CN113674855A - Data analysis method and device - Google Patents
Data analysis method and device Download PDFInfo
- Publication number
- CN113674855A CN113674855A CN202010401869.2A CN202010401869A CN113674855A CN 113674855 A CN113674855 A CN 113674855A CN 202010401869 A CN202010401869 A CN 202010401869A CN 113674855 A CN113674855 A CN 113674855A
- Authority
- CN
- China
- Prior art keywords
- data
- disease
- behavior
- user
- model component
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application relates to a data analysis method and a data analysis device, wherein the method comprises the following steps: acquiring behavior data of a user in various life scenes; inputting the behavior data into a behavior analysis model component, and outputting a judgment result through the behavior analysis model component, wherein the judgment result comprises whether the user needs to obtain medical diagnosis of the senile dementia; wherein the behavior analysis model component is configured to be trained using a plurality of sample data, the sample data including a correspondence between the behavior data and the determination result. By using the data analysis method and device provided by the embodiments of the application, the accuracy of the judgment result can be enhanced, and users, particularly old users, can be helped to provide disease early warning information in time.
Description
Technical Field
The present application relates to the field of big data technologies, and in particular, to a data analysis method and apparatus.
Background
In recent years, the problem of global population aging is increased, and according to related data, the increase of the population aging of Chinese people in 2019 is the first in the world. In 2030, the population proportion of China above 65 years old exceeds that of Japan, and the China becomes the country with the highest degree of global population aging, and in 2050, the society enters a deep aging stage, and the population proportion of China above 60 years old exceeds 30%. With the increase of the population of the elderly, the living care of the elderly is gradually improved, and particularly, the disease early warning for the elderly is provided. Many old people have a long-term illness, and are brought to hospitals by family members to diagnose the disease, and at the moment, the probability of rehabilitation is not as high as that of the condition of discovering the disease early, and the medical cost is low.
The early warning method for diseases of old people in the related art mainly determines whether the old people are at risk or not through regular physical examination, but the method needs the old people to go to a physical examination mechanism for physical examination in person, and for many old people with inconvenient actions or weak bodies, the regular physical examination is a difficult matter to persist for a long time.
Therefore, there is a need in the related art for a disease early warning method that can be conveniently performed on a patient to help the patient, especially an elderly patient, to find a disease in time.
Disclosure of Invention
An object of the embodiments of the present application is to provide a data analysis method and apparatus, which can enhance the accuracy of a determination result and help a user, especially an elderly user, to provide disease early warning information in time.
The data analysis method and device provided by the embodiment of the application are realized as follows:
a method of data analysis, the method comprising:
acquiring behavior data of a user in various life scenes;
inputting the behavior data into a behavior analysis model component, and outputting a judgment result through the behavior analysis model component, wherein the judgment result comprises whether the user needs to obtain disease medical examination;
wherein the behavioral analysis model component is configured to be trained using sample data for at least one disease, the sample data including a correspondence between behavioral data for the at least one disease and a determination result.
A data analysis apparatus comprising a processor and a memory for storing processor-executable instructions, the instructions when executed by the processor effecting:
acquiring behavior data of a user in various life scenes;
inputting the behavior data into a behavior analysis model component, and outputting a judgment result through the behavior analysis model component, wherein the judgment result comprises whether the user needs to obtain disease medical examination;
wherein the behavioral analysis model component is configured to be trained using sample data for at least one disease, the sample data including a correspondence between behavioral data for the at least one disease and a determination result.
A non-transitory computer readable storage medium having instructions therein which, when executed by a processor, enable the processor to perform the data analysis method.
The data analysis method and device provided by the embodiment of the application can acquire behavior data of a user in various life scenes, and determine whether the user needs to obtain medical diagnosis of the senile dementia or not by using the behavior analysis model component. On one hand, the behavior data of the user in a life scene is acquired, the data can be acquired under the condition that the user does not perceive the data, the daily life of the user is not influenced, the behavior data of the user is often rich, the information amount is large, and a generated judgment result has an enough data basis. On the other hand, the machine learning model component is used for determining the judgment result, and the machine learning model component is obtained by training a plurality of sample data, so that the accuracy of the judgment result can be enhanced based on a large amount of information of big data, and users, particularly old users, can be helped to provide disease early warning information in time.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic diagram of a scenario shown in accordance with an exemplary embodiment.
FIG. 2 is a flow diagram illustrating a method of data analysis according to an exemplary embodiment.
