics of the user can increase the accuracy of the obtained first user characteristics of the user, thereby improving the accuracy of predicting the first target risk level of the user suffering from a preset disease.

In another example, the information query system includes a medical system 15 and a public security system 14, recognizes the facial features of the first facial image, and determines from the public security system 14 and the medical system 15, respectively, the user's key influencing factors corresponding to preset diseases For example, obtain the first user characteristics such as the family genetic history of the user's preset disease, whether the nasal septum is crooked or whether it is craniofacial deformity from the medical system 15; obtain the user's age, weight or gender from the public security system 14 and so on for the first user characteristics. Part of the first user characteristics of the user obtained from the public security system 14 and the medical system 15 respectively are integrated into the first user characteristics of the user.

For determining the first user characteristic of the user based on the identity information, it can be implemented in the following ways:

Manner 1: With reference to FIG. 1 , based on the second terminal 12, the first user characteristic of the user is directly determined from the identity information according to the key influencing factor of the preset disease.

In this manner, the first user characteristic of the user is directly acquired through the second terminal 12 .

Manner 2: The user's identity information is output and displayed on the display interface of the second terminal 12 , the user selects based on the output identity information, and the first user characteristic of the user is determined according to the user's selection.

S105. The second terminal 12 predicts the first target risk level of the user suffering from a preset disease based on the physiological information and the first user characteristic.

In one example, in the case of acquiring the physiological information only once, the second terminal 12 may predict the first target risk level of the user suffering from a preset disease based on the physiological information and the first user characteristics; the second terminal 12 may also Based on the first risk level predicted based on the physiological information and the first user characteristic, the first target risk level of the user suffering from the preset disease is predicted.

In another example, after getting at least

In the case of two physiological information, the second terminal 12 can predict the first target risk level of the user suffering from the preset disease in the following manner:

Method 1: At least two uses based on acquisition

The user's physiological information related to the preset disease and the first user characteristics are used to predict the first target risk level of the user suffering from the preset disease.

Example 1: The first target risk level of the user suffering from a preset disease may be predicted by determining the latest physiological information among the physiological information at least twice, that is, the most recently obtained physiological information, combined with the first user feature.

Example 2: The first target risk level of the user suffering from a preset disease may be predicted based on the physiological information obtained by the synthesis or combination and the first user characteristic by combining or integrating each of the at least two physiological information .

The method for obtaining the physiological information in combination may be: for example, obtaining the physiological information of the user three times in total, the physiological information obtained each time includes: blood oxygen information, breathing information and sleep time, and the blood oxygen information obtained for the first time, the blood oxygen information obtained for the first time, the The respiration information obtained in the second time and the sleep time obtained in the third time are combined to obtain a complete physiological information.

The method of comprehensively obtaining the physiological information may be: for example, obtaining the physiological information of the user three times in total, the physiological information obtained each time includes: blood oxygen information, breathing information and sleep time, and obtaining the blood oxygen information and breathing information obtained three times respectively and the respective expected values of sleep time, combining the expected values of each information into a complete physiological information.

This embodiment only illustrates the method for obtaining physiological information by synthesis or combination, and does not limit the specific method. In actual situations, those skilled in the art can solve the problem based on experience or preset medical statistical laws of diseases.

Manner 2: Determine a first comprehensive risk level based on at least two first risk levels, and predict a first target risk level at which the user suffers from a preset disease based on the first comprehensive risk level and the first user characteristics.

It should be noted that the first comprehensive risk level may be determined according to experience, or may be determined according to a statistical rule corresponding to a preset disease. Specifically: the first risk level with the highest level among the at least two first risk levels may be used as the first comprehensive risk level; or the first risk level with the highest frequency among the at least two first risk levels may be used as the first comprehensive risk level level; or a first risk level that accounts for more than a certain ratio among at least two first risk levels. The ratio is generally set to be greater than or equal to 50%, so as to prevent the proportion of two or more first risk levels from exceeding the ratio at the same time. If the ratio is less than 50%, and the proportion of at least two first risk levels simultaneously exceeds the ratio, the first risk level with the largest proportion is used as the first comprehensive risk level.

