Automatic resident health assessment method and system

Abstract

The invention relates to a resident health automatic assessment method and system, and belongs to the technical field of health assessment. The method comprises the steps that personal information data, the number of gene mutation points, blood routine data, psychological assessment data and sleep data of residents are obtained, time sequence movement data and time sequence movement physiological index data are obtained through a measuring bracelet, and a database table is established according to the personal information data; integrating each score of the psychological assessment data to obtain psychological assessment score data, and obtaining a time sequence motion recognition result through calculation according to the time sequence motion data; marking the time sequence motion recognition result according to the abnormal result to obtain a marking result, and calculating to obtain sleep quality data and blood test score data; and calculating a physiological health assessment result and a psychological health assessment result, and storing the physiological health assessment result, the psychological health assessment result and the target result into the database table. Automatic evaluation of resident health and avoidance of unhealthy exercises are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of health assessment, and in particular relates to a method and system for automatic assessment of resident health. Background Art

[0002] With the rapid development of social economy and the improvement of people's living standards, residents' health issues have received increasing attention. Public health and individual health management have become important topics for improving residents' quality of life and improving the overall health level of society. In this context, health assessment, as an indispensable part of health management, plays a vital role.

[0003] Traditional resident health assessments mainly rely on manual questionnaires and regular health checks. Usually, residents need to fill out health questionnaires that contain information such as personal medical history, family medical history, and living habits. These methods can understand residents' health status to a certain extent, but they have problems such as strong subjectivity, delayed data updates, and high periodic costs.

[0004] In recent years, with the rapid development of information technology, the Internet of Things, big data, and artificial intelligence, the way residents manage their health has also been constantly innovating. Wearable devices (such as smart watches, health monitors, etc.) have begun to become popular. These devices can monitor physiological data such as heart rate, blood pressure, and blood sugar in real time, and automatically upload them to the cloud database to update the user's health information in real time, thus giving rise to health management systems. However, existing health management systems have problems such as data silos, insufficient intelligence, and lack of personalization. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention provides a method and system for automatically evaluating residents' health.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] S1: Obtaining personal information data, number of gene mutation points, routine blood data, psychological assessment data, and sleep data of residents, obtaining time-series motion data and time-series motion physiological index data through a measuring bracelet, establishing a database table based on the personal information data, and storing the number of gene mutation points, the routine blood data, the psychological assessment data, the motion data, the sleep data, and the motion physiological index data in the database table;

[0008] S2: Integrate each score of the psychological assessment data to obtain psychological assessment score data, and calculate the time series motion recognition result through the motion category recognition model according to the time series motion data;

[0009] S3: comparing the time-series motion physiological index data with a preset physiological index threshold to obtain an abnormal result, labeling the time-series motion recognition result according to the abnormal result to obtain a labeled result, calculating the sleep quality data through a sleep quality monitoring model according to the sleep data, and calculating the blood routine data through a blood test score calculation model to obtain blood test score data;

[0010] S4: Based on the number of gene mutation points and the blood test score data, the sleep quality data is calculated through a physiological health assessment model to obtain a physiological health assessment result, and the psychological health assessment result is obtained by comparing the psychological score data with a preset psychological condition threshold. The physiological health assessment result, the psychological health assessment result, and the target result are stored in the database table.

[0011] As a preferred technical solution of the present invention, the time-series motion data includes time-series human body movement acceleration and time-series arm swing rotation speed, and the specific calculation steps of the motion category recognition model are as follows:

[0012] S201: performing linear interpolation on the time series motion data to obtain uniform data, and performing noise reduction processing through a smoothing filter on the uniform data to obtain noise-reduced data;

[0013] S202: performing normalization processing on the denoised data by using a Z-score method to obtain normalized data, performing data segmentation on the normalized data by using a dynamic threshold to obtain data blocks, and obtaining time-frequency domain data by using a short-time Fourier transform calculation on the data blocks;

[0014] S203: Calculate the first feature and the second feature according to the time-frequency domain data through the CNN feature extractor and the BiGRU feature extractor, and concatenate the first feature and the second feature to obtain a concatenated feature, wherein the concatenated feature expression is:

[0015] G(X)=Concat(G a (X)+G b (x)),

[0016] Among them, G(X) is the splicing feature, Ga(X) is the first feature, and Gb(X) is the second feature.

[0017] S204: performing recognition by a motion recognizer according to the splicing features to obtain the time-series motion recognition result.