FIG. 3 is a block diagram illustrating a data analysis device according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
For the convenience of those skilled in the art to understand the technical solutions provided in the embodiments of the present application, the data analysis method provided in each embodiment of the present application is specifically described below through a specific scenario, the business scenario is illustrated as an example but not limited to alzheimer disease, and the types of diseases referred to in the embodiments of the present application may include mental diseases, respiratory diseases, heart diseases, bone diseases, ophthalmic diseases, and the like, which is not limited herein.
As shown in the scene diagram shown in fig. 1, in the embodiment of the application, a cloud end 102 may be provided, and when authorization of a user is obtained, the cloud end 102 may obtain behavior data of the user, where the behavior data may include behavior data generated when the user uses an electronic device such as a mobile phone, a computer, and an intelligent wearable device in daily life. Fig. 1 illustrates several exemplary application scenarios for obtaining user behavior data. As shown in fig. 1, the cloud 102 may establish a connection relationship with the smartphone 104 of the user to obtain behavior data of the user when using the smartphone 104, where the behavior data may include character input data, voice input data, reading data, audio-visual data, game data, exercise data, physical sign data, and the like. Cloud 102 may also establish a connection relationship with smart sound box 106 to obtain behavior data of the user when using smart sound box 106, where the behavior data may include voice input data, hearing data, and the like of the user. In addition, the cloud end 102 may further establish a connection relationship with the smart vehicle-mounted device 108 to acquire behavior data of the user when using the vehicle, the smart vehicle-mounted device 108 may include a vehicle-mounted computer, a vehicle recorder, a vehicle-mounted camera device, and the like coupled to the vehicle, and the behavior data may include user driving data, voice input data, and the like. Of course, the cloud 102 may also establish a connection relationship with the intelligent call device 110 to obtain behavior data of the user when using the intelligent call device 110, where the behavior data may include voice input data and the like. Certainly, in other embodiments, the connected electronic devices may further include an image pickup device, an intelligent bracelet, intelligent bedding, an intelligent television, and the like, for example, by using the image pickup device installed indoors, daily activity audio-video data of the user indoors may be photographed, and by analyzing and processing the daily activity audio-video data, the action state of the user may be obtained, such as that the senile dementia patient tends to have slow action, which does not limit the electronic device connectable to the cloud 102.
After acquiring the behavior data, the cloud end 102 may acquire parameter values of preset parameters from the behavior data, where the preset parameters may be used to reflect behavior characteristics of the user, and then may determine whether the user needs medical examination of a disease according to the behavior characteristic information. For specific description of the preset parameters, reference may be made to the following embodiments, which are not described herein again. In an embodiment of the present application, the preset parameters and their parameter values may be input to the behavior analysis model component 112, and a determination result including whether the user needs to obtain a medical examination is output through the behavior analysis model component 112. The behavior analysis model component 112 may be obtained by training in a machine learning manner, and specific training manners may refer to various embodiments described below in the specification, which are not described herein again.
The data analysis method described in the present application is described in detail below with reference to the drawings. Fig. 2 is a schematic method flow diagram of an embodiment of a data analysis method provided in the present application. Although the present application provides method steps as shown in the following examples or figures, more or fewer steps may be included in the method based on conventional or non-inventive efforts. In the case of steps where no necessary causal relationship exists logically, the order of execution of the steps is not limited to that provided by the embodiments of the present application. The method can be executed sequentially or in parallel (for example, in the context of a parallel processor or a multi-thread process) according to the method shown in the embodiment or the figures during the actual data analysis process or the device execution.
Specifically, an embodiment of the data analysis method provided in the present application is shown in fig. 2, where the method may include:
s201: behavior data of a user in various life scenes is acquired.