The second terminal 12 adjusts the first risk level (or the first comprehensive risk level) based on the first user characteristics, so as to predict that the user suffers from a first target risk level of a preset disease.

In one example, the first user characteristic and the first risk level (or the first comprehensive risk level) are input into the second prediction model, and the first target risk level of the user suffering from the preset disease is output.

The second prediction model can be established as follows:

By acquiring the first user characteristics, the first risk level (or the first comprehensive risk level) and the first target risk level of a plurality of users with preset diseases, and combining the first user characteristics, the first risk level of each user A one-to-one correspondence is established between the level (or the first comprehensive risk level) and the first target risk level, and the acquired first user characteristics, the first risk level (or the first comprehensive risk level) and the first target risk level are trained to obtain a second prediction model.

Optionally, after obtaining the first target risk level of the user suffering from a preset disease in S105, the second facial image of the user can be obtained at a first preset interval after the time when the first facial image of the user is obtained. . Based on the second facial image, a second user characteristic corresponding to the key influencing factor of the user suffering from a preset disease is obtained; then, according to the physiological information and the second user characteristic, a second target risk level of the user suffering from the preset disease is predicted.

After the first preset interval time, the second facial image of the user is actively acquired, the update of the first facial image is realized, the real-time performance of the acquired facial image of the user is improved, and the acquired facial image based on the second facial image is also updated. The second user feature of the user corresponding to the key influencing factor of the preset disease, which improves the real-time performance and accuracy of the second user feature. Thus, the real-time performance and accuracy of the second target risk level of the user suffering from the preset disease predicted based on the first risk level and the second user characteristics are improved.

Optionally, after obtaining the first target risk level of the user suffering from a preset disease in S105, the third facial image of the user can be obtained at a second preset interval after the time when the first facial image of the user is obtained. . In the case that the third facial image is changed compared to the first facial image, based on the third facial image, obtain the third user feature corresponding to the key influencing factor that the user suffers from the preset disease; then, according to the first risk level and the third user feature to predict the third target risk level of the user suffering from the preset disease.

After the second preset interval time, by acquiring the third facial image of the user, if the third facial image is changed compared with the first facial image, then based on the third facial image, the corresponding key influencing factors of the preset disease are acquired. The third user characteristic of the user, based on the first risk level and the third user characteristic, predicts a third target risk level of the user suffering from a preset disease. In this case, only when the third facial image changes relative to the first facial image, the third target risk level of the user suffering from the preset disease is re-predicted by using the third facial image, which improves real-time performance and accuracy at the same time. Compared with the above, directly updating the first facial image after acquiring the second facial image, and predicting the second target risk level of the user suffering from the preset disease based on the updated second facial image, reduces the workload of the system .

It should be noted that the preset interval time includes the first preset interval time and the second preset interval time, which may be 3 days, 10 days, or 15 days, etc. The preset time interval is generally determined based on experience, and the embodiment of the present application There is no specific restriction on this.

Optionally, after S105, when the first target risk level is greater than or equal to the second preset risk level, prompt information is output.

Wherein, the prompt information includes: a first user characteristic that satisfies a preset condition.

The first user characteristic that satisfies the preset condition can be determined in the following ways:

Manner 1: The weight value is greater than or equal to the first user feature corresponding to the preset weight value.

Each first user feature has a certain weight when it affects whether the user has a preset disease. For example, through a study of existing cases of obstructive sleep apnea and hypopnea syndrome, it was found that the first user characteristics included gender, age, degree of obesity, whether there was a deviated nasal septum, and whether there was a craniofacial deformity. Wherein, the weight value of whether the user's gender is male affects whether the user has the disease is greater than the weight value of the user's gender affecting whether the user has the disease. The weight value of whether the age is greater than the preset age affects whether the disease is affected, and the weight value of the age greater than or equal to the preset age affects whether the disease has the disease. The degree of obesity is the weight value of obesity on whether or not to have the disease, and the degree of greater than obesity is the weight value of leanness on whether or not to have the disease. The weight value of severe nasal septal deviance affects whether or not to have the disease, which is greater than the weight value of mild nasal septal deviation to affect whether or not to have the disease. Severe craniomaxillofacial deformity has a weight on whether or not to have the disease, which is greater than the weight value of mild craniomaxillofacial deformity on whether or not to have the disease.