[0018] Specifically, the action recognizer is composed of three fully connected layers, and the action recognizer is trained by splicing features with labels; when performing action recognition, a similarity value sequence is obtained by calculating the similarity between the splicing features and the target splicing feature sequence, and the maximum similarity value is selected according to the similarity value sequence. The target splicing feature is matched according to the maximum similarity value, and the label of the target splicing feature is used as the temporal motion recognition result. The similarity value calculation formula is:

[0019]

[0020] Among them, S is the similarity value, i is the variable coefficient, A i is the value of the concatenated feature on the i-th dimension, B ij is the value of the i-th dimension of the j-th target splicing feature in the target splicing feature sequence.

[0021] Specifically, the sleep quality monitoring model first preprocesses the sleep data to obtain preprocessed data, performs feature extraction based on the preprocessed data to obtain time domain features, frequency domain features, and time-frequency domain features, cascades the time domain features, the frequency domain features, and the time-frequency domain features to obtain a fused feature vector, and calculates the sleep quality data through a classifier based on the fused feature vector; the preprocessing includes baseline calibration, filtering, removing bad leads, filling bad leads, and removing trials.

[0022] Specifically, the blood test score calculation model classifies the routine blood data according to a preset level threshold to obtain level data, and summarizes and calculates the level data according to the weight coefficient of the level data to obtain the blood test score data. The blood test score calculation formula is:

[0023]

[0024] Wherein, Y is the blood test score, i is the variable parameter, n is the number of blood routine test items, a i is the weight coefficient of the i-th level data, A i is the i-th level data.

[0025] Specifically, the physiological health assessment model summarizes the number of gene mutation points, the blood test score data, and the sleep quality data according to the preset weights of the number of gene mutation points, the blood test score data, and the sleep quality data to obtain the physiological health score, and grades the physiological health score according to a preset grade threshold to obtain the physiological health assessment result.

[0026] Specifically, the time-series motion physiological index data represents the physiological index data collected when residents do different exercises, and the physiological index data includes blood pressure, heart rate, body temperature, and blood oxygen saturation.

[0027] A resident health automated assessment system of a resident health automated assessment method, comprising: a data acquisition module, a score aggregation module, a data calculation module, and an assessment module;

[0028] The data acquisition module is used to acquire residents' personal information data, the number of gene mutation points, routine blood data, psychological assessment data, and sleep data, acquire time-series motion data and time-series motion physiological index data through a measuring bracelet, establish a database table based on the personal information data, and store the number of gene mutation points, the routine blood data, the psychological assessment data, the motion data, the sleep data, and the motion physiological index data in the database table;

[0029] The score aggregation module is used to integrate each score of the psychological assessment data to obtain psychological assessment score data, and to calculate the time-series motion recognition result through the motion category recognition model according to the time-series motion data;

[0030] The data calculation module is used to compare the time-series motion physiological index data with a preset physiological index threshold to obtain an abnormal result, mark the time-series motion recognition result according to the abnormal result to obtain a marked result, calculate the sleep quality data according to the sleep data through a sleep quality monitoring model, and calculate the blood routine data through a blood test score calculation model to obtain blood test score data;

[0031] The evaluation module is used to calculate the physiological health evaluation result according to the number of gene mutation points, the blood test score data, and the sleep quality data through the physiological health evaluation model, and to obtain the mental health evaluation result by comparing the psychological score data with a preset psychological condition threshold, and to store the physiological health evaluation result, the mental health evaluation result, and the target result in the database table.

[0032] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for automated assessment of resident health as described above is implemented.

[0033] A storage medium containing computer executable instructions, characterized in that the computer executable instructions are used to execute the automated resident health assessment method as described above when executed by a computer processor.

[0034] The beneficial effects of the present invention are:

[0035] (1) The time-series motion data and time-series motion physiological index data are obtained through the measuring bracelet, and the time-series motion recognition results are calculated through the motion category recognition model. The time-series motion physiological index data are compared with the preset physiological index threshold to obtain abnormal results. The time-series motion recognition results are marked according to the abnormal results to obtain marked results, thereby realizing the recognition of motion patterns. According to the real-time monitoring of physiological data abnormalities and marking of motion patterns, residents can understand in real time the types of sports that are not suitable for them, adjust the sports items in time, and avoid injuries caused by wrong sports.

[0036] (2) Incorporate mental health assessment into residents’ health assessment to form a more complete health assessment system.