S203: inputting the behavior data into a behavior analysis model component, and outputting a judgment result through the behavior analysis model component, wherein the judgment result comprises whether the user needs to obtain disease medical examination;
wherein the behavioral analysis model component is configured to be trained using sample data for at least one disease, the sample data including a correspondence between behavioral data for the at least one disease and a determination result. In the embodiment of the application, under the condition of obtaining the authorization of the user, the behavior data of the user in various life scenes can be obtained. The behavior data in the life scene may include behavior data of the user generated in a daily life scene recorded without perception by the user. The life scenarios may include shopping, sports, gaming, sleeping, and the like. In one embodiment, the behavior data may include behavior data generated or recorded when a user uses an electronic device such as a mobile phone, a computer, a smart wearable device, and the like in daily life. In some examples, the behavioral data may include user input data at characters, voice input data, reading data, audio-visual data, game data, action data, athletic workout data, vital signs data, and the like. The character input data may include data resulting from a user entering characters using the electronic device. The voice input data may include data captured with a microphone of the electronic device that is generated when a user utters voice. The reading data includes data generated when a user reads with the electronic device. The audiovisual data includes data generated when a user views a video or listens to music using an electronic device. The game data may include data generated when a user plays a game using the electronic device. The action data may include image data or video data of a user action recorded with the image pickup apparatus. The athletic workout data may include data generated during exercise. The vital sign data may comprise characteristic data of the user's body. It should be noted that the behavior data is not limited to the above examples, and any data that can be related to the health information of the user belongs to the protection scope of the present application, and other modifications are possible for those skilled in the art in light of the technical spirit of the present application, but they should be covered by the protection scope of the present application as long as the achieved functions and effects are the same or similar to the present application.
It should be noted that the manner of obtaining the behavior data may include multiple manners, and in one embodiment, a buried point may be set in an application installed on the electronic device by using a buried point technology to obtain the buried point data. For example, a buried point is set on a play button of a video playing application, and a user can trigger recording of the play operation every time the user clicks the play button, where the recorded content may include a played content identifier, time, watching duration, and the like. In another embodiment, the behavior data may be retrieved from a user log. Generally, during the use of the electronic device by the user, the electronic device or the application may record the operation record of the user, such as generating a user log. Based on this, the required behavior data can be screened out from the operation record, for example, a usage record related to the usage of a microphone can be screened out from a user log, and the usage record can include information such as the speech speed of the user when speaking. Of course, in other embodiments, the behavior data of the user may also be obtained from a third party provider, which is not limited herein.
In one embodiment of the present application, the behavioural data may come from at least one data source, in particular may come from two or more different data sources. In one example, the behavior data may include data obtained from a local platform or may include data obtained from a third party platform. For applications on the client, the data sources may include a variety of different applications, such as a gaming application, a reading application, a social application, a video playing application, a fitness application, a health application, and so forth. In an actual application scenario, data from different data sources often have different data formats, and based on the data formats, behavior data of different data sources are subjected to data format unification preprocessing so as to adapt to the fact that the data are input into the behavior analysis model component for processing subsequently. By the method, data sources of the behavior data can be increased, richness of the user behavior data is enhanced, and a more accurate judgment result is obtained.
In practical applications, the obtained original behavior data from at least one data source, such as user logs and buried point data, may be repeated, for example, in different applications, character input data, voice input data, reading data, audio-visual data, etc. of a user may be obtained, and therefore, statistical processing needs to be performed on the original behavior data from at least one data source to determine a parameter value of at least one preset parameter. The preset parameters may include any parameters associated with a disease. In some examples, parameter values of preset parameters such as speed of inputting characters by a user, key interval when inputting characters, semantic continuity of input characters and the like can be determined from the character input data. And determining parameter values of preset parameters such as the speed of speech, the pause time in conversation, the continuity of speech semantics and the like from the speech input data. From the reading data, parameter values of preset parameters such as reading speed, reading amount and the like of the user can be determined. The parameter values of preset parameters such as the number of times that the user watches the same video, the volume of listening to music, the number of watching videos and the like can be determined from the audio-visual data. The game data can determine the times and the reaction speed of the user playing the game, the physical sign data during playing the game and other parameter values of preset parameters. From the action data, parameter values of preset parameters such as walking speed, frequency of wrestling, frequency of getting things back after going out, and the like of the user can be determined. And determining parameter values of preset data parameters of walking, riding, swimming, standing and the like of the user from the sports exercise data. Parameter values of preset parameters such as heartbeat, blood pressure, sleep time, body temperature and respiratory rate can be determined from the physical sign data. It should be noted that the preset parameters are not limited to the above examples, and any preset parameters that can be related to the health information of the user belong to the protection scope of the present application, and other modifications are possible for those skilled in the art based on the technical spirit of the present application, but all the functions and effects that are achieved by the preset parameters are the same as or similar to those of the present application, and are intended to be covered by the protection scope of the present application.