Determine the weight value of each first user feature of the user, and compare the weight value of each first user feature with a preset weight value, determine that the weight value is greater than or equal to the first user feature corresponding to the preset weight value, and use the determined weight value. The first user feature output. To prompt the user: the outputted first user characteristics cause the user to have a high first target risk level of a preset disease, so as to prompt the user to pay attention to this aspect. For example, if the weights of obesity and age 50 in the first user feature of the user are both greater than or equal to the preset weight value, then the two first user features of obesity and age are displayed on the display interface of the second terminal 12, Or output in the form of voice broadcast to prompt the user that obesity and age are the reasons for the high first target risk level of the user suffering from the preset disease.

The prompt information output by the second terminal 12, in addition to the first user feature corresponding to the weight value greater than or equal to the preset weight value, may also be based on the first user feature corresponding to the weight value greater than or equal to the preset weight value. Suggested information. For example, if the user's first target risk level for a preset disease is a high risk level, and the first user feature whose weight value is greater than or equal to the preset weight value is obesity, the output suggestion information may be: Please do appropriate sports.

In this embodiment, a threshold of the first target risk level can be determined. If the first target risk level is greater than or equal to the threshold, the first target risk level is determined to be a high risk level; otherwise, it is a low risk level.

Method 2: The first user features corresponding to the first preset number of weight values after the weight values are sorted in descending order.

It should be noted that the first preset number may be one, two, or three, etc. The first preset number may be determined based on experience, which is not specifically limited in this embodiment of the present application.

Exemplarily, if it is determined that the first user characteristic of the user is female, 25 years old, obese, and has craniofacial deformity, the weight values of female, 25 years old, obesity, and existence of craniomaxillofacial deformity are sorted in descending order. , the user's first user features are sorted as follows: obesity, craniomaxillofacial deformity, female, 25 years old, and the first preset number is 2, then it is determined that the output first user features are: obesity and craniomaxillofacial deformity. Suggested information can also be output, such as advice on weight loss and adjustment for craniofacial deformities.

In addition to sorting the weight values of the first user features from large to small, you can also sort the weight values of the first user features from small to large, and obtain the first user corresponding to the first preset number of weight values after sorting. feature.

Embodiment 2

The disease risk level prediction method adopted in this embodiment may be applied to the disease risk level prediction system shown in FIG. 2 . The embodiments of the present application are described by taking the third terminal 13 as an example of a smart bracelet having a function of acquiring physiological information, a function of taking pictures, and an APP installed with an APP that can predict a preset disease risk level.

Please refer to FIG. 6. FIG. 6 shows the second schematic flowchart of a method for predicting a disease risk level provided by an embodiment of the present application. The method may include the following steps:

S201. The third terminal 13 acquires the physiological information of the user.

S202 , the third terminal 13 predicts the first risk level of the user suffering from a preset disease based on the physiological information of the user.

S203. The third terminal 13 acquires the first facial image of the user.

S204 , the third terminal 13 acquires, based on the first facial image, the first user characteristic of the user corresponding to the key influencing factor of the preset disease.

S205 , the third terminal 13 predicts the first target risk level of the user suffering from a preset disease based on the physiological information and the first user characteristic.

Optionally, after obtaining the first target risk level of the user suffering from a preset disease in S205, the second facial image of the user can be obtained at a first preset interval after the time when the first facial image of the user is obtained. . Based on the second facial image, obtain the second user feature corresponding to the key influencing factor of the user suffering from the preset disease; then, predict the second target risk of the user suffering from the preset disease according to the first risk level and the second user feature grade.

Optionally, after obtaining the first target risk level of the user suffering from a preset disease in S205, the third facial image of the user can be obtained at a second preset interval after the time when the first facial image of the user is obtained. . In the case that the third facial image is changed compared to the first facial image, based on the third facial image, obtain the third user feature corresponding to the key influencing factor that the user suffers from the preset disease; then, according to the first risk level and the third user feature to predict the third target risk level of the user suffering from the preset disease.