[0037] (3) The number of gene mutation points, sleep quality data, and blood test score data are scored according to different preset weight values ​​to obtain a physiological health score, and the physiological health score is divided into levels to obtain a physiological health assessment result, thereby achieving a more intuitive understanding of the physiological health status.

[0038] (4) The number of gene mutation points is included in the health assessment, realizing the impact of gene mutation problems on residents' health. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0040] Figure 1 It is a flow chart of the automated resident health assessment method of the present invention. DETAILED DESCRIPTION

[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0042] See also Figure 1 , a method and system for automatically evaluating residents' health

[0043] S1: Obtaining personal information data, number of gene mutation points, routine blood data, psychological assessment data, and sleep data of residents, obtaining time-series motion data and time-series motion physiological index data through a measuring bracelet, establishing a database table based on the personal information data, and storing the number of gene mutation points, the routine blood data, the psychological assessment data, the motion data, the sleep data, and the motion physiological index data in the database table;

[0044] S2: Integrate each score of the psychological assessment data to obtain psychological assessment score data, and calculate the time series motion recognition result through the motion category recognition model according to the time series motion data;

[0045] S3: comparing the time-series motion physiological index data with a preset physiological index threshold to obtain an abnormal result, labeling the time-series motion recognition result according to the abnormal result to obtain a labeled result, calculating the sleep quality data through a sleep quality monitoring model according to the sleep data, and calculating the blood routine data through a blood test score calculation model to obtain blood test score data;

[0046] S4: Based on the number of gene mutation points and the blood test score data, the sleep quality data is calculated through a physiological health assessment model to obtain a physiological health assessment result, and the psychological health assessment result is obtained by comparing the psychological score data with a preset psychological condition threshold. The physiological health assessment result, the psychological health assessment result, and the target result are stored in the database table.

[0047] In this embodiment, the target result indicates that the resident is not suitable for the type of exercise, so as to avoid physical damage caused by the resident exercising in the wrong way; the time-series motion data includes the time-series human body movement acceleration and the time-series arm swing rotation speed; the time-series motion data includes the time-series human body movement acceleration and the time-series arm swing rotation speed.

[0048] As a preferred technical solution of the present invention, the specific calculation steps of the motion category recognition model are as follows:

[0049] S201: performing linear interpolation on the time series motion data to obtain uniform data, and performing noise reduction processing through a smoothing filter on the uniform data to obtain noise-reduced data;

[0050] S202: performing normalization processing on the denoised data by using a Z-score method to obtain normalized data, performing data segmentation on the normalized data by using a dynamic threshold to obtain data blocks, and obtaining time-frequency domain data by using a short-time Fourier transform calculation on the data blocks;

[0051] S203: Calculate the first feature and the second feature according to the time-frequency domain data through the CNN feature extractor and the BiGRU feature extractor, and concatenate the first feature and the second feature to obtain a concatenated feature, wherein the concatenated feature expression is:

[0052] G(X)=Concat(G a (X)+G b (X)),

[0053] Among them, G(X) is the splicing feature, Ga(X) is the first feature, and Gb(X) is the second feature.

[0054] S204: Recognize the splicing features through a motion recognizer to obtain the temporal motion recognition result.

[0055] Specifically, the action recognizer is composed of three fully connected layers, and the action recognizer is trained by splicing features with labels; when performing action recognition, a similarity value sequence is obtained by calculating the similarity between the splicing features and the target splicing feature sequence, and the maximum similarity value is selected according to the similarity value sequence. The target splicing feature is matched according to the maximum similarity value, and the label of the target splicing feature is used as the temporal motion recognition result. The similarity value calculation formula is:

[0056]

[0057] Among them, S is the similarity value, i is the variable coefficient, A i is the value of the concatenated feature on the i-th dimension, B ij is the value of the i-th dimension of the j-th target splicing feature in the target splicing feature sequence.

[0058] In this embodiment, the target splicing feature sequence is a target splicing feature with a label when training the action recognizer.

[0059] Specifically, the sleep quality monitoring model first preprocesses the sleep data to obtain preprocessed data, performs feature extraction based on the preprocessed data to obtain time domain features, frequency domain features, and time-frequency domain features, cascades the time domain features, the frequency domain features, and the time-frequency domain features to obtain a fused feature vector, and calculates the sleep quality data through a classifier based on the fused feature vector; the preprocessing includes baseline calibration, filtering, removing bad leads, filling bad leads, and removing trials.