In the embodiment of the application, some of the parameter values of the preset parameters may be directly obtained from the original behavior data, such as exercise data, physical sign data, and volume for listening to music, and some of the parameter values of the parameters need to be determined after processing the original behavior data, and the processing mode may include data statistics, voice recognition, image recognition, semantic analysis, and the like. For example, the reading speed may be calculated according to the number of words of the read text and the page turning interval of the user, the game reaction speed may be determined according to the game score of the user, the semantic compliance may be obtained by processing with a semantic analysis processor, the action data may be obtained from a video or an image by means of image recognition, and the data processing manner is not limited in the present application. By carrying out statistical processing on the original behavior data of different data sources, the information of the same parameters of different data sources can be uniformly processed.
In one embodiment of the present application, the preset parameters may be set according to an actual medical examination of a disease. For example, for senile dementia, the corresponding preset parameters may be set according to senile dementia examination rules, which may include simple mental condition examination (MMSE), long valley dementia examination table (HDS), dementia simple screening table (BSSD), ford table (POD), daily living ability table (ADL), and the like. The preset parameters are set by using an actual disease medical examination mode, so that the preset parameters and the diseases have closer relevance, and whether the acquired user needs disease medical examination is more accurate.
In one embodiment of the present application, a behavioral analysis model component can be utilized to determine whether a user needs to obtain a medical examination of a disease. In the using of the behavior analysis model component, the behavior data may be input into the behavior analysis model component, and a determination result including whether the user needs to obtain a medical examination of a disease may be output via the behavior analysis model component. In an embodiment of the present application, the sample data used for training the behavior analysis model component may include sample data composed of behavior data of patients for at least one disease and determination results thereof. For example, behavior data of 5000 senile dementia patients in the last five years, behavior data of 1 ten thousand heart disease patients in the last five years, behavior data of 8000 bone disease patients in the last five years, and the like are acquired. Because the sample data corresponding to the actual patient has authenticity, the method has an important role in obtaining more accurate and reliable behavior analysis model components for training. Of course, the sample data may also be constructed by other means, such as manual construction by a medical expert, and the present application is not limited thereto.
In the embodiment of the application, after the sample data is obtained, the behavior analysis model component may be constructed, and training parameters are set in the behavior analysis model component. The behavioral data can then be input into the behavioral analysis model component, respectively, to generate a prediction result. In one embodiment, the prediction result may include a probability that the user corresponding to the input behavior data needs to obtain a medical examination of the disease. Finally, the training parameters may be iteratively adjusted based on a difference between the prediction result and actual behavior feature information until the difference meets a preset requirement. Because the sample data comprises the behavior data aiming at the at least one disease, the behavior analysis model component after iterative training can analyze the abnormity related to the at least one disease in the behavior data, so that whether the user needs to obtain medical examination can be determined.
In the implementation process of the behavior analysis model component, the probability that the corresponding user needs to obtain the disease medical examination may be determined according to the behavior data, and then, whether the disease medical examination needs to be obtained may be determined according to the probability. In one example, the user is determined to need to obtain a medical examination of a disease if the probability is greater than a preset threshold, which may be set to 89%, 92%, 97%, etc., without limitation.
In an embodiment of the present application, the behavior analysis model component may output not only whether the user needs to obtain a medical examination of a disease, but also a type of a disease corresponding to the medical examination of the disease if it is determined that the user needs to obtain the medical examination of the disease. In some examples, the disease may include at least one type of: mental disorders, respiratory disorders, heart disorders, bone disorders, ophthalmic disorders. In this embodiment, after the behavior data is input into the behavior analysis model component, probabilities that a user needs to acquire medical examinations of a plurality of different diseases respectively may be output through the behavior analysis model component. In one example, a probability that the user needs to obtain a medical examination for a mental disease of 76%, a probability that the medical examination for a respiratory disease of 20%, a probability that the medical examination for a cardiac disease of 38%, a probability that the medical examination for a bone disease of 7%, a probability that the medical examination for an ophthalmic disease of 3%, and the like may be output. Then, the probability of a plurality of different disease medical examinations can be acquired according to the needs of the user, whether the user needs the disease medical examination or not is determined, and in the case that the user needs the disease medical examination, the type of the disease needing the medical examination is determined.
In an embodiment of the present application, the behavior analysis model component may include a sub-model component for the at least one disease respectively, and the sub-model component is configured to output whether the user needs to obtain a disease medical examination for a preset disease. In the actual use process, because the behavior data corresponding to different diseases may be different, the sub-behavior data required by the sub-model component may be determined respectively. For example, the sub-behavior data required for the sub-model components for senile dementia, the sub-behavior data required for the sub-model components for skeletal diseases, etc. may be determined. Then, the sub-behavior data can be respectively input into corresponding sub-model components, and whether the user needs to obtain disease medical examination for a preset disease or not is output through the sub-model components.