Optionally, after S205, when the first target risk level is greater than or equal to the second preset risk level, prompt information is output.

The functions and functions of the third terminal 13 in this embodiment are equivalent to the combination of the functions and functions of the first terminal 11 and the functions and functions of the second terminal 12 in the first embodiment. The technical solutions and benefits of each step in this embodiment are For the description of the effect, reference may be made to the description of the corresponding steps in the above-mentioned first embodiment, which will not be repeated here.

The solutions provided by the embodiments of the present application have been introduced above mainly from the perspective of methods. In order to realize the above-mentioned functions, it includes corresponding hardware structures and/or software modules for executing each function. Those skilled in the art should easily realize that the present application can be implemented in hardware or a combination of hardware and computer software with the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein. Whether a function is performed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

In the embodiments of the present application, the disease risk level prediction apparatus may be divided into functional modules according to the above method examples. For example, each functional module may be divided into each function, or two or more functions may be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. It should be noted that, the division of modules in the embodiments of the present application is schematic, and is only a logical function division, and there may be other division manners in actual implementation.

As shown in FIG. 8 , FIG. 8 is a schematic diagram of a disease risk level prediction apparatus provided by an embodiment of the present application. The disease risk level prediction apparatus is used for executing the above-mentioned disease risk level prediction method, for example, the disease risk level prediction method shown in FIG. 5 . For example, the disease risk level prediction apparatus may include: an information acquisition module 1 , an image acquisition module 2 , a feature acquisition module 3 and a prediction module 4 .

The information acquisition module 1 is used for acquiring the physiological information related to the preset disease of the user. An image acquisition module 2, configured to acquire a first facial image of the user. The feature acquisition module 3 is configured to acquire, based on the first facial image, the first user feature of the user corresponding to the key influencing factor of the preset disease. The prediction module 4 is configured to predict the first target risk level of the user suffering from the preset disease based on the physiological information and the first user characteristic.

5 , the information acquisition module 1 may perform S101 and/or S102, the image acquisition module 2 may perform S103, the feature acquisition module 3 may perform S104, and the prediction module 4 may perform S105.

Optionally, the information obtaining module 1 is specifically configured to: within the first preset time period, obtain the physiological information related to the preset disease of the user at least twice.

The prediction module 4 is specifically configured to: predict the first target risk level of the user suffering from the preset disease based on the obtained physiological information related to the preset disease of the user at least twice and the first user characteristic. Or, based on the physiological information obtained each time, predict the first risk level of the user suffering from the preset disease; based on at least two first risk levels and the first user characteristics, predict the first target risk of the user suffering from the preset disease grade.

Optionally, the image acquisition module 2 is specifically configured to acquire the first facial image of the user when the number of occurrences is greater than or equal to the first preset number of times. Or, in the case that the number of occurrences is greater than or equal to the second preset number of times, and the first risk level of at least two first risk levels greater than or equal to the first preset risk level is a continuous occurrence, obtain the first risk level of the user. face image.

Optionally, the image acquisition module 2 is specifically configured to: acquire at least two images, wherein the at least two images are images of a local area including the face image of the user, and the at least two images are fused into the first facial image.

Optionally, the feature acquisition module 3 is specifically configured to: identify the facial features in the first facial image; based on the facial features, obtain the key influencing factors related to the preset disease from the information query system Corresponding identity information of the user, and determining the first user characteristic based on the identity information.

Optionally, the image acquisition module 2 is further configured to acquire the second facial image of the user. The feature acquisition module 3 is further configured to acquire, based on the second facial image, the user suffering from the preset when the second facial image changes relative to the first facial image. The second user characteristics corresponding to the key influencing factors of the disease. The prediction module 4 is further configured to predict the second target risk level of the user suffering from the preset disease based on the physiological information and the second user characteristic.

Optionally, the disease risk level prediction device further includes: a prompt module, configured to output prompt information when the first target risk level is greater than or equal to a second preset risk level, wherein the prompt information includes: The first user characteristic that satisfies a preset condition.