[0060] Specifically, the blood test score calculation model classifies the routine blood data according to a preset level threshold to obtain level data, and summarizes and calculates the level data according to the weight coefficient of the level data to obtain the blood test score data. The blood test score calculation formula is:

[0061]

[0062] Wherein, Y is the blood test score, i is the variable parameter, n is the number of blood routine test items, a i is the weight coefficient of the i-th level data, A i is the i-th level data.

[0063] Specifically, the physiological health assessment model summarizes the number of gene mutation points, the blood test score data, and the sleep quality data according to the preset weights of the number of gene mutation points, the blood test score data, and the sleep quality data to obtain the physiological health score, and grades the physiological health score according to a preset grade threshold to obtain the physiological health assessment result.

[0064] Specifically, the time-series motion physiological index data represents the physiological index data collected when residents do different exercises, and the physiological index data includes blood pressure, heart rate, body temperature, and blood oxygen saturation.

[0065] In this embodiment, the blood oxygen saturation is calculated by measuring the intensity of light conduction through the tissue bed by using the measuring bracelet with near-infrared light of wavelengths of 660nm and 940nm as incident light sources.

[0066] A resident health automated assessment system of a resident health automated assessment method, comprising: a data acquisition module, a score aggregation module, a data calculation module, and an assessment module;

[0067] The data acquisition module is used to acquire residents' personal information data, the number of gene mutation points, routine blood data, psychological assessment data, and sleep data, acquire time-series motion data and time-series motion physiological index data through a measuring bracelet, establish a database table based on the personal information data, and store the number of gene mutation points, the routine blood data, the psychological assessment data, the motion data, the sleep data, and the motion physiological index data in the database table;

[0068] The score aggregation module is used to integrate each score of the psychological assessment data to obtain psychological assessment score data, and to calculate the time-series motion recognition result through the motion category recognition model according to the time-series motion data;

[0069] The data calculation module is used to calculate the optimism index through the evaluation model according to the pre-processed file data, compare the time-series motion physiological index data with the preset physiological index threshold to obtain an abnormal result, mark the time-series motion recognition result according to the abnormal result to obtain a marked result, calculate the sleep quality data through the sleep quality monitoring model according to the sleep data, and calculate the blood routine data through the blood test score calculation model to obtain the blood test score data;

[0070] The evaluation module is used to calculate the physiological health evaluation result according to the number of gene mutation points, the blood test score data, and the sleep quality data through the physiological health evaluation model, and to obtain the mental health evaluation result by comparing the psychological score data with a preset psychological condition threshold, and to store the physiological health evaluation result, the mental health evaluation result, and the target result in the database table.

[0071] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for automated assessment of resident health as described above is implemented.

[0072] A storage medium containing computer executable instructions, characterized in that the computer executable instructions are used to execute the automated resident health assessment method as described above when executed by a computer processor.

[0073] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0074] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0075] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0076] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A method for automatically assessing residents' health, characterized in that: include: S1: Obtaining personal information data, number of gene mutation points, routine blood data, psychological assessment data, and sleep data of residents, obtaining time-series motion data and time-series motion physiological index data through a measuring bracelet, establishing a database table based on the personal information data, and storing the number of gene mutation points, the routine blood data, the psychological assessment data, the motion data, the sleep data, and the motion physiological index data in the database table; S2: Integrate each score of the psychological assessment data to obtain psychological assessment score data, and calculate the time series motion recognition result through the motion category recognition model according to the time series motion data; S3: comparing the time-series motion physiological index data with a preset physiological index threshold to obtain an abnormal result, labeling the time-series motion recognition result according to the abnormal result to obtain a labeled result, calculating the sleep quality data through a sleep quality monitoring model according to the sleep data, and calculating the blood routine data through a blood test score calculation model to obtain blood test score data; S4: Based on the number of gene mutation points and the blood test score data, the sleep quality data is calculated through a physiological health assessment model to obtain a physiological health assessment result, and the psychological health assessment result is obtained by comparing the psychological score data with a preset psychological condition threshold. The physiological health assessment result, the psychological health assessment result, and the target result are stored in the database table.