By dividing the behavior analysis model into sub model assemblies aiming at different diseases, the specificity of the sub model assemblies can be enhanced to obtain more accurate results, the training difficulty of the behavior analysis model assemblies can be reduced, and the training efficiency is improved. In this embodiment, the behavior analysis model component and the sub-model component may include model components obtained by training in a machine learning manner. The machine learning mode can also comprise a K nearest neighbor algorithm, a perception machine algorithm, a decision tree, a support vector machine, a logistic background regression, a maximum entropy and the like, and correspondingly, the generated model components such as naive Bayes, hidden Markov and the like. Of course, in other embodiments, the machine learning manner may further include a deep learning manner, a reinforcement learning manner, and the like, and the generated model component may include a Convolutional Neural Network model Component (CNN), a Recurrent Neural Network model component (RNN), LeNet, ResNet, a Long-Short Term Memory Network model component (LSTM), a bidirectional Long-Short Term Memory Network model component (Bi-LSTM), and the like, which is not limited herein.
In one embodiment of the present application, in case it is determined that the user needs to obtain a medical examination for a disease, a reminding message for the medical examination for the disease may be sent to the user to remind the user to go to a professional institution for the medical examination for the disease. Further, in an embodiment of the present application, at least one approach for medical examination of a disease may also be included in the alert message. In practical applications, it may be difficult for some elderly users to find a way to perform professional medical examination of a disease, and therefore, setting a way for medical diagnosis in the reminder message may facilitate the user to quickly obtain a diagnosis. In the present embodiment, the medical diagnosis approach may include online and offline screening, genetic testing, famous medical recommendations, common treatment recommendations, and the like.
Further, in case it is determined by a medical examination of a disease that the user has a disease, the user's behavior data is constructed as sample data and used for training the behavior analysis model component. By the method, the use value of the collected data can be further mined, and the quantity of the sample data can be continuously increased, so that the accuracy and the reliability of the behavior analysis model component are improved.
The data analysis method provided by the embodiment of the application can acquire behavior data of a user in various life scenes, and determines whether the user needs to obtain medical diagnosis of the senile dementia or not by using the behavior analysis model component. On one hand, the behavior data of the user in a life scene is acquired, the data can be acquired under the condition that the user does not perceive the data, the daily life of the user is not influenced, the behavior data of the user is often rich, the information amount is large, and a generated judgment result has an enough data basis. On the other hand, the machine learning model component is used for determining the judgment result, and the machine learning model component is obtained by training a plurality of sample data, so that the accuracy of the judgment result can be enhanced based on a large amount of information of big data, and users, particularly old users, can be helped to provide disease early warning information in time.
Corresponding to the above data analysis method, as shown in fig. 3, the present application further provides a data analysis apparatus, including a processor and a memory for storing processor-executable instructions, where the processor executes the instructions to implement:
acquiring behavior data of a user in various life scenes;
inputting the behavior data into a behavior analysis model component, and outputting a judgment result through the behavior analysis model component, wherein the judgment result comprises whether the user needs to obtain disease medical examination;
wherein the behavioral analysis model component is configured to be trained using sample data for at least one disease, the sample data including a correspondence between behavioral data for the at least one disease and a determination result.
Optionally, in an embodiment of the application, the acquiring, by the processor, behavior data of the user in a plurality of life scenarios includes:
acquiring original behavior data of a user from at least one data source under various life scenes;
respectively carrying out statistical processing on the original behavior data of the at least one data source according to at least one preset parameter, and determining the parameter value of the at least one preset parameter;
and taking the at least one preset parameter and the parameter value thereof as the behavior data of the user.
Optionally, in an embodiment of the present application, the sample data includes sample data composed of behavior data of a plurality of patients for at least one disease and a determination result thereof.
Optionally, in an embodiment of the present application, the behavior analysis model component is configured to be trained in the following manner:
acquiring a plurality of sample data, wherein the sample data comprises a corresponding relation between behavior data and a judgment result;
constructing a behavior analysis model component, wherein training parameters are set in the behavior analysis model component;
respectively inputting the behavior data into the behavior analysis model component to generate a prediction result;
and iteratively adjusting the training parameters based on the difference between the prediction result and the judgment result until the difference meets the preset requirement.