The first user feature satisfying the preset condition includes: the weight value is greater than or equal to the first user feature corresponding to the preset weight value; The first user feature corresponding to the weight value.

Optionally, when the preset disease predicted by the disease risk level prediction device includes obstructive sleep apnea and hypopnea syndrome, the key influencing factors include gender, age, degree of obesity, whether the nasal septum is deviated or whether there is a craniofacial deformity. at least one of.

For the specific description of the foregoing optional manners, reference may be made to the foregoing method embodiments, which will not be repeated here. In addition, for the explanation of any disease risk level prediction device provided above and the description of the beneficial effects, reference may be made to the above-mentioned corresponding method embodiments, which will not be repeated.

As an example, with reference to FIG. 4 , some or all of the functions implemented by the information acquisition module 1 , the image acquisition module 2 , the feature acquisition module 3 and the prediction module 4 in the disease risk level prediction device may be executed by the processor in FIG. 4 . 4 is implemented in the program code in memory.

An embodiment of the present application further provides a chip system. As shown in FIG. 9 , the chip system 100 includes at least one processor 110 and at least one interface circuit 120 . As an example, when the system-on-a-chip 100 includes a processor and an interface circuit, the processor may be the processor 110 shown in the solid line box in FIG. 9 (or the processor 110 shown in the dotted line box), The one interface circuit may be the interface circuit 120 shown in the solid line box in FIG. 9 (or the interface circuit 120 shown in the dotted line box). When the chip system 100 includes two processors and two interface circuits, the two processors include the processor 110 shown in the solid line box and the processor 110 shown in the dotted line box in FIG. 9 , the two interfaces The circuit includes the interface circuit 120 shown in the solid line box and the interface circuit 120 shown in the dashed line box in FIG. 9 . This is not limited.

The processor 110 and the interface circuit 120 may be interconnected by wires. For example, the interface circuit 120 may be used to receive signals (eg, from a vehicle speed sensor or an edge service unit). As another example, the interface circuit 120 may be used to send signals to other devices (eg, the processor 110). Exemplarily, the interface circuit 120 may read the instructions stored in the memory and send the instructions to the processor 110 . When the instructions are executed by the processor 110, the apparatus for predicting the disease risk level can be made to perform each step in the above embodiment. Certainly, the chip system may also include other discrete devices, which are not specifically limited in this embodiment of the present application.

Another embodiment of the present application further provides a computer-readable storage medium, where an instruction is stored in the computer-readable storage medium. When the instruction is executed on the disease risk level prediction apparatus, the disease risk level prediction apparatus executes the above method embodiments Each step performed by the disease risk level prediction device in the shown method flow.

In some embodiments, the disclosed methods may be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of manufacture.

FIG. 10 schematically shows a conceptual partial view of a computer program product provided by an embodiment of the present application, where the computer program product includes a computer program for executing a computer process on a computing device.

In one embodiment, the computer program product is provided using the signal bearing medium 130 . The signal bearing medium 130 may include one or more program instructions that, when executed by one or more processors, may provide the functions, or portions thereof, described above with respect to FIG. 5 . Thus, for example, reference to one or more features of S101 - S105 in FIG. 5 may be undertaken by one or more instructions associated with the signal bearing medium 130 . Additionally, the program instructions in Figure 10 also describe example instructions.

In some examples, the signal bearing medium 130 may include a computer readable medium 131 such as, but not limited to, a hard drive, a compact disc (CD), a digital video disc (DVD), a digital tape, a memory, a read only memory (read only memory) -only memory, ROM) or random access memory (RAM), etc.

In some implementations, the signal bearing medium 130 may include a computer recordable medium 132 such as, but not limited to, memory, read/write (R/W) CDs, R/W DVDs, and the like.

In some embodiments, signal bearing medium 130 may include communication medium 133, such as, but not limited to, digital and/or analog communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

Signal bearing medium 130 may be conveyed by a wireless form of communication medium 133 (eg, a wireless communication medium that conforms to the IEEE 802.11 standard or other transmission protocol). The one or more program instructions may be, for example, computer-executable instructions or logic-implemented instructions.