2. The method for automated assessment of resident health according to claim 1, characterized in that: The specific calculation steps of the motion category recognition model are as follows: S201: performing linear interpolation on the time series motion data to obtain uniform data, and performing noise reduction processing through a smoothing filter on the uniform data to obtain noise-reduced data; S202: performing normalization processing on the denoised data by using a Z-score method to obtain normalized data, performing data segmentation on the normalized data by using a dynamic threshold to obtain data blocks, and obtaining time-frequency domain data by using a short-time Fourier transform calculation on the data blocks; S203: Calculate the first feature and the second feature according to the time-frequency domain data through the CNN feature extractor and the BiGRU feature extractor, and concatenate the first feature and the second feature to obtain a concatenated feature, wherein the concatenated feature expression is: G(X)=Concatt(Ga(X)+Gb(X)), Among them, G(X) is the splicing feature, Ga(X) is the first feature, and Gb(X) is the second feature. S204: Recognize the splicing features through a motion recognizer to obtain the temporal motion recognition result.

3. The method for automated assessment of resident health according to claim 2, characterized in that: The action recognizer is composed of three fully connected layers, and is trained by splicing features with labels. When performing action recognition, a similarity value sequence is obtained by calculating the similarity between the splicing features and the target splicing feature sequence, and the maximum similarity value is selected according to the similarity value sequence. The target splicing feature is matched according to the maximum similarity value, and the label of the target splicing feature is used as the temporal motion recognition result. The similarity value calculation formula is: Among them, S is the similarity value, i is the variable coefficient, A i is the value of the concatenated feature on the i-th dimension, Bi j is the value of the i-th dimension of the j-th target splicing feature in the target splicing feature sequence.

4. The method for automated assessment of resident health according to claim 1, characterized in that: The sleep quality monitoring model first preprocesses the sleep data to obtain preprocessed data, performs feature extraction based on the preprocessed data to obtain time domain features, frequency domain features, and time-frequency domain features, cascades the time domain features, the frequency domain features, and the time-frequency domain features to obtain a fused feature vector, and calculates the sleep quality data through a classifier based on the fused feature vector; the preprocessing includes baseline calibration, filtering, removing bad leads, filling bad leads, and removing trials.

5. The method for automated assessment of resident health according to claim 1, characterized in that: The blood test score calculation model classifies the routine blood data according to a preset level threshold to obtain level data, and summarizes and calculates the level data according to the weight coefficient of the level data to obtain the blood test score data. The blood test score calculation formula is: Wherein, Y is the blood test score, i is the variable parameter, n is the number of blood routine test items, a i is the weight coefficient of the i-th level data, A i is the i-th level data.

6. The method for automated assessment of resident health according to claim 1, characterized in that: The physiological health assessment model calculates the number of gene mutation points, the blood test score data, and the sleep quality data according to preset weights of the number of gene mutation points, the blood test score data, and the sleep quality data to obtain the physiological health score, and classifies the physiological health score according to a preset grade threshold to obtain the physiological health assessment result.

7. The method for automated assessment of resident health according to claim 1, characterized in that: The time-series exercise physiological index data represent the physiological index data collected when residents do different exercises, and the physiological index data include blood pressure, heart rate, body temperature, and blood oxygen saturation.

8. An automated health assessment system for residents using the automated health assessment method for residents described in claim 1, characterized in that: include: Data acquisition module, score aggregation module, data calculation module, and evaluation module; The data acquisition module is used to acquire residents' personal information data, the number of gene mutation points, routine blood data, psychological assessment data, and sleep data, acquire time-series motion data and time-series motion physiological index data through a measuring bracelet, establish a database table based on the personal information data, and store the number of gene mutation points, the routine blood data, the psychological assessment data, the motion data, the sleep data, and the motion physiological index data in the database table; The score aggregation module is used to integrate each score of the psychological assessment data to obtain psychological assessment score data, and to calculate the time-series motion recognition result through the motion category recognition model according to the time-series motion data; The data calculation module is used to compare the time-series motion physiological index data with a preset physiological index threshold to obtain an abnormal result, mark the time-series motion recognition result according to the abnormal result to obtain a marked result, calculate the sleep quality data according to the sleep data through a sleep quality monitoring model, and calculate the blood routine data through a blood test score calculation model to obtain blood test score data; The evaluation module is used to calculate the physiological health evaluation result according to the number of gene mutation points, the blood test score data, and the sleep quality data through the physiological health evaluation model, and to obtain the mental health evaluation result by comparing the psychological score data with a preset psychological condition threshold, and to store the physiological health evaluation result, the mental health evaluation result, and the target result in the database table.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the automated resident health assessment method as described in any one of claims 1-7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the automated resident health assessment method as described in any one of claims 1-7.

Images