Optionally, in an embodiment of the present application, in a case that the determination result includes that the user needs to obtain a medical examination of a disease, the processor further implements the following steps:
sending a reminder message of the medical examination of the disease to the user.
Optionally, in an embodiment of the present application, the alert message further includes at least one way for medical examination of a disease.
Optionally, in an embodiment of the present application, after the determining that the determination result includes that the user needs to obtain a medical examination of a disease, the processor further includes: and under the condition that the user is determined to have the disease through medical examination of the disease, constructing the behavior data of the user and the corresponding judgment result into sample data, and using the sample data for training the behavior analysis model component.
Optionally, in an embodiment of the application, in a case that the determination result includes that the user needs to obtain a medical examination of a disease, the behavior analysis model component further outputs a disease type corresponding to the medical examination of the disease.
Optionally, in an embodiment of the present application, the behavior analysis model component includes sub model components respectively for the at least one disease, and the sub model components are configured to output whether the user needs to obtain a disease medical examination for a preset disease.
Optionally, in an embodiment of the application, the processor, when the implementing step inputs the behavior data into the behavior analysis model component, and the behavior analysis model component outputs the determination result, includes:
respectively determining child behavior data required by the child model components;
and respectively inputting the sub-behavior data into corresponding sub-model components, and outputting whether the user needs to obtain disease medical examination aiming at a preset disease or not through the sub-model components.
Optionally, in one embodiment of the present application, the disease comprises at least one of: mental disorders, respiratory disorders, heart disorders, bone disorders, ophthalmic disorders.
In another aspect, the present application further provides a computer-readable storage medium, on which computer instructions are stored, and the instructions, when executed, implement the steps of the method according to any of the above embodiments.
The computer readable storage medium may include physical means for storing information, typically by digitizing the information for storage on a medium using electrical, magnetic or optical means. The computer-readable storage medium according to this embodiment may include: devices that store information using electrical energy, such as various types of memory, e.g., RAM, ROM, etc.; devices that store information using magnetic energy, such as hard disks, floppy disks, tapes, core memories, bubble memories, and usb disks; devices that store information optically, such as CDs or DVDs. Of course, there are other ways of storing media that can be read, such as quantum memory, graphene memory, and so forth.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (23)
1. A method of data analysis, the method comprising:
acquiring behavior data of a user in various life scenes;
inputting the behavior data into a behavior analysis model component, and outputting a judgment result through the behavior analysis model component, wherein the judgment result comprises whether the user needs to obtain disease medical examination;
wherein the behavioral analysis model component is configured to be trained using sample data for at least one disease, the sample data including a correspondence between behavioral data for the at least one disease and a determination result.
2. The method of claim 1, wherein the obtaining behavior data of the user in a plurality of life scenarios comprises:
acquiring original behavior data of a user from at least one data source under various life scenes;
respectively carrying out statistical processing on the original behavior data of the at least one data source according to at least one preset parameter, and determining the parameter value of the at least one preset parameter;
and taking the at least one preset parameter and the parameter value thereof as the behavior data of the user.
3. The method of claim 1, wherein the sample data comprises sample data of behavior data of a plurality of patients for at least one disease and the determination result thereof.
4. The method of claim 1, wherein the behavior analysis model component is configured to be trained in the following manner:
acquiring a plurality of sample data, wherein the sample data comprises a corresponding relation between behavior data and a judgment result;
constructing a behavior analysis model component, wherein training parameters are set in the behavior analysis model component;
respectively inputting the behavior data into the behavior analysis model component to generate a prediction result;
and iteratively adjusting the training parameters based on the difference between the prediction result and the judgment result until the difference meets the preset requirement.
5. The method according to claim 1, wherein in case the determination result includes that the user needs to obtain a medical examination of a disease, the method further comprises:
sending a reminder message of the medical examination of the disease to the user.
6. The method of claim 5, wherein the reminder message further includes at least one pathway for medical examination of the disease.
7. The method of claim 1, wherein after determining that the determination comprises that the user needs to obtain a medical examination of a disease, the method further comprises:
and under the condition that the user is determined to have the disease through medical examination of the disease, constructing the behavior data of the user and the corresponding judgment result into sample data, and using the sample data for training the behavior analysis model component.
8. The method of claim 1, wherein the behavior analysis model component further outputs a disease type corresponding to the medical examination of the disease if the determination result includes that the user needs to obtain the medical examination of the disease.