In some examples, a disease risk level prediction apparatus such as that described with respect to FIG. 10 may be configured, in response to one or more program instructions via computer readable medium 131 , computer recordable medium 132 , and/or communication medium 133 , , which provides various operations, functions, or actions.

It should be understood that the arrangements described herein are for illustrative purposes only. Thus, those skilled in the art will understand that other arrangements and other elements (eg, machines, interfaces, functions, sequences, and groups of functions, etc.) can be used instead and that some elements may be omitted altogether depending on the desired results . Additionally, many of the described elements are functional entities that may be implemented as discrete or distributed components, or in conjunction with other components in any suitable combination and position.

In the above-mentioned embodiments, it may be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer-executed instructions are loaded and executed on the computer, the flow or function according to the embodiments of the present application is generated in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device. Computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server, or data center over a wire (e.g. coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (eg infrared, wireless, microwave, etc.) means to transmit to another website site, computer, server or data center. Computer-readable storage media can be any available media that can be accessed by a computer or data storage devices including one or more servers, data centers, etc., that can be integrated with the media. Useful media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media (eg, solid state disks (SSDs)), and the like.

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention. should be included within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

A disease risk level prediction method, characterized in that the method comprises:

Obtain the user's physiological information related to the preset disease;

obtaining a first facial image of the user;

obtaining, based on the first facial image, the first user characteristic of the user corresponding to the key influencing factor of the preset disease;

Based on the physiological information and the first user characteristic, a first target risk level of the user suffering from the preset disease is predicted.
The method according to claim 1, wherein the acquiring the physiological information related to the preset disease of the user comprises:

Acquire the physiological information related to the preset disease of the user at least twice within the first preset time period;

The predicting the first target risk level of the user suffering from the preset disease based on the physiological information and the first user characteristic includes:

Predicting a first target risk level of the user suffering from the preset disease based on the obtained physiological information of the user related to the preset disease at least twice, and the first user characteristic;

Or, based on the physiological information acquired each time, predict the first risk level of the user suffering from the preset disease; predict the user based on at least two of the first risk levels and the first user characteristics The user suffers from a first target risk level of the preset disease.
The method according to claim 2, wherein the acquiring the first facial image of the user comprises:

In the case that the number of occurrences is greater than or equal to the first preset number of times, acquiring the first facial image of the user;

Or, when the number of occurrences is greater than or equal to a second preset number of times, and the first risk level of the at least two first risk levels greater than or equal to the first preset risk level is a continuous occurrence In the case of obtaining the first facial image of the user;

The number of occurrences is the number of occurrences of the first risk level that is greater than or equal to the first preset risk level among the at least two first risk levels, and each of the first risk levels is based on physiological information collected once obtained.
The method according to any one of claims 1-3, wherein the acquiring the first facial image of the user comprises:

Acquiring at least two images, wherein the at least two images are images of a local area containing the facial image of the user;

The at least two images are fused into the first facial image.
The method according to any one of claims 1-4, wherein the obtaining, based on the first facial image, the first user characteristic of the user corresponding to the key influencing factor of the preset disease, include:

identifying facial features in the first facial image;

Based on the facial feature, the user's identity information corresponding to the key influencing factor of the preset disease is acquired from an information query system; the identity information is used to determine the first user feature.
The method according to any one of claims 1-5, wherein the predicting the first target risk level of the user suffering from the preset disease based on the physiological information and the first user characteristics Afterwards, the method further includes:

obtaining a second facial image of the user;

In the case where the second facial image changes relative to the first facial image, acquiring, based on the second facial image, a second user corresponding to the key influencing factor that the user suffers from the preset disease feature;

Based on the physiological information and the second user characteristic, a second target risk level of the user suffering from the preset disease is predicted.
The method according to any one of claims 1-6, characterized in that, in the first target risk level of predicting that the user suffers from a preset disease based on the physiological information level and the first user characteristic Afterwards, the method further includes:

In the case that the first target risk level is greater than or equal to a second preset risk level, output prompt information, wherein the prompt information includes: the first user characteristics that meet preset conditions;

The first user characteristics that meet the preset conditions include:

The weight value is greater than or equal to the first user feature corresponding to the preset weight value;

Or, the first user features corresponding to the first first preset number of weight values after the weight values are sorted in descending order.
The method according to any one of claims 1-7, wherein when the preset disease includes obstructive sleep apnea and hypopnea syndrome, the key influencing factors include gender, age, degree of obesity, Whether the nasal septum is deviated or at least one of craniomaxillofacial deformities.
A disease risk level prediction device, characterized in that the device comprises:

The information acquisition module is used to acquire the user's physiological information related to the preset disease;

an image acquisition module for acquiring the first facial image of the user;

a feature acquisition module, configured to acquire, based on the first facial image, the first user feature of the user corresponding to the key influencing factor of the preset disease;

A prediction module, configured to predict the first target risk level of the user suffering from the preset disease based on the physiological information and the first user characteristic.
The device according to claim 9, wherein the information acquisition module is specifically used for:

Acquire the physiological information related to the preset disease of the user at least twice within the first preset time period;

The prediction module is specifically used for:

Predicting a first target risk level of the user suffering from the preset disease based on the obtained physiological information of the user related to the preset disease at least twice, and the first user characteristic;

Or, based on the physiological information obtained each time, predict the first risk level of the user suffering from the preset disease; based on at least two of the first risk levels and the first user characteristics, predict the user The user suffers from a first target risk level of the preset disease.
The device according to claim 10, wherein the image acquisition module is specifically configured to:

In the case that the number of occurrences is greater than or equal to the first preset number of times, acquiring the first facial image of the user;

Or, when the number of occurrences is greater than or equal to a second preset number of times, and the first risk level of the at least two first risk levels that is greater than or equal to the first preset risk level is a continuous occurrence In the case of obtaining the first facial image of the user;

The number of occurrences is the number of occurrences of the first risk level that is greater than or equal to the first preset risk level among the at least two first risk levels, and each of the first risk levels is based on physiological information collected once obtained.
The device according to any one of claims 9-11, wherein the image acquisition module is specifically configured to:

acquiring at least two images, wherein the at least two images are images of a local area containing the facial image of the user;

The at least two images are fused into the first facial image.
The device according to any one of claims 9-12, wherein the feature acquisition module is specifically configured to:

identifying facial features in the first facial image;

Based on the facial feature, the identity information of the user corresponding to the key influencing factor of the preset disease is acquired from an information query system, and the first user feature is determined based on the identity information.
The device according to any one of claims 9-13, characterized in that,

The image acquisition module is further configured to acquire the second facial image of the user;

The feature acquisition module is further configured to acquire, based on the second facial image, that the user suffers from the preset disease when the second facial image changes relative to the first facial image The second user characteristics corresponding to the key influence factors of ;

The prediction module is further configured to predict a second target risk level of the user suffering from the preset disease based on the physiological information and the second user characteristic.
The device according to any one of claims 9-14, wherein the device further comprises:

a prompting module, configured to output prompting information when the first target risk level is greater than or equal to a second preset risk level, wherein the prompting information includes: the first user feature that satisfies a preset condition;

The first user characteristics that meet the preset conditions include:

The weight value is greater than or equal to the first user feature corresponding to the preset weight value;

Or, the first user features corresponding to the first first preset number of weight values after the weight values are sorted in descending order.
The device according to any one of claims 9-15, wherein when the preset disease includes obstructive sleep apnea and hypopnea syndrome, the key influencing factors include gender, age, degree of obesity, Whether the nasal septum is deviated or whether it is at least one of craniomaxillofacial deformities.
A disease risk level prediction device, characterized by comprising: a memory and a processor, wherein the memory is used for storing a computer program, and the processor is used for calling the computer program to execute any one of claims 1-8. method described.
A computer-readable storage medium, characterized in that, a computer program is stored in the computer-readable storage medium, and when the computer program is executed on a computer, the computer is made to execute any one of claims 1-8. method described.