9. The method of claim 1, wherein the behavior analysis model component comprises sub-model components for the at least one disease respectively, the sub-model components for outputting whether the user needs to obtain a disease medical examination for a preset disease.
10. The method of claim 9, wherein inputting the behavior data into a behavior analysis model component and outputting a determination result via the behavior analysis model component comprises:
respectively determining child behavior data required by the child model components;
and respectively inputting the sub-behavior data into corresponding sub-model components, and outputting whether the user needs to obtain disease medical examination aiming at a preset disease or not through the sub-model components.
11. The method of claim 1, wherein the disease comprises at least one of: mental disorders, respiratory disorders, heart disorders, bone disorders, ophthalmic disorders.
12. A data analysis apparatus comprising a processor and a memory for storing processor-executable instructions, the instructions when executed by the processor performing:
acquiring behavior data of a user in various life scenes;
inputting the behavior data into a behavior analysis model component, and outputting a judgment result through the behavior analysis model component, wherein the judgment result comprises whether the user needs to obtain disease medical examination;
wherein the behavioral analysis model component is configured to be trained using sample data for at least one disease, the sample data including a correspondence between behavioral data for the at least one disease and a determination result.
13. The apparatus of claim 12, wherein the processor, when implementing the steps of obtaining behavior data of the user in a plurality of life scenarios, comprises:
acquiring original behavior data of a user from at least one data source under various life scenes;
respectively carrying out statistical processing on the original behavior data of the at least one data source according to at least one preset parameter, and determining the parameter value of the at least one preset parameter;
and taking the at least one preset parameter and the parameter value thereof as the behavior data of the user.
14. The apparatus of claim 12, wherein the sample data comprises sample data of behavior data of a plurality of patients for at least one disease and the determination result thereof.
15. The apparatus of claim 12, wherein the behavior analysis model component is configured to be trained in the following manner:
acquiring a plurality of sample data, wherein the sample data comprises a corresponding relation between behavior data and a judgment result;
constructing a behavior analysis model component, wherein training parameters are set in the behavior analysis model component;
respectively inputting the behavior data into the behavior analysis model component to generate a prediction result;
and iteratively adjusting the training parameters based on the difference between the prediction result and the judgment result until the difference meets the preset requirement.
16. The apparatus of claim 12, wherein in the event that the determination comprises a need for the user to obtain a medical examination of a disease, the processor further performs the steps of:
sending a reminder message of the medical examination of the disease to the user.
17. The apparatus of claim 16, wherein the reminder message further comprises at least one route for medical examination of a disease.
18. The apparatus of claim 12, wherein the processor, after the performing step determines that the determination includes that the user needs to obtain a medical examination for a disease, further comprises: and under the condition that the user is determined to have the disease through medical examination of the disease, constructing the behavior data of the user and the corresponding judgment result into sample data, and using the sample data for training the behavior analysis model component.
19. The apparatus of claim 12, wherein the behavior analysis model component further outputs a disease type corresponding to the medical examination of the disease if the determination result includes that the user needs to obtain the medical examination of the disease.
20. The apparatus of claim 12, wherein the behavior analysis model component comprises sub-model components for the at least one disease respectively, the sub-model components for outputting whether the user needs to obtain a disease medical examination for a preset disease.
21. The apparatus of claim 20, wherein the processor, when implementing the step of inputting the behavior data into the behavior analysis model component and outputting the determination result via the behavior analysis model component, comprises:
respectively determining child behavior data required by the child model components;
and respectively inputting the sub-behavior data into corresponding sub-model components, and outputting whether the user needs to obtain disease medical examination aiming at a preset disease or not through the sub-model components.
22. The apparatus of claim 12, wherein the disease comprises at least one of: mental disorders, respiratory disorders, heart disorders, bone disorders, ophthalmic disorders.
23. A non-transitory computer readable storage medium, wherein instructions in the storage medium, when executed by a processor, enable the processor to perform the data analysis method of any one of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010401869.2A CN113674855A (en) | 2020-05-13 | 2020-05-13 | Data analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010401869.2A CN113674855A (en) | 2020-05-13 | 2020-05-13 | Data analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113674855A true CN113674855A (en) | 2021-11-19 |
Family
ID=78536877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010401869.2A Pending CN113674855A (en) | 2020-05-13 | 2020-05-13 | Data analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674855A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010000810A1 (en) * | 1998-12-14 | 2001-05-03 | Oliver Alabaster | Computerized visual behavior analysis and training method |
| KR20190091788A (en) * | 2018-01-29 | 2019-08-07 | 연세대학교 산학협력단 | System and Method for Providing and Evaluating Preventive Medical Information based on Data Base |
| CN110288079A (en) * | 2019-05-20 | 2019-09-27 | 阿里巴巴集团控股有限公司 | Characteristic acquisition methods, device and equipment |
| CN110503206A (en) * | 2019-08-09 | 2019-11-26 | 阿里巴巴集团控股有限公司 | A kind of prediction model update method, device, equipment and readable medium |
| CN111081371A (en) * | 2019-11-27 | 2020-04-28 | 昆山杜克大学 | Virtual reality-based early autism screening and evaluating system and method |
-
2020
- 2020-05-13 CN CN202010401869.2A patent/CN113674855A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010000810A1 (en) * | 1998-12-14 | 2001-05-03 | Oliver Alabaster | Computerized visual behavior analysis and training method |
| KR20190091788A (en) * | 2018-01-29 | 2019-08-07 | 연세대학교 산학협력단 | System and Method for Providing and Evaluating Preventive Medical Information based on Data Base |
| CN110288079A (en) * | 2019-05-20 | 2019-09-27 | 阿里巴巴集团控股有限公司 | Characteristic acquisition methods, device and equipment |
| CN110503206A (en) * | 2019-08-09 | 2019-11-26 | 阿里巴巴集团控股有限公司 | A kind of prediction model update method, device, equipment and readable medium |
| CN111081371A (en) * | 2019-11-27 | 2020-04-28 | 昆山杜克大学 | Virtual reality-based early autism screening and evaluating system and method |
Non-Patent Citations (1)
| Title |
|---|
| 赵颖旭 等: "考虑老年痴呆症的医疗险住院费用预测与比较――基于机器学习模型", 保险研究, no. 09, pages 64 - 76 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ringeval et al. | AVEC 2018 workshop and challenge: Bipolar disorder and cross-cultural affect recognition | |
| US11545173B2 (en) | Automatic speech-based longitudinal emotion and mood recognition for mental health treatment | |
| US10236082B1 (en) | Personal assistant computing system monitoring | |
| Kaya et al. | Modelling auditory attention | |
| Schuller et al. | The interspeech 2017 computational paralinguistics challenge: Addressee, cold & snoring | |
| Sterling et al. | Automated cough assessment on a mobile platform | |
| Xu et al. | A three-level framework for affective content analysis and its case studies | |
| Qian et al. | Computer audition for fighting the sars-cov-2 corona crisis—introducing the multitask speech corpus for covid-19 | |
| Rahman et al. | Detecting parkinson disease using a web-based speech task: Observational study | |
| Mao et al. | Prediction of depression severity based on the prosodic and semantic features with bidirectional LSTM and time distributed CNN | |
| CN112802575A (en) | Medication decision support method, device, equipment and medium based on graphic state machine | |
| Tlachac et al. | StudentSADD: Rapid mobile depression and suicidal ideation screening of college students during the coronavirus pandemic | |
| Ma et al. | Cost-sensitive two-stage depression prediction using dynamic visual clues | |
| Mahmoud et al. | Smart nursery for smart cities: Infant sound classification based on novel features and support vector classifier | |
| Yadav et al. | Review of automated depression detection: Social posts, audio and video, open challenges and future direction | |
| CN113555105A (en) | Method and device for recommending medical products | |
| Das et al. | A deep learning model for depression detection based on MFCC and CNN generated spectrogram features | |
| CN113674855A (en) | Data analysis method and device | |
| CN113241178B (en) | Device for determining severity of depression of tested person | |
| Gupta et al. | REDE-Detecting human emotions using CNN and RASA | |
| CN114067956A (en) | Health data processing method and device | |
| Hsu et al. | Digital Phenotyping-Based Bipolar Disorder Assessment Using Multiple Correlation Data Imputation and Lasso-MLP | |
| Zhang et al. | Speech Analysis of Patients with Cleft Palate Using Artificial Intelligence Techniques: A Systematic Review | |
| Netscher | Applications of machine learning to support dementia care through commercially available off-the-shelf sensing | |
| Haider et al. | An Automated Mood Diary for Older User's using Ambient Assisted Living Recorded Speech. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |